diff --git a/README.md b/README.md
index c39c3f6..94c5fd3 100644
--- a/README.md
+++ b/README.md
@@ -19,7 +19,7 @@ Feel free to experiment with all of this stuff!
- [x] Autodetection of pages and posts
- [x] Info for posts shown on their page
- [x] HTML minification
-- [ ] Full Open Graph support
+- [x] Full Open Graph support
- [x] Custom categories for posts
- [x] Custom static page parts programmable by context
- [x] Showing creation and modified date for posts
diff --git a/Source/Build.py b/Source/Build.py
index 97e4ed7..77d62b9 100755
--- a/Source/Build.py
+++ b/Source/Build.py
@@ -13,22 +13,31 @@ from Libs import htmlmin
import os
import shutil
from ast import literal_eval
-from html.parser import HTMLParser
+from Libs.bs4 import BeautifulSoup
+#from html.parser import HTMLParser
from markdown import Markdown
from pathlib import Path
Extensions = {
'Pages': ('md', 'pug')}
-class MyHTMLParser(HTMLParser):
- Tags, Attrs, Data = [], [], []
+"""
+class HTMLParser(HTMLParser):
+ Tags = []
def handle_starttag(self, tag, attrs):
- self.Tags += [tag]
- self.Attrs += [attrs]
+ #print(tag, attrs)
+ #self.Tags += [tag, attrs]
+ self.Tags += [[tag,attrs]]
def handle_data(self, data):
- self.Data += [data]
+ #print(data)
+ if self.Tags:
+ #self.Tags += [data]
+ self.Tags[-1] += [data]
def Clean(self):
- self.Tags, self.Attrs, self.Data = [], [], []
+ self.Tags = []
+ self.reset()
+ self.close()
+"""
def ReadFile(p):
try:
@@ -250,18 +259,30 @@ def PatchHTML(Template, PartsText, ContextParts, ContextPartsText, HTMLPagesList
BodyDescription, BodyImage = '', ''
HTMLTitles = FormatTitles(Titles)
""" # This is broken and somehow always returns the same wrong values? Disabled for now
- parser = MyHTMLParser()
- parser.feed(Content)
- for i,e in enumerate(parser.Tags):
- if e == 'p' and not BodyDescription:
- BodyDescription = parser.Data[i]
- elif e == 'img' and not BodyImage:
- BodyImage = parser.Data[i]
- print(Content)
+ #print(Content)
+ Parser = HTMLParser()
+ Parser.feed(Content)
+ for e in Parser.Tags:
+ if not BodyDescription and e[0] == 'p':
+ BodyDescription = e[2][:150] + '...'
+ elif not BodyImage and e[0] == 'img':
+ for j,f in enumerate(e[1]):
+ if f == 'src':
+ BodyImage = e[1][j]
print(BodyDescription)
print(BodyImage)
- parser.Clean()
+ print(len(Parser.Tags))
+ #print(Parser.Tags)
+ #exit()
+ Parser.Clean()
"""
+ #Content.find("
tag), call handle_starttag and then
+ handle_endtag.
+ """
+
+ # Since BeautifulSoup subclasses Tag, it's possible to treat it as
+ # a Tag with a .name. This name makes it clear the BeautifulSoup
+ # object isn't a real markup tag.
+ ROOT_TAG_NAME = '[document]'
+
+ # If the end-user gives no indication which tree builder they
+ # want, look for one with these features.
+ DEFAULT_BUILDER_FEATURES = ['html', 'fast']
+
+ # A string containing all ASCII whitespace characters, used in
+ # endData() to detect data chunks that seem 'empty'.
+ ASCII_SPACES = '\x20\x0a\x09\x0c\x0d'
+
+ NO_PARSER_SPECIFIED_WARNING = "No parser was explicitly specified, so I'm using the best available %(markup_type)s parser for this system (\"%(parser)s\"). This usually isn't a problem, but if you run this code on another system, or in a different virtual environment, it may use a different parser and behave differently.\n\nThe code that caused this warning is on line %(line_number)s of the file %(filename)s. To get rid of this warning, pass the additional argument 'features=\"%(parser)s\"' to the BeautifulSoup constructor.\n"
+
+ def __init__(self, markup="", features=None, builder=None,
+ parse_only=None, from_encoding=None, exclude_encodings=None,
+ element_classes=None, **kwargs):
+ """Constructor.
+
+ :param markup: A string or a file-like object representing
+ markup to be parsed.
+
+ :param features: Desirable features of the parser to be
+ used. This may be the name of a specific parser ("lxml",
+ "lxml-xml", "html.parser", or "html5lib") or it may be the
+ type of markup to be used ("html", "html5", "xml"). It's
+ recommended that you name a specific parser, so that
+ Beautiful Soup gives you the same results across platforms
+ and virtual environments.
+
+ :param builder: A TreeBuilder subclass to instantiate (or
+ instance to use) instead of looking one up based on
+ `features`. You only need to use this if you've implemented a
+ custom TreeBuilder.
+
+ :param parse_only: A SoupStrainer. Only parts of the document
+ matching the SoupStrainer will be considered. This is useful
+ when parsing part of a document that would otherwise be too
+ large to fit into memory.
+
+ :param from_encoding: A string indicating the encoding of the
+ document to be parsed. Pass this in if Beautiful Soup is
+ guessing wrongly about the document's encoding.
+
+ :param exclude_encodings: A list of strings indicating
+ encodings known to be wrong. Pass this in if you don't know
+ the document's encoding but you know Beautiful Soup's guess is
+ wrong.
+
+ :param element_classes: A dictionary mapping BeautifulSoup
+ classes like Tag and NavigableString, to other classes you'd
+ like to be instantiated instead as the parse tree is
+ built. This is useful for subclassing Tag or NavigableString
+ to modify default behavior.
+
+ :param kwargs: For backwards compatibility purposes, the
+ constructor accepts certain keyword arguments used in
+ Beautiful Soup 3. None of these arguments do anything in
+ Beautiful Soup 4; they will result in a warning and then be
+ ignored.
+
+ Apart from this, any keyword arguments passed into the
+ BeautifulSoup constructor are propagated to the TreeBuilder
+ constructor. This makes it possible to configure a
+ TreeBuilder by passing in arguments, not just by saying which
+ one to use.
+ """
+ if 'convertEntities' in kwargs:
+ del kwargs['convertEntities']
+ warnings.warn(
+ "BS4 does not respect the convertEntities argument to the "
+ "BeautifulSoup constructor. Entities are always converted "
+ "to Unicode characters.")
+
+ if 'markupMassage' in kwargs:
+ del kwargs['markupMassage']
+ warnings.warn(
+ "BS4 does not respect the markupMassage argument to the "
+ "BeautifulSoup constructor. The tree builder is responsible "
+ "for any necessary markup massage.")
+
+ if 'smartQuotesTo' in kwargs:
+ del kwargs['smartQuotesTo']
+ warnings.warn(
+ "BS4 does not respect the smartQuotesTo argument to the "
+ "BeautifulSoup constructor. Smart quotes are always converted "
+ "to Unicode characters.")
+
+ if 'selfClosingTags' in kwargs:
+ del kwargs['selfClosingTags']
+ warnings.warn(
+ "BS4 does not respect the selfClosingTags argument to the "
+ "BeautifulSoup constructor. The tree builder is responsible "
+ "for understanding self-closing tags.")
+
+ if 'isHTML' in kwargs:
+ del kwargs['isHTML']
+ warnings.warn(
+ "BS4 does not respect the isHTML argument to the "
+ "BeautifulSoup constructor. Suggest you use "
+ "features='lxml' for HTML and features='lxml-xml' for "
+ "XML.")
+
+ def deprecated_argument(old_name, new_name):
+ if old_name in kwargs:
+ warnings.warn(
+ 'The "%s" argument to the BeautifulSoup constructor '
+ 'has been renamed to "%s."' % (old_name, new_name),
+ DeprecationWarning
+ )
+ return kwargs.pop(old_name)
+ return None
+
+ parse_only = parse_only or deprecated_argument(
+ "parseOnlyThese", "parse_only")
+
+ from_encoding = from_encoding or deprecated_argument(
+ "fromEncoding", "from_encoding")
+
+ if from_encoding and isinstance(markup, str):
+ warnings.warn("You provided Unicode markup but also provided a value for from_encoding. Your from_encoding will be ignored.")
+ from_encoding = None
+
+ self.element_classes = element_classes or dict()
+
+ # We need this information to track whether or not the builder
+ # was specified well enough that we can omit the 'you need to
+ # specify a parser' warning.
+ original_builder = builder
+ original_features = features
+
+ if isinstance(builder, type):
+ # A builder class was passed in; it needs to be instantiated.
+ builder_class = builder
+ builder = None
+ elif builder is None:
+ if isinstance(features, str):
+ features = [features]
+ if features is None or len(features) == 0:
+ features = self.DEFAULT_BUILDER_FEATURES
+ builder_class = builder_registry.lookup(*features)
+ if builder_class is None:
+ raise FeatureNotFound(
+ "Couldn't find a tree builder with the features you "
+ "requested: %s. Do you need to install a parser library?"
+ % ",".join(features))
+
+ # At this point either we have a TreeBuilder instance in
+ # builder, or we have a builder_class that we can instantiate
+ # with the remaining **kwargs.
+ if builder is None:
+ builder = builder_class(**kwargs)
+ if not original_builder and not (
+ original_features == builder.NAME or
+ original_features in builder.ALTERNATE_NAMES
+ ) and markup:
+ # The user did not tell us which TreeBuilder to use,
+ # and we had to guess. Issue a warning.
+ if builder.is_xml:
+ markup_type = "XML"
+ else:
+ markup_type = "HTML"
+
+ # This code adapted from warnings.py so that we get the same line
+ # of code as our warnings.warn() call gets, even if the answer is wrong
+ # (as it may be in a multithreading situation).
+ caller = None
+ try:
+ caller = sys._getframe(1)
+ except ValueError:
+ pass
+ if caller:
+ globals = caller.f_globals
+ line_number = caller.f_lineno
+ else:
+ globals = sys.__dict__
+ line_number= 1
+ filename = globals.get('__file__')
+ if filename:
+ fnl = filename.lower()
+ if fnl.endswith((".pyc", ".pyo")):
+ filename = filename[:-1]
+ if filename:
+ # If there is no filename at all, the user is most likely in a REPL,
+ # and the warning is not necessary.
+ values = dict(
+ filename=filename,
+ line_number=line_number,
+ parser=builder.NAME,
+ markup_type=markup_type
+ )
+ warnings.warn(
+ self.NO_PARSER_SPECIFIED_WARNING % values,
+ GuessedAtParserWarning, stacklevel=2
+ )
+ else:
+ if kwargs:
+ warnings.warn("Keyword arguments to the BeautifulSoup constructor will be ignored. These would normally be passed into the TreeBuilder constructor, but a TreeBuilder instance was passed in as `builder`.")
+
+ self.builder = builder
+ self.is_xml = builder.is_xml
+ self.known_xml = self.is_xml
+ self._namespaces = dict()
+ self.parse_only = parse_only
+
+ if hasattr(markup, 'read'): # It's a file-type object.
+ markup = markup.read()
+ elif len(markup) <= 256 and (
+ (isinstance(markup, bytes) and not b'<' in markup)
+ or (isinstance(markup, str) and not '<' in markup)
+ ):
+ # Issue warnings for a couple beginner problems
+ # involving passing non-markup to Beautiful Soup.
+ # Beautiful Soup will still parse the input as markup,
+ # since that is sometimes the intended behavior.
+ if not self._markup_is_url(markup):
+ self._markup_resembles_filename(markup)
+
+ rejections = []
+ success = False
+ for (self.markup, self.original_encoding, self.declared_html_encoding,
+ self.contains_replacement_characters) in (
+ self.builder.prepare_markup(
+ markup, from_encoding, exclude_encodings=exclude_encodings)):
+ self.reset()
+ self.builder.initialize_soup(self)
+ try:
+ self._feed()
+ success = True
+ break
+ except ParserRejectedMarkup as e:
+ rejections.append(e)
+ pass
+
+ if not success:
+ other_exceptions = [str(e) for e in rejections]
+ raise ParserRejectedMarkup(
+ "The markup you provided was rejected by the parser. Trying a different parser or a different encoding may help.\n\nOriginal exception(s) from parser:\n " + "\n ".join(other_exceptions)
+ )
+
+ # Clear out the markup and remove the builder's circular
+ # reference to this object.
+ self.markup = None
+ self.builder.soup = None
+
+ def __copy__(self):
+ """Copy a BeautifulSoup object by converting the document to a string and parsing it again."""
+ copy = type(self)(
+ self.encode('utf-8'), builder=self.builder, from_encoding='utf-8'
+ )
+
+ # Although we encoded the tree to UTF-8, that may not have
+ # been the encoding of the original markup. Set the copy's
+ # .original_encoding to reflect the original object's
+ # .original_encoding.
+ copy.original_encoding = self.original_encoding
+ return copy
+
+ def __getstate__(self):
+ # Frequently a tree builder can't be pickled.
+ d = dict(self.__dict__)
+ if 'builder' in d and d['builder'] is not None and not self.builder.picklable:
+ d['builder'] = None
+ return d
+
+ @classmethod
+ def _decode_markup(cls, markup):
+ """Ensure `markup` is bytes so it's safe to send into warnings.warn.
+
+ TODO: warnings.warn had this problem back in 2010 but it might not
+ anymore.
+ """
+ if isinstance(markup, bytes):
+ decoded = markup.decode('utf-8', 'replace')
+ else:
+ decoded = markup
+ return decoded
+
+ @classmethod
+ def _markup_is_url(cls, markup):
+ """Error-handling method to raise a warning if incoming markup looks
+ like a URL.
+
+ :param markup: A string.
+ :return: Whether or not the markup resembles a URL
+ closely enough to justify a warning.
+ """
+ if isinstance(markup, bytes):
+ space = b' '
+ cant_start_with = (b"http:", b"https:")
+ elif isinstance(markup, str):
+ space = ' '
+ cant_start_with = ("http:", "https:")
+ else:
+ return False
+
+ if any(markup.startswith(prefix) for prefix in cant_start_with):
+ if not space in markup:
+ warnings.warn(
+ 'The input looks more like a URL than markup. You may want to use'
+ ' an HTTP client like requests to get the document behind'
+ ' the URL, and feed that document to Beautiful Soup.',
+ MarkupResemblesLocatorWarning
+ )
+ return True
+ return False
+
+ @classmethod
+ def _markup_resembles_filename(cls, markup):
+ """Error-handling method to raise a warning if incoming markup
+ resembles a filename.
+
+ :param markup: A bytestring or string.
+ :return: Whether or not the markup resembles a filename
+ closely enough to justify a warning.
+ """
+ path_characters = '/\\'
+ extensions = ['.html', '.htm', '.xml', '.xhtml', '.txt']
+ if isinstance(markup, bytes):
+ path_characters = path_characters.encode("utf8")
+ extensions = [x.encode('utf8') for x in extensions]
+ filelike = False
+ if any(x in markup for x in path_characters):
+ filelike = True
+ else:
+ lower = markup.lower()
+ if any(lower.endswith(ext) for ext in extensions):
+ filelike = True
+ if filelike:
+ warnings.warn(
+ 'The input looks more like a filename than markup. You may'
+ ' want to open this file and pass the filehandle into'
+ ' Beautiful Soup.',
+ MarkupResemblesLocatorWarning
+ )
+ return True
+ return False
+
+ def _feed(self):
+ """Internal method that parses previously set markup, creating a large
+ number of Tag and NavigableString objects.
+ """
+ # Convert the document to Unicode.
+ self.builder.reset()
+
+ self.builder.feed(self.markup)
+ # Close out any unfinished strings and close all the open tags.
+ self.endData()
+ while self.currentTag.name != self.ROOT_TAG_NAME:
+ self.popTag()
+
+ def reset(self):
+ """Reset this object to a state as though it had never parsed any
+ markup.
+ """
+ Tag.__init__(self, self, self.builder, self.ROOT_TAG_NAME)
+ self.hidden = 1
+ self.builder.reset()
+ self.current_data = []
+ self.currentTag = None
+ self.tagStack = []
+ self.open_tag_counter = Counter()
+ self.preserve_whitespace_tag_stack = []
+ self.string_container_stack = []
+ self.pushTag(self)
+
+ def new_tag(self, name, namespace=None, nsprefix=None, attrs={},
+ sourceline=None, sourcepos=None, **kwattrs):
+ """Create a new Tag associated with this BeautifulSoup object.
+
+ :param name: The name of the new Tag.
+ :param namespace: The URI of the new Tag's XML namespace, if any.
+ :param prefix: The prefix for the new Tag's XML namespace, if any.
+ :param attrs: A dictionary of this Tag's attribute values; can
+ be used instead of `kwattrs` for attributes like 'class'
+ that are reserved words in Python.
+ :param sourceline: The line number where this tag was
+ (purportedly) found in its source document.
+ :param sourcepos: The character position within `sourceline` where this
+ tag was (purportedly) found.
+ :param kwattrs: Keyword arguments for the new Tag's attribute values.
+
+ """
+ kwattrs.update(attrs)
+ return self.element_classes.get(Tag, Tag)(
+ None, self.builder, name, namespace, nsprefix, kwattrs,
+ sourceline=sourceline, sourcepos=sourcepos
+ )
+
+ def string_container(self, base_class=None):
+ container = base_class or NavigableString
+
+ # There may be a general override of NavigableString.
+ container = self.element_classes.get(
+ container, container
+ )
+
+ # On top of that, we may be inside a tag that needs a special
+ # container class.
+ if self.string_container_stack and container is NavigableString:
+ container = self.builder.string_containers.get(
+ self.string_container_stack[-1].name, container
+ )
+ return container
+
+ def new_string(self, s, subclass=None):
+ """Create a new NavigableString associated with this BeautifulSoup
+ object.
+ """
+ container = self.string_container(subclass)
+ return container(s)
+
+ def insert_before(self, *args):
+ """This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
+ it because there is nothing before or after it in the parse tree.
+ """
+ raise NotImplementedError("BeautifulSoup objects don't support insert_before().")
+
+ def insert_after(self, *args):
+ """This method is part of the PageElement API, but `BeautifulSoup` doesn't implement
+ it because there is nothing before or after it in the parse tree.
+ """
+ raise NotImplementedError("BeautifulSoup objects don't support insert_after().")
+
+ def popTag(self):
+ """Internal method called by _popToTag when a tag is closed."""
+ tag = self.tagStack.pop()
+ if tag.name in self.open_tag_counter:
+ self.open_tag_counter[tag.name] -= 1
+ if self.preserve_whitespace_tag_stack and tag == self.preserve_whitespace_tag_stack[-1]:
+ self.preserve_whitespace_tag_stack.pop()
+ if self.string_container_stack and tag == self.string_container_stack[-1]:
+ self.string_container_stack.pop()
+ #print("Pop", tag.name)
+ if self.tagStack:
+ self.currentTag = self.tagStack[-1]
+ return self.currentTag
+
+ def pushTag(self, tag):
+ """Internal method called by handle_starttag when a tag is opened."""
+ #print("Push", tag.name)
+ if self.currentTag is not None:
+ self.currentTag.contents.append(tag)
+ self.tagStack.append(tag)
+ self.currentTag = self.tagStack[-1]
+ if tag.name != self.ROOT_TAG_NAME:
+ self.open_tag_counter[tag.name] += 1
+ if tag.name in self.builder.preserve_whitespace_tags:
+ self.preserve_whitespace_tag_stack.append(tag)
+ if tag.name in self.builder.string_containers:
+ self.string_container_stack.append(tag)
+
+ def endData(self, containerClass=None):
+ """Method called by the TreeBuilder when the end of a data segment
+ occurs.
+ """
+ if self.current_data:
+ current_data = ''.join(self.current_data)
+ # If whitespace is not preserved, and this string contains
+ # nothing but ASCII spaces, replace it with a single space
+ # or newline.
+ if not self.preserve_whitespace_tag_stack:
+ strippable = True
+ for i in current_data:
+ if i not in self.ASCII_SPACES:
+ strippable = False
+ break
+ if strippable:
+ if '\n' in current_data:
+ current_data = '\n'
+ else:
+ current_data = ' '
+
+ # Reset the data collector.
+ self.current_data = []
+
+ # Should we add this string to the tree at all?
+ if self.parse_only and len(self.tagStack) <= 1 and \
+ (not self.parse_only.text or \
+ not self.parse_only.search(current_data)):
+ return
+
+ containerClass = self.string_container(containerClass)
+ o = containerClass(current_data)
+ self.object_was_parsed(o)
+
+ def object_was_parsed(self, o, parent=None, most_recent_element=None):
+ """Method called by the TreeBuilder to integrate an object into the parse tree."""
+ if parent is None:
+ parent = self.currentTag
+ if most_recent_element is not None:
+ previous_element = most_recent_element
+ else:
+ previous_element = self._most_recent_element
+
+ next_element = previous_sibling = next_sibling = None
+ if isinstance(o, Tag):
+ next_element = o.next_element
+ next_sibling = o.next_sibling
+ previous_sibling = o.previous_sibling
+ if previous_element is None:
+ previous_element = o.previous_element
+
+ fix = parent.next_element is not None
+
+ o.setup(parent, previous_element, next_element, previous_sibling, next_sibling)
+
+ self._most_recent_element = o
+ parent.contents.append(o)
+
+ # Check if we are inserting into an already parsed node.
+ if fix:
+ self._linkage_fixer(parent)
+
+ def _linkage_fixer(self, el):
+ """Make sure linkage of this fragment is sound."""
+
+ first = el.contents[0]
+ child = el.contents[-1]
+ descendant = child
+
+ if child is first and el.parent is not None:
+ # Parent should be linked to first child
+ el.next_element = child
+ # We are no longer linked to whatever this element is
+ prev_el = child.previous_element
+ if prev_el is not None and prev_el is not el:
+ prev_el.next_element = None
+ # First child should be linked to the parent, and no previous siblings.
+ child.previous_element = el
+ child.previous_sibling = None
+
+ # We have no sibling as we've been appended as the last.
+ child.next_sibling = None
+
+ # This index is a tag, dig deeper for a "last descendant"
+ if isinstance(child, Tag) and child.contents:
+ descendant = child._last_descendant(False)
+
+ # As the final step, link last descendant. It should be linked
+ # to the parent's next sibling (if found), else walk up the chain
+ # and find a parent with a sibling. It should have no next sibling.
+ descendant.next_element = None
+ descendant.next_sibling = None
+ target = el
+ while True:
+ if target is None:
+ break
+ elif target.next_sibling is not None:
+ descendant.next_element = target.next_sibling
+ target.next_sibling.previous_element = child
+ break
+ target = target.parent
+
+ def _popToTag(self, name, nsprefix=None, inclusivePop=True):
+ """Pops the tag stack up to and including the most recent
+ instance of the given tag.
+
+ If there are no open tags with the given name, nothing will be
+ popped.
+
+ :param name: Pop up to the most recent tag with this name.
+ :param nsprefix: The namespace prefix that goes with `name`.
+ :param inclusivePop: It this is false, pops the tag stack up
+ to but *not* including the most recent instqance of the
+ given tag.
+
+ """
+ #print("Popping to %s" % name)
+ if name == self.ROOT_TAG_NAME:
+ # The BeautifulSoup object itself can never be popped.
+ return
+
+ most_recently_popped = None
+
+ stack_size = len(self.tagStack)
+ for i in range(stack_size - 1, 0, -1):
+ if not self.open_tag_counter.get(name):
+ break
+ t = self.tagStack[i]
+ if (name == t.name and nsprefix == t.prefix):
+ if inclusivePop:
+ most_recently_popped = self.popTag()
+ break
+ most_recently_popped = self.popTag()
+
+ return most_recently_popped
+
+ def handle_starttag(self, name, namespace, nsprefix, attrs, sourceline=None,
+ sourcepos=None, namespaces=None):
+ """Called by the tree builder when a new tag is encountered.
+
+ :param name: Name of the tag.
+ :param nsprefix: Namespace prefix for the tag.
+ :param attrs: A dictionary of attribute values.
+ :param sourceline: The line number where this tag was found in its
+ source document.
+ :param sourcepos: The character position within `sourceline` where this
+ tag was found.
+ :param namespaces: A dictionary of all namespace prefix mappings
+ currently in scope in the document.
+
+ If this method returns None, the tag was rejected by an active
+ SoupStrainer. You should proceed as if the tag had not occurred
+ in the document. For instance, if this was a self-closing tag,
+ don't call handle_endtag.
+ """
+ # print("Start tag %s: %s" % (name, attrs))
+ self.endData()
+
+ if (self.parse_only and len(self.tagStack) <= 1
+ and (self.parse_only.text
+ or not self.parse_only.search_tag(name, attrs))):
+ return None
+
+ tag = self.element_classes.get(Tag, Tag)(
+ self, self.builder, name, namespace, nsprefix, attrs,
+ self.currentTag, self._most_recent_element,
+ sourceline=sourceline, sourcepos=sourcepos,
+ namespaces=namespaces
+ )
+ if tag is None:
+ return tag
+ if self._most_recent_element is not None:
+ self._most_recent_element.next_element = tag
+ self._most_recent_element = tag
+ self.pushTag(tag)
+ return tag
+
+ def handle_endtag(self, name, nsprefix=None):
+ """Called by the tree builder when an ending tag is encountered.
+
+ :param name: Name of the tag.
+ :param nsprefix: Namespace prefix for the tag.
+ """
+ #print("End tag: " + name)
+ self.endData()
+ self._popToTag(name, nsprefix)
+
+ def handle_data(self, data):
+ """Called by the tree builder when a chunk of textual data is encountered."""
+ self.current_data.append(data)
+
+ def decode(self, pretty_print=False,
+ eventual_encoding=DEFAULT_OUTPUT_ENCODING,
+ formatter="minimal"):
+ """Returns a string or Unicode representation of the parse tree
+ as an HTML or XML document.
+
+ :param pretty_print: If this is True, indentation will be used to
+ make the document more readable.
+ :param eventual_encoding: The encoding of the final document.
+ If this is None, the document will be a Unicode string.
+ """
+ if self.is_xml:
+ # Print the XML declaration
+ encoding_part = ''
+ if eventual_encoding in PYTHON_SPECIFIC_ENCODINGS:
+ # This is a special Python encoding; it can't actually
+ # go into an XML document because it means nothing
+ # outside of Python.
+ eventual_encoding = None
+ if eventual_encoding != None:
+ encoding_part = ' encoding="%s"' % eventual_encoding
+ prefix = '\n' % encoding_part
+ else:
+ prefix = ''
+ if not pretty_print:
+ indent_level = None
+ else:
+ indent_level = 0
+ return prefix + super(BeautifulSoup, self).decode(
+ indent_level, eventual_encoding, formatter)
+
+# Aliases to make it easier to get started quickly, e.g. 'from bs4 import _soup'
+_s = BeautifulSoup
+_soup = BeautifulSoup
+
+class BeautifulStoneSoup(BeautifulSoup):
+ """Deprecated interface to an XML parser."""
+
+ def __init__(self, *args, **kwargs):
+ kwargs['features'] = 'xml'
+ warnings.warn(
+ 'The BeautifulStoneSoup class is deprecated. Instead of using '
+ 'it, pass features="xml" into the BeautifulSoup constructor.',
+ DeprecationWarning
+ )
+ super(BeautifulStoneSoup, self).__init__(*args, **kwargs)
+
+
+class StopParsing(Exception):
+ """Exception raised by a TreeBuilder if it's unable to continue parsing."""
+ pass
+
+class FeatureNotFound(ValueError):
+ """Exception raised by the BeautifulSoup constructor if no parser with the
+ requested features is found.
+ """
+ pass
+
+
+#If this file is run as a script, act as an HTML pretty-printer.
+if __name__ == '__main__':
+ import sys
+ soup = BeautifulSoup(sys.stdin)
+ print((soup.prettify()))
diff --git a/Source/Libs/bs4/builder/__init__.py b/Source/Libs/bs4/builder/__init__.py
new file mode 100644
index 0000000..0735681
--- /dev/null
+++ b/Source/Libs/bs4/builder/__init__.py
@@ -0,0 +1,631 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+from collections import defaultdict
+import itertools
+import re
+import warnings
+import sys
+from ..element import (
+ CharsetMetaAttributeValue,
+ ContentMetaAttributeValue,
+ RubyParenthesisString,
+ RubyTextString,
+ Stylesheet,
+ Script,
+ TemplateString,
+ nonwhitespace_re
+)
+
+__all__ = [
+ 'HTMLTreeBuilder',
+ 'SAXTreeBuilder',
+ 'TreeBuilder',
+ 'TreeBuilderRegistry',
+ ]
+
+# Some useful features for a TreeBuilder to have.
+FAST = 'fast'
+PERMISSIVE = 'permissive'
+STRICT = 'strict'
+XML = 'xml'
+HTML = 'html'
+HTML_5 = 'html5'
+
+class XMLParsedAsHTMLWarning(UserWarning):
+ """The warning issued when an HTML parser is used to parse
+ XML that is not XHTML.
+ """
+ MESSAGE = """It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features="xml"` into the BeautifulSoup constructor."""
+
+
+class TreeBuilderRegistry(object):
+ """A way of looking up TreeBuilder subclasses by their name or by desired
+ features.
+ """
+
+ def __init__(self):
+ self.builders_for_feature = defaultdict(list)
+ self.builders = []
+
+ def register(self, treebuilder_class):
+ """Register a treebuilder based on its advertised features.
+
+ :param treebuilder_class: A subclass of Treebuilder. its .features
+ attribute should list its features.
+ """
+ for feature in treebuilder_class.features:
+ self.builders_for_feature[feature].insert(0, treebuilder_class)
+ self.builders.insert(0, treebuilder_class)
+
+ def lookup(self, *features):
+ """Look up a TreeBuilder subclass with the desired features.
+
+ :param features: A list of features to look for. If none are
+ provided, the most recently registered TreeBuilder subclass
+ will be used.
+ :return: A TreeBuilder subclass, or None if there's no
+ registered subclass with all the requested features.
+ """
+ if len(self.builders) == 0:
+ # There are no builders at all.
+ return None
+
+ if len(features) == 0:
+ # They didn't ask for any features. Give them the most
+ # recently registered builder.
+ return self.builders[0]
+
+ # Go down the list of features in order, and eliminate any builders
+ # that don't match every feature.
+ features = list(features)
+ features.reverse()
+ candidates = None
+ candidate_set = None
+ while len(features) > 0:
+ feature = features.pop()
+ we_have_the_feature = self.builders_for_feature.get(feature, [])
+ if len(we_have_the_feature) > 0:
+ if candidates is None:
+ candidates = we_have_the_feature
+ candidate_set = set(candidates)
+ else:
+ # Eliminate any candidates that don't have this feature.
+ candidate_set = candidate_set.intersection(
+ set(we_have_the_feature))
+
+ # The only valid candidates are the ones in candidate_set.
+ # Go through the original list of candidates and pick the first one
+ # that's in candidate_set.
+ if candidate_set is None:
+ return None
+ for candidate in candidates:
+ if candidate in candidate_set:
+ return candidate
+ return None
+
+# The BeautifulSoup class will take feature lists from developers and use them
+# to look up builders in this registry.
+builder_registry = TreeBuilderRegistry()
+
+class TreeBuilder(object):
+ """Turn a textual document into a Beautiful Soup object tree."""
+
+ NAME = "[Unknown tree builder]"
+ ALTERNATE_NAMES = []
+ features = []
+
+ is_xml = False
+ picklable = False
+ empty_element_tags = None # A tag will be considered an empty-element
+ # tag when and only when it has no contents.
+
+ # A value for these tag/attribute combinations is a space- or
+ # comma-separated list of CDATA, rather than a single CDATA.
+ DEFAULT_CDATA_LIST_ATTRIBUTES = {}
+
+ # Whitespace should be preserved inside these tags.
+ DEFAULT_PRESERVE_WHITESPACE_TAGS = set()
+
+ # The textual contents of tags with these names should be
+ # instantiated with some class other than NavigableString.
+ DEFAULT_STRING_CONTAINERS = {}
+
+ USE_DEFAULT = object()
+
+ # Most parsers don't keep track of line numbers.
+ TRACKS_LINE_NUMBERS = False
+
+ def __init__(self, multi_valued_attributes=USE_DEFAULT,
+ preserve_whitespace_tags=USE_DEFAULT,
+ store_line_numbers=USE_DEFAULT,
+ string_containers=USE_DEFAULT,
+ ):
+ """Constructor.
+
+ :param multi_valued_attributes: If this is set to None, the
+ TreeBuilder will not turn any values for attributes like
+ 'class' into lists. Setting this to a dictionary will
+ customize this behavior; look at DEFAULT_CDATA_LIST_ATTRIBUTES
+ for an example.
+
+ Internally, these are called "CDATA list attributes", but that
+ probably doesn't make sense to an end-user, so the argument name
+ is `multi_valued_attributes`.
+
+ :param preserve_whitespace_tags: A list of tags to treat
+ the way
tags are treated in HTML. Tags in this list
+ are immune from pretty-printing; their contents will always be
+ output as-is.
+
+ :param string_containers: A dictionary mapping tag names to
+ the classes that should be instantiated to contain the textual
+ contents of those tags. The default is to use NavigableString
+ for every tag, no matter what the name. You can override the
+ default by changing DEFAULT_STRING_CONTAINERS.
+
+ :param store_line_numbers: If the parser keeps track of the
+ line numbers and positions of the original markup, that
+ information will, by default, be stored in each corresponding
+ `Tag` object. You can turn this off by passing
+ store_line_numbers=False. If the parser you're using doesn't
+ keep track of this information, then setting store_line_numbers=True
+ will do nothing.
+ """
+ self.soup = None
+ if multi_valued_attributes is self.USE_DEFAULT:
+ multi_valued_attributes = self.DEFAULT_CDATA_LIST_ATTRIBUTES
+ self.cdata_list_attributes = multi_valued_attributes
+ if preserve_whitespace_tags is self.USE_DEFAULT:
+ preserve_whitespace_tags = self.DEFAULT_PRESERVE_WHITESPACE_TAGS
+ self.preserve_whitespace_tags = preserve_whitespace_tags
+ if store_line_numbers == self.USE_DEFAULT:
+ store_line_numbers = self.TRACKS_LINE_NUMBERS
+ self.store_line_numbers = store_line_numbers
+ if string_containers == self.USE_DEFAULT:
+ string_containers = self.DEFAULT_STRING_CONTAINERS
+ self.string_containers = string_containers
+
+ def initialize_soup(self, soup):
+ """The BeautifulSoup object has been initialized and is now
+ being associated with the TreeBuilder.
+
+ :param soup: A BeautifulSoup object.
+ """
+ self.soup = soup
+
+ def reset(self):
+ """Do any work necessary to reset the underlying parser
+ for a new document.
+
+ By default, this does nothing.
+ """
+ pass
+
+ def can_be_empty_element(self, tag_name):
+ """Might a tag with this name be an empty-element tag?
+
+ The final markup may or may not actually present this tag as
+ self-closing.
+
+ For instance: an HTMLBuilder does not consider a tag to be
+ an empty-element tag (it's not in
+ HTMLBuilder.empty_element_tags). This means an empty
tag
+ will be presented as "
", not "
" or "".
+
+ The default implementation has no opinion about which tags are
+ empty-element tags, so a tag will be presented as an
+ empty-element tag if and only if it has no children.
+ " " will become " ", and "bar " will
+ be left alone.
+
+ :param tag_name: The name of a markup tag.
+ """
+ if self.empty_element_tags is None:
+ return True
+ return tag_name in self.empty_element_tags
+
+ def feed(self, markup):
+ """Run some incoming markup through some parsing process,
+ populating the `BeautifulSoup` object in self.soup.
+
+ This method is not implemented in TreeBuilder; it must be
+ implemented in subclasses.
+
+ :return: None.
+ """
+ raise NotImplementedError()
+
+ def prepare_markup(self, markup, user_specified_encoding=None,
+ document_declared_encoding=None, exclude_encodings=None):
+ """Run any preliminary steps necessary to make incoming markup
+ acceptable to the parser.
+
+ :param markup: Some markup -- probably a bytestring.
+ :param user_specified_encoding: The user asked to try this encoding.
+ :param document_declared_encoding: The markup itself claims to be
+ in this encoding. NOTE: This argument is not used by the
+ calling code and can probably be removed.
+ :param exclude_encodings: The user asked _not_ to try any of
+ these encodings.
+
+ :yield: A series of 4-tuples:
+ (markup, encoding, declared encoding,
+ has undergone character replacement)
+
+ Each 4-tuple represents a strategy for converting the
+ document to Unicode and parsing it. Each strategy will be tried
+ in turn.
+
+ By default, the only strategy is to parse the markup
+ as-is. See `LXMLTreeBuilderForXML` and
+ `HTMLParserTreeBuilder` for implementations that take into
+ account the quirks of particular parsers.
+ """
+ yield markup, None, None, False
+
+ def test_fragment_to_document(self, fragment):
+ """Wrap an HTML fragment to make it look like a document.
+
+ Different parsers do this differently. For instance, lxml
+ introduces an empty
tag, and html5lib
+ doesn't. Abstracting this away lets us write simple tests
+ which run HTML fragments through the parser and compare the
+ results against other HTML fragments.
+
+ This method should not be used outside of tests.
+
+ :param fragment: A string -- fragment of HTML.
+ :return: A string -- a full HTML document.
+ """
+ return fragment
+
+ def set_up_substitutions(self, tag):
+ """Set up any substitutions that will need to be performed on
+ a `Tag` when it's output as a string.
+
+ By default, this does nothing. See `HTMLTreeBuilder` for a
+ case where this is used.
+
+ :param tag: A `Tag`
+ :return: Whether or not a substitution was performed.
+ """
+ return False
+
+ def _replace_cdata_list_attribute_values(self, tag_name, attrs):
+ """When an attribute value is associated with a tag that can
+ have multiple values for that attribute, convert the string
+ value to a list of strings.
+
+ Basically, replaces class="foo bar" with class=["foo", "bar"]
+
+ NOTE: This method modifies its input in place.
+
+ :param tag_name: The name of a tag.
+ :param attrs: A dictionary containing the tag's attributes.
+ Any appropriate attribute values will be modified in place.
+ """
+ if not attrs:
+ return attrs
+ if self.cdata_list_attributes:
+ universal = self.cdata_list_attributes.get('*', [])
+ tag_specific = self.cdata_list_attributes.get(
+ tag_name.lower(), None)
+ for attr in list(attrs.keys()):
+ if attr in universal or (tag_specific and attr in tag_specific):
+ # We have a "class"-type attribute whose string
+ # value is a whitespace-separated list of
+ # values. Split it into a list.
+ value = attrs[attr]
+ if isinstance(value, str):
+ values = nonwhitespace_re.findall(value)
+ else:
+ # html5lib sometimes calls setAttributes twice
+ # for the same tag when rearranging the parse
+ # tree. On the second call the attribute value
+ # here is already a list. If this happens,
+ # leave the value alone rather than trying to
+ # split it again.
+ values = value
+ attrs[attr] = values
+ return attrs
+
+class SAXTreeBuilder(TreeBuilder):
+ """A Beautiful Soup treebuilder that listens for SAX events.
+
+ This is not currently used for anything, but it demonstrates
+ how a simple TreeBuilder would work.
+ """
+
+ def feed(self, markup):
+ raise NotImplementedError()
+
+ def close(self):
+ pass
+
+ def startElement(self, name, attrs):
+ attrs = dict((key[1], value) for key, value in list(attrs.items()))
+ #print("Start %s, %r" % (name, attrs))
+ self.soup.handle_starttag(name, attrs)
+
+ def endElement(self, name):
+ #print("End %s" % name)
+ self.soup.handle_endtag(name)
+
+ def startElementNS(self, nsTuple, nodeName, attrs):
+ # Throw away (ns, nodeName) for now.
+ self.startElement(nodeName, attrs)
+
+ def endElementNS(self, nsTuple, nodeName):
+ # Throw away (ns, nodeName) for now.
+ self.endElement(nodeName)
+ #handler.endElementNS((ns, node.nodeName), node.nodeName)
+
+ def startPrefixMapping(self, prefix, nodeValue):
+ # Ignore the prefix for now.
+ pass
+
+ def endPrefixMapping(self, prefix):
+ # Ignore the prefix for now.
+ # handler.endPrefixMapping(prefix)
+ pass
+
+ def characters(self, content):
+ self.soup.handle_data(content)
+
+ def startDocument(self):
+ pass
+
+ def endDocument(self):
+ pass
+
+
+class HTMLTreeBuilder(TreeBuilder):
+ """This TreeBuilder knows facts about HTML.
+
+ Such as which tags are empty-element tags.
+ """
+
+ empty_element_tags = set([
+ # These are from HTML5.
+ 'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input', 'keygen', 'link', 'menuitem', 'meta', 'param', 'source', 'track', 'wbr',
+
+ # These are from earlier versions of HTML and are removed in HTML5.
+ 'basefont', 'bgsound', 'command', 'frame', 'image', 'isindex', 'nextid', 'spacer'
+ ])
+
+ # The HTML standard defines these as block-level elements. Beautiful
+ # Soup does not treat these elements differently from other elements,
+ # but it may do so eventually, and this information is available if
+ # you need to use it.
+ block_elements = set(["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "dt", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"])
+
+ # These HTML tags need special treatment so they can be
+ # represented by a string class other than NavigableString.
+ #
+ # For some of these tags, it's because the HTML standard defines
+ # an unusual content model for them. I made this list by going
+ # through the HTML spec
+ # (https://html.spec.whatwg.org/#metadata-content) and looking for
+ # "metadata content" elements that can contain strings.
+ #
+ # The Ruby tags ( and ) are here despite being normal
+ # "phrasing content" tags, because the content they contain is
+ # qualitatively different from other text in the document, and it
+ # can be useful to be able to distinguish it.
+ #
+ # TODO: Arguably could go here but it seems
+ # qualitatively different from the other tags.
+ DEFAULT_STRING_CONTAINERS = {
+ 'rt' : RubyTextString,
+ 'rp' : RubyParenthesisString,
+ 'style': Stylesheet,
+ 'script': Script,
+ 'template': TemplateString,
+ }
+
+ # The HTML standard defines these attributes as containing a
+ # space-separated list of values, not a single value. That is,
+ # class="foo bar" means that the 'class' attribute has two values,
+ # 'foo' and 'bar', not the single value 'foo bar'. When we
+ # encounter one of these attributes, we will parse its value into
+ # a list of values if possible. Upon output, the list will be
+ # converted back into a string.
+ DEFAULT_CDATA_LIST_ATTRIBUTES = {
+ "*" : ['class', 'accesskey', 'dropzone'],
+ "a" : ['rel', 'rev'],
+ "link" : ['rel', 'rev'],
+ "td" : ["headers"],
+ "th" : ["headers"],
+ "td" : ["headers"],
+ "form" : ["accept-charset"],
+ "object" : ["archive"],
+
+ # These are HTML5 specific, as are *.accesskey and *.dropzone above.
+ "area" : ["rel"],
+ "icon" : ["sizes"],
+ "iframe" : ["sandbox"],
+ "output" : ["for"],
+ }
+
+ DEFAULT_PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
+
+ def set_up_substitutions(self, tag):
+ """Replace the declared encoding in a tag with a placeholder,
+ to be substituted when the tag is output to a string.
+
+ An HTML document may come in to Beautiful Soup as one
+ encoding, but exit in a different encoding, and the tag
+ needs to be changed to reflect this.
+
+ :param tag: A `Tag`
+ :return: Whether or not a substitution was performed.
+ """
+ # We are only interested in tags
+ if tag.name != 'meta':
+ return False
+
+ http_equiv = tag.get('http-equiv')
+ content = tag.get('content')
+ charset = tag.get('charset')
+
+ # We are interested in tags that say what encoding the
+ # document was originally in. This means HTML 5-style
+ # tags that provide the "charset" attribute. It also means
+ # HTML 4-style tags that provide the "content"
+ # attribute and have "http-equiv" set to "content-type".
+ #
+ # In both cases we will replace the value of the appropriate
+ # attribute with a standin object that can take on any
+ # encoding.
+ meta_encoding = None
+ if charset is not None:
+ # HTML 5 style:
+ #
+ meta_encoding = charset
+ tag['charset'] = CharsetMetaAttributeValue(charset)
+
+ elif (content is not None and http_equiv is not None
+ and http_equiv.lower() == 'content-type'):
+ # HTML 4 style:
+ #
+ tag['content'] = ContentMetaAttributeValue(content)
+
+ return (meta_encoding is not None)
+
+class DetectsXMLParsedAsHTML(object):
+ """A mixin class for any class (a TreeBuilder, or some class used by a
+ TreeBuilder) that's in a position to detect whether an XML
+ document is being incorrectly parsed as HTML, and issue an
+ appropriate warning.
+
+ This requires being able to observe an incoming processing
+ instruction that might be an XML declaration, and also able to
+ observe tags as they're opened. If you can't do that for a given
+ TreeBuilder, there's a less reliable implementation based on
+ examining the raw markup.
+ """
+
+ # Regular expression for seeing if markup has an tag.
+ LOOKS_LIKE_HTML = re.compile("<[^ +]html", re.I)
+ LOOKS_LIKE_HTML_B = re.compile(b"<[^ +]html", re.I)
+
+ XML_PREFIX = '%s' % fragment
+
+
+class TreeBuilderForHtml5lib(treebuilder_base.TreeBuilder):
+
+ def __init__(self, namespaceHTMLElements, soup=None,
+ store_line_numbers=True, **kwargs):
+ if soup:
+ self.soup = soup
+ else:
+ from bs4 import BeautifulSoup
+ # TODO: Why is the parser 'html.parser' here? To avoid an
+ # infinite loop?
+ self.soup = BeautifulSoup(
+ "", "html.parser", store_line_numbers=store_line_numbers,
+ **kwargs
+ )
+ # TODO: What are **kwargs exactly? Should they be passed in
+ # here in addition to/instead of being passed to the BeautifulSoup
+ # constructor?
+ super(TreeBuilderForHtml5lib, self).__init__(namespaceHTMLElements)
+
+ # This will be set later to an html5lib.html5parser.HTMLParser
+ # object, which we can use to track the current line number.
+ self.parser = None
+ self.store_line_numbers = store_line_numbers
+
+ def documentClass(self):
+ self.soup.reset()
+ return Element(self.soup, self.soup, None)
+
+ def insertDoctype(self, token):
+ name = token["name"]
+ publicId = token["publicId"]
+ systemId = token["systemId"]
+
+ doctype = Doctype.for_name_and_ids(name, publicId, systemId)
+ self.soup.object_was_parsed(doctype)
+
+ def elementClass(self, name, namespace):
+ kwargs = {}
+ if self.parser and self.store_line_numbers:
+ # This represents the point immediately after the end of the
+ # tag. We don't know when the tag started, but we do know
+ # where it ended -- the character just before this one.
+ sourceline, sourcepos = self.parser.tokenizer.stream.position()
+ kwargs['sourceline'] = sourceline
+ kwargs['sourcepos'] = sourcepos-1
+ tag = self.soup.new_tag(name, namespace, **kwargs)
+
+ return Element(tag, self.soup, namespace)
+
+ def commentClass(self, data):
+ return TextNode(Comment(data), self.soup)
+
+ def fragmentClass(self):
+ from bs4 import BeautifulSoup
+ # TODO: Why is the parser 'html.parser' here? To avoid an
+ # infinite loop?
+ self.soup = BeautifulSoup("", "html.parser")
+ self.soup.name = "[document_fragment]"
+ return Element(self.soup, self.soup, None)
+
+ def appendChild(self, node):
+ # XXX This code is not covered by the BS4 tests.
+ self.soup.append(node.element)
+
+ def getDocument(self):
+ return self.soup
+
+ def getFragment(self):
+ return treebuilder_base.TreeBuilder.getFragment(self).element
+
+ def testSerializer(self, element):
+ from bs4 import BeautifulSoup
+ rv = []
+ doctype_re = re.compile(r'^(.*?)(?: PUBLIC "(.*?)"(?: "(.*?)")?| SYSTEM "(.*?)")?$')
+
+ def serializeElement(element, indent=0):
+ if isinstance(element, BeautifulSoup):
+ pass
+ if isinstance(element, Doctype):
+ m = doctype_re.match(element)
+ if m:
+ name = m.group(1)
+ if m.lastindex > 1:
+ publicId = m.group(2) or ""
+ systemId = m.group(3) or m.group(4) or ""
+ rv.append("""|%s""" %
+ (' ' * indent, name, publicId, systemId))
+ else:
+ rv.append("|%s" % (' ' * indent, name))
+ else:
+ rv.append("|%s" % (' ' * indent,))
+ elif isinstance(element, Comment):
+ rv.append("|%s" % (' ' * indent, element))
+ elif isinstance(element, NavigableString):
+ rv.append("|%s\"%s\"" % (' ' * indent, element))
+ else:
+ if element.namespace:
+ name = "%s %s" % (prefixes[element.namespace],
+ element.name)
+ else:
+ name = element.name
+ rv.append("|%s<%s>" % (' ' * indent, name))
+ if element.attrs:
+ attributes = []
+ for name, value in list(element.attrs.items()):
+ if isinstance(name, NamespacedAttribute):
+ name = "%s %s" % (prefixes[name.namespace], name.name)
+ if isinstance(value, list):
+ value = " ".join(value)
+ attributes.append((name, value))
+
+ for name, value in sorted(attributes):
+ rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
+ indent += 2
+ for child in element.children:
+ serializeElement(child, indent)
+ serializeElement(element, 0)
+
+ return "\n".join(rv)
+
+class AttrList(object):
+ def __init__(self, element):
+ self.element = element
+ self.attrs = dict(self.element.attrs)
+ def __iter__(self):
+ return list(self.attrs.items()).__iter__()
+ def __setitem__(self, name, value):
+ # If this attribute is a multi-valued attribute for this element,
+ # turn its value into a list.
+ list_attr = self.element.cdata_list_attributes or {}
+ if (name in list_attr.get('*')
+ or (self.element.name in list_attr
+ and name in list_attr[self.element.name])):
+ # A node that is being cloned may have already undergone
+ # this procedure.
+ if not isinstance(value, list):
+ value = nonwhitespace_re.findall(value)
+ self.element[name] = value
+ def items(self):
+ return list(self.attrs.items())
+ def keys(self):
+ return list(self.attrs.keys())
+ def __len__(self):
+ return len(self.attrs)
+ def __getitem__(self, name):
+ return self.attrs[name]
+ def __contains__(self, name):
+ return name in list(self.attrs.keys())
+
+
+class Element(treebuilder_base.Node):
+ def __init__(self, element, soup, namespace):
+ treebuilder_base.Node.__init__(self, element.name)
+ self.element = element
+ self.soup = soup
+ self.namespace = namespace
+
+ def appendChild(self, node):
+ string_child = child = None
+ if isinstance(node, str):
+ # Some other piece of code decided to pass in a string
+ # instead of creating a TextElement object to contain the
+ # string.
+ string_child = child = node
+ elif isinstance(node, Tag):
+ # Some other piece of code decided to pass in a Tag
+ # instead of creating an Element object to contain the
+ # Tag.
+ child = node
+ elif node.element.__class__ == NavigableString:
+ string_child = child = node.element
+ node.parent = self
+ else:
+ child = node.element
+ node.parent = self
+
+ if not isinstance(child, str) and child.parent is not None:
+ node.element.extract()
+
+ if (string_child is not None and self.element.contents
+ and self.element.contents[-1].__class__ == NavigableString):
+ # We are appending a string onto another string.
+ # TODO This has O(n^2) performance, for input like
+ # "aaa..."
+ old_element = self.element.contents[-1]
+ new_element = self.soup.new_string(old_element + string_child)
+ old_element.replace_with(new_element)
+ self.soup._most_recent_element = new_element
+ else:
+ if isinstance(node, str):
+ # Create a brand new NavigableString from this string.
+ child = self.soup.new_string(node)
+
+ # Tell Beautiful Soup to act as if it parsed this element
+ # immediately after the parent's last descendant. (Or
+ # immediately after the parent, if it has no children.)
+ if self.element.contents:
+ most_recent_element = self.element._last_descendant(False)
+ elif self.element.next_element is not None:
+ # Something from further ahead in the parse tree is
+ # being inserted into this earlier element. This is
+ # very annoying because it means an expensive search
+ # for the last element in the tree.
+ most_recent_element = self.soup._last_descendant()
+ else:
+ most_recent_element = self.element
+
+ self.soup.object_was_parsed(
+ child, parent=self.element,
+ most_recent_element=most_recent_element)
+
+ def getAttributes(self):
+ if isinstance(self.element, Comment):
+ return {}
+ return AttrList(self.element)
+
+ def setAttributes(self, attributes):
+ if attributes is not None and len(attributes) > 0:
+ converted_attributes = []
+ for name, value in list(attributes.items()):
+ if isinstance(name, tuple):
+ new_name = NamespacedAttribute(*name)
+ del attributes[name]
+ attributes[new_name] = value
+
+ self.soup.builder._replace_cdata_list_attribute_values(
+ self.name, attributes)
+ for name, value in list(attributes.items()):
+ self.element[name] = value
+
+ # The attributes may contain variables that need substitution.
+ # Call set_up_substitutions manually.
+ #
+ # The Tag constructor called this method when the Tag was created,
+ # but we just set/changed the attributes, so call it again.
+ self.soup.builder.set_up_substitutions(self.element)
+ attributes = property(getAttributes, setAttributes)
+
+ def insertText(self, data, insertBefore=None):
+ text = TextNode(self.soup.new_string(data), self.soup)
+ if insertBefore:
+ self.insertBefore(text, insertBefore)
+ else:
+ self.appendChild(text)
+
+ def insertBefore(self, node, refNode):
+ index = self.element.index(refNode.element)
+ if (node.element.__class__ == NavigableString and self.element.contents
+ and self.element.contents[index-1].__class__ == NavigableString):
+ # (See comments in appendChild)
+ old_node = self.element.contents[index-1]
+ new_str = self.soup.new_string(old_node + node.element)
+ old_node.replace_with(new_str)
+ else:
+ self.element.insert(index, node.element)
+ node.parent = self
+
+ def removeChild(self, node):
+ node.element.extract()
+
+ def reparentChildren(self, new_parent):
+ """Move all of this tag's children into another tag."""
+ # print("MOVE", self.element.contents)
+ # print("FROM", self.element)
+ # print("TO", new_parent.element)
+
+ element = self.element
+ new_parent_element = new_parent.element
+ # Determine what this tag's next_element will be once all the children
+ # are removed.
+ final_next_element = element.next_sibling
+
+ new_parents_last_descendant = new_parent_element._last_descendant(False, False)
+ if len(new_parent_element.contents) > 0:
+ # The new parent already contains children. We will be
+ # appending this tag's children to the end.
+ new_parents_last_child = new_parent_element.contents[-1]
+ new_parents_last_descendant_next_element = new_parents_last_descendant.next_element
+ else:
+ # The new parent contains no children.
+ new_parents_last_child = None
+ new_parents_last_descendant_next_element = new_parent_element.next_element
+
+ to_append = element.contents
+ if len(to_append) > 0:
+ # Set the first child's previous_element and previous_sibling
+ # to elements within the new parent
+ first_child = to_append[0]
+ if new_parents_last_descendant is not None:
+ first_child.previous_element = new_parents_last_descendant
+ else:
+ first_child.previous_element = new_parent_element
+ first_child.previous_sibling = new_parents_last_child
+ if new_parents_last_descendant is not None:
+ new_parents_last_descendant.next_element = first_child
+ else:
+ new_parent_element.next_element = first_child
+ if new_parents_last_child is not None:
+ new_parents_last_child.next_sibling = first_child
+
+ # Find the very last element being moved. It is now the
+ # parent's last descendant. It has no .next_sibling and
+ # its .next_element is whatever the previous last
+ # descendant had.
+ last_childs_last_descendant = to_append[-1]._last_descendant(False, True)
+
+ last_childs_last_descendant.next_element = new_parents_last_descendant_next_element
+ if new_parents_last_descendant_next_element is not None:
+ # TODO: This code has no test coverage and I'm not sure
+ # how to get html5lib to go through this path, but it's
+ # just the other side of the previous line.
+ new_parents_last_descendant_next_element.previous_element = last_childs_last_descendant
+ last_childs_last_descendant.next_sibling = None
+
+ for child in to_append:
+ child.parent = new_parent_element
+ new_parent_element.contents.append(child)
+
+ # Now that this element has no children, change its .next_element.
+ element.contents = []
+ element.next_element = final_next_element
+
+ # print("DONE WITH MOVE")
+ # print("FROM", self.element)
+ # print("TO", new_parent_element)
+
+ def cloneNode(self):
+ tag = self.soup.new_tag(self.element.name, self.namespace)
+ node = Element(tag, self.soup, self.namespace)
+ for key,value in self.attributes:
+ node.attributes[key] = value
+ return node
+
+ def hasContent(self):
+ return self.element.contents
+
+ def getNameTuple(self):
+ if self.namespace == None:
+ return namespaces["html"], self.name
+ else:
+ return self.namespace, self.name
+
+ nameTuple = property(getNameTuple)
+
+class TextNode(Element):
+ def __init__(self, element, soup):
+ treebuilder_base.Node.__init__(self, None)
+ self.element = element
+ self.soup = soup
+
+ def cloneNode(self):
+ raise NotImplementedError
diff --git a/Source/Libs/bs4/builder/_htmlparser.py b/Source/Libs/bs4/builder/_htmlparser.py
new file mode 100644
index 0000000..e37cdcd
--- /dev/null
+++ b/Source/Libs/bs4/builder/_htmlparser.py
@@ -0,0 +1,499 @@
+# encoding: utf-8
+"""Use the HTMLParser library to parse HTML files that aren't too bad."""
+
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+__all__ = [
+ 'HTMLParserTreeBuilder',
+ ]
+
+from html.parser import HTMLParser
+
+try:
+ from html.parser import HTMLParseError
+except ImportError as e:
+ # HTMLParseError is removed in Python 3.5. Since it can never be
+ # thrown in 3.5, we can just define our own class as a placeholder.
+ class HTMLParseError(Exception):
+ pass
+
+import sys
+import warnings
+
+# Starting in Python 3.2, the HTMLParser constructor takes a 'strict'
+# argument, which we'd like to set to False. Unfortunately,
+# http://bugs.python.org/issue13273 makes strict=True a better bet
+# before Python 3.2.3.
+#
+# At the end of this file, we monkeypatch HTMLParser so that
+# strict=True works well on Python 3.2.2.
+major, minor, release = sys.version_info[:3]
+CONSTRUCTOR_TAKES_STRICT = major == 3 and minor == 2 and release >= 3
+CONSTRUCTOR_STRICT_IS_DEPRECATED = major == 3 and minor == 3
+CONSTRUCTOR_TAKES_CONVERT_CHARREFS = major == 3 and minor >= 4
+
+
+from ..element import (
+ CData,
+ Comment,
+ Declaration,
+ Doctype,
+ ProcessingInstruction,
+ )
+from ..dammit import EntitySubstitution, UnicodeDammit
+
+from ..builder import (
+ DetectsXMLParsedAsHTML,
+ HTML,
+ HTMLTreeBuilder,
+ STRICT,
+ )
+
+
+HTMLPARSER = 'html.parser'
+
+class BeautifulSoupHTMLParser(HTMLParser, DetectsXMLParsedAsHTML):
+ """A subclass of the Python standard library's HTMLParser class, which
+ listens for HTMLParser events and translates them into calls
+ to Beautiful Soup's tree construction API.
+ """
+
+ # Strategies for handling duplicate attributes
+ IGNORE = 'ignore'
+ REPLACE = 'replace'
+
+ def __init__(self, *args, **kwargs):
+ """Constructor.
+
+ :param on_duplicate_attribute: A strategy for what to do if a
+ tag includes the same attribute more than once. Accepted
+ values are: REPLACE (replace earlier values with later
+ ones, the default), IGNORE (keep the earliest value
+ encountered), or a callable. A callable must take three
+ arguments: the dictionary of attributes already processed,
+ the name of the duplicate attribute, and the most recent value
+ encountered.
+ """
+ self.on_duplicate_attribute = kwargs.pop(
+ 'on_duplicate_attribute', self.REPLACE
+ )
+ HTMLParser.__init__(self, *args, **kwargs)
+
+ # Keep a list of empty-element tags that were encountered
+ # without an explicit closing tag. If we encounter a closing tag
+ # of this type, we'll associate it with one of those entries.
+ #
+ # This isn't a stack because we don't care about the
+ # order. It's a list of closing tags we've already handled and
+ # will ignore, assuming they ever show up.
+ self.already_closed_empty_element = []
+
+ self._initialize_xml_detector()
+
+ def error(self, msg):
+ """In Python 3, HTMLParser subclasses must implement error(), although
+ this requirement doesn't appear to be documented.
+
+ In Python 2, HTMLParser implements error() by raising an exception,
+ which we don't want to do.
+
+ In any event, this method is called only on very strange
+ markup and our best strategy is to pretend it didn't happen
+ and keep going.
+ """
+ warnings.warn(msg)
+
+ def handle_startendtag(self, name, attrs):
+ """Handle an incoming empty-element tag.
+
+ This is only called when the markup looks like .
+
+ :param name: Name of the tag.
+ :param attrs: Dictionary of the tag's attributes.
+ """
+ # is_startend() tells handle_starttag not to close the tag
+ # just because its name matches a known empty-element tag. We
+ # know that this is an empty-element tag and we want to call
+ # handle_endtag ourselves.
+ tag = self.handle_starttag(name, attrs, handle_empty_element=False)
+ self.handle_endtag(name)
+
+ def handle_starttag(self, name, attrs, handle_empty_element=True):
+ """Handle an opening tag, e.g. ''
+
+ :param name: Name of the tag.
+ :param attrs: Dictionary of the tag's attributes.
+ :param handle_empty_element: True if this tag is known to be
+ an empty-element tag (i.e. there is not expected to be any
+ closing tag).
+ """
+ # XXX namespace
+ attr_dict = {}
+ for key, value in attrs:
+ # Change None attribute values to the empty string
+ # for consistency with the other tree builders.
+ if value is None:
+ value = ''
+ if key in attr_dict:
+ # A single attribute shows up multiple times in this
+ # tag. How to handle it depends on the
+ # on_duplicate_attribute setting.
+ on_dupe = self.on_duplicate_attribute
+ if on_dupe == self.IGNORE:
+ pass
+ elif on_dupe in (None, self.REPLACE):
+ attr_dict[key] = value
+ else:
+ on_dupe(attr_dict, key, value)
+ else:
+ attr_dict[key] = value
+ attrvalue = '""'
+ #print("START", name)
+ sourceline, sourcepos = self.getpos()
+ tag = self.soup.handle_starttag(
+ name, None, None, attr_dict, sourceline=sourceline,
+ sourcepos=sourcepos
+ )
+ if tag and tag.is_empty_element and handle_empty_element:
+ # Unlike other parsers, html.parser doesn't send separate end tag
+ # events for empty-element tags. (It's handled in
+ # handle_startendtag, but only if the original markup looked like
+ # .)
+ #
+ # So we need to call handle_endtag() ourselves. Since we
+ # know the start event is identical to the end event, we
+ # don't want handle_endtag() to cross off any previous end
+ # events for tags of this name.
+ self.handle_endtag(name, check_already_closed=False)
+
+ # But we might encounter an explicit closing tag for this tag
+ # later on. If so, we want to ignore it.
+ self.already_closed_empty_element.append(name)
+
+ if self._root_tag is None:
+ self._root_tag_encountered(name)
+
+ def handle_endtag(self, name, check_already_closed=True):
+ """Handle a closing tag, e.g. ' '
+
+ :param name: A tag name.
+ :param check_already_closed: True if this tag is expected to
+ be the closing portion of an empty-element tag,
+ e.g. ' '.
+ """
+ #print("END", name)
+ if check_already_closed and name in self.already_closed_empty_element:
+ # This is a redundant end tag for an empty-element tag.
+ # We've already called handle_endtag() for it, so just
+ # check it off the list.
+ #print("ALREADY CLOSED", name)
+ self.already_closed_empty_element.remove(name)
+ else:
+ self.soup.handle_endtag(name)
+
+ def handle_data(self, data):
+ """Handle some textual data that shows up between tags."""
+ self.soup.handle_data(data)
+
+ def handle_charref(self, name):
+ """Handle a numeric character reference by converting it to the
+ corresponding Unicode character and treating it as textual
+ data.
+
+ :param name: Character number, possibly in hexadecimal.
+ """
+ # XXX workaround for a bug in HTMLParser. Remove this once
+ # it's fixed in all supported versions.
+ # http://bugs.python.org/issue13633
+ if name.startswith('x'):
+ real_name = int(name.lstrip('x'), 16)
+ elif name.startswith('X'):
+ real_name = int(name.lstrip('X'), 16)
+ else:
+ real_name = int(name)
+
+ data = None
+ if real_name < 256:
+ # HTML numeric entities are supposed to reference Unicode
+ # code points, but sometimes they reference code points in
+ # some other encoding (ahem, Windows-1252). E.g.
+ # instead of É for LEFT DOUBLE QUOTATION MARK. This
+ # code tries to detect this situation and compensate.
+ for encoding in (self.soup.original_encoding, 'windows-1252'):
+ if not encoding:
+ continue
+ try:
+ data = bytearray([real_name]).decode(encoding)
+ except UnicodeDecodeError as e:
+ pass
+ if not data:
+ try:
+ data = chr(real_name)
+ except (ValueError, OverflowError) as e:
+ pass
+ data = data or "\N{REPLACEMENT CHARACTER}"
+ self.handle_data(data)
+
+ def handle_entityref(self, name):
+ """Handle a named entity reference by converting it to the
+ corresponding Unicode character(s) and treating it as textual
+ data.
+
+ :param name: Name of the entity reference.
+ """
+ character = EntitySubstitution.HTML_ENTITY_TO_CHARACTER.get(name)
+ if character is not None:
+ data = character
+ else:
+ # If this were XML, it would be ambiguous whether "&foo"
+ # was an character entity reference with a missing
+ # semicolon or the literal string "&foo". Since this is
+ # HTML, we have a complete list of all character entity references,
+ # and this one wasn't found, so assume it's the literal string "&foo".
+ data = "&%s" % name
+ self.handle_data(data)
+
+ def handle_comment(self, data):
+ """Handle an HTML comment.
+
+ :param data: The text of the comment.
+ """
+ self.soup.endData()
+ self.soup.handle_data(data)
+ self.soup.endData(Comment)
+
+ def handle_decl(self, data):
+ """Handle a DOCTYPE declaration.
+
+ :param data: The text of the declaration.
+ """
+ self.soup.endData()
+ data = data[len("DOCTYPE "):]
+ self.soup.handle_data(data)
+ self.soup.endData(Doctype)
+
+ def unknown_decl(self, data):
+ """Handle a declaration of unknown type -- probably a CDATA block.
+
+ :param data: The text of the declaration.
+ """
+ if data.upper().startswith('CDATA['):
+ cls = CData
+ data = data[len('CDATA['):]
+ else:
+ cls = Declaration
+ self.soup.endData()
+ self.soup.handle_data(data)
+ self.soup.endData(cls)
+
+ def handle_pi(self, data):
+ """Handle a processing instruction.
+
+ :param data: The text of the instruction.
+ """
+ self.soup.endData()
+ self.soup.handle_data(data)
+ self._document_might_be_xml(data)
+ self.soup.endData(ProcessingInstruction)
+
+
+class HTMLParserTreeBuilder(HTMLTreeBuilder):
+ """A Beautiful soup `TreeBuilder` that uses the `HTMLParser` parser,
+ found in the Python standard library.
+ """
+ is_xml = False
+ picklable = True
+ NAME = HTMLPARSER
+ features = [NAME, HTML, STRICT]
+
+ # The html.parser knows which line number and position in the
+ # original file is the source of an element.
+ TRACKS_LINE_NUMBERS = True
+
+ def __init__(self, parser_args=None, parser_kwargs=None, **kwargs):
+ """Constructor.
+
+ :param parser_args: Positional arguments to pass into
+ the BeautifulSoupHTMLParser constructor, once it's
+ invoked.
+ :param parser_kwargs: Keyword arguments to pass into
+ the BeautifulSoupHTMLParser constructor, once it's
+ invoked.
+ :param kwargs: Keyword arguments for the superclass constructor.
+ """
+ # Some keyword arguments will be pulled out of kwargs and placed
+ # into parser_kwargs.
+ extra_parser_kwargs = dict()
+ for arg in ('on_duplicate_attribute',):
+ if arg in kwargs:
+ value = kwargs.pop(arg)
+ extra_parser_kwargs[arg] = value
+ super(HTMLParserTreeBuilder, self).__init__(**kwargs)
+ parser_args = parser_args or []
+ parser_kwargs = parser_kwargs or {}
+ parser_kwargs.update(extra_parser_kwargs)
+ if CONSTRUCTOR_TAKES_STRICT and not CONSTRUCTOR_STRICT_IS_DEPRECATED:
+ parser_kwargs['strict'] = False
+ if CONSTRUCTOR_TAKES_CONVERT_CHARREFS:
+ parser_kwargs['convert_charrefs'] = False
+ self.parser_args = (parser_args, parser_kwargs)
+
+ def prepare_markup(self, markup, user_specified_encoding=None,
+ document_declared_encoding=None, exclude_encodings=None):
+
+ """Run any preliminary steps necessary to make incoming markup
+ acceptable to the parser.
+
+ :param markup: Some markup -- probably a bytestring.
+ :param user_specified_encoding: The user asked to try this encoding.
+ :param document_declared_encoding: The markup itself claims to be
+ in this encoding.
+ :param exclude_encodings: The user asked _not_ to try any of
+ these encodings.
+
+ :yield: A series of 4-tuples:
+ (markup, encoding, declared encoding,
+ has undergone character replacement)
+
+ Each 4-tuple represents a strategy for converting the
+ document to Unicode and parsing it. Each strategy will be tried
+ in turn.
+ """
+ if isinstance(markup, str):
+ # Parse Unicode as-is.
+ yield (markup, None, None, False)
+ return
+
+ # Ask UnicodeDammit to sniff the most likely encoding.
+
+ # This was provided by the end-user; treat it as a known
+ # definite encoding per the algorithm laid out in the HTML5
+ # spec. (See the EncodingDetector class for details.)
+ known_definite_encodings = [user_specified_encoding]
+
+ # This was found in the document; treat it as a slightly lower-priority
+ # user encoding.
+ user_encodings = [document_declared_encoding]
+
+ try_encodings = [user_specified_encoding, document_declared_encoding]
+ dammit = UnicodeDammit(
+ markup,
+ known_definite_encodings=known_definite_encodings,
+ user_encodings=user_encodings,
+ is_html=True,
+ exclude_encodings=exclude_encodings
+ )
+ yield (dammit.markup, dammit.original_encoding,
+ dammit.declared_html_encoding,
+ dammit.contains_replacement_characters)
+
+ def feed(self, markup):
+ """Run some incoming markup through some parsing process,
+ populating the `BeautifulSoup` object in self.soup.
+ """
+ args, kwargs = self.parser_args
+ parser = BeautifulSoupHTMLParser(*args, **kwargs)
+ parser.soup = self.soup
+ try:
+ parser.feed(markup)
+ parser.close()
+ except HTMLParseError as e:
+ warnings.warn(RuntimeWarning(
+ "Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help."))
+ raise e
+ parser.already_closed_empty_element = []
+
+# Patch 3.2 versions of HTMLParser earlier than 3.2.3 to use some
+# 3.2.3 code. This ensures they don't treat markup like
as a
+# string.
+#
+# XXX This code can be removed once most Python 3 users are on 3.2.3.
+if major == 3 and minor == 2 and not CONSTRUCTOR_TAKES_STRICT:
+ import re
+ attrfind_tolerant = re.compile(
+ r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
+ r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
+ HTMLParserTreeBuilder.attrfind_tolerant = attrfind_tolerant
+
+ locatestarttagend = re.compile(r"""
+ <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
+ (?:\s+ # whitespace before attribute name
+ (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
+ (?:\s*=\s* # value indicator
+ (?:'[^']*' # LITA-enclosed value
+ |\"[^\"]*\" # LIT-enclosed value
+ |[^'\">\s]+ # bare value
+ )
+ )?
+ )
+ )*
+ \s* # trailing whitespace
+""", re.VERBOSE)
+ BeautifulSoupHTMLParser.locatestarttagend = locatestarttagend
+
+ from html.parser import tagfind, attrfind
+
+ def parse_starttag(self, i):
+ self.__starttag_text = None
+ endpos = self.check_for_whole_start_tag(i)
+ if endpos < 0:
+ return endpos
+ rawdata = self.rawdata
+ self.__starttag_text = rawdata[i:endpos]
+
+ # Now parse the data between i+1 and j into a tag and attrs
+ attrs = []
+ match = tagfind.match(rawdata, i+1)
+ assert match, 'unexpected call to parse_starttag()'
+ k = match.end()
+ self.lasttag = tag = rawdata[i+1:k].lower()
+ while k < endpos:
+ if self.strict:
+ m = attrfind.match(rawdata, k)
+ else:
+ m = attrfind_tolerant.match(rawdata, k)
+ if not m:
+ break
+ attrname, rest, attrvalue = m.group(1, 2, 3)
+ if not rest:
+ attrvalue = None
+ elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
+ attrvalue[:1] == '"' == attrvalue[-1:]:
+ attrvalue = attrvalue[1:-1]
+ if attrvalue:
+ attrvalue = self.unescape(attrvalue)
+ attrs.append((attrname.lower(), attrvalue))
+ k = m.end()
+
+ end = rawdata[k:endpos].strip()
+ if end not in (">", "/>"):
+ lineno, offset = self.getpos()
+ if "\n" in self.__starttag_text:
+ lineno = lineno + self.__starttag_text.count("\n")
+ offset = len(self.__starttag_text) \
+ - self.__starttag_text.rfind("\n")
+ else:
+ offset = offset + len(self.__starttag_text)
+ if self.strict:
+ self.error("junk characters in start tag: %r"
+ % (rawdata[k:endpos][:20],))
+ self.handle_data(rawdata[i:endpos])
+ return endpos
+ if end.endswith('/>'):
+ # XHTML-style empty tag:
+ self.handle_startendtag(tag, attrs)
+ else:
+ self.handle_starttag(tag, attrs)
+ if tag in self.CDATA_CONTENT_ELEMENTS:
+ self.set_cdata_mode(tag)
+ return endpos
+
+ def set_cdata_mode(self, elem):
+ self.cdata_elem = elem.lower()
+ self.interesting = re.compile(r'\s*%s\s*>' % self.cdata_elem, re.I)
+
+ BeautifulSoupHTMLParser.parse_starttag = parse_starttag
+ BeautifulSoupHTMLParser.set_cdata_mode = set_cdata_mode
+
+ CONSTRUCTOR_TAKES_STRICT = True
diff --git a/Source/Libs/bs4/builder/_lxml.py b/Source/Libs/bs4/builder/_lxml.py
new file mode 100644
index 0000000..971c81e
--- /dev/null
+++ b/Source/Libs/bs4/builder/_lxml.py
@@ -0,0 +1,386 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+__all__ = [
+ 'LXMLTreeBuilderForXML',
+ 'LXMLTreeBuilder',
+ ]
+
+try:
+ from collections.abc import Callable # Python 3.6
+except ImportError as e:
+ from collections import Callable
+
+from io import BytesIO
+from io import StringIO
+from lxml import etree
+from bs4.element import (
+ Comment,
+ Doctype,
+ NamespacedAttribute,
+ ProcessingInstruction,
+ XMLProcessingInstruction,
+)
+from bs4.builder import (
+ DetectsXMLParsedAsHTML,
+ FAST,
+ HTML,
+ HTMLTreeBuilder,
+ PERMISSIVE,
+ ParserRejectedMarkup,
+ TreeBuilder,
+ XML)
+from bs4.dammit import EncodingDetector
+
+LXML = 'lxml'
+
+def _invert(d):
+ "Invert a dictionary."
+ return dict((v,k) for k, v in list(d.items()))
+
+class LXMLTreeBuilderForXML(TreeBuilder):
+ DEFAULT_PARSER_CLASS = etree.XMLParser
+
+ is_xml = True
+ processing_instruction_class = XMLProcessingInstruction
+
+ NAME = "lxml-xml"
+ ALTERNATE_NAMES = ["xml"]
+
+ # Well, it's permissive by XML parser standards.
+ features = [NAME, LXML, XML, FAST, PERMISSIVE]
+
+ CHUNK_SIZE = 512
+
+ # This namespace mapping is specified in the XML Namespace
+ # standard.
+ DEFAULT_NSMAPS = dict(xml='http://www.w3.org/XML/1998/namespace')
+
+ DEFAULT_NSMAPS_INVERTED = _invert(DEFAULT_NSMAPS)
+
+ # NOTE: If we parsed Element objects and looked at .sourceline,
+ # we'd be able to see the line numbers from the original document.
+ # But instead we build an XMLParser or HTMLParser object to serve
+ # as the target of parse messages, and those messages don't include
+ # line numbers.
+ # See: https://bugs.launchpad.net/lxml/+bug/1846906
+
+ def initialize_soup(self, soup):
+ """Let the BeautifulSoup object know about the standard namespace
+ mapping.
+
+ :param soup: A `BeautifulSoup`.
+ """
+ super(LXMLTreeBuilderForXML, self).initialize_soup(soup)
+ self._register_namespaces(self.DEFAULT_NSMAPS)
+
+ def _register_namespaces(self, mapping):
+ """Let the BeautifulSoup object know about namespaces encountered
+ while parsing the document.
+
+ This might be useful later on when creating CSS selectors.
+
+ This will track (almost) all namespaces, even ones that were
+ only in scope for part of the document. If two namespaces have
+ the same prefix, only the first one encountered will be
+ tracked. Un-prefixed namespaces are not tracked.
+
+ :param mapping: A dictionary mapping namespace prefixes to URIs.
+ """
+ for key, value in list(mapping.items()):
+ # This is 'if key' and not 'if key is not None' because we
+ # don't track un-prefixed namespaces. Soupselect will
+ # treat an un-prefixed namespace as the default, which
+ # causes confusion in some cases.
+ if key and key not in self.soup._namespaces:
+ # Let the BeautifulSoup object know about a new namespace.
+ # If there are multiple namespaces defined with the same
+ # prefix, the first one in the document takes precedence.
+ self.soup._namespaces[key] = value
+
+ def default_parser(self, encoding):
+ """Find the default parser for the given encoding.
+
+ :param encoding: A string.
+ :return: Either a parser object or a class, which
+ will be instantiated with default arguments.
+ """
+ if self._default_parser is not None:
+ return self._default_parser
+ return etree.XMLParser(
+ target=self, strip_cdata=False, recover=True, encoding=encoding)
+
+ def parser_for(self, encoding):
+ """Instantiate an appropriate parser for the given encoding.
+
+ :param encoding: A string.
+ :return: A parser object such as an `etree.XMLParser`.
+ """
+ # Use the default parser.
+ parser = self.default_parser(encoding)
+
+ if isinstance(parser, Callable):
+ # Instantiate the parser with default arguments
+ parser = parser(
+ target=self, strip_cdata=False, recover=True, encoding=encoding
+ )
+ return parser
+
+ def __init__(self, parser=None, empty_element_tags=None, **kwargs):
+ # TODO: Issue a warning if parser is present but not a
+ # callable, since that means there's no way to create new
+ # parsers for different encodings.
+ self._default_parser = parser
+ if empty_element_tags is not None:
+ self.empty_element_tags = set(empty_element_tags)
+ self.soup = None
+ self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
+ self.active_namespace_prefixes = [dict(self.DEFAULT_NSMAPS)]
+ super(LXMLTreeBuilderForXML, self).__init__(**kwargs)
+
+ def _getNsTag(self, tag):
+ # Split the namespace URL out of a fully-qualified lxml tag
+ # name. Copied from lxml's src/lxml/sax.py.
+ if tag[0] == '{':
+ return tuple(tag[1:].split('}', 1))
+ else:
+ return (None, tag)
+
+ def prepare_markup(self, markup, user_specified_encoding=None,
+ exclude_encodings=None,
+ document_declared_encoding=None):
+ """Run any preliminary steps necessary to make incoming markup
+ acceptable to the parser.
+
+ lxml really wants to get a bytestring and convert it to
+ Unicode itself. So instead of using UnicodeDammit to convert
+ the bytestring to Unicode using different encodings, this
+ implementation uses EncodingDetector to iterate over the
+ encodings, and tell lxml to try to parse the document as each
+ one in turn.
+
+ :param markup: Some markup -- hopefully a bytestring.
+ :param user_specified_encoding: The user asked to try this encoding.
+ :param document_declared_encoding: The markup itself claims to be
+ in this encoding.
+ :param exclude_encodings: The user asked _not_ to try any of
+ these encodings.
+
+ :yield: A series of 4-tuples:
+ (markup, encoding, declared encoding,
+ has undergone character replacement)
+
+ Each 4-tuple represents a strategy for converting the
+ document to Unicode and parsing it. Each strategy will be tried
+ in turn.
+ """
+ is_html = not self.is_xml
+ if is_html:
+ self.processing_instruction_class = ProcessingInstruction
+ # We're in HTML mode, so if we're given XML, that's worth
+ # noting.
+ DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
+ else:
+ self.processing_instruction_class = XMLProcessingInstruction
+
+ if isinstance(markup, str):
+ # We were given Unicode. Maybe lxml can parse Unicode on
+ # this system?
+
+ # TODO: This is a workaround for
+ # https://bugs.launchpad.net/lxml/+bug/1948551.
+ # We can remove it once the upstream issue is fixed.
+ if len(markup) > 0 and markup[0] == u'\N{BYTE ORDER MARK}':
+ markup = markup[1:]
+ yield markup, None, document_declared_encoding, False
+
+ if isinstance(markup, str):
+ # No, apparently not. Convert the Unicode to UTF-8 and
+ # tell lxml to parse it as UTF-8.
+ yield (markup.encode("utf8"), "utf8",
+ document_declared_encoding, False)
+
+ # This was provided by the end-user; treat it as a known
+ # definite encoding per the algorithm laid out in the HTML5
+ # spec. (See the EncodingDetector class for details.)
+ known_definite_encodings = [user_specified_encoding]
+
+ # This was found in the document; treat it as a slightly lower-priority
+ # user encoding.
+ user_encodings = [document_declared_encoding]
+ detector = EncodingDetector(
+ markup, known_definite_encodings=known_definite_encodings,
+ user_encodings=user_encodings, is_html=is_html,
+ exclude_encodings=exclude_encodings
+ )
+ for encoding in detector.encodings:
+ yield (detector.markup, encoding, document_declared_encoding, False)
+
+ def feed(self, markup):
+ if isinstance(markup, bytes):
+ markup = BytesIO(markup)
+ elif isinstance(markup, str):
+ markup = StringIO(markup)
+
+ # Call feed() at least once, even if the markup is empty,
+ # or the parser won't be initialized.
+ data = markup.read(self.CHUNK_SIZE)
+ try:
+ self.parser = self.parser_for(self.soup.original_encoding)
+ self.parser.feed(data)
+ while len(data) != 0:
+ # Now call feed() on the rest of the data, chunk by chunk.
+ data = markup.read(self.CHUNK_SIZE)
+ if len(data) != 0:
+ self.parser.feed(data)
+ self.parser.close()
+ except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
+ raise ParserRejectedMarkup(e)
+
+ def close(self):
+ self.nsmaps = [self.DEFAULT_NSMAPS_INVERTED]
+
+ def start(self, name, attrs, nsmap={}):
+ # Make sure attrs is a mutable dict--lxml may send an immutable dictproxy.
+ attrs = dict(attrs)
+ nsprefix = None
+ # Invert each namespace map as it comes in.
+ if len(nsmap) == 0 and len(self.nsmaps) > 1:
+ # There are no new namespaces for this tag, but
+ # non-default namespaces are in play, so we need a
+ # separate tag stack to know when they end.
+ self.nsmaps.append(None)
+ elif len(nsmap) > 0:
+ # A new namespace mapping has come into play.
+
+ # First, Let the BeautifulSoup object know about it.
+ self._register_namespaces(nsmap)
+
+ # Then, add it to our running list of inverted namespace
+ # mappings.
+ self.nsmaps.append(_invert(nsmap))
+
+ # The currently active namespace prefixes have
+ # changed. Calculate the new mapping so it can be stored
+ # with all Tag objects created while these prefixes are in
+ # scope.
+ current_mapping = dict(self.active_namespace_prefixes[-1])
+ current_mapping.update(nsmap)
+
+ # We should not track un-prefixed namespaces as we can only hold one
+ # and it will be recognized as the default namespace by soupsieve,
+ # which may be confusing in some situations.
+ if '' in current_mapping:
+ del current_mapping['']
+ self.active_namespace_prefixes.append(current_mapping)
+
+ # Also treat the namespace mapping as a set of attributes on the
+ # tag, so we can recreate it later.
+ attrs = attrs.copy()
+ for prefix, namespace in list(nsmap.items()):
+ attribute = NamespacedAttribute(
+ "xmlns", prefix, "http://www.w3.org/2000/xmlns/")
+ attrs[attribute] = namespace
+
+ # Namespaces are in play. Find any attributes that came in
+ # from lxml with namespaces attached to their names, and
+ # turn then into NamespacedAttribute objects.
+ new_attrs = {}
+ for attr, value in list(attrs.items()):
+ namespace, attr = self._getNsTag(attr)
+ if namespace is None:
+ new_attrs[attr] = value
+ else:
+ nsprefix = self._prefix_for_namespace(namespace)
+ attr = NamespacedAttribute(nsprefix, attr, namespace)
+ new_attrs[attr] = value
+ attrs = new_attrs
+
+ namespace, name = self._getNsTag(name)
+ nsprefix = self._prefix_for_namespace(namespace)
+ self.soup.handle_starttag(
+ name, namespace, nsprefix, attrs,
+ namespaces=self.active_namespace_prefixes[-1]
+ )
+
+ def _prefix_for_namespace(self, namespace):
+ """Find the currently active prefix for the given namespace."""
+ if namespace is None:
+ return None
+ for inverted_nsmap in reversed(self.nsmaps):
+ if inverted_nsmap is not None and namespace in inverted_nsmap:
+ return inverted_nsmap[namespace]
+ return None
+
+ def end(self, name):
+ self.soup.endData()
+ completed_tag = self.soup.tagStack[-1]
+ namespace, name = self._getNsTag(name)
+ nsprefix = None
+ if namespace is not None:
+ for inverted_nsmap in reversed(self.nsmaps):
+ if inverted_nsmap is not None and namespace in inverted_nsmap:
+ nsprefix = inverted_nsmap[namespace]
+ break
+ self.soup.handle_endtag(name, nsprefix)
+ if len(self.nsmaps) > 1:
+ # This tag, or one of its parents, introduced a namespace
+ # mapping, so pop it off the stack.
+ out_of_scope_nsmap = self.nsmaps.pop()
+
+ if out_of_scope_nsmap is not None:
+ # This tag introduced a namespace mapping which is no
+ # longer in scope. Recalculate the currently active
+ # namespace prefixes.
+ self.active_namespace_prefixes.pop()
+
+ def pi(self, target, data):
+ self.soup.endData()
+ data = target + ' ' + data
+ self.soup.handle_data(data)
+ self.soup.endData(self.processing_instruction_class)
+
+ def data(self, content):
+ self.soup.handle_data(content)
+
+ def doctype(self, name, pubid, system):
+ self.soup.endData()
+ doctype = Doctype.for_name_and_ids(name, pubid, system)
+ self.soup.object_was_parsed(doctype)
+
+ def comment(self, content):
+ "Handle comments as Comment objects."
+ self.soup.endData()
+ self.soup.handle_data(content)
+ self.soup.endData(Comment)
+
+ def test_fragment_to_document(self, fragment):
+ """See `TreeBuilder`."""
+ return '\n%s' % fragment
+
+
+class LXMLTreeBuilder(HTMLTreeBuilder, LXMLTreeBuilderForXML):
+
+ NAME = LXML
+ ALTERNATE_NAMES = ["lxml-html"]
+
+ features = ALTERNATE_NAMES + [NAME, HTML, FAST, PERMISSIVE]
+ is_xml = False
+ processing_instruction_class = ProcessingInstruction
+
+ def default_parser(self, encoding):
+ return etree.HTMLParser
+
+ def feed(self, markup):
+ encoding = self.soup.original_encoding
+ try:
+ self.parser = self.parser_for(encoding)
+ self.parser.feed(markup)
+ self.parser.close()
+ except (UnicodeDecodeError, LookupError, etree.ParserError) as e:
+ raise ParserRejectedMarkup(e)
+
+
+ def test_fragment_to_document(self, fragment):
+ """See `TreeBuilder`."""
+ return '%s' % fragment
diff --git a/Source/Libs/bs4/dammit.py b/Source/Libs/bs4/dammit.py
new file mode 100644
index 0000000..692433c
--- /dev/null
+++ b/Source/Libs/bs4/dammit.py
@@ -0,0 +1,1095 @@
+# -*- coding: utf-8 -*-
+"""Beautiful Soup bonus library: Unicode, Dammit
+
+This library converts a bytestream to Unicode through any means
+necessary. It is heavily based on code from Mark Pilgrim's Universal
+Feed Parser. It works best on XML and HTML, but it does not rewrite the
+XML or HTML to reflect a new encoding; that's the tree builder's job.
+"""
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+from html.entities import codepoint2name
+from collections import defaultdict
+import codecs
+import re
+import logging
+import string
+
+# Import a library to autodetect character encodings. We'll support
+# any of a number of libraries that all support the same API:
+#
+# * cchardet
+# * chardet
+# * charset-normalizer
+chardet_module = None
+try:
+ # PyPI package: cchardet
+ import cchardet as chardet_module
+except ImportError:
+ try:
+ # Debian package: python-chardet
+ # PyPI package: chardet
+ import chardet as chardet_module
+ except ImportError:
+ try:
+ # PyPI package: charset-normalizer
+ import charset_normalizer as chardet_module
+ except ImportError:
+ # No chardet available.
+ chardet_module = None
+
+if chardet_module:
+ def chardet_dammit(s):
+ if isinstance(s, str):
+ return None
+ return chardet_module.detect(s)['encoding']
+else:
+ def chardet_dammit(s):
+ return None
+
+# Build bytestring and Unicode versions of regular expressions for finding
+# a declared encoding inside an XML or HTML document.
+xml_encoding = '^\\s*<\\?.*encoding=[\'"](.*?)[\'"].*\\?>'
+html_meta = '<\\s*meta[^>]+charset\\s*=\\s*["\']?([^>]*?)[ /;\'">]'
+encoding_res = dict()
+encoding_res[bytes] = {
+ 'html' : re.compile(html_meta.encode("ascii"), re.I),
+ 'xml' : re.compile(xml_encoding.encode("ascii"), re.I),
+}
+encoding_res[str] = {
+ 'html' : re.compile(html_meta, re.I),
+ 'xml' : re.compile(xml_encoding, re.I)
+}
+
+from html.entities import html5
+
+class EntitySubstitution(object):
+ """The ability to substitute XML or HTML entities for certain characters."""
+
+ def _populate_class_variables():
+ """Initialize variables used by this class to manage the plethora of
+ HTML5 named entities.
+
+ This function returns a 3-tuple containing two dictionaries
+ and a regular expression:
+
+ unicode_to_name - A mapping of Unicode strings like "⦨" to
+ entity names like "angmsdaa". When a single Unicode string has
+ multiple entity names, we try to choose the most commonly-used
+ name.
+
+ name_to_unicode: A mapping of entity names like "angmsdaa" to
+ Unicode strings like "⦨".
+
+ named_entity_re: A regular expression matching (almost) any
+ Unicode string that corresponds to an HTML5 named entity.
+ """
+ unicode_to_name = {}
+ name_to_unicode = {}
+
+ short_entities = set()
+ long_entities_by_first_character = defaultdict(set)
+
+ for name_with_semicolon, character in sorted(html5.items()):
+ # "It is intentional, for legacy compatibility, that many
+ # code points have multiple character reference names. For
+ # example, some appear both with and without the trailing
+ # semicolon, or with different capitalizations."
+ # - https://html.spec.whatwg.org/multipage/named-characters.html#named-character-references
+ #
+ # The parsers are in charge of handling (or not) character
+ # references with no trailing semicolon, so we remove the
+ # semicolon whenever it appears.
+ if name_with_semicolon.endswith(';'):
+ name = name_with_semicolon[:-1]
+ else:
+ name = name_with_semicolon
+
+ # When parsing HTML, we want to recognize any known named
+ # entity and convert it to a sequence of Unicode
+ # characters.
+ if name not in name_to_unicode:
+ name_to_unicode[name] = character
+
+ # When _generating_ HTML, we want to recognize special
+ # character sequences that _could_ be converted to named
+ # entities.
+ unicode_to_name[character] = name
+
+ # We also need to build a regular expression that lets us
+ # _find_ those characters in output strings so we can
+ # replace them.
+ #
+ # This is tricky, for two reasons.
+
+ if (len(character) == 1 and ord(character) < 128
+ and character not in '<>&'):
+ # First, it would be annoying to turn single ASCII
+ # characters like | into named entities like
+ # |. The exceptions are <>&, which we _must_
+ # turn into named entities to produce valid HTML.
+ continue
+
+ if len(character) > 1 and all(ord(x) < 128 for x in character):
+ # We also do not want to turn _combinations_ of ASCII
+ # characters like 'fj' into named entities like 'fj',
+ # though that's more debateable.
+ continue
+
+ # Second, some named entities have a Unicode value that's
+ # a subset of the Unicode value for some _other_ named
+ # entity. As an example, \u2267' is ≧,
+ # but '\u2267\u0338' is ≧̸. Our regular
+ # expression needs to match the first two characters of
+ # "\u2267\u0338foo", but only the first character of
+ # "\u2267foo".
+ #
+ # In this step, we build two sets of characters that
+ # _eventually_ need to go into the regular expression. But
+ # we won't know exactly what the regular expression needs
+ # to look like until we've gone through the entire list of
+ # named entities.
+ if len(character) == 1:
+ short_entities.add(character)
+ else:
+ long_entities_by_first_character[character[0]].add(character)
+
+ # Now that we've been through the entire list of entities, we
+ # can create a regular expression that matches any of them.
+ particles = set()
+ for short in short_entities:
+ long_versions = long_entities_by_first_character[short]
+ if not long_versions:
+ particles.add(short)
+ else:
+ ignore = "".join([x[1] for x in long_versions])
+ # This finds, e.g. \u2267 but only if it is _not_
+ # followed by \u0338.
+ particles.add("%s(?![%s])" % (short, ignore))
+
+ for long_entities in list(long_entities_by_first_character.values()):
+ for long_entity in long_entities:
+ particles.add(long_entity)
+
+ re_definition = "(%s)" % "|".join(particles)
+
+ # If an entity shows up in both html5 and codepoint2name, it's
+ # likely that HTML5 gives it several different names, such as
+ # 'rsquo' and 'rsquor'. When converting Unicode characters to
+ # named entities, the codepoint2name name should take
+ # precedence where possible, since that's the more easily
+ # recognizable one.
+ for codepoint, name in list(codepoint2name.items()):
+ character = chr(codepoint)
+ unicode_to_name[character] = name
+
+ return unicode_to_name, name_to_unicode, re.compile(re_definition)
+ (CHARACTER_TO_HTML_ENTITY, HTML_ENTITY_TO_CHARACTER,
+ CHARACTER_TO_HTML_ENTITY_RE) = _populate_class_variables()
+
+ CHARACTER_TO_XML_ENTITY = {
+ "'": "apos",
+ '"': "quot",
+ "&": "amp",
+ "<": "lt",
+ ">": "gt",
+ }
+
+ BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
+ "&(?!#\\d+;|#x[0-9a-fA-F]+;|\\w+;)"
+ ")")
+
+ AMPERSAND_OR_BRACKET = re.compile("([<>&])")
+
+ @classmethod
+ def _substitute_html_entity(cls, matchobj):
+ """Used with a regular expression to substitute the
+ appropriate HTML entity for a special character string."""
+ entity = cls.CHARACTER_TO_HTML_ENTITY.get(matchobj.group(0))
+ return "&%s;" % entity
+
+ @classmethod
+ def _substitute_xml_entity(cls, matchobj):
+ """Used with a regular expression to substitute the
+ appropriate XML entity for a special character string."""
+ entity = cls.CHARACTER_TO_XML_ENTITY[matchobj.group(0)]
+ return "&%s;" % entity
+
+ @classmethod
+ def quoted_attribute_value(self, value):
+ """Make a value into a quoted XML attribute, possibly escaping it.
+
+ Most strings will be quoted using double quotes.
+
+ Bob's Bar -> "Bob's Bar"
+
+ If a string contains double quotes, it will be quoted using
+ single quotes.
+
+ Welcome to "my bar" -> 'Welcome to "my bar"'
+
+ If a string contains both single and double quotes, the
+ double quotes will be escaped, and the string will be quoted
+ using double quotes.
+
+ Welcome to "Bob's Bar" -> "Welcome to "Bob's bar"
+ """
+ quote_with = '"'
+ if '"' in value:
+ if "'" in value:
+ # The string contains both single and double
+ # quotes. Turn the double quotes into
+ # entities. We quote the double quotes rather than
+ # the single quotes because the entity name is
+ # """ whether this is HTML or XML. If we
+ # quoted the single quotes, we'd have to decide
+ # between ' and &squot;.
+ replace_with = """
+ value = value.replace('"', replace_with)
+ else:
+ # There are double quotes but no single quotes.
+ # We can use single quotes to quote the attribute.
+ quote_with = "'"
+ return quote_with + value + quote_with
+
+ @classmethod
+ def substitute_xml(cls, value, make_quoted_attribute=False):
+ """Substitute XML entities for special XML characters.
+
+ :param value: A string to be substituted. The less-than sign
+ will become <, the greater-than sign will become >,
+ and any ampersands will become &. If you want ampersands
+ that appear to be part of an entity definition to be left
+ alone, use substitute_xml_containing_entities() instead.
+
+ :param make_quoted_attribute: If True, then the string will be
+ quoted, as befits an attribute value.
+ """
+ # Escape angle brackets and ampersands.
+ value = cls.AMPERSAND_OR_BRACKET.sub(
+ cls._substitute_xml_entity, value)
+
+ if make_quoted_attribute:
+ value = cls.quoted_attribute_value(value)
+ return value
+
+ @classmethod
+ def substitute_xml_containing_entities(
+ cls, value, make_quoted_attribute=False):
+ """Substitute XML entities for special XML characters.
+
+ :param value: A string to be substituted. The less-than sign will
+ become <, the greater-than sign will become >, and any
+ ampersands that are not part of an entity defition will
+ become &.
+
+ :param make_quoted_attribute: If True, then the string will be
+ quoted, as befits an attribute value.
+ """
+ # Escape angle brackets, and ampersands that aren't part of
+ # entities.
+ value = cls.BARE_AMPERSAND_OR_BRACKET.sub(
+ cls._substitute_xml_entity, value)
+
+ if make_quoted_attribute:
+ value = cls.quoted_attribute_value(value)
+ return value
+
+ @classmethod
+ def substitute_html(cls, s):
+ """Replace certain Unicode characters with named HTML entities.
+
+ This differs from data.encode(encoding, 'xmlcharrefreplace')
+ in that the goal is to make the result more readable (to those
+ with ASCII displays) rather than to recover from
+ errors. There's absolutely nothing wrong with a UTF-8 string
+ containg a LATIN SMALL LETTER E WITH ACUTE, but replacing that
+ character with "é" will make it more readable to some
+ people.
+
+ :param s: A Unicode string.
+ """
+ return cls.CHARACTER_TO_HTML_ENTITY_RE.sub(
+ cls._substitute_html_entity, s)
+
+
+class EncodingDetector:
+ """Suggests a number of possible encodings for a bytestring.
+
+ Order of precedence:
+
+ 1. Encodings you specifically tell EncodingDetector to try first
+ (the known_definite_encodings argument to the constructor).
+
+ 2. An encoding determined by sniffing the document's byte-order mark.
+
+ 3. Encodings you specifically tell EncodingDetector to try if
+ byte-order mark sniffing fails (the user_encodings argument to the
+ constructor).
+
+ 4. An encoding declared within the bytestring itself, either in an
+ XML declaration (if the bytestring is to be interpreted as an XML
+ document), or in a tag (if the bytestring is to be
+ interpreted as an HTML document.)
+
+ 5. An encoding detected through textual analysis by chardet,
+ cchardet, or a similar external library.
+
+ 4. UTF-8.
+
+ 5. Windows-1252.
+
+ """
+ def __init__(self, markup, known_definite_encodings=None,
+ is_html=False, exclude_encodings=None,
+ user_encodings=None, override_encodings=None):
+ """Constructor.
+
+ :param markup: Some markup in an unknown encoding.
+
+ :param known_definite_encodings: When determining the encoding
+ of `markup`, these encodings will be tried first, in
+ order. In HTML terms, this corresponds to the "known
+ definite encoding" step defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#parsing-with-a-known-character-encoding
+
+ :param user_encodings: These encodings will be tried after the
+ `known_definite_encodings` have been tried and failed, and
+ after an attempt to sniff the encoding by looking at a
+ byte order mark has failed. In HTML terms, this
+ corresponds to the step "user has explicitly instructed
+ the user agent to override the document's character
+ encoding", defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding
+
+ :param override_encodings: A deprecated alias for
+ known_definite_encodings. Any encodings here will be tried
+ immediately after the encodings in
+ known_definite_encodings.
+
+ :param is_html: If True, this markup is considered to be
+ HTML. Otherwise it's assumed to be XML.
+
+ :param exclude_encodings: These encodings will not be tried,
+ even if they otherwise would be.
+
+ """
+ self.known_definite_encodings = list(known_definite_encodings or [])
+ if override_encodings:
+ self.known_definite_encodings += override_encodings
+ self.user_encodings = user_encodings or []
+ exclude_encodings = exclude_encodings or []
+ self.exclude_encodings = set([x.lower() for x in exclude_encodings])
+ self.chardet_encoding = None
+ self.is_html = is_html
+ self.declared_encoding = None
+
+ # First order of business: strip a byte-order mark.
+ self.markup, self.sniffed_encoding = self.strip_byte_order_mark(markup)
+
+ def _usable(self, encoding, tried):
+ """Should we even bother to try this encoding?
+
+ :param encoding: Name of an encoding.
+ :param tried: Encodings that have already been tried. This will be modified
+ as a side effect.
+ """
+ if encoding is not None:
+ encoding = encoding.lower()
+ if encoding in self.exclude_encodings:
+ return False
+ if encoding not in tried:
+ tried.add(encoding)
+ return True
+ return False
+
+ @property
+ def encodings(self):
+ """Yield a number of encodings that might work for this markup.
+
+ :yield: A sequence of strings.
+ """
+ tried = set()
+
+ # First, try the known definite encodings
+ for e in self.known_definite_encodings:
+ if self._usable(e, tried):
+ yield e
+
+ # Did the document originally start with a byte-order mark
+ # that indicated its encoding?
+ if self._usable(self.sniffed_encoding, tried):
+ yield self.sniffed_encoding
+
+ # Sniffing the byte-order mark did nothing; try the user
+ # encodings.
+ for e in self.user_encodings:
+ if self._usable(e, tried):
+ yield e
+
+ # Look within the document for an XML or HTML encoding
+ # declaration.
+ if self.declared_encoding is None:
+ self.declared_encoding = self.find_declared_encoding(
+ self.markup, self.is_html)
+ if self._usable(self.declared_encoding, tried):
+ yield self.declared_encoding
+
+ # Use third-party character set detection to guess at the
+ # encoding.
+ if self.chardet_encoding is None:
+ self.chardet_encoding = chardet_dammit(self.markup)
+ if self._usable(self.chardet_encoding, tried):
+ yield self.chardet_encoding
+
+ # As a last-ditch effort, try utf-8 and windows-1252.
+ for e in ('utf-8', 'windows-1252'):
+ if self._usable(e, tried):
+ yield e
+
+ @classmethod
+ def strip_byte_order_mark(cls, data):
+ """If a byte-order mark is present, strip it and return the encoding it implies.
+
+ :param data: Some markup.
+ :return: A 2-tuple (modified data, implied encoding)
+ """
+ encoding = None
+ if isinstance(data, str):
+ # Unicode data cannot have a byte-order mark.
+ return data, encoding
+ if (len(data) >= 4) and (data[:2] == b'\xfe\xff') \
+ and (data[2:4] != '\x00\x00'):
+ encoding = 'utf-16be'
+ data = data[2:]
+ elif (len(data) >= 4) and (data[:2] == b'\xff\xfe') \
+ and (data[2:4] != '\x00\x00'):
+ encoding = 'utf-16le'
+ data = data[2:]
+ elif data[:3] == b'\xef\xbb\xbf':
+ encoding = 'utf-8'
+ data = data[3:]
+ elif data[:4] == b'\x00\x00\xfe\xff':
+ encoding = 'utf-32be'
+ data = data[4:]
+ elif data[:4] == b'\xff\xfe\x00\x00':
+ encoding = 'utf-32le'
+ data = data[4:]
+ return data, encoding
+
+ @classmethod
+ def find_declared_encoding(cls, markup, is_html=False, search_entire_document=False):
+ """Given a document, tries to find its declared encoding.
+
+ An XML encoding is declared at the beginning of the document.
+
+ An HTML encoding is declared in a tag, hopefully near the
+ beginning of the document.
+
+ :param markup: Some markup.
+ :param is_html: If True, this markup is considered to be HTML. Otherwise
+ it's assumed to be XML.
+ :param search_entire_document: Since an encoding is supposed to declared near the beginning
+ of the document, most of the time it's only necessary to search a few kilobytes of data.
+ Set this to True to force this method to search the entire document.
+ """
+ if search_entire_document:
+ xml_endpos = html_endpos = len(markup)
+ else:
+ xml_endpos = 1024
+ html_endpos = max(2048, int(len(markup) * 0.05))
+
+ if isinstance(markup, bytes):
+ res = encoding_res[bytes]
+ else:
+ res = encoding_res[str]
+
+ xml_re = res['xml']
+ html_re = res['html']
+ declared_encoding = None
+ declared_encoding_match = xml_re.search(markup, endpos=xml_endpos)
+ if not declared_encoding_match and is_html:
+ declared_encoding_match = html_re.search(markup, endpos=html_endpos)
+ if declared_encoding_match is not None:
+ declared_encoding = declared_encoding_match.groups()[0]
+ if declared_encoding:
+ if isinstance(declared_encoding, bytes):
+ declared_encoding = declared_encoding.decode('ascii', 'replace')
+ return declared_encoding.lower()
+ return None
+
+class UnicodeDammit:
+ """A class for detecting the encoding of a *ML document and
+ converting it to a Unicode string. If the source encoding is
+ windows-1252, can replace MS smart quotes with their HTML or XML
+ equivalents."""
+
+ # This dictionary maps commonly seen values for "charset" in HTML
+ # meta tags to the corresponding Python codec names. It only covers
+ # values that aren't in Python's aliases and can't be determined
+ # by the heuristics in find_codec.
+ CHARSET_ALIASES = {"macintosh": "mac-roman",
+ "x-sjis": "shift-jis"}
+
+ ENCODINGS_WITH_SMART_QUOTES = [
+ "windows-1252",
+ "iso-8859-1",
+ "iso-8859-2",
+ ]
+
+ def __init__(self, markup, known_definite_encodings=[],
+ smart_quotes_to=None, is_html=False, exclude_encodings=[],
+ user_encodings=None, override_encodings=None
+ ):
+ """Constructor.
+
+ :param markup: A bytestring representing markup in an unknown encoding.
+
+ :param known_definite_encodings: When determining the encoding
+ of `markup`, these encodings will be tried first, in
+ order. In HTML terms, this corresponds to the "known
+ definite encoding" step defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#parsing-with-a-known-character-encoding
+
+ :param user_encodings: These encodings will be tried after the
+ `known_definite_encodings` have been tried and failed, and
+ after an attempt to sniff the encoding by looking at a
+ byte order mark has failed. In HTML terms, this
+ corresponds to the step "user has explicitly instructed
+ the user agent to override the document's character
+ encoding", defined here:
+ https://html.spec.whatwg.org/multipage/parsing.html#determining-the-character-encoding
+
+ :param override_encodings: A deprecated alias for
+ known_definite_encodings. Any encodings here will be tried
+ immediately after the encodings in
+ known_definite_encodings.
+
+ :param smart_quotes_to: By default, Microsoft smart quotes will, like all other characters, be converted
+ to Unicode characters. Setting this to 'ascii' will convert them to ASCII quotes instead.
+ Setting it to 'xml' will convert them to XML entity references, and setting it to 'html'
+ will convert them to HTML entity references.
+ :param is_html: If True, this markup is considered to be HTML. Otherwise
+ it's assumed to be XML.
+ :param exclude_encodings: These encodings will not be considered, even
+ if the sniffing code thinks they might make sense.
+
+ """
+ self.smart_quotes_to = smart_quotes_to
+ self.tried_encodings = []
+ self.contains_replacement_characters = False
+ self.is_html = is_html
+ self.log = logging.getLogger(__name__)
+ self.detector = EncodingDetector(
+ markup, known_definite_encodings, is_html, exclude_encodings,
+ user_encodings, override_encodings
+ )
+
+ # Short-circuit if the data is in Unicode to begin with.
+ if isinstance(markup, str) or markup == '':
+ self.markup = markup
+ self.unicode_markup = str(markup)
+ self.original_encoding = None
+ return
+
+ # The encoding detector may have stripped a byte-order mark.
+ # Use the stripped markup from this point on.
+ self.markup = self.detector.markup
+
+ u = None
+ for encoding in self.detector.encodings:
+ markup = self.detector.markup
+ u = self._convert_from(encoding)
+ if u is not None:
+ break
+
+ if not u:
+ # None of the encodings worked. As an absolute last resort,
+ # try them again with character replacement.
+
+ for encoding in self.detector.encodings:
+ if encoding != "ascii":
+ u = self._convert_from(encoding, "replace")
+ if u is not None:
+ self.log.warning(
+ "Some characters could not be decoded, and were "
+ "replaced with REPLACEMENT CHARACTER."
+ )
+ self.contains_replacement_characters = True
+ break
+
+ # If none of that worked, we could at this point force it to
+ # ASCII, but that would destroy so much data that I think
+ # giving up is better.
+ self.unicode_markup = u
+ if not u:
+ self.original_encoding = None
+
+ def _sub_ms_char(self, match):
+ """Changes a MS smart quote character to an XML or HTML
+ entity, or an ASCII character."""
+ orig = match.group(1)
+ if self.smart_quotes_to == 'ascii':
+ sub = self.MS_CHARS_TO_ASCII.get(orig).encode()
+ else:
+ sub = self.MS_CHARS.get(orig)
+ if type(sub) == tuple:
+ if self.smart_quotes_to == 'xml':
+ sub = ''.encode() + sub[1].encode() + ';'.encode()
+ else:
+ sub = '&'.encode() + sub[0].encode() + ';'.encode()
+ else:
+ sub = sub.encode()
+ return sub
+
+ def _convert_from(self, proposed, errors="strict"):
+ """Attempt to convert the markup to the proposed encoding.
+
+ :param proposed: The name of a character encoding.
+ """
+ proposed = self.find_codec(proposed)
+ if not proposed or (proposed, errors) in self.tried_encodings:
+ return None
+ self.tried_encodings.append((proposed, errors))
+ markup = self.markup
+ # Convert smart quotes to HTML if coming from an encoding
+ # that might have them.
+ if (self.smart_quotes_to is not None
+ and proposed in self.ENCODINGS_WITH_SMART_QUOTES):
+ smart_quotes_re = b"([\x80-\x9f])"
+ smart_quotes_compiled = re.compile(smart_quotes_re)
+ markup = smart_quotes_compiled.sub(self._sub_ms_char, markup)
+
+ try:
+ #print("Trying to convert document to %s (errors=%s)" % (
+ # proposed, errors))
+ u = self._to_unicode(markup, proposed, errors)
+ self.markup = u
+ self.original_encoding = proposed
+ except Exception as e:
+ #print("That didn't work!")
+ #print(e)
+ return None
+ #print("Correct encoding: %s" % proposed)
+ return self.markup
+
+ def _to_unicode(self, data, encoding, errors="strict"):
+ """Given a string and its encoding, decodes the string into Unicode.
+
+ :param encoding: The name of an encoding.
+ """
+ return str(data, encoding, errors)
+
+ @property
+ def declared_html_encoding(self):
+ """If the markup is an HTML document, returns the encoding declared _within_
+ the document.
+ """
+ if not self.is_html:
+ return None
+ return self.detector.declared_encoding
+
+ def find_codec(self, charset):
+ """Convert the name of a character set to a codec name.
+
+ :param charset: The name of a character set.
+ :return: The name of a codec.
+ """
+ value = (self._codec(self.CHARSET_ALIASES.get(charset, charset))
+ or (charset and self._codec(charset.replace("-", "")))
+ or (charset and self._codec(charset.replace("-", "_")))
+ or (charset and charset.lower())
+ or charset
+ )
+ if value:
+ return value.lower()
+ return None
+
+ def _codec(self, charset):
+ if not charset:
+ return charset
+ codec = None
+ try:
+ codecs.lookup(charset)
+ codec = charset
+ except (LookupError, ValueError):
+ pass
+ return codec
+
+
+ # A partial mapping of ISO-Latin-1 to HTML entities/XML numeric entities.
+ MS_CHARS = {b'\x80': ('euro', '20AC'),
+ b'\x81': ' ',
+ b'\x82': ('sbquo', '201A'),
+ b'\x83': ('fnof', '192'),
+ b'\x84': ('bdquo', '201E'),
+ b'\x85': ('hellip', '2026'),
+ b'\x86': ('dagger', '2020'),
+ b'\x87': ('Dagger', '2021'),
+ b'\x88': ('circ', '2C6'),
+ b'\x89': ('permil', '2030'),
+ b'\x8A': ('Scaron', '160'),
+ b'\x8B': ('lsaquo', '2039'),
+ b'\x8C': ('OElig', '152'),
+ b'\x8D': '?',
+ b'\x8E': ('#x17D', '17D'),
+ b'\x8F': '?',
+ b'\x90': '?',
+ b'\x91': ('lsquo', '2018'),
+ b'\x92': ('rsquo', '2019'),
+ b'\x93': ('ldquo', '201C'),
+ b'\x94': ('rdquo', '201D'),
+ b'\x95': ('bull', '2022'),
+ b'\x96': ('ndash', '2013'),
+ b'\x97': ('mdash', '2014'),
+ b'\x98': ('tilde', '2DC'),
+ b'\x99': ('trade', '2122'),
+ b'\x9a': ('scaron', '161'),
+ b'\x9b': ('rsaquo', '203A'),
+ b'\x9c': ('oelig', '153'),
+ b'\x9d': '?',
+ b'\x9e': ('#x17E', '17E'),
+ b'\x9f': ('Yuml', ''),}
+
+ # A parochial partial mapping of ISO-Latin-1 to ASCII. Contains
+ # horrors like stripping diacritical marks to turn á into a, but also
+ # contains non-horrors like turning “ into ".
+ MS_CHARS_TO_ASCII = {
+ b'\x80' : 'EUR',
+ b'\x81' : ' ',
+ b'\x82' : ',',
+ b'\x83' : 'f',
+ b'\x84' : ',,',
+ b'\x85' : '...',
+ b'\x86' : '+',
+ b'\x87' : '++',
+ b'\x88' : '^',
+ b'\x89' : '%',
+ b'\x8a' : 'S',
+ b'\x8b' : '<',
+ b'\x8c' : 'OE',
+ b'\x8d' : '?',
+ b'\x8e' : 'Z',
+ b'\x8f' : '?',
+ b'\x90' : '?',
+ b'\x91' : "'",
+ b'\x92' : "'",
+ b'\x93' : '"',
+ b'\x94' : '"',
+ b'\x95' : '*',
+ b'\x96' : '-',
+ b'\x97' : '--',
+ b'\x98' : '~',
+ b'\x99' : '(TM)',
+ b'\x9a' : 's',
+ b'\x9b' : '>',
+ b'\x9c' : 'oe',
+ b'\x9d' : '?',
+ b'\x9e' : 'z',
+ b'\x9f' : 'Y',
+ b'\xa0' : ' ',
+ b'\xa1' : '!',
+ b'\xa2' : 'c',
+ b'\xa3' : 'GBP',
+ b'\xa4' : '$', #This approximation is especially parochial--this is the
+ #generic currency symbol.
+ b'\xa5' : 'YEN',
+ b'\xa6' : '|',
+ b'\xa7' : 'S',
+ b'\xa8' : '..',
+ b'\xa9' : '',
+ b'\xaa' : '(th)',
+ b'\xab' : '<<',
+ b'\xac' : '!',
+ b'\xad' : ' ',
+ b'\xae' : '(R)',
+ b'\xaf' : '-',
+ b'\xb0' : 'o',
+ b'\xb1' : '+-',
+ b'\xb2' : '2',
+ b'\xb3' : '3',
+ b'\xb4' : ("'", 'acute'),
+ b'\xb5' : 'u',
+ b'\xb6' : 'P',
+ b'\xb7' : '*',
+ b'\xb8' : ',',
+ b'\xb9' : '1',
+ b'\xba' : '(th)',
+ b'\xbb' : '>>',
+ b'\xbc' : '1/4',
+ b'\xbd' : '1/2',
+ b'\xbe' : '3/4',
+ b'\xbf' : '?',
+ b'\xc0' : 'A',
+ b'\xc1' : 'A',
+ b'\xc2' : 'A',
+ b'\xc3' : 'A',
+ b'\xc4' : 'A',
+ b'\xc5' : 'A',
+ b'\xc6' : 'AE',
+ b'\xc7' : 'C',
+ b'\xc8' : 'E',
+ b'\xc9' : 'E',
+ b'\xca' : 'E',
+ b'\xcb' : 'E',
+ b'\xcc' : 'I',
+ b'\xcd' : 'I',
+ b'\xce' : 'I',
+ b'\xcf' : 'I',
+ b'\xd0' : 'D',
+ b'\xd1' : 'N',
+ b'\xd2' : 'O',
+ b'\xd3' : 'O',
+ b'\xd4' : 'O',
+ b'\xd5' : 'O',
+ b'\xd6' : 'O',
+ b'\xd7' : '*',
+ b'\xd8' : 'O',
+ b'\xd9' : 'U',
+ b'\xda' : 'U',
+ b'\xdb' : 'U',
+ b'\xdc' : 'U',
+ b'\xdd' : 'Y',
+ b'\xde' : 'b',
+ b'\xdf' : 'B',
+ b'\xe0' : 'a',
+ b'\xe1' : 'a',
+ b'\xe2' : 'a',
+ b'\xe3' : 'a',
+ b'\xe4' : 'a',
+ b'\xe5' : 'a',
+ b'\xe6' : 'ae',
+ b'\xe7' : 'c',
+ b'\xe8' : 'e',
+ b'\xe9' : 'e',
+ b'\xea' : 'e',
+ b'\xeb' : 'e',
+ b'\xec' : 'i',
+ b'\xed' : 'i',
+ b'\xee' : 'i',
+ b'\xef' : 'i',
+ b'\xf0' : 'o',
+ b'\xf1' : 'n',
+ b'\xf2' : 'o',
+ b'\xf3' : 'o',
+ b'\xf4' : 'o',
+ b'\xf5' : 'o',
+ b'\xf6' : 'o',
+ b'\xf7' : '/',
+ b'\xf8' : 'o',
+ b'\xf9' : 'u',
+ b'\xfa' : 'u',
+ b'\xfb' : 'u',
+ b'\xfc' : 'u',
+ b'\xfd' : 'y',
+ b'\xfe' : 'b',
+ b'\xff' : 'y',
+ }
+
+ # A map used when removing rogue Windows-1252/ISO-8859-1
+ # characters in otherwise UTF-8 documents.
+ #
+ # Note that \x81, \x8d, \x8f, \x90, and \x9d are undefined in
+ # Windows-1252.
+ WINDOWS_1252_TO_UTF8 = {
+ 0x80 : b'\xe2\x82\xac', # €
+ 0x82 : b'\xe2\x80\x9a', # ‚
+ 0x83 : b'\xc6\x92', # ƒ
+ 0x84 : b'\xe2\x80\x9e', # „
+ 0x85 : b'\xe2\x80\xa6', # …
+ 0x86 : b'\xe2\x80\xa0', # †
+ 0x87 : b'\xe2\x80\xa1', # ‡
+ 0x88 : b'\xcb\x86', # ˆ
+ 0x89 : b'\xe2\x80\xb0', # ‰
+ 0x8a : b'\xc5\xa0', # Š
+ 0x8b : b'\xe2\x80\xb9', # ‹
+ 0x8c : b'\xc5\x92', # Œ
+ 0x8e : b'\xc5\xbd', # Ž
+ 0x91 : b'\xe2\x80\x98', # ‘
+ 0x92 : b'\xe2\x80\x99', # ’
+ 0x93 : b'\xe2\x80\x9c', # “
+ 0x94 : b'\xe2\x80\x9d', # ”
+ 0x95 : b'\xe2\x80\xa2', # •
+ 0x96 : b'\xe2\x80\x93', # –
+ 0x97 : b'\xe2\x80\x94', # —
+ 0x98 : b'\xcb\x9c', # ˜
+ 0x99 : b'\xe2\x84\xa2', # ™
+ 0x9a : b'\xc5\xa1', # š
+ 0x9b : b'\xe2\x80\xba', # ›
+ 0x9c : b'\xc5\x93', # œ
+ 0x9e : b'\xc5\xbe', # ž
+ 0x9f : b'\xc5\xb8', # Ÿ
+ 0xa0 : b'\xc2\xa0', #
+ 0xa1 : b'\xc2\xa1', # ¡
+ 0xa2 : b'\xc2\xa2', # ¢
+ 0xa3 : b'\xc2\xa3', # £
+ 0xa4 : b'\xc2\xa4', # ¤
+ 0xa5 : b'\xc2\xa5', # ¥
+ 0xa6 : b'\xc2\xa6', # ¦
+ 0xa7 : b'\xc2\xa7', # §
+ 0xa8 : b'\xc2\xa8', # ¨
+ 0xa9 : b'\xc2\xa9', # ©
+ 0xaa : b'\xc2\xaa', # ª
+ 0xab : b'\xc2\xab', # «
+ 0xac : b'\xc2\xac', # ¬
+ 0xad : b'\xc2\xad', #
+ 0xae : b'\xc2\xae', # ®
+ 0xaf : b'\xc2\xaf', # ¯
+ 0xb0 : b'\xc2\xb0', # °
+ 0xb1 : b'\xc2\xb1', # ±
+ 0xb2 : b'\xc2\xb2', # ²
+ 0xb3 : b'\xc2\xb3', # ³
+ 0xb4 : b'\xc2\xb4', # ´
+ 0xb5 : b'\xc2\xb5', # µ
+ 0xb6 : b'\xc2\xb6', # ¶
+ 0xb7 : b'\xc2\xb7', # ·
+ 0xb8 : b'\xc2\xb8', # ¸
+ 0xb9 : b'\xc2\xb9', # ¹
+ 0xba : b'\xc2\xba', # º
+ 0xbb : b'\xc2\xbb', # »
+ 0xbc : b'\xc2\xbc', # ¼
+ 0xbd : b'\xc2\xbd', # ½
+ 0xbe : b'\xc2\xbe', # ¾
+ 0xbf : b'\xc2\xbf', # ¿
+ 0xc0 : b'\xc3\x80', # À
+ 0xc1 : b'\xc3\x81', # Á
+ 0xc2 : b'\xc3\x82', # Â
+ 0xc3 : b'\xc3\x83', # Ã
+ 0xc4 : b'\xc3\x84', # Ä
+ 0xc5 : b'\xc3\x85', # Å
+ 0xc6 : b'\xc3\x86', # Æ
+ 0xc7 : b'\xc3\x87', # Ç
+ 0xc8 : b'\xc3\x88', # È
+ 0xc9 : b'\xc3\x89', # É
+ 0xca : b'\xc3\x8a', # Ê
+ 0xcb : b'\xc3\x8b', # Ë
+ 0xcc : b'\xc3\x8c', # Ì
+ 0xcd : b'\xc3\x8d', # Í
+ 0xce : b'\xc3\x8e', # Î
+ 0xcf : b'\xc3\x8f', # Ï
+ 0xd0 : b'\xc3\x90', # Ð
+ 0xd1 : b'\xc3\x91', # Ñ
+ 0xd2 : b'\xc3\x92', # Ò
+ 0xd3 : b'\xc3\x93', # Ó
+ 0xd4 : b'\xc3\x94', # Ô
+ 0xd5 : b'\xc3\x95', # Õ
+ 0xd6 : b'\xc3\x96', # Ö
+ 0xd7 : b'\xc3\x97', # ×
+ 0xd8 : b'\xc3\x98', # Ø
+ 0xd9 : b'\xc3\x99', # Ù
+ 0xda : b'\xc3\x9a', # Ú
+ 0xdb : b'\xc3\x9b', # Û
+ 0xdc : b'\xc3\x9c', # Ü
+ 0xdd : b'\xc3\x9d', # Ý
+ 0xde : b'\xc3\x9e', # Þ
+ 0xdf : b'\xc3\x9f', # ß
+ 0xe0 : b'\xc3\xa0', # à
+ 0xe1 : b'\xa1', # á
+ 0xe2 : b'\xc3\xa2', # â
+ 0xe3 : b'\xc3\xa3', # ã
+ 0xe4 : b'\xc3\xa4', # ä
+ 0xe5 : b'\xc3\xa5', # å
+ 0xe6 : b'\xc3\xa6', # æ
+ 0xe7 : b'\xc3\xa7', # ç
+ 0xe8 : b'\xc3\xa8', # è
+ 0xe9 : b'\xc3\xa9', # é
+ 0xea : b'\xc3\xaa', # ê
+ 0xeb : b'\xc3\xab', # ë
+ 0xec : b'\xc3\xac', # ì
+ 0xed : b'\xc3\xad', # í
+ 0xee : b'\xc3\xae', # î
+ 0xef : b'\xc3\xaf', # ï
+ 0xf0 : b'\xc3\xb0', # ð
+ 0xf1 : b'\xc3\xb1', # ñ
+ 0xf2 : b'\xc3\xb2', # ò
+ 0xf3 : b'\xc3\xb3', # ó
+ 0xf4 : b'\xc3\xb4', # ô
+ 0xf5 : b'\xc3\xb5', # õ
+ 0xf6 : b'\xc3\xb6', # ö
+ 0xf7 : b'\xc3\xb7', # ÷
+ 0xf8 : b'\xc3\xb8', # ø
+ 0xf9 : b'\xc3\xb9', # ù
+ 0xfa : b'\xc3\xba', # ú
+ 0xfb : b'\xc3\xbb', # û
+ 0xfc : b'\xc3\xbc', # ü
+ 0xfd : b'\xc3\xbd', # ý
+ 0xfe : b'\xc3\xbe', # þ
+ }
+
+ MULTIBYTE_MARKERS_AND_SIZES = [
+ (0xc2, 0xdf, 2), # 2-byte characters start with a byte C2-DF
+ (0xe0, 0xef, 3), # 3-byte characters start with E0-EF
+ (0xf0, 0xf4, 4), # 4-byte characters start with F0-F4
+ ]
+
+ FIRST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[0][0]
+ LAST_MULTIBYTE_MARKER = MULTIBYTE_MARKERS_AND_SIZES[-1][1]
+
+ @classmethod
+ def detwingle(cls, in_bytes, main_encoding="utf8",
+ embedded_encoding="windows-1252"):
+ """Fix characters from one encoding embedded in some other encoding.
+
+ Currently the only situation supported is Windows-1252 (or its
+ subset ISO-8859-1), embedded in UTF-8.
+
+ :param in_bytes: A bytestring that you suspect contains
+ characters from multiple encodings. Note that this _must_
+ be a bytestring. If you've already converted the document
+ to Unicode, you're too late.
+ :param main_encoding: The primary encoding of `in_bytes`.
+ :param embedded_encoding: The encoding that was used to embed characters
+ in the main document.
+ :return: A bytestring in which `embedded_encoding`
+ characters have been converted to their `main_encoding`
+ equivalents.
+ """
+ if embedded_encoding.replace('_', '-').lower() not in (
+ 'windows-1252', 'windows_1252'):
+ raise NotImplementedError(
+ "Windows-1252 and ISO-8859-1 are the only currently supported "
+ "embedded encodings.")
+
+ if main_encoding.lower() not in ('utf8', 'utf-8'):
+ raise NotImplementedError(
+ "UTF-8 is the only currently supported main encoding.")
+
+ byte_chunks = []
+
+ chunk_start = 0
+ pos = 0
+ while pos < len(in_bytes):
+ byte = in_bytes[pos]
+ if not isinstance(byte, int):
+ # Python 2.x
+ byte = ord(byte)
+ if (byte >= cls.FIRST_MULTIBYTE_MARKER
+ and byte <= cls.LAST_MULTIBYTE_MARKER):
+ # This is the start of a UTF-8 multibyte character. Skip
+ # to the end.
+ for start, end, size in cls.MULTIBYTE_MARKERS_AND_SIZES:
+ if byte >= start and byte <= end:
+ pos += size
+ break
+ elif byte >= 0x80 and byte in cls.WINDOWS_1252_TO_UTF8:
+ # We found a Windows-1252 character!
+ # Save the string up to this point as a chunk.
+ byte_chunks.append(in_bytes[chunk_start:pos])
+
+ # Now translate the Windows-1252 character into UTF-8
+ # and add it as another, one-byte chunk.
+ byte_chunks.append(cls.WINDOWS_1252_TO_UTF8[byte])
+ pos += 1
+ chunk_start = pos
+ else:
+ # Go on to the next character.
+ pos += 1
+ if chunk_start == 0:
+ # The string is unchanged.
+ return in_bytes
+ else:
+ # Store the final chunk.
+ byte_chunks.append(in_bytes[chunk_start:])
+ return b''.join(byte_chunks)
+
diff --git a/Source/Libs/bs4/diagnose.py b/Source/Libs/bs4/diagnose.py
new file mode 100644
index 0000000..3bf583f
--- /dev/null
+++ b/Source/Libs/bs4/diagnose.py
@@ -0,0 +1,248 @@
+"""Diagnostic functions, mainly for use when doing tech support."""
+
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+import cProfile
+from io import BytesIO
+from html.parser import HTMLParser
+import bs4
+from bs4 import BeautifulSoup, __version__
+from bs4.builder import builder_registry
+
+import os
+import pstats
+import random
+import tempfile
+import time
+import traceback
+import sys
+import cProfile
+
+def diagnose(data):
+ """Diagnostic suite for isolating common problems.
+
+ :param data: A string containing markup that needs to be explained.
+ :return: None; diagnostics are printed to standard output.
+ """
+ print(("Diagnostic running on Beautiful Soup %s" % __version__))
+ print(("Python version %s" % sys.version))
+
+ basic_parsers = ["html.parser", "html5lib", "lxml"]
+ for name in basic_parsers:
+ for builder in builder_registry.builders:
+ if name in builder.features:
+ break
+ else:
+ basic_parsers.remove(name)
+ print((
+ "I noticed that %s is not installed. Installing it may help." %
+ name))
+
+ if 'lxml' in basic_parsers:
+ basic_parsers.append("lxml-xml")
+ try:
+ from lxml import etree
+ print(("Found lxml version %s" % ".".join(map(str,etree.LXML_VERSION))))
+ except ImportError as e:
+ print(
+ "lxml is not installed or couldn't be imported.")
+
+
+ if 'html5lib' in basic_parsers:
+ try:
+ import html5lib
+ print(("Found html5lib version %s" % html5lib.__version__))
+ except ImportError as e:
+ print(
+ "html5lib is not installed or couldn't be imported.")
+
+ if hasattr(data, 'read'):
+ data = data.read()
+ elif data.startswith("http:") or data.startswith("https:"):
+ print(('"%s" looks like a URL. Beautiful Soup is not an HTTP client.' % data))
+ print("You need to use some other library to get the document behind the URL, and feed that document to Beautiful Soup.")
+ return
+ else:
+ try:
+ if os.path.exists(data):
+ print(('"%s" looks like a filename. Reading data from the file.' % data))
+ with open(data) as fp:
+ data = fp.read()
+ except ValueError:
+ # This can happen on some platforms when the 'filename' is
+ # too long. Assume it's data and not a filename.
+ pass
+ print("")
+
+ for parser in basic_parsers:
+ print(("Trying to parse your markup with %s" % parser))
+ success = False
+ try:
+ soup = BeautifulSoup(data, features=parser)
+ success = True
+ except Exception as e:
+ print(("%s could not parse the markup." % parser))
+ traceback.print_exc()
+ if success:
+ print(("Here's what %s did with the markup:" % parser))
+ print((soup.prettify()))
+
+ print(("-" * 80))
+
+def lxml_trace(data, html=True, **kwargs):
+ """Print out the lxml events that occur during parsing.
+
+ This lets you see how lxml parses a document when no Beautiful
+ Soup code is running. You can use this to determine whether
+ an lxml-specific problem is in Beautiful Soup's lxml tree builders
+ or in lxml itself.
+
+ :param data: Some markup.
+ :param html: If True, markup will be parsed with lxml's HTML parser.
+ if False, lxml's XML parser will be used.
+ """
+ from lxml import etree
+ recover = kwargs.pop('recover', True)
+ if isinstance(data, str):
+ data = data.encode("utf8")
+ reader = BytesIO(data)
+ for event, element in etree.iterparse(
+ reader, html=html, recover=recover, **kwargs
+ ):
+ print(("%s, %4s, %s" % (event, element.tag, element.text)))
+
+class AnnouncingParser(HTMLParser):
+ """Subclass of HTMLParser that announces parse events, without doing
+ anything else.
+
+ You can use this to get a picture of how html.parser sees a given
+ document. The easiest way to do this is to call `htmlparser_trace`.
+ """
+
+ def _p(self, s):
+ print(s)
+
+ def handle_starttag(self, name, attrs):
+ self._p("%s START" % name)
+
+ def handle_endtag(self, name):
+ self._p("%s END" % name)
+
+ def handle_data(self, data):
+ self._p("%s DATA" % data)
+
+ def handle_charref(self, name):
+ self._p("%s CHARREF" % name)
+
+ def handle_entityref(self, name):
+ self._p("%s ENTITYREF" % name)
+
+ def handle_comment(self, data):
+ self._p("%s COMMENT" % data)
+
+ def handle_decl(self, data):
+ self._p("%s DECL" % data)
+
+ def unknown_decl(self, data):
+ self._p("%s UNKNOWN-DECL" % data)
+
+ def handle_pi(self, data):
+ self._p("%s PI" % data)
+
+def htmlparser_trace(data):
+ """Print out the HTMLParser events that occur during parsing.
+
+ This lets you see how HTMLParser parses a document when no
+ Beautiful Soup code is running.
+
+ :param data: Some markup.
+ """
+ parser = AnnouncingParser()
+ parser.feed(data)
+
+_vowels = "aeiou"
+_consonants = "bcdfghjklmnpqrstvwxyz"
+
+def rword(length=5):
+ "Generate a random word-like string."
+ s = ''
+ for i in range(length):
+ if i % 2 == 0:
+ t = _consonants
+ else:
+ t = _vowels
+ s += random.choice(t)
+ return s
+
+def rsentence(length=4):
+ "Generate a random sentence-like string."
+ return " ".join(rword(random.randint(4,9)) for i in range(length))
+
+def rdoc(num_elements=1000):
+ """Randomly generate an invalid HTML document."""
+ tag_names = ['p', 'div', 'span', 'i', 'b', 'script', 'table']
+ elements = []
+ for i in range(num_elements):
+ choice = random.randint(0,3)
+ if choice == 0:
+ # New tag.
+ tag_name = random.choice(tag_names)
+ elements.append("<%s>" % tag_name)
+ elif choice == 1:
+ elements.append(rsentence(random.randint(1,4)))
+ elif choice == 2:
+ # Close a tag.
+ tag_name = random.choice(tag_names)
+ elements.append("%s>" % tag_name)
+ return "" + "\n".join(elements) + ""
+
+def benchmark_parsers(num_elements=100000):
+ """Very basic head-to-head performance benchmark."""
+ print(("Comparative parser benchmark on Beautiful Soup %s" % __version__))
+ data = rdoc(num_elements)
+ print(("Generated a large invalid HTML document (%d bytes)." % len(data)))
+
+ for parser in ["lxml", ["lxml", "html"], "html5lib", "html.parser"]:
+ success = False
+ try:
+ a = time.time()
+ soup = BeautifulSoup(data, parser)
+ b = time.time()
+ success = True
+ except Exception as e:
+ print(("%s could not parse the markup." % parser))
+ traceback.print_exc()
+ if success:
+ print(("BS4+%s parsed the markup in %.2fs." % (parser, b-a)))
+
+ from lxml import etree
+ a = time.time()
+ etree.HTML(data)
+ b = time.time()
+ print(("Raw lxml parsed the markup in %.2fs." % (b-a)))
+
+ import html5lib
+ parser = html5lib.HTMLParser()
+ a = time.time()
+ parser.parse(data)
+ b = time.time()
+ print(("Raw html5lib parsed the markup in %.2fs." % (b-a)))
+
+def profile(num_elements=100000, parser="lxml"):
+ """Use Python's profiler on a randomly generated document."""
+ filehandle = tempfile.NamedTemporaryFile()
+ filename = filehandle.name
+
+ data = rdoc(num_elements)
+ vars = dict(bs4=bs4, data=data, parser=parser)
+ cProfile.runctx('bs4.BeautifulSoup(data, parser)' , vars, vars, filename)
+
+ stats = pstats.Stats(filename)
+ # stats.strip_dirs()
+ stats.sort_stats("cumulative")
+ stats.print_stats('_html5lib|bs4', 50)
+
+# If this file is run as a script, standard input is diagnosed.
+if __name__ == '__main__':
+ diagnose(sys.stdin.read())
diff --git a/Source/Libs/bs4/element.py b/Source/Libs/bs4/element.py
new file mode 100644
index 0000000..0199eff
--- /dev/null
+++ b/Source/Libs/bs4/element.py
@@ -0,0 +1,2291 @@
+# Use of this source code is governed by the MIT license.
+__license__ = "MIT"
+
+try:
+ from collections.abc import Callable # Python 3.6
+except ImportError as e:
+ from collections import Callable
+import re
+import sys
+import warnings
+try:
+ import soupsieve
+except ImportError as e:
+ soupsieve = None
+ warnings.warn(
+ 'The soupsieve package is not installed. CSS selectors cannot be used.'
+ )
+
+from .formatter import (
+ Formatter,
+ HTMLFormatter,
+ XMLFormatter,
+)
+
+DEFAULT_OUTPUT_ENCODING = "utf-8"
+
+nonwhitespace_re = re.compile(r"\S+")
+
+# NOTE: This isn't used as of 4.7.0. I'm leaving it for a little bit on
+# the off chance someone imported it for their own use.
+whitespace_re = re.compile(r"\s+")
+
+def _alias(attr):
+ """Alias one attribute name to another for backward compatibility"""
+ @property
+ def alias(self):
+ return getattr(self, attr)
+
+ @alias.setter
+ def alias(self):
+ return setattr(self, attr)
+ return alias
+
+
+# These encodings are recognized by Python (so PageElement.encode
+# could theoretically support them) but XML and HTML don't recognize
+# them (so they should not show up in an XML or HTML document as that
+# document's encoding).
+#
+# If an XML document is encoded in one of these encodings, no encoding
+# will be mentioned in the XML declaration. If an HTML document is
+# encoded in one of these encodings, and the HTML document has a
+# tag that mentions an encoding, the encoding will be given as
+# the empty string.
+#
+# Source:
+# https://docs.python.org/3/library/codecs.html#python-specific-encodings
+PYTHON_SPECIFIC_ENCODINGS = set([
+ "idna",
+ "mbcs",
+ "oem",
+ "palmos",
+ "punycode",
+ "raw_unicode_escape",
+ "undefined",
+ "unicode_escape",
+ "raw-unicode-escape",
+ "unicode-escape",
+ "string-escape",
+ "string_escape",
+])
+
+
+class NamespacedAttribute(str):
+ """A namespaced string (e.g. 'xml:lang') that remembers the namespace
+ ('xml') and the name ('lang') that were used to create it.
+ """
+
+ def __new__(cls, prefix, name=None, namespace=None):
+ if not name:
+ # This is the default namespace. Its name "has no value"
+ # per https://www.w3.org/TR/xml-names/#defaulting
+ name = None
+
+ if not name:
+ obj = str.__new__(cls, prefix)
+ elif not prefix:
+ # Not really namespaced.
+ obj = str.__new__(cls, name)
+ else:
+ obj = str.__new__(cls, prefix + ":" + name)
+ obj.prefix = prefix
+ obj.name = name
+ obj.namespace = namespace
+ return obj
+
+class AttributeValueWithCharsetSubstitution(str):
+ """A stand-in object for a character encoding specified in HTML."""
+
+class CharsetMetaAttributeValue(AttributeValueWithCharsetSubstitution):
+ """A generic stand-in for the value of a meta tag's 'charset' attribute.
+
+ When Beautiful Soup parses the markup ' ', the
+ value of the 'charset' attribute will be one of these objects.
+ """
+
+ def __new__(cls, original_value):
+ obj = str.__new__(cls, original_value)
+ obj.original_value = original_value
+ return obj
+
+ def encode(self, encoding):
+ """When an HTML document is being encoded to a given encoding, the
+ value of a meta tag's 'charset' is the name of the encoding.
+ """
+ if encoding in PYTHON_SPECIFIC_ENCODINGS:
+ return ''
+ return encoding
+
+
+class ContentMetaAttributeValue(AttributeValueWithCharsetSubstitution):
+ """A generic stand-in for the value of a meta tag's 'content' attribute.
+
+ When Beautiful Soup parses the markup:
+
+
+ The value of the 'content' attribute will be one of these objects.
+ """
+
+ CHARSET_RE = re.compile(r"((^|;)\s*charset=)([^;]*)", re.M)
+
+ def __new__(cls, original_value):
+ match = cls.CHARSET_RE.search(original_value)
+ if match is None:
+ # No substitution necessary.
+ return str.__new__(str, original_value)
+
+ obj = str.__new__(cls, original_value)
+ obj.original_value = original_value
+ return obj
+
+ def encode(self, encoding):
+ if encoding in PYTHON_SPECIFIC_ENCODINGS:
+ return ''
+ def rewrite(match):
+ return match.group(1) + encoding
+ return self.CHARSET_RE.sub(rewrite, self.original_value)
+
+
+class PageElement(object):
+ """Contains the navigational information for some part of the page:
+ that is, its current location in the parse tree.
+
+ NavigableString, Tag, etc. are all subclasses of PageElement.
+ """
+
+ def setup(self, parent=None, previous_element=None, next_element=None,
+ previous_sibling=None, next_sibling=None):
+ """Sets up the initial relations between this element and
+ other elements.
+
+ :param parent: The parent of this element.
+
+ :param previous_element: The element parsed immediately before
+ this one.
+
+ :param next_element: The element parsed immediately before
+ this one.
+
+ :param previous_sibling: The most recently encountered element
+ on the same level of the parse tree as this one.
+
+ :param previous_sibling: The next element to be encountered
+ on the same level of the parse tree as this one.
+ """
+ self.parent = parent
+
+ self.previous_element = previous_element
+ if previous_element is not None:
+ self.previous_element.next_element = self
+
+ self.next_element = next_element
+ if self.next_element is not None:
+ self.next_element.previous_element = self
+
+ self.next_sibling = next_sibling
+ if self.next_sibling is not None:
+ self.next_sibling.previous_sibling = self
+
+ if (previous_sibling is None
+ and self.parent is not None and self.parent.contents):
+ previous_sibling = self.parent.contents[-1]
+
+ self.previous_sibling = previous_sibling
+ if previous_sibling is not None:
+ self.previous_sibling.next_sibling = self
+
+ def format_string(self, s, formatter):
+ """Format the given string using the given formatter.
+
+ :param s: A string.
+ :param formatter: A Formatter object, or a string naming one of the standard formatters.
+ """
+ if formatter is None:
+ return s
+ if not isinstance(formatter, Formatter):
+ formatter = self.formatter_for_name(formatter)
+ output = formatter.substitute(s)
+ return output
+
+ def formatter_for_name(self, formatter):
+ """Look up or create a Formatter for the given identifier,
+ if necessary.
+
+ :param formatter: Can be a Formatter object (used as-is), a
+ function (used as the entity substitution hook for an
+ XMLFormatter or HTMLFormatter), or a string (used to look
+ up an XMLFormatter or HTMLFormatter in the appropriate
+ registry.
+ """
+ if isinstance(formatter, Formatter):
+ return formatter
+ if self._is_xml:
+ c = XMLFormatter
+ else:
+ c = HTMLFormatter
+ if isinstance(formatter, Callable):
+ return c(entity_substitution=formatter)
+ return c.REGISTRY[formatter]
+
+ @property
+ def _is_xml(self):
+ """Is this element part of an XML tree or an HTML tree?
+
+ This is used in formatter_for_name, when deciding whether an
+ XMLFormatter or HTMLFormatter is more appropriate. It can be
+ inefficient, but it should be called very rarely.
+ """
+ if self.known_xml is not None:
+ # Most of the time we will have determined this when the
+ # document is parsed.
+ return self.known_xml
+
+ # Otherwise, it's likely that this element was created by
+ # direct invocation of the constructor from within the user's
+ # Python code.
+ if self.parent is None:
+ # This is the top-level object. It should have .known_xml set
+ # from tree creation. If not, take a guess--BS is usually
+ # used on HTML markup.
+ return getattr(self, 'is_xml', False)
+ return self.parent._is_xml
+
+ nextSibling = _alias("next_sibling") # BS3
+ previousSibling = _alias("previous_sibling") # BS3
+
+ default = object()
+ def _all_strings(self, strip=False, types=default):
+ """Yield all strings of certain classes, possibly stripping them.
+
+ This is implemented differently in Tag and NavigableString.
+ """
+ raise NotImplementedError()
+
+ @property
+ def stripped_strings(self):
+ """Yield all strings in this PageElement, stripping them first.
+
+ :yield: A sequence of stripped strings.
+ """
+ for string in self._all_strings(True):
+ yield string
+
+ def get_text(self, separator="", strip=False,
+ types=default):
+ """Get all child strings of this PageElement, concatenated using the
+ given separator.
+
+ :param separator: Strings will be concatenated using this separator.
+
+ :param strip: If True, strings will be stripped before being
+ concatenated.
+
+ :param types: A tuple of NavigableString subclasses. Any
+ strings of a subclass not found in this list will be
+ ignored. Although there are exceptions, the default
+ behavior in most cases is to consider only NavigableString
+ and CData objects. That means no comments, processing
+ instructions, etc.
+
+ :return: A string.
+ """
+ return separator.join([s for s in self._all_strings(
+ strip, types=types)])
+ getText = get_text
+ text = property(get_text)
+
+ def replace_with(self, *args):
+ """Replace this PageElement with one or more PageElements, keeping the
+ rest of the tree the same.
+
+ :param args: One or more PageElements.
+ :return: `self`, no longer part of the tree.
+ """
+ if self.parent is None:
+ raise ValueError(
+ "Cannot replace one element with another when the "
+ "element to be replaced is not part of a tree.")
+ if len(args) == 1 and args[0] is self:
+ return
+ if any(x is self.parent for x in args):
+ raise ValueError("Cannot replace a Tag with its parent.")
+ old_parent = self.parent
+ my_index = self.parent.index(self)
+ self.extract(_self_index=my_index)
+ for idx, replace_with in enumerate(args, start=my_index):
+ old_parent.insert(idx, replace_with)
+ return self
+ replaceWith = replace_with # BS3
+
+ def unwrap(self):
+ """Replace this PageElement with its contents.
+
+ :return: `self`, no longer part of the tree.
+ """
+ my_parent = self.parent
+ if self.parent is None:
+ raise ValueError(
+ "Cannot replace an element with its contents when that"
+ "element is not part of a tree.")
+ my_index = self.parent.index(self)
+ self.extract(_self_index=my_index)
+ for child in reversed(self.contents[:]):
+ my_parent.insert(my_index, child)
+ return self
+ replace_with_children = unwrap
+ replaceWithChildren = unwrap # BS3
+
+ def wrap(self, wrap_inside):
+ """Wrap this PageElement inside another one.
+
+ :param wrap_inside: A PageElement.
+ :return: `wrap_inside`, occupying the position in the tree that used
+ to be occupied by `self`, and with `self` inside it.
+ """
+ me = self.replace_with(wrap_inside)
+ wrap_inside.append(me)
+ return wrap_inside
+
+ def extract(self, _self_index=None):
+ """Destructively rips this element out of the tree.
+
+ :param _self_index: The location of this element in its parent's
+ .contents, if known. Passing this in allows for a performance
+ optimization.
+
+ :return: `self`, no longer part of the tree.
+ """
+ if self.parent is not None:
+ if _self_index is None:
+ _self_index = self.parent.index(self)
+ del self.parent.contents[_self_index]
+
+ #Find the two elements that would be next to each other if
+ #this element (and any children) hadn't been parsed. Connect
+ #the two.
+ last_child = self._last_descendant()
+ next_element = last_child.next_element
+
+ if (self.previous_element is not None and
+ self.previous_element is not next_element):
+ self.previous_element.next_element = next_element
+ if next_element is not None and next_element is not self.previous_element:
+ next_element.previous_element = self.previous_element
+ self.previous_element = None
+ last_child.next_element = None
+
+ self.parent = None
+ if (self.previous_sibling is not None
+ and self.previous_sibling is not self.next_sibling):
+ self.previous_sibling.next_sibling = self.next_sibling
+ if (self.next_sibling is not None
+ and self.next_sibling is not self.previous_sibling):
+ self.next_sibling.previous_sibling = self.previous_sibling
+ self.previous_sibling = self.next_sibling = None
+ return self
+
+ def _last_descendant(self, is_initialized=True, accept_self=True):
+ """Finds the last element beneath this object to be parsed.
+
+ :param is_initialized: Has `setup` been called on this PageElement
+ yet?
+ :param accept_self: Is `self` an acceptable answer to the question?
+ """
+ if is_initialized and self.next_sibling is not None:
+ last_child = self.next_sibling.previous_element
+ else:
+ last_child = self
+ while isinstance(last_child, Tag) and last_child.contents:
+ last_child = last_child.contents[-1]
+ if not accept_self and last_child is self:
+ last_child = None
+ return last_child
+ # BS3: Not part of the API!
+ _lastRecursiveChild = _last_descendant
+
+ def insert(self, position, new_child):
+ """Insert a new PageElement in the list of this PageElement's children.
+
+ This works the same way as `list.insert`.
+
+ :param position: The numeric position that should be occupied
+ in `self.children` by the new PageElement.
+ :param new_child: A PageElement.
+ """
+ if new_child is None:
+ raise ValueError("Cannot insert None into a tag.")
+ if new_child is self:
+ raise ValueError("Cannot insert a tag into itself.")
+ if (isinstance(new_child, str)
+ and not isinstance(new_child, NavigableString)):
+ new_child = NavigableString(new_child)
+
+ from bs4 import BeautifulSoup
+ if isinstance(new_child, BeautifulSoup):
+ # We don't want to end up with a situation where one BeautifulSoup
+ # object contains another. Insert the children one at a time.
+ for subchild in list(new_child.contents):
+ self.insert(position, subchild)
+ position += 1
+ return
+ position = min(position, len(self.contents))
+ if hasattr(new_child, 'parent') and new_child.parent is not None:
+ # We're 'inserting' an element that's already one
+ # of this object's children.
+ if new_child.parent is self:
+ current_index = self.index(new_child)
+ if current_index < position:
+ # We're moving this element further down the list
+ # of this object's children. That means that when
+ # we extract this element, our target index will
+ # jump down one.
+ position -= 1
+ new_child.extract()
+
+ new_child.parent = self
+ previous_child = None
+ if position == 0:
+ new_child.previous_sibling = None
+ new_child.previous_element = self
+ else:
+ previous_child = self.contents[position - 1]
+ new_child.previous_sibling = previous_child
+ new_child.previous_sibling.next_sibling = new_child
+ new_child.previous_element = previous_child._last_descendant(False)
+ if new_child.previous_element is not None:
+ new_child.previous_element.next_element = new_child
+
+ new_childs_last_element = new_child._last_descendant(False)
+
+ if position >= len(self.contents):
+ new_child.next_sibling = None
+
+ parent = self
+ parents_next_sibling = None
+ while parents_next_sibling is None and parent is not None:
+ parents_next_sibling = parent.next_sibling
+ parent = parent.parent
+ if parents_next_sibling is not None:
+ # We found the element that comes next in the document.
+ break
+ if parents_next_sibling is not None:
+ new_childs_last_element.next_element = parents_next_sibling
+ else:
+ # The last element of this tag is the last element in
+ # the document.
+ new_childs_last_element.next_element = None
+ else:
+ next_child = self.contents[position]
+ new_child.next_sibling = next_child
+ if new_child.next_sibling is not None:
+ new_child.next_sibling.previous_sibling = new_child
+ new_childs_last_element.next_element = next_child
+
+ if new_childs_last_element.next_element is not None:
+ new_childs_last_element.next_element.previous_element = new_childs_last_element
+ self.contents.insert(position, new_child)
+
+ def append(self, tag):
+ """Appends the given PageElement to the contents of this one.
+
+ :param tag: A PageElement.
+ """
+ self.insert(len(self.contents), tag)
+
+ def extend(self, tags):
+ """Appends the given PageElements to this one's contents.
+
+ :param tags: A list of PageElements.
+ """
+ if isinstance(tags, Tag):
+ # Calling self.append() on another tag's contents will change
+ # the list we're iterating over. Make a list that won't
+ # change.
+ tags = list(tags.contents)
+ for tag in tags:
+ self.append(tag)
+
+ def insert_before(self, *args):
+ """Makes the given element(s) the immediate predecessor of this one.
+
+ All the elements will have the same parent, and the given elements
+ will be immediately before this one.
+
+ :param args: One or more PageElements.
+ """
+ parent = self.parent
+ if parent is None:
+ raise ValueError(
+ "Element has no parent, so 'before' has no meaning.")
+ if any(x is self for x in args):
+ raise ValueError("Can't insert an element before itself.")
+ for predecessor in args:
+ # Extract first so that the index won't be screwed up if they
+ # are siblings.
+ if isinstance(predecessor, PageElement):
+ predecessor.extract()
+ index = parent.index(self)
+ parent.insert(index, predecessor)
+
+ def insert_after(self, *args):
+ """Makes the given element(s) the immediate successor of this one.
+
+ The elements will have the same parent, and the given elements
+ will be immediately after this one.
+
+ :param args: One or more PageElements.
+ """
+ # Do all error checking before modifying the tree.
+ parent = self.parent
+ if parent is None:
+ raise ValueError(
+ "Element has no parent, so 'after' has no meaning.")
+ if any(x is self for x in args):
+ raise ValueError("Can't insert an element after itself.")
+
+ offset = 0
+ for successor in args:
+ # Extract first so that the index won't be screwed up if they
+ # are siblings.
+ if isinstance(successor, PageElement):
+ successor.extract()
+ index = parent.index(self)
+ parent.insert(index+1+offset, successor)
+ offset += 1
+
+ def find_next(self, name=None, attrs={}, string=None, **kwargs):
+ """Find the first PageElement that matches the given criteria and
+ appears later in the document than this PageElement.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ return self._find_one(self.find_all_next, name, attrs, string, **kwargs)
+ findNext = find_next # BS3
+
+ def find_all_next(self, name=None, attrs={}, string=None, limit=None,
+ **kwargs):
+ """Find all PageElements that match the given criteria and appear
+ later in the document than this PageElement.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :param limit: Stop looking after finding this many results.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A ResultSet containing PageElements.
+ """
+ return self._find_all(name, attrs, string, limit, self.next_elements,
+ **kwargs)
+ findAllNext = find_all_next # BS3
+
+ def find_next_sibling(self, name=None, attrs={}, string=None, **kwargs):
+ """Find the closest sibling to this PageElement that matches the
+ given criteria and appears later in the document.
+
+ All find_* methods take a common set of arguments. See the
+ online documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ return self._find_one(self.find_next_siblings, name, attrs, string,
+ **kwargs)
+ findNextSibling = find_next_sibling # BS3
+
+ def find_next_siblings(self, name=None, attrs={}, string=None, limit=None,
+ **kwargs):
+ """Find all siblings of this PageElement that match the given criteria
+ and appear later in the document.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :param limit: Stop looking after finding this many results.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A ResultSet of PageElements.
+ :rtype: bs4.element.ResultSet
+ """
+ return self._find_all(name, attrs, string, limit,
+ self.next_siblings, **kwargs)
+ findNextSiblings = find_next_siblings # BS3
+ fetchNextSiblings = find_next_siblings # BS2
+
+ def find_previous(self, name=None, attrs={}, string=None, **kwargs):
+ """Look backwards in the document from this PageElement and find the
+ first PageElement that matches the given criteria.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ return self._find_one(
+ self.find_all_previous, name, attrs, string, **kwargs)
+ findPrevious = find_previous # BS3
+
+ def find_all_previous(self, name=None, attrs={}, string=None, limit=None,
+ **kwargs):
+ """Look backwards in the document from this PageElement and find all
+ PageElements that match the given criteria.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :param limit: Stop looking after finding this many results.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A ResultSet of PageElements.
+ :rtype: bs4.element.ResultSet
+ """
+ return self._find_all(name, attrs, string, limit, self.previous_elements,
+ **kwargs)
+ findAllPrevious = find_all_previous # BS3
+ fetchPrevious = find_all_previous # BS2
+
+ def find_previous_sibling(self, name=None, attrs={}, string=None, **kwargs):
+ """Returns the closest sibling to this PageElement that matches the
+ given criteria and appears earlier in the document.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ return self._find_one(self.find_previous_siblings, name, attrs, string,
+ **kwargs)
+ findPreviousSibling = find_previous_sibling # BS3
+
+ def find_previous_siblings(self, name=None, attrs={}, string=None,
+ limit=None, **kwargs):
+ """Returns all siblings to this PageElement that match the
+ given criteria and appear earlier in the document.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :param limit: Stop looking after finding this many results.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A ResultSet of PageElements.
+ :rtype: bs4.element.ResultSet
+ """
+ return self._find_all(name, attrs, string, limit,
+ self.previous_siblings, **kwargs)
+ findPreviousSiblings = find_previous_siblings # BS3
+ fetchPreviousSiblings = find_previous_siblings # BS2
+
+ def find_parent(self, name=None, attrs={}, **kwargs):
+ """Find the closest parent of this PageElement that matches the given
+ criteria.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :kwargs: A dictionary of filters on attribute values.
+
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ # NOTE: We can't use _find_one because findParents takes a different
+ # set of arguments.
+ r = None
+ l = self.find_parents(name, attrs, 1, **kwargs)
+ if l:
+ r = l[0]
+ return r
+ findParent = find_parent # BS3
+
+ def find_parents(self, name=None, attrs={}, limit=None, **kwargs):
+ """Find all parents of this PageElement that match the given criteria.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param limit: Stop looking after finding this many results.
+ :kwargs: A dictionary of filters on attribute values.
+
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ return self._find_all(name, attrs, None, limit, self.parents,
+ **kwargs)
+ findParents = find_parents # BS3
+ fetchParents = find_parents # BS2
+
+ @property
+ def next(self):
+ """The PageElement, if any, that was parsed just after this one.
+
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ return self.next_element
+
+ @property
+ def previous(self):
+ """The PageElement, if any, that was parsed just before this one.
+
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ return self.previous_element
+
+ #These methods do the real heavy lifting.
+
+ def _find_one(self, method, name, attrs, string, **kwargs):
+ r = None
+ l = method(name, attrs, string, 1, **kwargs)
+ if l:
+ r = l[0]
+ return r
+
+ def _find_all(self, name, attrs, string, limit, generator, **kwargs):
+ "Iterates over a generator looking for things that match."
+
+ if string is None and 'text' in kwargs:
+ string = kwargs.pop('text')
+ warnings.warn(
+ "The 'text' argument to find()-type methods is deprecated. Use 'string' instead.",
+ DeprecationWarning
+ )
+
+ if isinstance(name, SoupStrainer):
+ strainer = name
+ else:
+ strainer = SoupStrainer(name, attrs, string, **kwargs)
+
+ if string is None and not limit and not attrs and not kwargs:
+ if name is True or name is None:
+ # Optimization to find all tags.
+ result = (element for element in generator
+ if isinstance(element, Tag))
+ return ResultSet(strainer, result)
+ elif isinstance(name, str):
+ # Optimization to find all tags with a given name.
+ if name.count(':') == 1:
+ # This is a name with a prefix. If this is a namespace-aware document,
+ # we need to match the local name against tag.name. If not,
+ # we need to match the fully-qualified name against tag.name.
+ prefix, local_name = name.split(':', 1)
+ else:
+ prefix = None
+ local_name = name
+ result = (element for element in generator
+ if isinstance(element, Tag)
+ and (
+ element.name == name
+ ) or (
+ element.name == local_name
+ and (prefix is None or element.prefix == prefix)
+ )
+ )
+ return ResultSet(strainer, result)
+ results = ResultSet(strainer)
+ while True:
+ try:
+ i = next(generator)
+ except StopIteration:
+ break
+ if i:
+ found = strainer.search(i)
+ if found:
+ results.append(found)
+ if limit and len(results) >= limit:
+ break
+ return results
+
+ #These generators can be used to navigate starting from both
+ #NavigableStrings and Tags.
+ @property
+ def next_elements(self):
+ """All PageElements that were parsed after this one.
+
+ :yield: A sequence of PageElements.
+ """
+ i = self.next_element
+ while i is not None:
+ yield i
+ i = i.next_element
+
+ @property
+ def next_siblings(self):
+ """All PageElements that are siblings of this one but were parsed
+ later.
+
+ :yield: A sequence of PageElements.
+ """
+ i = self.next_sibling
+ while i is not None:
+ yield i
+ i = i.next_sibling
+
+ @property
+ def previous_elements(self):
+ """All PageElements that were parsed before this one.
+
+ :yield: A sequence of PageElements.
+ """
+ i = self.previous_element
+ while i is not None:
+ yield i
+ i = i.previous_element
+
+ @property
+ def previous_siblings(self):
+ """All PageElements that are siblings of this one but were parsed
+ earlier.
+
+ :yield: A sequence of PageElements.
+ """
+ i = self.previous_sibling
+ while i is not None:
+ yield i
+ i = i.previous_sibling
+
+ @property
+ def parents(self):
+ """All PageElements that are parents of this PageElement.
+
+ :yield: A sequence of PageElements.
+ """
+ i = self.parent
+ while i is not None:
+ yield i
+ i = i.parent
+
+ @property
+ def decomposed(self):
+ """Check whether a PageElement has been decomposed.
+
+ :rtype: bool
+ """
+ return getattr(self, '_decomposed', False) or False
+
+ # Old non-property versions of the generators, for backwards
+ # compatibility with BS3.
+ def nextGenerator(self):
+ return self.next_elements
+
+ def nextSiblingGenerator(self):
+ return self.next_siblings
+
+ def previousGenerator(self):
+ return self.previous_elements
+
+ def previousSiblingGenerator(self):
+ return self.previous_siblings
+
+ def parentGenerator(self):
+ return self.parents
+
+
+class NavigableString(str, PageElement):
+ """A Python Unicode string that is part of a parse tree.
+
+ When Beautiful Soup parses the markup penguin , it will
+ create a NavigableString for the string "penguin".
+ """
+
+ PREFIX = ''
+ SUFFIX = ''
+
+ # We can't tell just by looking at a string whether it's contained
+ # in an XML document or an HTML document.
+
+ known_xml = None
+
+ def __new__(cls, value):
+ """Create a new NavigableString.
+
+ When unpickling a NavigableString, this method is called with
+ the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be
+ passed in to the superclass's __new__ or the superclass won't know
+ how to handle non-ASCII characters.
+ """
+ if isinstance(value, str):
+ u = str.__new__(cls, value)
+ else:
+ u = str.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
+ u.setup()
+ return u
+
+ def __copy__(self):
+ """A copy of a NavigableString has the same contents and class
+ as the original, but it is not connected to the parse tree.
+ """
+ return type(self)(self)
+
+ def __getnewargs__(self):
+ return (str(self),)
+
+ def __getattr__(self, attr):
+ """text.string gives you text. This is for backwards
+ compatibility for Navigable*String, but for CData* it lets you
+ get the string without the CData wrapper."""
+ if attr == 'string':
+ return self
+ else:
+ raise AttributeError(
+ "'%s' object has no attribute '%s'" % (
+ self.__class__.__name__, attr))
+
+ def output_ready(self, formatter="minimal"):
+ """Run the string through the provided formatter.
+
+ :param formatter: A Formatter object, or a string naming one of the standard formatters.
+ """
+ output = self.format_string(self, formatter)
+ return self.PREFIX + output + self.SUFFIX
+
+ @property
+ def name(self):
+ """Since a NavigableString is not a Tag, it has no .name.
+
+ This property is implemented so that code like this doesn't crash
+ when run on a mixture of Tag and NavigableString objects:
+ [x.name for x in tag.children]
+ """
+ return None
+
+ @name.setter
+ def name(self, name):
+ """Prevent NavigableString.name from ever being set."""
+ raise AttributeError("A NavigableString cannot be given a name.")
+
+ def _all_strings(self, strip=False, types=PageElement.default):
+ """Yield all strings of certain classes, possibly stripping them.
+
+ This makes it easy for NavigableString to implement methods
+ like get_text() as conveniences, creating a consistent
+ text-extraction API across all PageElements.
+
+ :param strip: If True, all strings will be stripped before being
+ yielded.
+
+ :param types: A tuple of NavigableString subclasses. If this
+ NavigableString isn't one of those subclasses, the
+ sequence will be empty. By default, the subclasses
+ considered are NavigableString and CData objects. That
+ means no comments, processing instructions, etc.
+
+ :yield: A sequence that either contains this string, or is empty.
+
+ """
+ if types is self.default:
+ # This is kept in Tag because it's full of subclasses of
+ # this class, which aren't defined until later in the file.
+ types = Tag.DEFAULT_INTERESTING_STRING_TYPES
+
+ # Do nothing if the caller is looking for specific types of
+ # string, and we're of a different type.
+ #
+ # We check specific types instead of using isinstance(self,
+ # types) because all of these classes subclass
+ # NavigableString. Anyone who's using this feature probably
+ # wants generic NavigableStrings but not other stuff.
+ my_type = type(self)
+ if types is not None:
+ if isinstance(types, type):
+ # Looking for a single type.
+ if my_type is not types:
+ return
+ elif my_type not in types:
+ # Looking for one of a list of types.
+ return
+
+ value = self
+ if strip:
+ value = value.strip()
+ if len(value) > 0:
+ yield value
+ strings = property(_all_strings)
+
+class PreformattedString(NavigableString):
+ """A NavigableString not subject to the normal formatting rules.
+
+ This is an abstract class used for special kinds of strings such
+ as comments (the Comment class) and CDATA blocks (the CData
+ class).
+ """
+
+ PREFIX = ''
+ SUFFIX = ''
+
+ def output_ready(self, formatter=None):
+ """Make this string ready for output by adding any subclass-specific
+ prefix or suffix.
+
+ :param formatter: A Formatter object, or a string naming one
+ of the standard formatters. The string will be passed into the
+ Formatter, but only to trigger any side effects: the return
+ value is ignored.
+
+ :return: The string, with any subclass-specific prefix and
+ suffix added on.
+ """
+ if formatter is not None:
+ ignore = self.format_string(self, formatter)
+ return self.PREFIX + self + self.SUFFIX
+
+class CData(PreformattedString):
+ """A CDATA block."""
+ PREFIX = ''
+
+class ProcessingInstruction(PreformattedString):
+ """A SGML processing instruction."""
+
+ PREFIX = ''
+ SUFFIX = '>'
+
+class XMLProcessingInstruction(ProcessingInstruction):
+ """An XML processing instruction."""
+ PREFIX = ''
+ SUFFIX = '?>'
+
+class Comment(PreformattedString):
+ """An HTML or XML comment."""
+ PREFIX = ''
+
+
+class Declaration(PreformattedString):
+ """An XML declaration."""
+ PREFIX = ''
+ SUFFIX = '?>'
+
+
+class Doctype(PreformattedString):
+ """A document type declaration."""
+ @classmethod
+ def for_name_and_ids(cls, name, pub_id, system_id):
+ """Generate an appropriate document type declaration for a given
+ public ID and system ID.
+
+ :param name: The name of the document's root element, e.g. 'html'.
+ :param pub_id: The Formal Public Identifier for this document type,
+ e.g. '-//W3C//DTD XHTML 1.1//EN'
+ :param system_id: The system identifier for this document type,
+ e.g. 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd'
+
+ :return: A Doctype.
+ """
+ value = name or ''
+ if pub_id is not None:
+ value += ' PUBLIC "%s"' % pub_id
+ if system_id is not None:
+ value += ' "%s"' % system_id
+ elif system_id is not None:
+ value += ' SYSTEM "%s"' % system_id
+
+ return Doctype(value)
+
+ PREFIX = '\n'
+
+
+class Stylesheet(NavigableString):
+ """A NavigableString representing an stylesheet (probably
+ CSS).
+
+ Used to distinguish embedded stylesheets from textual content.
+ """
+ pass
+
+
+class Script(NavigableString):
+ """A NavigableString representing an executable script (probably
+ Javascript).
+
+ Used to distinguish executable code from textual content.
+ """
+ pass
+
+
+class TemplateString(NavigableString):
+ """A NavigableString representing a string found inside an HTML
+ template embedded in a larger document.
+
+ Used to distinguish such strings from the main body of the document.
+ """
+ pass
+
+
+class RubyTextString(NavigableString):
+ """A NavigableString representing the contents of the HTML
+ element.
+
+ https://dev.w3.org/html5/spec-LC/text-level-semantics.html#the-rt-element
+
+ Can be used to distinguish such strings from the strings they're
+ annotating.
+ """
+ pass
+
+
+class RubyParenthesisString(NavigableString):
+ """A NavigableString representing the contents of the HTML
+ element.
+
+ https://dev.w3.org/html5/spec-LC/text-level-semantics.html#the-rp-element
+ """
+ pass
+
+
+class Tag(PageElement):
+ """Represents an HTML or XML tag that is part of a parse tree, along
+ with its attributes and contents.
+
+ When Beautiful Soup parses the markup penguin , it will
+ create a Tag object representing the tag.
+ """
+
+ def __init__(self, parser=None, builder=None, name=None, namespace=None,
+ prefix=None, attrs=None, parent=None, previous=None,
+ is_xml=None, sourceline=None, sourcepos=None,
+ can_be_empty_element=None, cdata_list_attributes=None,
+ preserve_whitespace_tags=None,
+ interesting_string_types=None,
+ namespaces=None
+ ):
+ """Basic constructor.
+
+ :param parser: A BeautifulSoup object.
+ :param builder: A TreeBuilder.
+ :param name: The name of the tag.
+ :param namespace: The URI of this Tag's XML namespace, if any.
+ :param prefix: The prefix for this Tag's XML namespace, if any.
+ :param attrs: A dictionary of this Tag's attribute values.
+ :param parent: The PageElement to use as this Tag's parent.
+ :param previous: The PageElement that was parsed immediately before
+ this tag.
+ :param is_xml: If True, this is an XML tag. Otherwise, this is an
+ HTML tag.
+ :param sourceline: The line number where this tag was found in its
+ source document.
+ :param sourcepos: The character position within `sourceline` where this
+ tag was found.
+ :param can_be_empty_element: If True, this tag should be
+ represented as . If False, this tag should be represented
+ as .
+ :param cdata_list_attributes: A list of attributes whose values should
+ be treated as CDATA if they ever show up on this tag.
+ :param preserve_whitespace_tags: A list of tag names whose contents
+ should have their whitespace preserved.
+ :param interesting_string_types: This is a NavigableString
+ subclass or a tuple of them. When iterating over this
+ Tag's strings in methods like Tag.strings or Tag.get_text,
+ these are the types of strings that are interesting enough
+ to be considered. The default is to consider
+ NavigableString and CData the only interesting string
+ subtypes.
+ :param namespaces: A dictionary mapping currently active
+ namespace prefixes to URIs. This can be used later to
+ construct CSS selectors.
+ """
+ if parser is None:
+ self.parser_class = None
+ else:
+ # We don't actually store the parser object: that lets extracted
+ # chunks be garbage-collected.
+ self.parser_class = parser.__class__
+ if name is None:
+ raise ValueError("No value provided for new tag's name.")
+ self.name = name
+ self.namespace = namespace
+ self._namespaces = namespaces or {}
+ self.prefix = prefix
+ if ((not builder or builder.store_line_numbers)
+ and (sourceline is not None or sourcepos is not None)):
+ self.sourceline = sourceline
+ self.sourcepos = sourcepos
+ if attrs is None:
+ attrs = {}
+ elif attrs:
+ if builder is not None and builder.cdata_list_attributes:
+ attrs = builder._replace_cdata_list_attribute_values(
+ self.name, attrs)
+ else:
+ attrs = dict(attrs)
+ else:
+ attrs = dict(attrs)
+
+ # If possible, determine ahead of time whether this tag is an
+ # XML tag.
+ if builder:
+ self.known_xml = builder.is_xml
+ else:
+ self.known_xml = is_xml
+ self.attrs = attrs
+ self.contents = []
+ self.setup(parent, previous)
+ self.hidden = False
+
+ if builder is None:
+ # In the absence of a TreeBuilder, use whatever values were
+ # passed in here. They're probably None, unless this is a copy of some
+ # other tag.
+ self.can_be_empty_element = can_be_empty_element
+ self.cdata_list_attributes = cdata_list_attributes
+ self.preserve_whitespace_tags = preserve_whitespace_tags
+ self.interesting_string_types = interesting_string_types
+ else:
+ # Set up any substitutions for this tag, such as the charset in a META tag.
+ builder.set_up_substitutions(self)
+
+ # Ask the TreeBuilder whether this tag might be an empty-element tag.
+ self.can_be_empty_element = builder.can_be_empty_element(name)
+
+ # Keep track of the list of attributes of this tag that
+ # might need to be treated as a list.
+ #
+ # For performance reasons, we store the whole data structure
+ # rather than asking the question of every tag. Asking would
+ # require building a new data structure every time, and
+ # (unlike can_be_empty_element), we almost never need
+ # to check this.
+ self.cdata_list_attributes = builder.cdata_list_attributes
+
+ # Keep track of the names that might cause this tag to be treated as a
+ # whitespace-preserved tag.
+ self.preserve_whitespace_tags = builder.preserve_whitespace_tags
+
+ if self.name in builder.string_containers:
+ # This sort of tag uses a special string container
+ # subclass for most of its strings. When we ask the
+ self.interesting_string_types = builder.string_containers[self.name]
+ else:
+ self.interesting_string_types = self.DEFAULT_INTERESTING_STRING_TYPES
+
+ parserClass = _alias("parser_class") # BS3
+
+ def __copy__(self):
+ """A copy of a Tag is a new Tag, unconnected to the parse tree.
+ Its contents are a copy of the old Tag's contents.
+ """
+ clone = type(self)(
+ None, self.builder, self.name, self.namespace,
+ self.prefix, self.attrs, is_xml=self._is_xml,
+ sourceline=self.sourceline, sourcepos=self.sourcepos,
+ can_be_empty_element=self.can_be_empty_element,
+ cdata_list_attributes=self.cdata_list_attributes,
+ preserve_whitespace_tags=self.preserve_whitespace_tags
+ )
+ for attr in ('can_be_empty_element', 'hidden'):
+ setattr(clone, attr, getattr(self, attr))
+ for child in self.contents:
+ clone.append(child.__copy__())
+ return clone
+
+ @property
+ def is_empty_element(self):
+ """Is this tag an empty-element tag? (aka a self-closing tag)
+
+ A tag that has contents is never an empty-element tag.
+
+ A tag that has no contents may or may not be an empty-element
+ tag. It depends on the builder used to create the tag. If the
+ builder has a designated list of empty-element tags, then only
+ a tag whose name shows up in that list is considered an
+ empty-element tag.
+
+ If the builder has no designated list of empty-element tags,
+ then any tag with no contents is an empty-element tag.
+ """
+ return len(self.contents) == 0 and self.can_be_empty_element
+ isSelfClosing = is_empty_element # BS3
+
+ @property
+ def string(self):
+ """Convenience property to get the single string within this
+ PageElement.
+
+ TODO It might make sense to have NavigableString.string return
+ itself.
+
+ :return: If this element has a single string child, return
+ value is that string. If this element has one child tag,
+ return value is the 'string' attribute of the child tag,
+ recursively. If this element is itself a string, has no
+ children, or has more than one child, return value is None.
+ """
+ if len(self.contents) != 1:
+ return None
+ child = self.contents[0]
+ if isinstance(child, NavigableString):
+ return child
+ return child.string
+
+ @string.setter
+ def string(self, string):
+ """Replace this PageElement's contents with `string`."""
+ self.clear()
+ self.append(string.__class__(string))
+
+ DEFAULT_INTERESTING_STRING_TYPES = (NavigableString, CData)
+ def _all_strings(self, strip=False, types=PageElement.default):
+ """Yield all strings of certain classes, possibly stripping them.
+
+ :param strip: If True, all strings will be stripped before being
+ yielded.
+
+ :param types: A tuple of NavigableString subclasses. Any strings of
+ a subclass not found in this list will be ignored. By
+ default, the subclasses considered are the ones found in
+ self.interesting_string_types. If that's not specified,
+ only NavigableString and CData objects will be
+ considered. That means no comments, processing
+ instructions, etc.
+
+ :yield: A sequence of strings.
+
+ """
+ if types is self.default:
+ types = self.interesting_string_types
+
+ for descendant in self.descendants:
+ if (types is None and not isinstance(descendant, NavigableString)):
+ continue
+ descendant_type = type(descendant)
+ if isinstance(types, type):
+ if descendant_type is not types:
+ # We're not interested in strings of this type.
+ continue
+ elif types is not None and descendant_type not in types:
+ # We're not interested in strings of this type.
+ continue
+ if strip:
+ descendant = descendant.strip()
+ if len(descendant) == 0:
+ continue
+ yield descendant
+ strings = property(_all_strings)
+
+ def decompose(self):
+ """Recursively destroys this PageElement and its children.
+
+ This element will be removed from the tree and wiped out; so
+ will everything beneath it.
+
+ The behavior of a decomposed PageElement is undefined and you
+ should never use one for anything, but if you need to _check_
+ whether an element has been decomposed, you can use the
+ `decomposed` property.
+ """
+ self.extract()
+ i = self
+ while i is not None:
+ n = i.next_element
+ i.__dict__.clear()
+ i.contents = []
+ i._decomposed = True
+ i = n
+
+ def clear(self, decompose=False):
+ """Wipe out all children of this PageElement by calling extract()
+ on them.
+
+ :param decompose: If this is True, decompose() (a more
+ destructive method) will be called instead of extract().
+ """
+ if decompose:
+ for element in self.contents[:]:
+ if isinstance(element, Tag):
+ element.decompose()
+ else:
+ element.extract()
+ else:
+ for element in self.contents[:]:
+ element.extract()
+
+ def smooth(self):
+ """Smooth out this element's children by consolidating consecutive
+ strings.
+
+ This makes pretty-printed output look more natural following a
+ lot of operations that modified the tree.
+ """
+ # Mark the first position of every pair of children that need
+ # to be consolidated. Do this rather than making a copy of
+ # self.contents, since in most cases very few strings will be
+ # affected.
+ marked = []
+ for i, a in enumerate(self.contents):
+ if isinstance(a, Tag):
+ # Recursively smooth children.
+ a.smooth()
+ if i == len(self.contents)-1:
+ # This is the last item in .contents, and it's not a
+ # tag. There's no chance it needs any work.
+ continue
+ b = self.contents[i+1]
+ if (isinstance(a, NavigableString)
+ and isinstance(b, NavigableString)
+ and not isinstance(a, PreformattedString)
+ and not isinstance(b, PreformattedString)
+ ):
+ marked.append(i)
+
+ # Go over the marked positions in reverse order, so that
+ # removing items from .contents won't affect the remaining
+ # positions.
+ for i in reversed(marked):
+ a = self.contents[i]
+ b = self.contents[i+1]
+ b.extract()
+ n = NavigableString(a+b)
+ a.replace_with(n)
+
+ def index(self, element):
+ """Find the index of a child by identity, not value.
+
+ Avoids issues with tag.contents.index(element) getting the
+ index of equal elements.
+
+ :param element: Look for this PageElement in `self.contents`.
+ """
+ for i, child in enumerate(self.contents):
+ if child is element:
+ return i
+ raise ValueError("Tag.index: element not in tag")
+
+ def get(self, key, default=None):
+ """Returns the value of the 'key' attribute for the tag, or
+ the value given for 'default' if it doesn't have that
+ attribute."""
+ return self.attrs.get(key, default)
+
+ def get_attribute_list(self, key, default=None):
+ """The same as get(), but always returns a list.
+
+ :param key: The attribute to look for.
+ :param default: Use this value if the attribute is not present
+ on this PageElement.
+ :return: A list of values, probably containing only a single
+ value.
+ """
+ value = self.get(key, default)
+ if not isinstance(value, list):
+ value = [value]
+ return value
+
+ def has_attr(self, key):
+ """Does this PageElement have an attribute with the given name?"""
+ return key in self.attrs
+
+ def __hash__(self):
+ return str(self).__hash__()
+
+ def __getitem__(self, key):
+ """tag[key] returns the value of the 'key' attribute for the Tag,
+ and throws an exception if it's not there."""
+ return self.attrs[key]
+
+ def __iter__(self):
+ "Iterating over a Tag iterates over its contents."
+ return iter(self.contents)
+
+ def __len__(self):
+ "The length of a Tag is the length of its list of contents."
+ return len(self.contents)
+
+ def __contains__(self, x):
+ return x in self.contents
+
+ def __bool__(self):
+ "A tag is non-None even if it has no contents."
+ return True
+
+ def __setitem__(self, key, value):
+ """Setting tag[key] sets the value of the 'key' attribute for the
+ tag."""
+ self.attrs[key] = value
+
+ def __delitem__(self, key):
+ "Deleting tag[key] deletes all 'key' attributes for the tag."
+ self.attrs.pop(key, None)
+
+ def __call__(self, *args, **kwargs):
+ """Calling a Tag like a function is the same as calling its
+ find_all() method. Eg. tag('a') returns a list of all the A tags
+ found within this tag."""
+ return self.find_all(*args, **kwargs)
+
+ def __getattr__(self, tag):
+ """Calling tag.subtag is the same as calling tag.find(name="subtag")"""
+ #print("Getattr %s.%s" % (self.__class__, tag))
+ if len(tag) > 3 and tag.endswith('Tag'):
+ # BS3: soup.aTag -> "soup.find("a")
+ tag_name = tag[:-3]
+ warnings.warn(
+ '.%(name)sTag is deprecated, use .find("%(name)s") instead. If you really were looking for a tag called %(name)sTag, use .find("%(name)sTag")' % dict(
+ name=tag_name
+ ),
+ DeprecationWarning
+ )
+ return self.find(tag_name)
+ # We special case contents to avoid recursion.
+ elif not tag.startswith("__") and not tag == "contents":
+ return self.find(tag)
+ raise AttributeError(
+ "'%s' object has no attribute '%s'" % (self.__class__, tag))
+
+ def __eq__(self, other):
+ """Returns true iff this Tag has the same name, the same attributes,
+ and the same contents (recursively) as `other`."""
+ if self is other:
+ return True
+ if (not hasattr(other, 'name') or
+ not hasattr(other, 'attrs') or
+ not hasattr(other, 'contents') or
+ self.name != other.name or
+ self.attrs != other.attrs or
+ len(self) != len(other)):
+ return False
+ for i, my_child in enumerate(self.contents):
+ if my_child != other.contents[i]:
+ return False
+ return True
+
+ def __ne__(self, other):
+ """Returns true iff this Tag is not identical to `other`,
+ as defined in __eq__."""
+ return not self == other
+
+ def __repr__(self, encoding="unicode-escape"):
+ """Renders this PageElement as a string.
+
+ :param encoding: The encoding to use (Python 2 only).
+ TODO: This is now ignored and a warning should be issued
+ if a value is provided.
+ :return: A (Unicode) string.
+ """
+ # "The return value must be a string object", i.e. Unicode
+ return self.decode()
+
+ def __unicode__(self):
+ """Renders this PageElement as a Unicode string."""
+ return self.decode()
+
+ __str__ = __repr__ = __unicode__
+
+ def encode(self, encoding=DEFAULT_OUTPUT_ENCODING,
+ indent_level=None, formatter="minimal",
+ errors="xmlcharrefreplace"):
+ """Render a bytestring representation of this PageElement and its
+ contents.
+
+ :param encoding: The destination encoding.
+ :param indent_level: Each line of the rendering will be
+ indented this many levels. (The formatter decides what a
+ 'level' means in terms of spaces or other characters
+ output.) Used internally in recursive calls while
+ pretty-printing.
+ :param formatter: A Formatter object, or a string naming one of
+ the standard formatters.
+ :param errors: An error handling strategy such as
+ 'xmlcharrefreplace'. This value is passed along into
+ encode() and its value should be one of the constants
+ defined by Python.
+ :return: A bytestring.
+
+ """
+ # Turn the data structure into Unicode, then encode the
+ # Unicode.
+ u = self.decode(indent_level, encoding, formatter)
+ return u.encode(encoding, errors)
+
+ def decode(self, indent_level=None,
+ eventual_encoding=DEFAULT_OUTPUT_ENCODING,
+ formatter="minimal"):
+ """Render a Unicode representation of this PageElement and its
+ contents.
+
+ :param indent_level: Each line of the rendering will be
+ indented this many spaces. Used internally in
+ recursive calls while pretty-printing.
+ :param eventual_encoding: The tag is destined to be
+ encoded into this encoding. This method is _not_
+ responsible for performing that encoding. This information
+ is passed in so that it can be substituted in if the
+ document contains a tag that mentions the document's
+ encoding.
+ :param formatter: A Formatter object, or a string naming one of
+ the standard formatters.
+ """
+
+ # First off, turn a non-Formatter `formatter` into a Formatter
+ # object. This will stop the lookup from happening over and
+ # over again.
+ if not isinstance(formatter, Formatter):
+ formatter = self.formatter_for_name(formatter)
+ attributes = formatter.attributes(self)
+ attrs = []
+ for key, val in attributes:
+ if val is None:
+ decoded = key
+ else:
+ if isinstance(val, list) or isinstance(val, tuple):
+ val = ' '.join(val)
+ elif not isinstance(val, str):
+ val = str(val)
+ elif (
+ isinstance(val, AttributeValueWithCharsetSubstitution)
+ and eventual_encoding is not None
+ ):
+ val = val.encode(eventual_encoding)
+
+ text = formatter.attribute_value(val)
+ decoded = (
+ str(key) + '='
+ + formatter.quoted_attribute_value(text))
+ attrs.append(decoded)
+ close = ''
+ closeTag = ''
+
+ prefix = ''
+ if self.prefix:
+ prefix = self.prefix + ":"
+
+ if self.is_empty_element:
+ close = formatter.void_element_close_prefix or ''
+ else:
+ closeTag = '%s%s>' % (prefix, self.name)
+
+ pretty_print = self._should_pretty_print(indent_level)
+ space = ''
+ indent_space = ''
+ if indent_level is not None:
+ indent_space = (formatter.indent * (indent_level - 1))
+ if pretty_print:
+ space = indent_space
+ indent_contents = indent_level + 1
+ else:
+ indent_contents = None
+ contents = self.decode_contents(
+ indent_contents, eventual_encoding, formatter
+ )
+
+ if self.hidden:
+ # This is the 'document root' object.
+ s = contents
+ else:
+ s = []
+ attribute_string = ''
+ if attrs:
+ attribute_string = ' ' + ' '.join(attrs)
+ if indent_level is not None:
+ # Even if this particular tag is not pretty-printed,
+ # we should indent up to the start of the tag.
+ s.append(indent_space)
+ s.append('<%s%s%s%s>' % (
+ prefix, self.name, attribute_string, close))
+ if pretty_print:
+ s.append("\n")
+ s.append(contents)
+ if pretty_print and contents and contents[-1] != "\n":
+ s.append("\n")
+ if pretty_print and closeTag:
+ s.append(space)
+ s.append(closeTag)
+ if indent_level is not None and closeTag and self.next_sibling:
+ # Even if this particular tag is not pretty-printed,
+ # we're now done with the tag, and we should add a
+ # newline if appropriate.
+ s.append("\n")
+ s = ''.join(s)
+ return s
+
+ def _should_pretty_print(self, indent_level):
+ """Should this tag be pretty-printed?
+
+ Most of them should, but some (such as in HTML
+ documents) should not.
+ """
+ return (
+ indent_level is not None
+ and (
+ not self.preserve_whitespace_tags
+ or self.name not in self.preserve_whitespace_tags
+ )
+ )
+
+ def prettify(self, encoding=None, formatter="minimal"):
+ """Pretty-print this PageElement as a string.
+
+ :param encoding: The eventual encoding of the string. If this is None,
+ a Unicode string will be returned.
+ :param formatter: A Formatter object, or a string naming one of
+ the standard formatters.
+ :return: A Unicode string (if encoding==None) or a bytestring
+ (otherwise).
+ """
+ if encoding is None:
+ return self.decode(True, formatter=formatter)
+ else:
+ return self.encode(encoding, True, formatter=formatter)
+
+ def decode_contents(self, indent_level=None,
+ eventual_encoding=DEFAULT_OUTPUT_ENCODING,
+ formatter="minimal"):
+ """Renders the contents of this tag as a Unicode string.
+
+ :param indent_level: Each line of the rendering will be
+ indented this many levels. (The formatter decides what a
+ 'level' means in terms of spaces or other characters
+ output.) Used internally in recursive calls while
+ pretty-printing.
+
+ :param eventual_encoding: The tag is destined to be
+ encoded into this encoding. decode_contents() is _not_
+ responsible for performing that encoding. This information
+ is passed in so that it can be substituted in if the
+ document contains a tag that mentions the document's
+ encoding.
+
+ :param formatter: A Formatter object, or a string naming one of
+ the standard Formatters.
+
+ """
+ # First off, turn a string formatter into a Formatter object. This
+ # will stop the lookup from happening over and over again.
+ if not isinstance(formatter, Formatter):
+ formatter = self.formatter_for_name(formatter)
+
+ pretty_print = (indent_level is not None)
+ s = []
+ for c in self:
+ text = None
+ if isinstance(c, NavigableString):
+ text = c.output_ready(formatter)
+ elif isinstance(c, Tag):
+ s.append(c.decode(indent_level, eventual_encoding,
+ formatter))
+ preserve_whitespace = (
+ self.preserve_whitespace_tags and self.name in self.preserve_whitespace_tags
+ )
+ if text and indent_level and not preserve_whitespace:
+ text = text.strip()
+ if text:
+ if pretty_print and not preserve_whitespace:
+ s.append(formatter.indent * (indent_level - 1))
+ s.append(text)
+ if pretty_print and not preserve_whitespace:
+ s.append("\n")
+ return ''.join(s)
+
+ def encode_contents(
+ self, indent_level=None, encoding=DEFAULT_OUTPUT_ENCODING,
+ formatter="minimal"):
+ """Renders the contents of this PageElement as a bytestring.
+
+ :param indent_level: Each line of the rendering will be
+ indented this many levels. (The formatter decides what a
+ 'level' means in terms of spaces or other characters
+ output.) Used internally in recursive calls while
+ pretty-printing.
+
+ :param eventual_encoding: The bytestring will be in this encoding.
+
+ :param formatter: A Formatter object, or a string naming one of
+ the standard Formatters.
+
+ :return: A bytestring.
+ """
+ contents = self.decode_contents(indent_level, encoding, formatter)
+ return contents.encode(encoding)
+
+ # Old method for BS3 compatibility
+ def renderContents(self, encoding=DEFAULT_OUTPUT_ENCODING,
+ prettyPrint=False, indentLevel=0):
+ """Deprecated method for BS3 compatibility."""
+ if not prettyPrint:
+ indentLevel = None
+ return self.encode_contents(
+ indent_level=indentLevel, encoding=encoding)
+
+ #Soup methods
+
+ def find(self, name=None, attrs={}, recursive=True, string=None,
+ **kwargs):
+ """Look in the children of this PageElement and find the first
+ PageElement that matches the given criteria.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param recursive: If this is True, find() will perform a
+ recursive search of this PageElement's children. Otherwise,
+ only the direct children will be considered.
+ :param limit: Stop looking after finding this many results.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A PageElement.
+ :rtype: bs4.element.Tag | bs4.element.NavigableString
+ """
+ r = None
+ l = self.find_all(name, attrs, recursive, string, 1, **kwargs)
+ if l:
+ r = l[0]
+ return r
+ findChild = find #BS2
+
+ def find_all(self, name=None, attrs={}, recursive=True, string=None,
+ limit=None, **kwargs):
+ """Look in the children of this PageElement and find all
+ PageElements that match the given criteria.
+
+ All find_* methods take a common set of arguments. See the online
+ documentation for detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param recursive: If this is True, find_all() will perform a
+ recursive search of this PageElement's children. Otherwise,
+ only the direct children will be considered.
+ :param limit: Stop looking after finding this many results.
+ :kwargs: A dictionary of filters on attribute values.
+ :return: A ResultSet of PageElements.
+ :rtype: bs4.element.ResultSet
+ """
+ generator = self.descendants
+ if not recursive:
+ generator = self.children
+ return self._find_all(name, attrs, string, limit, generator, **kwargs)
+ findAll = find_all # BS3
+ findChildren = find_all # BS2
+
+ #Generator methods
+ @property
+ def children(self):
+ """Iterate over all direct children of this PageElement.
+
+ :yield: A sequence of PageElements.
+ """
+ # return iter() to make the purpose of the method clear
+ return iter(self.contents) # XXX This seems to be untested.
+
+ @property
+ def descendants(self):
+ """Iterate over all children of this PageElement in a
+ breadth-first sequence.
+
+ :yield: A sequence of PageElements.
+ """
+ if not len(self.contents):
+ return
+ stopNode = self._last_descendant().next_element
+ current = self.contents[0]
+ while current is not stopNode:
+ yield current
+ current = current.next_element
+
+ # CSS selector code
+ def select_one(self, selector, namespaces=None, **kwargs):
+ """Perform a CSS selection operation on the current element.
+
+ :param selector: A CSS selector.
+
+ :param namespaces: A dictionary mapping namespace prefixes
+ used in the CSS selector to namespace URIs. By default,
+ Beautiful Soup will use the prefixes it encountered while
+ parsing the document.
+
+ :param kwargs: Keyword arguments to be passed into SoupSieve's
+ soupsieve.select() method.
+
+ :return: A Tag.
+ :rtype: bs4.element.Tag
+ """
+ value = self.select(selector, namespaces, 1, **kwargs)
+ if value:
+ return value[0]
+ return None
+
+ def select(self, selector, namespaces=None, limit=None, **kwargs):
+ """Perform a CSS selection operation on the current element.
+
+ This uses the SoupSieve library.
+
+ :param selector: A string containing a CSS selector.
+
+ :param namespaces: A dictionary mapping namespace prefixes
+ used in the CSS selector to namespace URIs. By default,
+ Beautiful Soup will use the prefixes it encountered while
+ parsing the document.
+
+ :param limit: After finding this number of results, stop looking.
+
+ :param kwargs: Keyword arguments to be passed into SoupSieve's
+ soupsieve.select() method.
+
+ :return: A ResultSet of Tags.
+ :rtype: bs4.element.ResultSet
+ """
+ if namespaces is None:
+ namespaces = self._namespaces
+
+ if limit is None:
+ limit = 0
+ if soupsieve is None:
+ raise NotImplementedError(
+ "Cannot execute CSS selectors because the soupsieve package is not installed."
+ )
+
+ results = soupsieve.select(selector, self, namespaces, limit, **kwargs)
+
+ # We do this because it's more consistent and because
+ # ResultSet.__getattr__ has a helpful error message.
+ return ResultSet(None, results)
+
+ # Old names for backwards compatibility
+ def childGenerator(self):
+ """Deprecated generator."""
+ return self.children
+
+ def recursiveChildGenerator(self):
+ """Deprecated generator."""
+ return self.descendants
+
+ def has_key(self, key):
+ """Deprecated method. This was kind of misleading because has_key()
+ (attributes) was different from __in__ (contents).
+
+ has_key() is gone in Python 3, anyway.
+ """
+ warnings.warn(
+ 'has_key is deprecated. Use has_attr(key) instead.',
+ DeprecationWarning
+ )
+ return self.has_attr(key)
+
+# Next, a couple classes to represent queries and their results.
+class SoupStrainer(object):
+ """Encapsulates a number of ways of matching a markup element (tag or
+ string).
+
+ This is primarily used to underpin the find_* methods, but you can
+ create one yourself and pass it in as `parse_only` to the
+ `BeautifulSoup` constructor, to parse a subset of a large
+ document.
+ """
+
+ def __init__(self, name=None, attrs={}, string=None, **kwargs):
+ """Constructor.
+
+ The SoupStrainer constructor takes the same arguments passed
+ into the find_* methods. See the online documentation for
+ detailed explanations.
+
+ :param name: A filter on tag name.
+ :param attrs: A dictionary of filters on attribute values.
+ :param string: A filter for a NavigableString with specific text.
+ :kwargs: A dictionary of filters on attribute values.
+ """
+ if string is None and 'text' in kwargs:
+ string = kwargs.pop('text')
+ warnings.warn(
+ "The 'text' argument to the SoupStrainer constructor is deprecated. Use 'string' instead.",
+ DeprecationWarning
+ )
+
+ self.name = self._normalize_search_value(name)
+ if not isinstance(attrs, dict):
+ # Treat a non-dict value for attrs as a search for the 'class'
+ # attribute.
+ kwargs['class'] = attrs
+ attrs = None
+
+ if 'class_' in kwargs:
+ # Treat class_="foo" as a search for the 'class'
+ # attribute, overriding any non-dict value for attrs.
+ kwargs['class'] = kwargs['class_']
+ del kwargs['class_']
+
+ if kwargs:
+ if attrs:
+ attrs = attrs.copy()
+ attrs.update(kwargs)
+ else:
+ attrs = kwargs
+ normalized_attrs = {}
+ for key, value in list(attrs.items()):
+ normalized_attrs[key] = self._normalize_search_value(value)
+
+ self.attrs = normalized_attrs
+ self.string = self._normalize_search_value(string)
+
+ # DEPRECATED but just in case someone is checking this.
+ self.text = self.string
+
+ def _normalize_search_value(self, value):
+ # Leave it alone if it's a Unicode string, a callable, a
+ # regular expression, a boolean, or None.
+ if (isinstance(value, str) or isinstance(value, Callable) or hasattr(value, 'match')
+ or isinstance(value, bool) or value is None):
+ return value
+
+ # If it's a bytestring, convert it to Unicode, treating it as UTF-8.
+ if isinstance(value, bytes):
+ return value.decode("utf8")
+
+ # If it's listlike, convert it into a list of strings.
+ if hasattr(value, '__iter__'):
+ new_value = []
+ for v in value:
+ if (hasattr(v, '__iter__') and not isinstance(v, bytes)
+ and not isinstance(v, str)):
+ # This is almost certainly the user's mistake. In the
+ # interests of avoiding infinite loops, we'll let
+ # it through as-is rather than doing a recursive call.
+ new_value.append(v)
+ else:
+ new_value.append(self._normalize_search_value(v))
+ return new_value
+
+ # Otherwise, convert it into a Unicode string.
+ # The unicode(str()) thing is so this will do the same thing on Python 2
+ # and Python 3.
+ return str(str(value))
+
+ def __str__(self):
+ """A human-readable representation of this SoupStrainer."""
+ if self.string:
+ return self.string
+ else:
+ return "%s|%s" % (self.name, self.attrs)
+
+ def search_tag(self, markup_name=None, markup_attrs={}):
+ """Check whether a Tag with the given name and attributes would
+ match this SoupStrainer.
+
+ Used prospectively to decide whether to even bother creating a Tag
+ object.
+
+ :param markup_name: A tag name as found in some markup.
+ :param markup_attrs: A dictionary of attributes as found in some markup.
+
+ :return: True if the prospective tag would match this SoupStrainer;
+ False otherwise.
+ """
+ found = None
+ markup = None
+ if isinstance(markup_name, Tag):
+ markup = markup_name
+ markup_attrs = markup
+
+ if isinstance(self.name, str):
+ # Optimization for a very common case where the user is
+ # searching for a tag with one specific name, and we're
+ # looking at a tag with a different name.
+ if markup and not markup.prefix and self.name != markup.name:
+ return False
+
+ call_function_with_tag_data = (
+ isinstance(self.name, Callable)
+ and not isinstance(markup_name, Tag))
+
+ if ((not self.name)
+ or call_function_with_tag_data
+ or (markup and self._matches(markup, self.name))
+ or (not markup and self._matches(markup_name, self.name))):
+ if call_function_with_tag_data:
+ match = self.name(markup_name, markup_attrs)
+ else:
+ match = True
+ markup_attr_map = None
+ for attr, match_against in list(self.attrs.items()):
+ if not markup_attr_map:
+ if hasattr(markup_attrs, 'get'):
+ markup_attr_map = markup_attrs
+ else:
+ markup_attr_map = {}
+ for k, v in markup_attrs:
+ markup_attr_map[k] = v
+ attr_value = markup_attr_map.get(attr)
+ if not self._matches(attr_value, match_against):
+ match = False
+ break
+ if match:
+ if markup:
+ found = markup
+ else:
+ found = markup_name
+ if found and self.string and not self._matches(found.string, self.string):
+ found = None
+ return found
+
+ # For BS3 compatibility.
+ searchTag = search_tag
+
+ def search(self, markup):
+ """Find all items in `markup` that match this SoupStrainer.
+
+ Used by the core _find_all() method, which is ultimately
+ called by all find_* methods.
+
+ :param markup: A PageElement or a list of them.
+ """
+ # print('looking for %s in %s' % (self, markup))
+ found = None
+ # If given a list of items, scan it for a text element that
+ # matches.
+ if hasattr(markup, '__iter__') and not isinstance(markup, (Tag, str)):
+ for element in markup:
+ if isinstance(element, NavigableString) \
+ and self.search(element):
+ found = element
+ break
+ # If it's a Tag, make sure its name or attributes match.
+ # Don't bother with Tags if we're searching for text.
+ elif isinstance(markup, Tag):
+ if not self.string or self.name or self.attrs:
+ found = self.search_tag(markup)
+ # If it's text, make sure the text matches.
+ elif isinstance(markup, NavigableString) or \
+ isinstance(markup, str):
+ if not self.name and not self.attrs and self._matches(markup, self.string):
+ found = markup
+ else:
+ raise Exception(
+ "I don't know how to match against a %s" % markup.__class__)
+ return found
+
+ def _matches(self, markup, match_against, already_tried=None):
+ # print(u"Matching %s against %s" % (markup, match_against))
+ result = False
+ if isinstance(markup, list) or isinstance(markup, tuple):
+ # This should only happen when searching a multi-valued attribute
+ # like 'class'.
+ for item in markup:
+ if self._matches(item, match_against):
+ return True
+ # We didn't match any particular value of the multivalue
+ # attribute, but maybe we match the attribute value when
+ # considered as a string.
+ if self._matches(' '.join(markup), match_against):
+ return True
+ return False
+
+ if match_against is True:
+ # True matches any non-None value.
+ return markup is not None
+
+ if isinstance(match_against, Callable):
+ return match_against(markup)
+
+ # Custom callables take the tag as an argument, but all
+ # other ways of matching match the tag name as a string.
+ original_markup = markup
+ if isinstance(markup, Tag):
+ markup = markup.name
+
+ # Ensure that `markup` is either a Unicode string, or None.
+ markup = self._normalize_search_value(markup)
+
+ if markup is None:
+ # None matches None, False, an empty string, an empty list, and so on.
+ return not match_against
+
+ if (hasattr(match_against, '__iter__')
+ and not isinstance(match_against, str)):
+ # We're asked to match against an iterable of items.
+ # The markup must be match at least one item in the
+ # iterable. We'll try each one in turn.
+ #
+ # To avoid infinite recursion we need to keep track of
+ # items we've already seen.
+ if not already_tried:
+ already_tried = set()
+ for item in match_against:
+ if item.__hash__:
+ key = item
+ else:
+ key = id(item)
+ if key in already_tried:
+ continue
+ else:
+ already_tried.add(key)
+ if self._matches(original_markup, item, already_tried):
+ return True
+ else:
+ return False
+
+ # Beyond this point we might need to run the test twice: once against
+ # the tag's name and once against its prefixed name.
+ match = False
+
+ if not match and isinstance(match_against, str):
+ # Exact string match
+ match = markup == match_against
+
+ if not match and hasattr(match_against, 'search'):
+ # Regexp match
+ return match_against.search(markup)
+
+ if (not match
+ and isinstance(original_markup, Tag)
+ and original_markup.prefix):
+ # Try the whole thing again with the prefixed tag name.
+ return self._matches(
+ original_markup.prefix + ':' + original_markup.name, match_against
+ )
+
+ return match
+
+
+class ResultSet(list):
+ """A ResultSet is just a list that keeps track of the SoupStrainer
+ that created it."""
+ def __init__(self, source, result=()):
+ """Constructor.
+
+ :param source: A SoupStrainer.
+ :param result: A list of PageElements.
+ """
+ super(ResultSet, self).__init__(result)
+ self.source = source
+
+ def __getattr__(self, key):
+ """Raise a helpful exception to explain a common code fix."""
+ raise AttributeError(
+ "ResultSet object has no attribute '%s'. You're probably treating a list of elements like a single element. Did you call find_all() when you meant to call find()?" % key
+ )
diff --git a/Source/Libs/bs4/formatter.py b/Source/Libs/bs4/formatter.py
new file mode 100644
index 0000000..8b0ff4d
--- /dev/null
+++ b/Source/Libs/bs4/formatter.py
@@ -0,0 +1,185 @@
+from .dammit import EntitySubstitution
+
+class Formatter(EntitySubstitution):
+ """Describes a strategy to use when outputting a parse tree to a string.
+
+ Some parts of this strategy come from the distinction between
+ HTML4, HTML5, and XML. Others are configurable by the user.
+
+ Formatters are passed in as the `formatter` argument to methods
+ like `PageElement.encode`. Most people won't need to think about
+ formatters, and most people who need to think about them can pass
+ in one of these predefined strings as `formatter` rather than
+ making a new Formatter object:
+
+ For HTML documents:
+ * 'html' - HTML entity substitution for generic HTML documents. (default)
+ * 'html5' - HTML entity substitution for HTML5 documents, as
+ well as some optimizations in the way tags are rendered.
+ * 'minimal' - Only make the substitutions necessary to guarantee
+ valid HTML.
+ * None - Do not perform any substitution. This will be faster
+ but may result in invalid markup.
+
+ For XML documents:
+ * 'html' - Entity substitution for XHTML documents.
+ * 'minimal' - Only make the substitutions necessary to guarantee
+ valid XML. (default)
+ * None - Do not perform any substitution. This will be faster
+ but may result in invalid markup.
+ """
+ # Registries of XML and HTML formatters.
+ XML_FORMATTERS = {}
+ HTML_FORMATTERS = {}
+
+ HTML = 'html'
+ XML = 'xml'
+
+ HTML_DEFAULTS = dict(
+ cdata_containing_tags=set(["script", "style"]),
+ )
+
+ def _default(self, language, value, kwarg):
+ if value is not None:
+ return value
+ if language == self.XML:
+ return set()
+ return self.HTML_DEFAULTS[kwarg]
+
+ def __init__(
+ self, language=None, entity_substitution=None,
+ void_element_close_prefix='/', cdata_containing_tags=None,
+ empty_attributes_are_booleans=False, indent=1,
+ ):
+ """Constructor.
+
+ :param language: This should be Formatter.XML if you are formatting
+ XML markup and Formatter.HTML if you are formatting HTML markup.
+
+ :param entity_substitution: A function to call to replace special
+ characters with XML/HTML entities. For examples, see
+ bs4.dammit.EntitySubstitution.substitute_html and substitute_xml.
+ :param void_element_close_prefix: By default, void elements
+ are represented as (XML rules) rather than
+ (HTML rules). To get , pass in the empty string.
+ :param cdata_containing_tags: The list of tags that are defined
+ as containing CDATA in this dialect. For example, in HTML,
+
+This numeric entity is missing the final semicolon:
+
+a
+This document contains (do you see it?)
+
+The doctype is invalid because it contains extra whitespace
+That boolean attribute had no value
+Here's a nonexistent entity: foo; (do you see it?)
+This document ends before the entity finishes: >
+
Paragraphs shouldn't contain block display elements, but this one does:
you see?
+Multiple values for the same attribute.
+
+