Download videos after extracting information

This is achieved by letting the InfoExtractors instruct its downloader to
process the information dictionary just after extracting the information. As a
consequence, some code is simplified too.
This commit is contained in:
Ricardo Garcia 2009-04-23 22:20:06 +02:00
parent 147753eb33
commit 6f21f68629
1 changed files with 44 additions and 55 deletions

View File

@ -301,21 +301,8 @@ class FileDownloader(object):
# Suitable InfoExtractor found # Suitable InfoExtractor found
suitable_found = True suitable_found = True
# Extract information from URL # Extract information from URL and process it
all_results = ie.extract(url) ie.extract(url)
results = [x for x in all_results if x is not None]
# See if there were problems extracting any information
if len(results) != len(all_results):
self.trouble()
# Two results could go to the same file
if len(results) > 1 and self.fixed_template():
raise SameFileError(self.params['outtmpl'])
# Process each result
for result in results:
self.process_info(result)
# Suitable InfoExtractor had been found; go to next URL # Suitable InfoExtractor had been found; go to next URL
break break
@ -508,7 +495,7 @@ class YoutubeIE(InfoExtractor):
else: else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE) raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError), err: except (IOError, netrc.NetrcParseError), err:
self._downloader.trouble(u'WARNING: parsing .netrc: %s' % str(err)) self._downloader.to_stderr(u'WARNING: parsing .netrc: %s' % str(err))
return return
# Set language # Set language
@ -517,7 +504,7 @@ class YoutubeIE(InfoExtractor):
self.report_lang() self.report_lang()
urllib2.urlopen(request).read() urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'WARNING: unable to set language: %s' % str(err)) self._downloader.to_stderr(u'WARNING: unable to set language: %s' % str(err))
return return
# No authentication to be performed # No authentication to be performed
@ -537,10 +524,10 @@ class YoutubeIE(InfoExtractor):
self.report_login() self.report_login()
login_results = urllib2.urlopen(request).read() login_results = urllib2.urlopen(request).read()
if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None: if re.search(r'(?i)<form[^>]* name="loginForm"', login_results) is not None:
self._downloader.trouble(u'WARNING: unable to log in: bad username or password') self._downloader.to_stderr(u'WARNING: unable to log in: bad username or password')
return return
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'WARNING: unable to log in: %s' % str(err)) self._downloader.to_stderr(u'WARNING: unable to log in: %s' % str(err))
return return
# Confirm age # Confirm age
@ -561,7 +548,7 @@ class YoutubeIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return [None] return
video_id = mobj.group(2) video_id = mobj.group(2)
# Downloader parameters # Downloader parameters
@ -587,14 +574,14 @@ class YoutubeIE(InfoExtractor):
video_webpage = urllib2.urlopen(request).read() video_webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err)) self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
return [None] return
self.report_information_extraction(video_id) self.report_information_extraction(video_id)
# "t" param # "t" param
mobj = re.search(r', "t": "([^"]+)"', video_webpage) mobj = re.search(r', "t": "([^"]+)"', video_webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract "t" parameter') self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
return [None] return
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1)) video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
if format_param is not None: if format_param is not None:
video_real_url = '%s&fmt=%s' % (video_real_url, format_param) video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
@ -604,14 +591,14 @@ class YoutubeIE(InfoExtractor):
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage) mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname') self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return [None] return
video_uploader = mobj.group(1) video_uploader = mobj.group(1)
# title # title
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage) mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract video title') self._downloader.trouble(u'ERROR: unable to extract video title')
return [None] return
video_title = mobj.group(1).decode('utf-8') video_title = mobj.group(1).decode('utf-8')
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title) video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
video_title = video_title.replace(os.sep, u'%') video_title = video_title.replace(os.sep, u'%')
@ -621,14 +608,14 @@ class YoutubeIE(InfoExtractor):
simple_title = simple_title.strip(ur'_') simple_title = simple_title.strip(ur'_')
# Process video information # Process video information
return [{ self._downloader.process_info({
'id': video_id.decode('utf-8'), 'id': video_id.decode('utf-8'),
'url': video_real_url.decode('utf-8'), 'url': video_real_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'),
'title': video_title, 'title': video_title,
'stitle': simple_title, 'stitle': simple_title,
'ext': video_extension.decode('utf-8'), 'ext': video_extension.decode('utf-8'),
}] })
class MetacafeIE(InfoExtractor): class MetacafeIE(InfoExtractor):
"""Information Extractor for metacafe.com.""" """Information Extractor for metacafe.com."""
@ -689,14 +676,15 @@ class MetacafeIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url) self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return [None] return
video_id = mobj.group(1) video_id = mobj.group(1)
# Check if video comes from YouTube # Check if video comes from YouTube
mobj2 = re.match(r'^yt-(.*)$', video_id) mobj2 = re.match(r'^yt-(.*)$', video_id)
if mobj2 is not None: if mobj2 is not None:
return self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1)) self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % mobj2.group(1))
return
simple_title = mobj.group(2).decode('utf-8') simple_title = mobj.group(2).decode('utf-8')
video_extension = 'flv' video_extension = 'flv'
@ -708,20 +696,20 @@ class MetacafeIE(InfoExtractor):
webpage = urllib2.urlopen(request).read() webpage = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err)) self._downloader.trouble(u'ERROR: unable retrieve video webpage: %s' % str(err))
return [None] return
# Extract URL, uploader and title from webpage # Extract URL, uploader and title from webpage
self.report_extraction(video_id) self.report_extraction(video_id)
mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage) mobj = re.search(r'(?m)"mediaURL":"(http.*?\.flv)"', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL') self._downloader.trouble(u'ERROR: unable to extract media URL')
return [None] return
mediaURL = mobj.group(1).replace('\\', '') mediaURL = mobj.group(1).replace('\\', '')
mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage) mobj = re.search(r'(?m)"gdaKey":"(.*?)"', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract gdaKey') self._downloader.trouble(u'ERROR: unable to extract gdaKey')
return [None] return
gdaKey = mobj.group(1) gdaKey = mobj.group(1)
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey) video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
@ -729,24 +717,24 @@ class MetacafeIE(InfoExtractor):
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage) mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract title') self._downloader.trouble(u'ERROR: unable to extract title')
return [None] return
video_title = mobj.group(1).decode('utf-8') video_title = mobj.group(1).decode('utf-8')
mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage) mobj = re.search(r'(?m)<li id="ChnlUsr">.*?Submitter:<br />(.*?)</li>', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname') self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return [None] return
video_uploader = re.sub(r'<.*?>', '', mobj.group(1)) video_uploader = re.sub(r'<.*?>', '', mobj.group(1))
# Return information # Process video information
return [{ self._downloader.process_info({
'id': video_id.decode('utf-8'), 'id': video_id.decode('utf-8'),
'url': video_url.decode('utf-8'), 'url': video_url.decode('utf-8'),
'uploader': video_uploader.decode('utf-8'), 'uploader': video_uploader.decode('utf-8'),
'title': video_title, 'title': video_title,
'stitle': simple_title, 'stitle': simple_title,
'ext': video_extension.decode('utf-8'), 'ext': video_extension.decode('utf-8'),
}] })
class YoutubeSearchIE(InfoExtractor): class YoutubeSearchIE(InfoExtractor):
@ -777,26 +765,30 @@ class YoutubeSearchIE(InfoExtractor):
mobj = re.match(self._VALID_QUERY, query) mobj = re.match(self._VALID_QUERY, query)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid search query "%s"' % query) self._downloader.trouble(u'ERROR: invalid search query "%s"' % query)
return [None] return
prefix, query = query.split(':') prefix, query = query.split(':')
prefix = prefix[8:] prefix = prefix[8:]
if prefix == '': if prefix == '':
return self._download_n_results(query, 1) self._download_n_results(query, 1)
return
elif prefix == 'all': elif prefix == 'all':
return self._download_n_results(query, self._max_youtube_results) self._download_n_results(query, self._max_youtube_results)
return
else: else:
try: try:
n = int(prefix) n = int(prefix)
if n <= 0: if n <= 0:
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query)) self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
return [None] return
elif n > self._max_youtube_results: elif n > self._max_youtube_results:
self._downloader.trouble(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n)) self._downloader.to_stderr(u'WARNING: ytsearch returns max %i results (you requested %i)' % (self._max_youtube_results, n))
n = self._max_youtube_results n = self._max_youtube_results
return self._download_n_results(query, n) self._download_n_results(query, n)
return
except ValueError: # parsing prefix as int fails except ValueError: # parsing prefix as int fails
return self._download_n_results(query, 1) self._download_n_results(query, 1)
return
def _download_n_results(self, query, n): def _download_n_results(self, query, n):
"""Downloads a specified number of results for a query""" """Downloads a specified number of results for a query"""
@ -813,7 +805,7 @@ class YoutubeSearchIE(InfoExtractor):
page = urllib2.urlopen(request).read() page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return [None] return
# Extract video identifiers # Extract video identifiers
for mobj in re.finditer(self._VIDEO_INDICATOR, page): for mobj in re.finditer(self._VIDEO_INDICATOR, page):
@ -823,16 +815,14 @@ class YoutubeSearchIE(InfoExtractor):
already_seen.add(video_id) already_seen.add(video_id)
if len(video_ids) == n: if len(video_ids) == n:
# Specified n videos reached # Specified n videos reached
information = []
for id in video_ids: for id in video_ids:
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return information return
if self._MORE_PAGES_INDICATOR not in page: if self._MORE_PAGES_INDICATOR not in page:
information = []
for id in video_ids: for id in video_ids:
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return information return
pagenum = pagenum + 1 pagenum = pagenum + 1
@ -865,7 +855,7 @@ class YoutubePlaylistIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: invalid url: %s' % url) self._downloader.trouble(u'ERROR: invalid url: %s' % url)
return [None] return
# Download playlist pages # Download playlist pages
playlist_id = mobj.group(1) playlist_id = mobj.group(1)
@ -879,7 +869,7 @@ class YoutubePlaylistIE(InfoExtractor):
page = urllib2.urlopen(request).read() page = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err: except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err))
return [None] return
# Extract video identifiers # Extract video identifiers
ids_in_page = [] ids_in_page = []
@ -892,10 +882,9 @@ class YoutubePlaylistIE(InfoExtractor):
break break
pagenum = pagenum + 1 pagenum = pagenum + 1
information = []
for id in video_ids: for id in video_ids:
information.extend(self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)) self._youtube_ie.extract('http://www.youtube.com/watch?v=%s' % id)
return information return
class PostProcessor(object): class PostProcessor(object):
"""Post Processor class. """Post Processor class.