fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[extractor/common] Add _meta_regex and clarify tags field

This commit is contained in:
Sergey M․ 2015-07-29 03:43:03 +06:00
parent 5316bf7487
commit 864f24bd2c
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
youtube_dl/extractor/common.py
View File

@ -181,13 +181,13 @@ class InfoExtractor(object):
by YoutubeDL if it's missing) by YoutubeDL if it's missing)
categories: A list of categories that the video falls in, for example categories: A list of categories that the video falls in, for example
["Sports", "Berlin"] ["Sports", "Berlin"]
tags: A list of tags assigned to the video, e.g. ["sweden", "pop music"]
is_live: True, False, or None (=unknown). Whether this video is a is_live: True, False, or None (=unknown). Whether this video is a
live stream that goes on instead of a fixed-length video. live stream that goes on instead of a fixed-length video.
start_time: Time in seconds where the reproduction should start, as start_time: Time in seconds where the reproduction should start, as
specified in the URL. specified in the URL.
end_time: Time in seconds where the reproduction should end, as end_time: Time in seconds where the reproduction should end, as
specified in the URL. specified in the URL.
tags: A list of keywords attached to the video.
Unless mentioned otherwise, the fields should be Unicode strings. Unless mentioned otherwise, the fields should be Unicode strings.
@ -631,6 +631,12 @@ class InfoExtractor(object):
template % (content_re, property_re), template % (content_re, property_re),
] ]
@staticmethod
def _meta_regex(prop):
return r'''(?isx)<meta
(?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
[^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
def _og_search_property(self, prop, html, name=None, **kargs): def _og_search_property(self, prop, html, name=None, **kargs):
if name is None: if name is None:
name = 'OpenGraph %s' % prop name = 'OpenGraph %s' % prop
@ -661,9 +667,7 @@ class InfoExtractor(object):
if display_name is None: if display_name is None:
display_name = name display_name = name
return self._html_search_regex( return self._html_search_regex(
r'''(?isx)<meta self._meta_regex(name),
(?=[^>]+(?:itemprop|name|property)=(["\']?)%s\1)
[^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(name),
html, display_name, fatal=fatal, group='content', **kwargs) html, display_name, fatal=fatal, group='content', **kwargs)
def _dc_search_uploader(self, html): def _dc_search_uploader(self, html):