github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[ign] Fix extraction of video in articles

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-08-26 15:38:29 +02:00
parent 15a1f4b8fe
commit a204c85408
1 changed files with 14 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
youtube_dl/extractor/ign.py
View file

@ -18,6 +18,7 @@ class IGNIE(InfoExtractor):
_DESCRIPTION_RE = [ _DESCRIPTION_RE = [
r'<span class="page-object-description">(.+?)</span>', r'<span class="page-object-description">(.+?)</span>',
r'id="my_show_video">.*?<p>(.*?)</p>', r'id="my_show_video">.*?<p>(.*?)</p>',
r'<meta name="description" content="(.*?)"',
] ]
_TESTS = [ _TESTS = [
@ -55,6 +56,17 @@ class IGNIE(InfoExtractor):
'skip_download': True, 'skip_download': True,
}, },
}, },
{
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7',
'info_dict': {
'id': '078fdd005f6d3c02f63d795faa1b984f',
'ext': 'mp4',
'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
'description': 'Giant skeletons, bloody hunts, and captivating'
' natural beauty take our breath away.',
},
},
] ]
def _find_video_id(self, webpage): def _find_video_id(self, webpage):
@ -62,6 +74,7 @@ def _find_video_id(self, webpage):
r'data-video-id="(.+?)"', r'data-video-id="(.+?)"',
r'<object id="vid_(.+?)"', r'<object id="vid_(.+?)"',
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"', r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
] ]
return self._search_regex(res_id, webpage, 'video id') return self._search_regex(res_id, webpage, 'video id')
@ -70,10 +83,7 @@ def _real_extract(self, url):
name_or_id = mobj.group('name_or_id') name_or_id = mobj.group('name_or_id')
page_type = mobj.group('type') page_type = mobj.group('type')
webpage = self._download_webpage(url, name_or_id) webpage = self._download_webpage(url, name_or_id)
if page_type == 'articles': if page_type != 'video':
video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, 'video url')
return self.url_result(video_url, ie='IGN')
elif page_type != 'video':
multiple_urls = re.findall( multiple_urls = re.findall(
'<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', '<param name="flashvars" value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
webpage) webpage)