projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[mailru] Fix extraction (closes #24530) (#25239)
[youtube-dl]
/
youtube_dl
/
extractor
/
ign.py
diff --git
a/youtube_dl/extractor/ign.py
b/youtube_dl/extractor/ign.py
index fa4e673947c395870fe6b4b15c32da74a4bc9616..a96ea801019c808e6a8fe1f8f6590b0e018feeef 100644
(file)
--- a/
youtube_dl/extractor/ign.py
+++ b/
youtube_dl/extractor/ign.py
@@
-32,6
+32,7
@@
class IGNIE(InfoExtractor):
'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
'timestamp': 1370440800,
'upload_date': '20130605',
'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
'timestamp': 1370440800,
'upload_date': '20130605',
+ 'uploader_id': 'cberidon@ign.com',
}
},
{
}
},
{
@@
-48,6
+49,7
@@
class IGNIE(InfoExtractor):
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
+ 'uploader_id': 'danieljkrupa@gmail.com',
},
},
{
},
},
{
@@
-58,6
+60,7
@@
class IGNIE(InfoExtractor):
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
+ 'uploader_id': 'togilvie@ign.com',
},
},
],
},
},
],
@@
-75,8
+78,22
@@
class IGNIE(InfoExtractor):
'description': 'Brian and Jared explore Michel Ancel\'s captivating new preview.',
'timestamp': 1408047180,
'upload_date': '20140814',
'description': 'Brian and Jared explore Michel Ancel\'s captivating new preview.',
'timestamp': 1408047180,
'upload_date': '20140814',
+ 'uploader_id': 'jamesduggan1990@gmail.com',
},
},
},
},
+ {
+ 'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
+ 'only_matching': True,
+ },
+ {
+ 'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
+ 'only_matching': True,
+ },
+ {
+ # videoId pattern
+ 'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
+ 'only_matching': True,
+ },
]
def _find_video_id(self, webpage):
]
def _find_video_id(self, webpage):
@@
-86,6
+103,8
@@
class IGNIE(InfoExtractor):
r'data-video-id="(.+?)"',
r'<object id="vid_(.+?)"',
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
r'data-video-id="(.+?)"',
r'<object id="vid_(.+?)"',
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
+ r'videoId"\s*:\s*"(.+?)"',
+ r'videoId["\']\s*:\s*["\']([^"\']+?)["\']',
]
return self._search_regex(res_id, webpage, 'video id', default=None)
]
return self._search_regex(res_id, webpage, 'video id', default=None)
@@
-96,7
+115,7
@@
class IGNIE(InfoExtractor):
webpage = self._download_webpage(url, name_or_id)
if page_type != 'video':
multiple_urls = re.findall(
webpage = self._download_webpage(url, name_or_id)
if page_type != 'video':
multiple_urls = re.findall(
- '<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
+
r
'<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
webpage)
if multiple_urls:
entries = [self.url_result(u, ie='IGN') for u in multiple_urls]
webpage)
if multiple_urls:
entries = [self.url_result(u, ie='IGN') for u in multiple_urls]
@@
-108,19
+127,24
@@
class IGNIE(InfoExtractor):
video_id = self._find_video_id(webpage)
if not video_id:
video_id = self._find_video_id(webpage)
if not video_id:
- return self.url_result(self._search_regex(self._EMBED_RE, webpage, 'embed url'))
+ return self.url_result(self._search_regex(
+ self._EMBED_RE, webpage, 'embed url'))
return self._get_video_info(video_id)
def _get_video_info(self, video_id):
return self._get_video_info(video_id)
def _get_video_info(self, video_id):
- api_data = self._download_json(self._API_URL_TEMPLATE % video_id, video_id)
+ api_data = self._download_json(
+ self._API_URL_TEMPLATE % video_id, video_id)
formats = []
m3u8_url = api_data['refs'].get('m3uUrl')
if m3u8_url:
formats = []
m3u8_url = api_data['refs'].get('m3uUrl')
if m3u8_url:
- formats.extend(self._extract_m3u8_formats(m3u8_url, video_id))
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False))
f4m_url = api_data['refs'].get('f4mUrl')
if f4m_url:
f4m_url = api_data['refs'].get('f4mUrl')
if f4m_url:
- formats.extend(self._extract_f4m_formats(f4m_url, video_id))
+ formats.extend(self._extract_f4m_formats(
+ f4m_url, video_id, f4m_id='hds', fatal=False))
for asset in api_data['assets']:
formats.append({
'url': asset['url'],
for asset in api_data['assets']:
formats.append({
'url': asset['url'],
@@
-131,9
+155,9
@@
class IGNIE(InfoExtractor):
})
self._sort_formats(formats)
})
self._sort_formats(formats)
- thumbnails = [
]
- for thumbnail in api_data['thumbnails']:
- thumbnails.append({'url': thumbnail['url']})
+ thumbnails = [
{
+ 'url': thumbnail['url']
+ } for thumbnail in api_data.get('thumbnails', [])]
metadata = api_data['metadata']
metadata = api_data['metadata']
@@
-144,6
+168,7
@@
class IGNIE(InfoExtractor):
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
'display_id': metadata.get('slug') or video_id,
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
'display_id': metadata.get('slug') or video_id,
+ 'uploader_id': metadata.get('creator'),
'thumbnails': thumbnails,
'formats': formats,
}
'thumbnails': thumbnails,
'formats': formats,
}
@@
-163,6
+188,7
@@
class OneUPIE(IGNIE):
'description': 'md5:bf0516c5ee32a3217aa703e9b1bc7826',
'timestamp': 1313099220,
'upload_date': '20110811',
'description': 'md5:bf0516c5ee32a3217aa703e9b1bc7826',
'timestamp': 1313099220,
'upload_date': '20110811',
+ 'uploader_id': 'IGN',
}
}]
}
}]
@@
-177,7
+203,7
@@
class PCMagIE(IGNIE):
_VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)'
IE_NAME = 'pcmag'
_VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)'
IE_NAME = 'pcmag'
- _EMBED_RE = r'iframe
.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content
.html?[^"]*url=([^"]+)["&]'
+ _EMBED_RE = r'iframe
\.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content\
.html?[^"]*url=([^"]+)["&]'
_TESTS = [{
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
_TESTS = [{
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
@@
-189,8
+215,9
@@
class PCMagIE(IGNIE):
'description': 'md5:a7071ae64d2f68cc821c729d4ded6bb3',
'timestamp': 1420571160,
'upload_date': '20150106',
'description': 'md5:a7071ae64d2f68cc821c729d4ded6bb3',
'timestamp': 1420571160,
'upload_date': '20150106',
+ 'uploader_id': 'cozzipix@gmail.com',
}
}
- },{
+ },
{
'url': 'http://www.pcmag.com/article2/0,2817,2470156,00.asp',
'md5': '94130c1ca07ba0adb6088350681f16c1',
'info_dict': {
'url': 'http://www.pcmag.com/article2/0,2817,2470156,00.asp',
'md5': '94130c1ca07ba0adb6088350681f16c1',
'info_dict': {
@@
-200,5
+227,6
@@
class PCMagIE(IGNIE):
'description': 'md5:53433c45df96d2ea5d0fda18be2ca908',
'timestamp': 1412953920,
'upload_date': '20141010',
'description': 'md5:53433c45df96d2ea5d0fda18be2ca908',
'timestamp': 1412953920,
'upload_date': '20141010',
+ 'uploader_id': 'chris_snyder@pcmag.com',
}
}]
}
}]