projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
git pushMerge branch 'master' of github.com:rg3/youtube-dl
[youtube-dl]
/
youtube_dl
/
extractor
/
funnyordie.py
diff --git
a/youtube_dl/extractor/funnyordie.py
b/youtube_dl/extractor/funnyordie.py
index 8ffcfca3b58a1e9570a23c5da5d904943ac9ea73..8c5ffc9e84cec305e9fc813a6366b360b7e36230 100644
(file)
--- a/
youtube_dl/extractor/funnyordie.py
+++ b/
youtube_dl/extractor/funnyordie.py
@@
-21,7
+21,6
@@
class FunnyOrDieIE(InfoExtractor):
},
}, {
'url': 'http://www.funnyordie.com/embed/e402820827',
},
}, {
'url': 'http://www.funnyordie.com/embed/e402820827',
- 'md5': '29f4c5e5a61ca39dfd7e8348a75d0aad',
'info_dict': {
'id': 'e402820827',
'ext': 'mp4',
'info_dict': {
'id': 'e402820827',
'ext': 'mp4',
@@
-29,6
+28,9
@@
class FunnyOrDieIE(InfoExtractor):
'description': 'Please use this to sell something. www.jonlajoie.com',
'thumbnail': 're:^http:.*\.jpg$',
},
'description': 'Please use this to sell something. www.jonlajoie.com',
'thumbnail': 're:^http:.*\.jpg$',
},
+ }, {
+ 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
+ 'only_matching': True,
}]
def _real_extract(self, url):
}]
def _real_extract(self, url):
@@
-43,20
+45,33
@@
class FunnyOrDieIE(InfoExtractor):
links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
- bitrates = self._html_search_regex(r'<source src="[^"]+/v,((?:\d+,)+)\.mp4\.csmil', webpage, 'video bitrates')
- bitrates = [int(b) for b in bitrates.rstrip(',').split(',')]
-
bitrates.sort(
)
+ m3u8_url = self._search_regex(
+ r'<source[^>]+src=(["\'])(?P<url>.+?/master\.m3u8[^"\']*)\1',
+
webpage, 'm3u8 url', group='url'
)
formats = []
formats = []
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
+
+ bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)[,/]', m3u8_url)]
+ bitrates.sort()
+
for bitrate in bitrates:
for link in links:
formats.append({
for bitrate in bitrates:
for link in links:
formats.append({
- 'url':
'%s%d.%s' % (link[0], bitrate, link[1]
),
+ 'url':
self._proto_relative_url('%s%d.%s' % (link[0], bitrate, link[1])
),
'format_id': '%s-%d' % (link[1], bitrate),
'vbr': bitrate,
})
'format_id': '%s-%d' % (link[1], bitrate),
'vbr': bitrate,
})
+ subtitles = {}
+ for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):
+ subtitles[src_lang] = [{
+ 'ext': src.split('/')[-1],
+ 'url': 'http://www.funnyordie.com%s' % src,
+ }]
+
post_json = self._search_regex(
r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
post = json.loads(post_json)
post_json = self._search_regex(
r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details')
post = json.loads(post_json)
@@
-67,4
+82,5
@@
class FunnyOrDieIE(InfoExtractor):
'description': post.get('description'),
'thumbnail': post.get('picture'),
'formats': formats,
'description': post.get('description'),
'thumbnail': post.get('picture'),
'formats': formats,
+ 'subtitles': subtitles,
}
}