github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[twitter] Now Twitter serves the same file for Firefox and Chrome

Browse source
This commit is contained in:
Yen Chi Hsuan 2016-03-03 14:27:27 +08:00
parent b8972bd69d
commit c8398a9b87
1 changed files with 47 additions and 60 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

107
youtube_dl/extractor/twitter.py
View file

@ -10,7 +10,6 @@
remove_end, remove_end,
int_or_none, int_or_none,
ExtractorError, ExtractorError,
sanitized_Request,
) )
@ -87,78 +86,66 @@ class TwitterCardIE(TwitterBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
# Different formats served for different User-Agents
USER_AGENTS = [
'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', # mp4
'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:38.0) Gecko/20100101 Firefox/38.0', # webm
]
config = None config = None
formats = [] formats = []
duration = None duration = None
for user_agent in USER_AGENTS: webpage = self._download_webpage(url, video_id)
request = sanitized_Request(url)
request.add_header('User-Agent', user_agent)
webpage = self._download_webpage(request, video_id)
iframe_url = self._html_search_regex( iframe_url = self._html_search_regex(
r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', r'<iframe[^>]+src="((?:https?:)?//(?:www.youtube.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
webpage, 'video iframe', default=None) webpage, 'video iframe', default=None)
if iframe_url: if iframe_url:
return self.url_result(iframe_url) return self.url_result(iframe_url)
config = self._parse_json(self._html_search_regex( config = self._parse_json(self._html_search_regex(
r'data-(?:player-)?config="([^"]+)"', webpage, 'data player config'), r'data-(?:player-)?config="([^"]+)"', webpage, 'data player config'),
video_id) video_id)
playlist = config.get('playlist') playlist = config.get('playlist')
if playlist: if playlist:
video_url = playlist[0]['source'] video_url = playlist[0]['source']
f = { f = {
'url': video_url, 'url': video_url,
} }
m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url) m = re.search(r'/(?P<width>\d+)x(?P<height>\d+)/', video_url)
if m: if m:
f.update({ f.update({
'width': int(m.group('width')), 'width': int(m.group('width')),
'height': int(m.group('height')), 'height': int(m.group('height')),
})
formats.append(f)
continue
vmap_url = config.get('vmapUrl') or config.get('vmap_url')
if vmap_url:
formats.append({
'url': self._get_vmap_video_url(vmap_url, video_id),
}) })
break # same video regardless of UA formats.append(f)
media_info = config.get('status', {}).get('entities', [{}])[0].get('mediaInfo', {}) vmap_url = config.get('vmapUrl') or config.get('vmap_url')
if media_info: if vmap_url:
for media_variant in media_info['variants']: formats.append({
media_url = media_variant['url'] 'url': self._get_vmap_video_url(vmap_url, video_id),
if media_url.endswith('.m3u8'): })
formats.extend(self._extract_m3u8_formats(media_url, video_id, ext='mp4', m3u8_id='hls'))
elif media_url.endswith('.mpd'):
formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash'))
else:
vbr = int_or_none(media_variant.get('bitRate'), scale=1000)
a_format = {
'url': media_url,
'format_id': 'http-%d' % vbr if vbr else 'http',
'vbr': vbr,
}
# Reported bitRate may be zero
if not a_format['vbr']:
del a_format['vbr']
formats.append(a_format) media_info = config.get('status', {}).get('entities', [{}])[0].get('mediaInfo', {})
if media_info:
for media_variant in media_info['variants']:
media_url = media_variant['url']
if media_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(media_url, video_id, ext='mp4', m3u8_id='hls'))
elif media_url.endswith('.mpd'):
formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash'))
else:
vbr = int_or_none(media_variant.get('bitRate'), scale=1000)
a_format = {
'url': media_url,
'format_id': 'http-%d' % vbr if vbr else 'http',
'vbr': vbr,
}
# Reported bitRate may be zero
if not a_format['vbr']:
del a_format['vbr']
duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) formats.append(a_format)
break # same video regardless of UA
duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9)
self._sort_formats(formats) self._sort_formats(formats)