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

[metacafe] Add support for movieclips videos (Fixes #3555)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-08-22 01:36:07 +02:00
parent 61882bf7c6
commit ea6e8d5454
1 changed files with 61 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

66
youtube_dl/extractor/metacafe.py
View file

@ -9,6 +9,7 @@
compat_urllib_request,
determine_ext,
ExtractorError,
int_or_none,
)
@ -83,6 +84,21 @@ class MetacafeIE(InfoExtractor):
'skip_download': True,
},
},
# Movieclips.com video
{
'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/',
'info_dict': {
'id': 'mv-Wy7ZU',
'ext': 'mp4',
'title': 'My Week with Marilyn - Do You Love Me?',
'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.',
'uploader': 'movie_trailers',
'duration': 176,
},
'params': {
'skip_download': 'requires rtmpdump',
}
}
]
def report_disclaimer(self):
@ -167,7 +183,36 @@ def _real_extract(self, url):
mediaURL = mobj.group('mediaURL').replace('\\/', '/')
video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
video_ext = determine_ext(video_url)
if video_url is None:
player_url = self._search_regex(
r"swfobject\.embedSWF\('([^']+)'",
webpage, 'config URL', default=None)
if player_url:
config_url = self._search_regex(
r'config=(.+)$', player_url, 'config URL')
config_doc = self._download_xml(
config_url, video_id,
note='Downloading video config')
smil_url = config_doc.find('.//properties').attrib['smil_file']
smil_doc = self._download_xml(
smil_url, video_id,
note='Downloading SMIL document')
base_url = smil_doc.find('./head/meta').attrib['base']
video_url = []
for vn in smil_doc.findall('.//video'):
br = int(vn.attrib['system-bitrate'])
play_path = vn.attrib['src']
video_url.append({
'format_id': 'smil-%d' % br,
'url': base_url,
'play_path': play_path,
'page_url': url,
'player_url': player_url,
'ext': play_path.partition(':')[0],
})
if video_url is None:
raise ExtractorError('Unsupported video type')
video_title = self._html_search_regex(
r'(?im)<title>(.*) - Video</title>', webpage, 'title')
@ -176,19 +221,30 @@ def _real_extract(self, url):
video_uploader = self._html_search_regex(
r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
webpage, 'uploader nickname', fatal=False)
duration = int_or_none(
self._html_search_meta('video:duration', webpage))
if re.search(r'"contentRating":"restricted"', webpage) is not None:
age_limit = 18
age_limit = (
18
if re.search(r'"contentRating":"restricted"', webpage)
else 0)
if isinstance(video_url, list):
formats = video_url
else:
age_limit = 0
formats = [{
'url': video_url,
'ext': video_ext,
}]
self._sort_formats(formats)
return {
'id': video_id,
'url': video_url,
'description': description,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'ext': video_ext,
'age_limit': age_limit,
'formats': formats,
'duration': duration,
}