aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-08-22 01:36:07 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2014-08-22 01:36:07 +0200
commitea6e8d545430ebd8cf622c5c04571f180452360e (patch)
tree0272bfe1b0f3f2fe9509149d15fe8fa40352ed83
parent61882bf7c69ddeee58b5e02bf7cd8973632fe2c9 (diff)
[metacafe] Add support for movieclips videos (Fixes #3555)
-rw-r--r--youtube_dl/extractor/metacafe.py66
1 files changed, 61 insertions, 5 deletions
diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 96a4f1018..1a896b536 100644
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -9,6 +9,7 @@ from ..utils import (
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 @@ class MetacafeIE(InfoExtractor):
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 @@ class MetacafeIE(InfoExtractor):
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))
+
+ age_limit = (
+ 18
+ if re.search(r'"contentRating":"restricted"', webpage)
+ else 0)
- if re.search(r'"contentRating":"restricted"', webpage) is not None:
- age_limit = 18
+ 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,
}