Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-03 08:19:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

[viki] Extract m3u8 videos (#4855)

Browse Source
This commit is contained in:
Yen Chi Hsuan 2015-05-02 01:19:06 +08:00
parent 89966a5aea
commit d948e09b61
1 changed files with 31 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
youtube_dl/extractor/viki.py
View File

@ -12,6 +12,8 @@
unified_strdate, unified_strdate,
US_RATINGS, US_RATINGS,
clean_html, clean_html,
determine_ext,
mimetype2ext,
) )
from .common import InfoExtractor from .common import InfoExtractor
@ -45,6 +47,19 @@ class VikiIE(InfoExtractor):
'upload_date': '20150430', 'upload_date': '20150430',
'title': '\'The Avengers: Age of Ultron\' Press Conference', 'title': '\'The Avengers: Age of Ultron\' Press Conference',
} }
}, {
'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
'info_dict': {
'id': '1048879v',
'ext': 'mp4',
'upload_date': '20140820',
'description': 'md5:54ff56d51bdfc7a30441ec967394e91c',
'title': 'Ankhon Dekhi',
},
'params': {
# requires ffmpeg
'skip_download': True,
}
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -81,8 +96,21 @@ def _real_extract(self, url):
expected=True) expected=True)
else: else:
raise ExtractorError('Viki said: ' + err_msg) raise ExtractorError('Viki said: ' + err_msg)
video_url = self._html_search_regex( mobj = re.search(
r'<source[^>]+src="([^"]+)"', info_webpage, 'video URL') r'<source[^>]+type="(?P<mime_type>[^"]+)"[^>]+src="(?P<url>[^"]+)"', info_webpage)
if not mobj:
raise ExtractorError('Unable to find video URL')
video_url = unescapeHTML(mobj.group('url'))
video_ext = mimetype2ext(mobj.group('mime_type'))
if determine_ext(video_url) == 'm3u8':
formats = self._extract_m3u8_formats(
video_url, video_id, ext=video_ext)
else:
formats = [{
'url': video_url,
'ext': video_ext,
}]
upload_date_str = self._html_search_regex( upload_date_str = self._html_search_regex(
r'"created_at":"([^"]+)"', info_webpage, 'upload date') r'"created_at":"([^"]+)"', info_webpage, 'upload date')
@ -98,7 +126,7 @@ def _real_extract(self, url):
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'formats': formats,
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'age_limit': age_limit, 'age_limit': age_limit,