diff options
| author | rzhxeo <rzhxeot7z81b4700@mailcatch.com> | 2013-12-30 06:07:52 +0100 |
|---|---|---|
| committer | rzhxeo <rzhxeot7z81b4700@mailcatch.com> | 2013-12-30 06:14:10 +0100 |
| commit | c0f9969b9e297a2c4ceb87017081792e13f4cdc6 (patch) | |
| tree | 4163c5d0dfc995a5e9e9b2bef4e8b211af4b043f /youtube_dl | |
| parent | b26559878fa47bb13ad283fcad36c3a9ef484528 (diff) | |
[BlipTVIE] Fix and simplify extraction of embedded videos
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/extractor/bliptv.py | 19 |
1 files changed, 7 insertions, 12 deletions
diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index c7e0a53c1..8a8c2e7a8 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -20,7 +20,7 @@ from ..utils import ( class BlipTVIE(InfoExtractor): """Information extractor for blip.tv""" - _VALID_URL = r'^(?:https?://)?(?:www\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$' + _VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$' _URL_EXT = r'^.*\.([a-z0-9]+)$' IE_NAME = u'blip.tv' _TEST = { @@ -45,17 +45,12 @@ class BlipTVIE(InfoExtractor): raise ExtractorError(u'Invalid URL: %s' % url) # See https://github.com/rg3/youtube-dl/issues/857 - api_mobj = re.match(r'http://a\.blip\.tv/api\.swf#(?P<video_id>[\d\w]+)', url) - if api_mobj is not None: - url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id') - urlp = compat_urllib_parse_urlparse(url) - if urlp.path.startswith('/play/'): - response = self._request_webpage(url, None, False) - redirecturl = response.geturl() - rurlp = compat_urllib_parse_urlparse(redirecturl) - file_id = compat_parse_qs(rurlp.fragment)['file'][0].rpartition('/')[2] - url = 'http://blip.tv/a/a-' + file_id - return self._real_extract(url) + embed_mobj = re.search(r'^(?:https?://)?(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url) + if embed_mobj: + info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1) + info_page = self._download_webpage(info_url, embed_mobj.group(1)) + video_id = self._search_regex(r'data-episode-id="(\d+)', info_page, u'video_id') + return self.url_result('http://blip.tv/a/a-'+video_id, 'BlipTV') if '?' in url: cchar = '&' |