fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[BlipTVIE] Fix and simplify extraction of embedded videos

This commit is contained in:
rzhxeo 2013-12-30 06:07:52 +01:00
parent b26559878f
commit c0f9969b9e
1 changed files with 7 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/bliptv.py
View File

@ -20,7 +20,7 @@ from ..utils import (
class BlipTVIE(InfoExtractor): class BlipTVIE(InfoExtractor):
"""Information extractor for blip.tv""" """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]+)$' _URL_EXT = r'^.*\.([a-z0-9]+)$'
IE_NAME = u'blip.tv' IE_NAME = u'blip.tv'
_TEST = { _TEST = {
@ -45,17 +45,12 @@ class BlipTVIE(InfoExtractor):
raise ExtractorError(u'Invalid URL: %s' % url) raise ExtractorError(u'Invalid URL: %s' % url)
# See https://github.com/rg3/youtube-dl/issues/857 # 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) embed_mobj = re.search(r'^(?:https?://)?(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', url)
if api_mobj is not None: if embed_mobj:
url = 'http://blip.tv/play/g_%s' % api_mobj.group('video_id') info_url = 'http://blip.tv/play/%s.x?p=1' % embed_mobj.group(1)
urlp = compat_urllib_parse_urlparse(url) info_page = self._download_webpage(info_url, embed_mobj.group(1))
if urlp.path.startswith('/play/'): video_id = self._search_regex(r'data-episode-id="(\d+)', info_page, u'video_id')
response = self._request_webpage(url, None, False) return self.url_result('http://blip.tv/a/a-'+video_id, 'BlipTV')
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)
if '?' in url: if '?' in url:
cchar = '&' cchar = '&'