diff options
author | sahutd <sahutd@gmail.com> | 2014-01-15 16:48:55 +0530 |
---|---|---|
committer | sahutd <sahutd@gmail.com> | 2014-01-15 16:48:55 +0530 |
commit | c8650f7ecd4fd253b37103c5581d39ddc37b6337 (patch) | |
tree | e14aa1ccdf7999f4ab0a4bee4077f9c69b1a561e /youtube_dl/extractor/franceinter.py | |
parent | 14e7543a5a0559086aa33a94557ecb61538c967b (diff) |
Made modification as suggested on https://github.com/rg3/youtube-dl/pull/2151
Diffstat (limited to 'youtube_dl/extractor/franceinter.py')
-rw-r--r-- | youtube_dl/extractor/franceinter.py | 27 |
1 files changed, 9 insertions, 18 deletions
diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 47e06f5a1..932a1f161 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -1,29 +1,20 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class FranceInterIE(InfoExtractor): - _VALID_URL=r'http://www.franceinter.fr/player/reecouter\?play=(?P<id>[0-9]{6})' - IE_NAME='FranceInter' + _VALID_URL=r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})' _TEST={ u'url':u'http://www.franceinter.fr/player/reecouter?play=793962', u'file':u'793962.mp3' - - + } - #Easier to use python string matching than regex for a simple match - def get_download_url(self,webpage): + - start=webpage.index('&urlAOD=')+8 - end=webpage.index('&startTime') - return u'http://www.franceinter.fr/%s'%webpage[start:end] - - def get_title(self,webpage): - start=webpage.index('<span class="title diffusion">')+30 - end=webpage.index('</span> dans') - - return webpage[start:end] + def _real_extract(self,url): mobj = re.match(self._VALID_URL, url) @@ -31,10 +22,10 @@ class FranceInterIE(InfoExtractor): webpage=self._download_webpage(url,video_id) - title=self.get_title(webpage) + title=self._search_regex(u'(?<=<span class="roll_overflow">)(.*)(?=</span></h1>)', webpage, u'title') - video_url=self.get_download_url(webpage) + video_url='http://www.franceinter.fr/'+self._search_regex(u'(?<=&urlAOD=)(.*)(?=&startTime)', webpage, u'video url') return{'id': video_id,u'url': video_url,u'title': title} - +
\ No newline at end of file |