diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-01-17 03:09:07 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-01-17 03:09:07 +0100 |
commit | 677b3ce82f7bb27f614f3972a6d6581bf89e14a6 (patch) | |
tree | 65736950ab7cc73d18c212c3f3cb5441834c9538 /youtube_dl/extractor | |
parent | fabfe17d5e783eaed7d3fb15a323756c031bcf4f (diff) |
[franceinter] Minor improvements (#2152)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/franceinter.py | 49 |
1 files changed, 29 insertions, 20 deletions
diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 932a1f161..7728410da 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -1,31 +1,40 @@ +# coding: utf-8 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})' - _TEST={ - u'url':u'http://www.franceinter.fr/player/reecouter?play=793962', - u'file':u'793962.mp3' - - } - - - - - def _real_extract(self,url): + _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})' + _TEST = { + 'url': 'http://www.franceinter.fr/player/reecouter?play=793962', + 'file': '793962.mp3', + 'md5': '4764932e466e6f6c79c317d2e74f6884', + "info_dict": { + "title": "L’Histoire dans les jeux vidéo", + }, + } + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage=self._download_webpage(url,video_id) - - title=self._search_regex(u'(?<=<span class="roll_overflow">)(.*)(?=</span></h1>)', webpage, u'title') - - 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} - + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title') + path = self._search_regex( + r'&urlAOD=(.*?)&startTime', webpage, 'video url') + video_url = 'http://www.franceinter.fr/' + path + + return { + 'id': video_id, + 'formats': [{ + 'url': video_url, + 'vcodec': 'none', + }], + 'title': title, + } +
\ No newline at end of file |