diff options
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 27 | ||||
| -rw-r--r-- | youtube_dl/extractor/ina.py | 31 |
2 files changed, 32 insertions, 26 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index c06ecbe52..d5167fef9 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -34,6 +34,7 @@ from .extractor.gametrailers import GametrailersIE from .extractor.generic import GenericIE from .extractor.googleplus import GooglePlusIE from .extractor.googlesearch import GoogleSearchIE +from .extractor.ina import InaIE from .extractor.infoq import InfoQIE from .extractor.justintv import JustinTVIE from .extractor.keek import KeekIE @@ -103,32 +104,6 @@ from .extractor.zdf import ZDFIE -class InaIE(InfoExtractor): - """Information Extractor for Ina.fr""" - _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*' - - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id - video_extension = 'mp4' - webpage = self._download_webpage(mrss_url, video_id) - - self.report_extraction(video_id) - - video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', - webpage, u'video URL') - - video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', - webpage, u'title') - - return [{ - 'id': video_id, - 'url': video_url, - 'ext': video_extension, - 'title': video_title, - }] class HowcastIE(InfoExtractor): """Information Extractor for Howcast.com""" diff --git a/youtube_dl/extractor/ina.py b/youtube_dl/extractor/ina.py new file mode 100644 index 000000000..c19b95659 --- /dev/null +++ b/youtube_dl/extractor/ina.py @@ -0,0 +1,31 @@ +import re + +from .common import InfoExtractor + + +class InaIE(InfoExtractor): + """Information Extractor for Ina.fr""" + _VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*' + + def _real_extract(self,url): + mobj = re.match(self._VALID_URL, url) + + video_id = mobj.group('id') + mrss_url='http://player.ina.fr/notices/%s.mrss' % video_id + video_extension = 'mp4' + webpage = self._download_webpage(mrss_url, video_id) + + self.report_extraction(video_id) + + video_url = self._html_search_regex(r'<media:player url="(?P<mp4url>http://mp4.ina.fr/[^"]+\.mp4)', + webpage, u'video URL') + + video_title = self._search_regex(r'<title><!\[CDATA\[(?P<titre>.*?)]]></title>', + webpage, u'title') + + return [{ + 'id': video_id, + 'url': video_url, + 'ext': video_extension, + 'title': video_title, + }] |