github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[ina] Move into own file

Browse source
This commit is contained in:
Philipp Hagemeister 2013-06-23 22:28:19 +02:00
parent d26d440e19
commit 9fe4de3471
2 changed files with 32 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/InfoExtractors.py
View file

@ -34,6 +34,7 @@
from .extractor.generic import GenericIE from .extractor.generic import GenericIE
from .extractor.googleplus import GooglePlusIE from .extractor.googleplus import GooglePlusIE
from .extractor.googlesearch import GoogleSearchIE from .extractor.googlesearch import GoogleSearchIE
from .extractor.ina import InaIE
from .extractor.infoq import InfoQIE from .extractor.infoq import InfoQIE
from .extractor.justintv import JustinTVIE from .extractor.justintv import JustinTVIE
from .extractor.keek import KeekIE from .extractor.keek import KeekIE
@ -103,32 +104,6 @@
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): class HowcastIE(InfoExtractor):
"""Information Extractor for Howcast.com""" """Information Extractor for Howcast.com"""

31
youtube_dl/extractor/ina.py Normal file
View file

@ -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,
}]