gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[d8] inherit from CanalplusIE

Browse source 
it reuses the same extraction process
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-11-19 20:43:49 +01:00
parent 495da337ae
commit 69545c2aff
2 changed files with 5 additions and 34 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
youtube_dl/extractor/canalplus.py
View file

@ -5,6 +5,7 @@ import xml.etree.ElementTree
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import unified_strdate from ..utils import unified_strdate
class CanalplusIE(InfoExtractor): class CanalplusIE(InfoExtractor):
_VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))' _VALID_URL = r'https?://(www\.canalplus\.fr/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>\d+))'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
@ -25,7 +26,7 @@ class CanalplusIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.groupdict().get('id')
if video_id is None: if video_id is None:
webpage = self._download_webpage(url, mobj.group('path')) webpage = self._download_webpage(url, mobj.group('path'))
video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id') video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')

36
youtube_dl/extractor/d8.py
View file

@ -1,11 +1,8 @@
# encoding: utf-8 # encoding: utf-8
import re from .canalplus import CanalplusIE
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import unified_strdate
class D8IE(InfoExtractor): class D8IE(CanalplusIE):
_VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)' _VALID_URL = r'https?://www\.d8\.tv/.*?/(?P<path>.*)'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s'
IE_NAME = u'd8.tv' IE_NAME = u'd8.tv'
@ -19,34 +16,7 @@ class D8IE(InfoExtractor):
u'upload_date': u'20131108', u'upload_date': u'20131108',
}, },
u'params': { u'params': {
# rtmp
u'skip_download': True, u'skip_download': True,
}, },
} }
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
webpage = self._download_webpage(url, mobj.group('path'))
video_id = self._search_regex(r'videoId = "(\d+)";', webpage, u'video id')
info_url = self._VIDEO_INFO_TEMPLATE % video_id
info_page = self._download_webpage(info_url,video_id,
u'Downloading video info')
self.report_extraction(video_id)
doc = xml.etree.ElementTree.fromstring(info_page.encode('utf-8'))
video_info = [video for video in doc if video.find('ID').text == video_id][0]
infos = video_info.find('INFOS')
media = video_info.find('MEDIA')
formats = [media.find('VIDEOS/%s' % format)
for format in ['BAS_DEBIT', 'HAUT_DEBIT', 'HD']]
video_url = [format.text for format in formats if format is not None][-1]
return {'id': video_id,
'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
infos.find('TITRAGE/SOUS_TITRE').text),
'url': video_url,
'ext': 'flv',
'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text),
'thumbnail': media.find('IMAGES/GRAND').text,
'description': infos.find('DESCRIPTION').text,
'view_count': int(infos.find('NB_VUES').text),
}