pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-23 12:40:11 +09:00
Code Issues Projects Releases Wiki Activity

[canalplus] Prefer f4m and modernize (Closes #2749)

Browse Source
This commit is contained in:
Sergey M․ 2014-04-16 20:47:39 +07:00
parent 3d1bb6b4dd
commit b075d25bed
1 changed files with 42 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
youtube_dl/extractor/canalplus.py
View File

@ -1,4 +1,6 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -8,46 +10,58 @@ 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'
IE_NAME = u'canalplus.fr' IE_NAME = 'canalplus.fr'
_TEST = { _TEST = {
u'url': u'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470', 'url': 'http://www.canalplus.fr/c-infos-documentaires/pid1830-c-zapping.html?vid=922470',
u'file': u'922470.flv', 'info_dict': {
u'info_dict': { 'id': '922470',
u'title': u'Zapping - 26/08/13', 'ext': 'flv',
u'description': u'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013', 'title': 'Zapping - 26/08/13',
u'upload_date': u'20130826', 'description': 'Le meilleur de toutes les chaînes, tous les jours.\nEmission du 26 août 2013',
'upload_date': '20130826',
}, },
u'params': { 'params': {
u'skip_download': True, 'skip_download': True,
}, },
} }
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.groupdict().get('id') video_id = mobj.group('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'<canal:player videoId="(\d+)"', webpage, u'video id') video_id = self._search_regex(r'<canal:player videoId="(\d+)"', webpage, 'video id')
info_url = self._VIDEO_INFO_TEMPLATE % video_id info_url = self._VIDEO_INFO_TEMPLATE % video_id
doc = self._download_xml(info_url,video_id, doc = self._download_xml(info_url, video_id, 'Downloading video XML')
u'Downloading video info')
self.report_extraction(video_id)
video_info = [video for video in doc if video.find('ID').text == video_id][0] 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') media = video_info.find('MEDIA')
formats = [media.find('VIDEOS/%s' % format) infos = video_info.find('INFOS')
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, preferences = ['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD', 'HLS', 'HDS']
'title': u'%s - %s' % (infos.find('TITRAGE/TITRE').text,
infos.find('TITRAGE/SOUS_TITRE').text), formats = [
'url': video_url, {
'ext': 'flv', 'url': fmt.text + '?hdcore=2.11.3' if fmt.tag == 'HDS' else fmt.text,
'upload_date': unified_strdate(infos.find('PUBLICATION/DATE').text), 'format_id': fmt.tag,
'thumbnail': media.find('IMAGES/GRAND').text, 'ext': 'mp4' if fmt.tag == 'HLS' else 'flv',
'description': infos.find('DESCRIPTION').text, 'preference': preferences.index(fmt.tag) if fmt.tag in preferences else -1,
'view_count': int(infos.find('NB_VUES').text), } for fmt in media.find('VIDEOS') if fmt.text
} ]
self._sort_formats(formats)
return {
'id': video_id,
'title': '%s - %s' % (infos.find('TITRAGE/TITRE').text,
infos.find('TITRAGE/SOUS_TITRE').text),
'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),
'like_count': int(infos.find('NB_LIKES').text),
'comment_count': int(infos.find('NB_COMMENTS').text),
'formats': formats,
}