Mirrors
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[canal+] Improve extraction (Closes #9718)

This commit is contained in:
Sergey M․ 2016-06-07 22:12:20 +07:00
parent fb94e260b5
commit 74193838f7
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 24 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
youtube_dl/extractor/canalplus.py
View File

@ -4,11 +4,11 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
HEADRequest, HEADRequest,
unified_strdate, unified_strdate,
url_basename,
qualities, qualities,
int_or_none, int_or_none,
) )
@ -16,13 +16,25 @@ from ..utils import (
class CanalplusIE(InfoExtractor): class CanalplusIE(InfoExtractor):
IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv' IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
_VALID_URL = r'https?://(?:www\.(?P<site>canalplus\.fr|piwiplus\.fr|d8\.tv|itele\.fr)/.*?/(?P<path>.*)|player\.canalplus\.fr/#/(?P<id>[0-9]+))' _VALID_URL = r'''(?x)
https?://
(?:
(?:
(?:(?:www|m)\.)?canalplus\.fr|
(?:www\.)?piwiplus\.fr|
(?:www\.)?d8\.tv|
(?:www\.)?itele\.fr
)/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
player\.canalplus\.fr/#/(?P<id>\d+)
)
'''
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
_SITE_ID_MAP = { _SITE_ID_MAP = {
'canalplus.fr': 'cplus', 'canalplus': 'cplus',
'piwiplus.fr': 'teletoon', 'piwiplus': 'teletoon',
'd8.tv': 'd8', 'd8': 'd8',
'itele.fr': 'itele', 'itele': 'itele',
} }
_TESTS = [{ _TESTS = [{
@ -65,16 +77,19 @@ class CanalplusIE(InfoExtractor):
'description': 'md5:8216206ec53426ea6321321f3b3c16db', 'description': 'md5:8216206ec53426ea6321321f3b3c16db',
'upload_date': '20150211', 'upload_date': '20150211',
}, },
}, {
'url': 'http://m.canalplus.fr/?vid=1398231',
'only_matching': 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.groupdict().get('id') or mobj.groupdict().get('vid')
site_id = self._SITE_ID_MAP[mobj.group('site') or 'canal'] site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
# Beware, some subclasses do not define an id group # Beware, some subclasses do not define an id group
display_id = url_basename(mobj.group('path')) display_id = mobj.group('display_id') or video_id
if video_id is None: if video_id is None:
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)