github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[tele5] Improve extraction (closes #7805, closes #7922, closes #17331, closes #17414)

Browse source
This commit is contained in:
Sergey M․ 2018-09-08 16:04:39 +07:00
parent d0de6a287a
commit ae2384ff5f
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 22 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
youtube_dl/extractor/tele5.py
View file

@ -1,38 +1,43 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .nexx import NexxIE
from ..compat import compat_urlparse
class Tele5IE(InfoExtractor):
_VALID_URL = r'https://www\.tele5\.de/(?:mediathek/filme-online/videos\?vid=|tv/)(?P<display_id>[\w-]+)'
_VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)'
_TESTS = [{
'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1550589',
'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
'info_dict': {
'id': '1550589',
'id': '1549416',
'ext': 'mp4',
'upload_date': '20180822',
'timestamp': 1534927316,
'title': 'SchleFaZ: Atomic Shark',
}
'upload_date': '20180814',
'timestamp': 1534290623,
'title': 'Pandorum',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
'only_matching': True,
}, {
'url': 'https://www.tele5.de/tv/dark-matter/videos',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'id\s*=\s*["\']video-player["\']\s*data-id\s*=\s*["\']([0-9]+)["\']',
webpage, 'video_id')
if not video_id:
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
webpage, 'video id')
return self.url_result(
'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,