From ae2384ff5f9d6a18209139a4b2e2cd33921be63a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 8 Sep 2018 16:04:39 +0700 Subject: [PATCH] [tele5] Improve extraction (closes #7805, closes #7922, closes #17331, closes #17414) --- youtube_dl/extractor/tele5.py | 39 ++++++++++++++++++++--------------- 1 file changed, 22 insertions(+), 17 deletions(-) diff --git a/youtube_dl/extractor/tele5.py b/youtube_dl/extractor/tele5.py index cfa8d2475..25573e49f 100644 --- a/youtube_dl/extractor/tele5.py +++ b/youtube_dl/extractor/tele5.py @@ -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[\w-]+)' - + _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P[^?#&]+)' _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,