From 55b8588f0e4dd9597b6da5c46d05b9dd1e9f5960 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 24 Feb 2019 23:19:15 +0700 Subject: [PATCH] [servus] Fix extraction (closes #19297) --- youtube_dl/extractor/servus.py | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/servus.py b/youtube_dl/extractor/servus.py index 264e1dd8b..e579d42cf 100644 --- a/youtube_dl/extractor/servus.py +++ b/youtube_dl/extractor/servus.py @@ -1,31 +1,44 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor class ServusIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:at|de)/p/[^/]+/(?PAA-\w+|\d+-\d+)' + _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P[aA]{2}-\w+|\d+-\d+)' _TESTS = [{ 'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/', - 'md5': '046dee641cda1c4cabe13baef3be2c1c', + 'md5': '3e1dd16775aa8d5cbef23628cfffc1f4', 'info_dict': { 'id': 'AA-1T6VBU5PW1W12', 'ext': 'mp4', - 'title': 'Die Grünen aus Volkssicht', - 'description': 'md5:052b5da1cb2cd7d562ef1f19be5a5cba', - 'thumbnail': r're:^https?://.*\.jpg$', + 'title': 'Die Grünen aus Sicht des Volkes', + 'description': 'md5:1247204d85783afe3682644398ff2ec4', + 'thumbnail': r're:^https?://.*\.jpg', } }, { 'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/', 'only_matching': True, + }, { + 'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/', + 'only_matching': True, + }, { + 'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/', + 'only_matching': True, }] def _real_extract(self, url): - video_id = self._match_id(url) + video_id = self._match_id(url).upper() webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage) + title = self._search_regex( + (r'videoLabel\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + r'<h\d+[^>]+\bclass=["\']heading--(?:one|two)["\'][^>]*>(?P<title>[^<]+)'), + webpage, 'title', default=None, + group='title') or self._og_search_title(webpage) + title = re.sub(r'\s*-\s*Servus TV\s*$', '', title) description = self._og_search_description(webpage) thumbnail = self._og_search_thumbnail(webpage)