From 5e1a5ac8de12391cb22d2fa0dfb2119527bd7fc2 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 21 Aug 2015 13:20:32 +0800 Subject: [PATCH] [rtl2] Fix extraction for test_RTL2_1 --- youtube_dl/extractor/rtl2.py | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py index 9e0c6890e..276612fc7 100644 --- a/youtube_dl/extractor/rtl2.py +++ b/youtube_dl/extractor/rtl2.py @@ -1,6 +1,7 @@ # encoding: utf-8 from __future__ import unicode_literals +import re from .common import InfoExtractor @@ -28,6 +29,10 @@ class RTL2IE(InfoExtractor): 'title': 'Anna erwischt Alex!', 'description': 'Anna ist Alex\' Tochter bei Köln 50667.' }, + 'params': { + # rtmp download + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -38,10 +43,17 @@ def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - vico_id = self._html_search_regex( - r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id') - vivi_id = self._html_search_regex( - r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id') + mobj = re.search( + r']+data-collection="(?P\d+)"[^>]+data-video="(?P\d+)"', + webpage) + if mobj: + vico_id = mobj.group('vico_id') + vivi_id = mobj.group('vivi_id') + else: + vico_id = self._html_search_regex( + r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id') + vivi_id = self._html_search_regex( + r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id') info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id info = self._download_json(info_url, video_id)