github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[rtl2] Fix extraction for test_RTL2_1

Browse source
This commit is contained in:
Yen Chi Hsuan 2015-08-21 13:20:32 +08:00
parent 9eb4ab6ad9
commit 5e1a5ac8de
1 changed files with 16 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
youtube_dl/extractor/rtl2.py
View file

@ -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'<div[^>]+data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\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)