Browse Source

[tf1] fix info extraction(fixes #8599)

master
remitamine 6 years ago
parent
commit
6212bcb191
  1. 4
      youtube_dl/extractor/tf1.py
  2. 10
      youtube_dl/extractor/wat.py

4
youtube_dl/extractor/tf1.py

@ -50,6 +50,4 @@ class TF1IE(InfoExtractor):
wat_id = self._html_search_regex(
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
webpage, 'wat id', group='id')
wat_info = self._download_json(
'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id)
return self.url_result(wat_info['media']['url'], 'Wat')
return self.url_result('wat:%s' % wat_id, 'Wat')

10
youtube_dl/extractor/wat.py

@ -12,7 +12,7 @@ from ..utils import (
class WatIE(InfoExtractor):
_VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
_VALID_URL = r'(?:wat:(?P<real_id>\d{8})|http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html)'
IE_NAME = 'wat.tv'
_TESTS = [
{
@ -54,10 +54,12 @@ class WatIE(InfoExtractor):
def real_id_for_chapter(chapter):
return chapter['tc_start'].split('-')[0]
mobj = re.match(self._VALID_URL, url)
short_id = mobj.group('short_id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id or short_id)
real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
real_id = mobj.group('real_id')
if not real_id:
short_id = mobj.group('short_id')
webpage = self._download_webpage(url, display_id or short_id)
real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
video_info = self.download_video_info(real_id)

Loading…
Cancel
Save