[tf1] fix info extraction(fixes #8599)

pull/8/head
remitamine 9 years ago
parent d69abbd3f0
commit 6212bcb191

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

@ -12,7 +12,7 @@ from ..utils import (
class WatIE(InfoExtractor): 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' IE_NAME = 'wat.tv'
_TESTS = [ _TESTS = [
{ {
@ -54,8 +54,10 @@ class WatIE(InfoExtractor):
def real_id_for_chapter(chapter): def real_id_for_chapter(chapter):
return chapter['tc_start'].split('-')[0] return chapter['tc_start'].split('-')[0]
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
short_id = mobj.group('short_id')
display_id = mobj.group('display_id') display_id = mobj.group('display_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) webpage = self._download_webpage(url, display_id or short_id)
real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id') real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')

Loading…
Cancel
Save