'info_dict': {
'id': '727589',
'ext': 'mp4',
- 'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
+ 'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance From This Judicial Injustice!",
'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Kadokawa Pictures Inc.',
'series': "KONOSUBA -God's blessing on this wonderful world!",
'season': "KONOSUBA -God's blessing on this wonderful world! 2",
'season_number': 2,
- 'episode': 'Give Me Deliverance from this Judicial Injustice!',
+ 'episode': 'Give Me Deliverance From This Judicial Injustice!',
'episode_number': 1,
},
'params': {
else:
webpage_url = 'http://www.' + mobj.group('url')
- webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
+ webpage = self._download_webpage(
+ self._add_skip_wall(webpage_url), video_id,
+ headers=self.geo_verification_headers())
note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='')
# webpage provide more accurate data than series_title from XML
series = self._html_search_regex(
- r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
+ r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
webpage, 'series', fatal=False)
season = xpath_text(metadata, 'series_title')
episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
season_number = int_or_none(self._search_regex(
- r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
+ r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
webpage, 'season number', default=None))
return {
def _real_extract(self, url):
show_id = self._match_id(url)
- webpage = self._download_webpage(self._add_skip_wall(url), show_id)
+ webpage = self._download_webpage(
+ self._add_skip_wall(url), show_id,
+ headers=self.geo_verification_headers())
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')