[miomio] Fix extraction

Closes #12291
Closes #12388
Closes #12402
This commit is contained in:
Yen Chi Hsuan 2017-03-08 19:46:58 +08:00
parent d7344d33b1
commit 0f6b87d067
No known key found for this signature in database
GPG key ID: 7F902A182457CA23
2 changed files with 18 additions and 2 deletions

View file

@ -1,3 +1,9 @@
version <unreleased>
Extractors
* [miomio] Fix extraction (#12291, #12388, #12402)
version 2017.03.07 version 2017.03.07
Core Core

View file

@ -51,6 +51,7 @@ class MioMioIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'マツコの知らない世界【劇的進化SPビニール傘冷凍食品2016】 1_2 - 16 05 31', 'title': 'マツコの知らない世界【劇的進化SPビニール傘冷凍食品2016】 1_2 - 16 05 31',
}, },
'skip': 'Unable to load videos',
}] }]
def _extract_mioplayer(self, webpage, video_id, title, http_headers): def _extract_mioplayer(self, webpage, video_id, title, http_headers):
@ -94,9 +95,18 @@ def _extract_mioplayer(self, webpage, video_id, title, http_headers):
return entries return entries
def _download_chinese_webpage(self, *args, **kwargs):
# Requests with English locales return garbage
headers = {
'Accept-Language': 'zh-TW,en-US;q=0.7,en;q=0.3',
}
kwargs.setdefault('headers', {}).update(headers)
return self._download_webpage(*args, **kwargs)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_chinese_webpage(
url, video_id)
title = self._html_search_meta( title = self._html_search_meta(
'description', webpage, 'title', fatal=True) 'description', webpage, 'title', fatal=True)
@ -106,7 +116,7 @@ def _real_extract(self, url):
if '_h5' in mioplayer_path: if '_h5' in mioplayer_path:
player_url = compat_urlparse.urljoin(url, mioplayer_path) player_url = compat_urlparse.urljoin(url, mioplayer_path)
player_webpage = self._download_webpage( player_webpage = self._download_chinese_webpage(
player_url, video_id, player_url, video_id,
note='Downloading player webpage', headers={'Referer': url}) note='Downloading player webpage', headers={'Referer': url})
entries = self._parse_html5_media_entries(player_url, player_webpage, video_id) entries = self._parse_html5_media_entries(player_url, player_webpage, video_id)