]> git.bitcoin.ninja Git - youtube-dl/commitdiff
[miomio] Fix extraction
authorYen Chi Hsuan <yan12125@gmail.com>
Wed, 8 Mar 2017 11:46:58 +0000 (19:46 +0800)
committerYen Chi Hsuan <yan12125@gmail.com>
Wed, 8 Mar 2017 11:46:58 +0000 (19:46 +0800)
Closes #12291
Closes #12388
Closes #12402

ChangeLog
youtube_dl/extractor/miomio.py

index 601aad9022141541e2fc8e20a9ca86f03288974d..b000e2e9447a7f45af45842b31f902e2f42b5a91 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+version <unreleased>
+
+Extractors
+* [miomio] Fix extraction (#12291, #12388, #12402)
+
+
 version 2017.03.07
 
 Core
index ec1b4c4fea111ded48f530c7020dd9aabd38dbb8..40f72d66f25eb33d2fdb75c8a03e37d873b26afe 100644 (file)
@@ -51,6 +51,7 @@ class MioMioIE(InfoExtractor):
             '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',
         },
+        'skip': 'Unable to load videos',
     }]
 
     def _extract_mioplayer(self, webpage, video_id, title, http_headers):
@@ -94,9 +95,18 @@ class MioMioIE(InfoExtractor):
 
         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):
         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(
             'description', webpage, 'title', fatal=True)
@@ -106,7 +116,7 @@ class MioMioIE(InfoExtractor):
 
         if '_h5' in 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,
                 note='Downloading player webpage', headers={'Referer': url})
             entries = self._parse_html5_media_entries(player_url, player_webpage, video_id)