aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2017-06-15 11:19:03 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2017-06-15 11:19:03 +0800
commitca270371718fda18b3331dd645a200a365b096c9 (patch)
treecd1c5afe08b3ec5604b4430fe801716e72291de3
parent0bf4b71b753534ac4a93d9893dcd7333b5f229b3 (diff)
downloadyoutube-dl-ca270371718fda18b3331dd645a200a365b096c9.tar.xz
[bilibili] Fix extraction of videos with double quotes in titles
Closes #13387
-rw-r--r--ChangeLog6
-rw-r--r--youtube_dl/extractor/bilibili.py18
2 files changed, 23 insertions, 1 deletions
diff --git a/ChangeLog b/ChangeLog
index e3b7f7d60..9b45f08e3 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+version <unreleased>
+
+Extractors
+* [bilibili] Fix extraction of videos with double quotes in titles (#13387)
+
+
version 2017.06.12
Core
diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py
index 1e3f25515..1e57310d6 100644
--- a/youtube_dl/extractor/bilibili.py
+++ b/youtube_dl/extractor/bilibili.py
@@ -54,6 +54,22 @@ class BiliBiliIE(InfoExtractor):
'description': '如果你是神明,并且能够让妄想成为现实。那你会进行怎么样的妄想?是淫靡的世界?独裁社会?毁灭性的制裁?还是……2015年,涩谷。从6年前发生的大灾害“涩谷地震”之后复兴了的这个街区里新设立的私立高中...',
},
'skip': 'Geo-restricted to China',
+ }, {
+ # Title with double quotes
+ 'url': 'http://www.bilibili.com/video/av8903802/',
+ 'info_dict': {
+ 'id': '8903802',
+ 'ext': 'mp4',
+ 'title': '阿滴英文|英文歌分享#6 "Closer',
+ 'description': '滴妹今天唱Closer給你聽! 有史以来,被推最多次也是最久的歌曲,其实歌词跟我原本想像差蛮多的,不过还是好听! 微博@阿滴英文',
+ 'uploader': '阿滴英文',
+ 'uploader_id': '65880958',
+ 'timestamp': 1488382620,
+ 'upload_date': '20170301',
+ },
+ 'params': {
+ 'skip_download': True, # Test metadata only
+ },
}]
_APP_KEY = '84956560bc028eb7'
@@ -135,7 +151,7 @@ class BiliBiliIE(InfoExtractor):
'formats': formats,
})
- title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
+ title = self._html_search_regex('<h1[^>]*>([^<]+)</h1>', webpage, 'title')
description = self._html_search_meta('description', webpage)
timestamp = unified_timestamp(self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', default=None))