diff options
| author | Yen Chi Hsuan <yan12125@gmail.com> | 2016-09-18 18:33:54 +0800 |
|---|---|---|
| committer | Yen Chi Hsuan <yan12125@gmail.com> | 2016-09-18 18:35:38 +0800 |
| commit | d8dbf8707d4e45a939fc74c76bb919771007f8ba (patch) | |
| tree | cb2d560b4a4f67d0d60867cf19a6e9d4922beeea | |
| parent | a1da888d0cc92fdf3506b30ee85ce241e9090408 (diff) | |
[thisav] Improve title extraction (closes #10682)
I didn't add a test case as the one in #10682 looks like a copyrighted
product.
| -rw-r--r-- | ChangeLog | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/thisav.py | 5 |
2 files changed, 10 insertions, 1 deletions
@@ -1,3 +1,9 @@ +version <unreleased> + +Extractors +* [thisav] Improve title extraction (#10682) + + version 2016.09.18 Core diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py index 027a8e907..4473a3c77 100644 --- a/youtube_dl/extractor/thisav.py +++ b/youtube_dl/extractor/thisav.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .jwplatform import JWPlatformBaseIE +from ..utils import remove_end class ThisAVIE(JWPlatformBaseIE): @@ -35,7 +36,9 @@ class ThisAVIE(JWPlatformBaseIE): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'<h1>([^<]*)</h1>', webpage, 'title') + title = remove_end(self._html_search_regex( + r'<title>([^<]+)</title>', webpage, 'title'), + ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站') video_url = self._html_search_regex( r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None) if video_url: |