From d8dbf8707d4e45a939fc74c76bb919771007f8ba Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sun, 18 Sep 2016 18:33:54 +0800 Subject: [PATCH] [thisav] Improve title extraction (closes #10682) I didn't add a test case as the one in #10682 looks like a copyrighted product. --- ChangeLog | 6 ++++++ youtube_dl/extractor/thisav.py | 5 ++++- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/ChangeLog b/ChangeLog index a71fadfa7..18f9fa861 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +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'

([^<]*)

', webpage, 'title') + title = remove_end(self._html_search_regex( + r'([^<]+)', 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: