[thisav] Improve title extraction (closes #10682)
I didn't add a test case as the one in #10682 looks like a copyrighted product.main
parent
a1da888d0c
commit
d8dbf8707d
|
@ -1,3 +1,9 @@
|
||||||
|
version <unreleased>
|
||||||
|
|
||||||
|
Extractors
|
||||||
|
* [thisav] Improve title extraction (#10682)
|
||||||
|
|
||||||
|
|
||||||
version 2016.09.18
|
version 2016.09.18
|
||||||
|
|
||||||
Core
|
Core
|
||||||
|
|
|
@ -4,6 +4,7 @@ from __future__ import unicode_literals
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .jwplatform import JWPlatformBaseIE
|
from .jwplatform import JWPlatformBaseIE
|
||||||
|
from ..utils import remove_end
|
||||||
|
|
||||||
|
|
||||||
class ThisAVIE(JWPlatformBaseIE):
|
class ThisAVIE(JWPlatformBaseIE):
|
||||||
|
@ -35,7 +36,9 @@ class ThisAVIE(JWPlatformBaseIE):
|
||||||
|
|
||||||
video_id = mobj.group('id')
|
video_id = mobj.group('id')
|
||||||
webpage = self._download_webpage(url, video_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(
|
video_url = self._html_search_regex(
|
||||||
r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
|
r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None)
|
||||||
if video_url:
|
if video_url:
|
||||||
|
|
Loading…
Reference in New Issue