[thisav] Improve title extraction (closes #10682)
I didn't add a test case as the one in #10682 looks like a copyrighted product.
This commit is contained in:
		
							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…
	
	
			
			x
			
			
		
	
		Reference in New Issue
	
	Block a user