RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fixed bug in RegexLinkExtractor. Encoding was not being specified 

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40677
This commit is contained in:
elpolilla 2009-01-07 17:39:09 +00:00
parent 307f8b3321
commit 382621b814
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scrapy/trunk/scrapy/link/extractors.py
View File

@ -55,7 +55,7 @@ class RegexLinkExtractor(LinkExtractor):
if self.restrict_xpaths:
hxs = HtmlXPathSelector(response)
html_slice = ''.join(''.join(html_fragm for html_fragm in hxs.x(xpath_expr).extract()) for xpath_expr in self.restrict_xpaths)
links = self._extract_links(html_slice, response.url)
links = self._extract_links(html_slice, response.url, response.body.get_real_encoding())
else:
links = LinkExtractor.extract_links(self, response)