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

Merge pull request #1786 from redapple/header-encoding 

More liberal Content-Disposition header parsing
This commit is contained in:
Mikhail Korobov 2016-02-17 21:33:43 +05:00
parent 41588397c0 cabed6f183
commit 4e2b7207ec
2 changed files with 11 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
scrapy/responsetypes.py
View File

@ -59,7 +59,8 @@ class ResponseTypes(object):
def from_content_disposition(self, content_disposition): def from_content_disposition(self, content_disposition):
try: try:
filename = to_native_str(content_disposition).split(';')[1].split('=')[1] filename = to_native_str(content_disposition,
encoding='latin-1', errors='replace').split(';')[1].split('=')[1]
filename = filename.strip('"\'') filename = filename.strip('"\'')
return self.from_filename(filename) return self.from_filename(filename)
except IndexError: except IndexError:

11
tests/test_responsetypes.py
View File

@ -1,3 +1,4 @@
# -*- coding: utf-8 -*-
import unittest import unittest
from scrapy.responsetypes import responsetypes from scrapy.responsetypes import responsetypes
@ -20,8 +21,14 @@ class ResponseTypesTest(unittest.TestCase):
def test_from_content_disposition(self): def test_from_content_disposition(self):
mappings = [ mappings = [
('attachment; filename="data.xml"', XmlResponse), (b'attachment; filename="data.xml"', XmlResponse),
('attachment; filename=data.xml', XmlResponse), (b'attachment; filename=data.xml', XmlResponse),
(u'attachment;filename=data£.tar.gz'.encode('utf-8'), Response),
(u'attachment;filename=dataµ.tar.gz'.encode('latin-1'), Response),
(u'attachment;filename=data高.doc'.encode('gbk'), Response),
(u'attachment;filename=دورهdata.html'.encode('cp720'), HtmlResponse),
(u'attachment;filename=日本語版Wikipedia.xml'.encode('iso2022_jp'), XmlResponse),
] ]
for source, cls in mappings: for source, cls in mappings:
retcls = responsetypes.from_content_disposition(source) retcls = responsetypes.from_content_disposition(source)