1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
import zlib
from scrapy.utils.gz import gunzip, is_gzipped
from scrapy.http import Response, TextResponse
from scrapy.responsetypes import responsetypes
from scrapy.exceptions import NotConfigured
class HttpCompressionMiddleware(object):
"""This middleware allows compressed (gzip, deflate) traffic to be
sent/received from web sites"""
@classmethod
def from_crawler(cls, crawler):
if not crawler.settings.getbool('COMPRESSION_ENABLED'):
raise NotConfigured
return cls()
def process_request(self, request, spider):
request.headers.setdefault('Accept-Encoding', 'gzip,deflate')
def process_response(self, request, response, spider):
if isinstance(response, Response):
content_encoding = response.headers.getlist('Content-Encoding')
if content_encoding and not is_gzipped(response):
encoding = content_encoding.pop()
decoded_body = self._decode(response.body, encoding.lower())
respcls = responsetypes.from_args(headers=response.headers, \
url=response.url)
kwargs = dict(cls=respcls, body=decoded_body)
if issubclass(respcls, TextResponse):
# force recalculating the encoding until we make sure the
# responsetypes guessing is reliable
kwargs['encoding'] = None
response = response.replace(**kwargs)
if not content_encoding:
del response.headers['Content-Encoding']
return response
def _decode(self, body, encoding):
if encoding == 'gzip' or encoding == 'x-gzip':
body = gunzip(body)
if encoding == 'deflate':
try:
body = zlib.decompress(body)
except zlib.error:
# ugly hack to work with raw deflate content that may
# be sent by microsoft servers. For more information, see:
# http://carsten.codimi.de/gzip.yaws/
# http://www.port80software.com/200ok/archive/2005/10/31/868.aspx
# http://www.gzip.org/zlib/zlib_faq.html#faq38
body = zlib.decompress(body, -15)
return body
|
