File: httpcompression.py

package info (click to toggle)
python-scrapy 0.8-3
  • links: PTS, VCS
  • area: main
  • in suites: squeeze
  • size: 2,904 kB
  • ctags: 2,981
  • sloc: python: 15,349; xml: 199; makefile: 68; sql: 64; sh: 34
file content (42 lines) | stat: -rw-r--r-- 1,574 bytes parent folder | download
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
import zlib
from gzip import GzipFile
from cStringIO import StringIO

from scrapy.http import Response


class HttpCompressionMiddleware(object):
    """This middleware allows compressed (gzip, deflate) traffic to be
    sent/received from web sites"""

    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:
                encoding = content_encoding.pop()
                decoded_body = self._decode(response.body, encoding.lower())
                response = response.replace(body=decoded_body)
                if not content_encoding:
                    del response.headers['Content-Encoding']

        return response

    def _decode(self, body, encoding):
        if encoding == 'gzip':
            body = GzipFile(fileobj=StringIO(body)).read()

        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