File: xml.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 (29 lines) | stat: -rw-r--r-- 883 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
"""
This module implements the XmlResponse class which adds encoding
discovering through XML encoding declarations to the TextResponse class.

See documentation in docs/topics/request-response.rst
"""

import re

from scrapy.http.response.text import TextResponse
from scrapy.utils.python import memoizemethod_noargs

class XmlResponse(TextResponse):

    __slots__ = ()

    _template = r'''%s\s*=\s*["']?\s*%s\s*["']?'''
    _encoding_re  = _template % ('encoding', r'(?P<charset>[\w-]+)')
    XMLDECL_RE  = re.compile(r'<\?xml\s.*?%s' % _encoding_re, re.I)

    def body_encoding(self):
        return self._body_declared_encoding() or super(XmlResponse, self).body_encoding()

    @memoizemethod_noargs
    def _body_declared_encoding(self):
        chunk = self.body[:5000]
        match = self.XMLDECL_RE.search(chunk)
        return match.group('charset') if match else None