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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
|
# -*- coding: utf-8 -*-
from __future__ import absolute_import
import re
from scrapy import log
from scrapy.exceptions import NotConfigured
from scrapy.http import HtmlResponse
from scrapy.utils.response import _noscript_re, _script_re
from w3lib import html
class AjaxCrawlMiddleware(object):
"""
Handle 'AJAX crawlable' pages marked as crawlable via meta tag.
For more info see https://developers.google.com/webmasters/ajax-crawling/docs/getting-started.
"""
def __init__(self, settings):
if not settings.getbool('AJAXCRAWL_ENABLED'):
raise NotConfigured
# XXX: Google parses at least first 100k bytes; scrapy's redirect
# middleware parses first 4k. 4k turns out to be insufficient
# for this middleware, and parsing 100k could be slow.
# We use something in between (32K) by default.
self.lookup_bytes = settings.getint('AJAXCRAWL_MAXSIZE', 32768)
@classmethod
def from_crawler(cls, crawler):
return cls(crawler.settings)
def process_response(self, request, response, spider):
if not isinstance(response, HtmlResponse) or response.status != 200:
return response
if request.method != 'GET':
# other HTTP methods are either not safe or don't have a body
return response
if 'ajax_crawlable' in request.meta: # prevent loops
return response
if not self._has_ajax_crawlable_variant(response):
return response
# scrapy already handles #! links properly
ajax_crawl_request = request.replace(url=request.url+'#!')
log.msg(format="Downloading AJAX crawlable %(ajax_crawl_request)s instead of %(request)s",
level=log.DEBUG, spider=spider,
ajax_crawl_request=ajax_crawl_request, request=request)
ajax_crawl_request.meta['ajax_crawlable'] = True
return ajax_crawl_request
def _has_ajax_crawlable_variant(self, response):
"""
Return True if a page without hash fragment could be "AJAX crawlable"
according to https://developers.google.com/webmasters/ajax-crawling/docs/getting-started.
"""
body = response.body_as_unicode()[:self.lookup_bytes]
return _has_ajaxcrawlable_meta(body)
# XXX: move it to w3lib?
_ajax_crawlable_re = re.compile(ur'<meta\s+name=["\']fragment["\']\s+content=["\']!["\']/?>')
def _has_ajaxcrawlable_meta(text):
"""
>>> _has_ajaxcrawlable_meta('<html><head><meta name="fragment" content="!"/></head><body></body></html>')
True
>>> _has_ajaxcrawlable_meta("<html><head><meta name='fragment' content='!'></head></html>")
True
>>> _has_ajaxcrawlable_meta('<html><head><!--<meta name="fragment" content="!"/>--></head><body></body></html>')
False
>>> _has_ajaxcrawlable_meta('<html></html>')
False
"""
# Stripping scripts and comments is slow (about 20x slower than
# just checking if a string is in text); this is a quick fail-fast
# path that should work for most pages.
if 'fragment' not in text:
return False
if 'content' not in text:
return False
text = _script_re.sub(u'', text)
text = _noscript_re.sub(u'', text)
text = html.remove_comments(html.remove_entities(text))
return _ajax_crawlable_re.search(text) is not None
|
