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
|
"""
Offsite Spider Middleware
See documentation in docs/topics/spider-middleware.rst
"""
import re
import logging
import warnings
from scrapy import signals
from scrapy.http import Request
from scrapy.utils.httpobj import urlparse_cached
logger = logging.getLogger(__name__)
class OffsiteMiddleware(object):
def __init__(self, stats):
self.stats = stats
@classmethod
def from_crawler(cls, crawler):
o = cls(crawler.stats)
crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
return o
def process_spider_output(self, response, result, spider):
for x in result:
if isinstance(x, Request):
if x.dont_filter or self.should_follow(x, spider):
yield x
else:
domain = urlparse_cached(x).hostname
if domain and domain not in self.domains_seen:
self.domains_seen.add(domain)
logger.debug("Filtered offsite request to %(domain)r: %(request)s",
{'domain': domain, 'request': x}, extra={'spider': spider})
self.stats.inc_value('offsite/domains', spider=spider)
self.stats.inc_value('offsite/filtered', spider=spider)
else:
yield x
def should_follow(self, request, spider):
regex = self.host_regex
# hostname can be None for wrong urls (like javascript links)
host = urlparse_cached(request).hostname or ''
return bool(regex.search(host))
def get_host_regex(self, spider):
"""Override this method to implement a different offsite policy"""
allowed_domains = getattr(spider, 'allowed_domains', None)
if not allowed_domains:
return re.compile('') # allow all by default
url_pattern = re.compile("^https?://.*$")
for domain in allowed_domains:
if url_pattern.match(domain):
warnings.warn("allowed_domains accepts only domains, not URLs. Ignoring URL entry %s in allowed_domains." % domain, URLWarning)
regex = r'^(.*\.)?(%s)$' % '|'.join(re.escape(d) for d in allowed_domains if d is not None)
return re.compile(regex)
def spider_opened(self, spider):
self.host_regex = self.get_host_regex(spider)
self.domains_seen = set()
class URLWarning(Warning):
pass
|
