RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

PEP8 ofsite middleware

This commit is contained in:
Steven Almeroth 2018-08-24 15:18:16 -04:00
parent e45ef7dcd9
commit 6e9fa3a41f
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
scrapy/spidermiddlewares/offsite.py
View File

@ -3,7 +3,6 @@ Offsite Spider Middleware
See documentation in docs/topics/spider-middleware.rst
"""
import re
import logging
import warnings
@ -35,8 +34,9 @@ class OffsiteMiddleware(object):
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})
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:
@ -52,13 +52,15 @@ class OffsiteMiddleware(object):
"""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
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)
message = ("allowed_domains accepts only domains, not URLs. "
"Ignoring URL entry %s in allowed_domains." % domain)
warnings.warn(message, URLWarning)
domains = [re.escape(d) for d in allowed_domains if d is not None]
regex = r'^(.*\.)?(%s)$' % '|'.join(domains)
return re.compile(regex)
def spider_opened(self, spider):