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

Rule.process_request: optionally take a Response object

This commit is contained in:
Eugenio Lacuesta 2019-03-13 10:21:50 +00:00
parent c72ab1d4ba
commit 43fd622968
1 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
scrapy/spiders/crawl.py
View File

@ -24,12 +24,23 @@ class Rule(object):
self.callback = callback
self.cb_kwargs = cb_kwargs or {}
self.process_links = process_links
self.process_request = process_request
self.process_request_function = process_request
if follow is None:
self.follow = False if callback else True
else:
self.follow = follow
def process_request(self, request, response):
"""
Wrapper around the request processing function to maintain backward compatibility
with functions that do not take a Response object as parameter.
"""
argcount = self.process_request_function.__code__.co_argcount
if getattr(self.process_request_function, '__self__', None):
argcount = argcount - 1
args = [request] if argcount == 1 else [request, response]
return self.process_request_function(*args)
class CrawlSpider(Spider):
@ -65,7 +76,7 @@ class CrawlSpider(Spider):
for link in links:
seen.add(link)
r = self._build_request(n, link)
yield rule.process_request(r)
yield rule.process_request(r, response)
def _response_downloaded(self, response):
rule = self._rules[response.meta['rule']]
@ -93,7 +104,7 @@ class CrawlSpider(Spider):
for rule in self._rules:
rule.callback = get_method(rule.callback)
rule.process_links = get_method(rule.process_links)
rule.process_request = get_method(rule.process_request)
rule.process_request_function = get_method(rule.process_request_function)
@classmethod
def from_crawler(cls, crawler, *args, **kwargs):