BackTrackZ/scrapy
BackTrackZ/scrapy
1
0
Fork 0
mirror of https://github.com/scrapy/scrapy.git synced 2025-02-27 04:03:49 +00:00
Code Releases Wiki Activity

Modified parse command to make it default to "parse" method if no rules are found

Browse Source 
--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40474
This commit is contained in:
elpolilla 2008-12-05 17:56:36 +00:00
parent aeb95200a1
commit f373fc0f7c
1 changed files with 14 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
scrapy/trunk/scrapy/command/commands/parse.py
View File

@ -73,20 +73,24 @@ class Command(ScrapyCommand):
continue
if self.callbacks:
items, links = [], []
for callback in self.callbacks:
r_items, r_links = self.run_callback(spider, response, callback, args, opts)
items.extend(r_items)
links.extend(r_links)
items, links = self.run_callback(spider, response, callback, args, opts)
ret_items.extend(items)
ret_links.extend(links)
continue
elif opts.rules:
for rule in getattr(spider, 'rules', ()):
if rule.link_extractor.matches(response.url):
items, links = self.run_callback(spider, response, rule.callback, args, opts)
break
rules = getattr(spider, 'rules')
if rules:
items, links = [], []
for rule in rules:
if rule.callback and rule.link_extractor.matches(response.url):
items, links = self.run_callback(spider, response, rule.callback, args, opts)
break
else:
log.msg('No rules found for spider "%s", please specify a parsing callback' % spider.domain_name)
continue
log.msg('No rules found for spider "%s", calling default method "parse"' % spider.domain_name)
items, links = self.run_callback(spider, response, 'parse', args, opts)
else:
items, links = self.run_callback(spider, response, 'parse', args, opts)