BackTrackZ/scrapy
BackTrackZ/scrapy
1
0
Fork 0
mirror of https://github.com/scrapy/scrapy.git synced 2025-02-24 00:23:52 +00:00
Code Releases Wiki Activity

Two fixes for when using the parse command and the '-r' flag (rules).

Browse Source 
1. Use default "parse" as callback when the matching rule has no callback.
2. Log error and return when no rule matches the parsed url.
This commit is contained in:
Joakim Uddholm 2016-09-08 21:52:14 +02:00
parent 0ef570f6f0
commit 743a0aa422
1 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
scrapy/commands/parse.py
View File

@ -121,8 +121,8 @@ class Command(ScrapyCommand):
def get_callback_from_rules(self, spider, response):
if getattr(spider, 'rules', None):
for rule in spider.rules:
if rule.link_extractor.matches(response.url) and rule.callback:
return rule.callback
if rule.link_extractor.matches(response.url):
return rule.callback or "parse"
else:
logger.error('No CrawlSpider rules found in spider %(spider)r, '
'please specify a callback to use for parsing',
@ -166,6 +166,11 @@ class Command(ScrapyCommand):
if not cb:
if opts.rules and self.first_response == response:
cb = self.get_callback_from_rules(spider, response)
if not cb:
logger.error('Cannot find a rule that matches %(url)r in spider: %(spider)s',
{'url': response.url, 'spider': spider.name})
return
else:
cb = 'parse'