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

some line wrapping at 80 cols

This commit is contained in:
Pablo Hoffman 2009-08-28 17:52:44 -03:00
parent 3e7e321a07
commit ee40929df4
1 changed files with 16 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
scrapy/command/commands/crawl.py
View File

@ -19,10 +19,14 @@ class Command(ScrapyCommand):
def add_options(self, parser): def add_options(self, parser):
ScrapyCommand.add_options(self, parser) ScrapyCommand.add_options(self, parser)
parser.add_option("--nopipeline", dest="nopipeline", action="store_true", help="disable scraped item pipeline") parser.add_option("--nopipeline", dest="nopipeline", action="store_true", \
parser.add_option("--restrict", dest="restrict", action="store_true", help="restrict crawling only to the given urls") help="disable scraped item pipeline")
parser.add_option("-n", "--nofollow", dest="nofollow", action="store_true", help="don't follow links (for use with URLs only)") parser.add_option("--restrict", dest="restrict", action="store_true", \
parser.add_option("-c", "--callback", dest="callback", action="store", help="use the provided callback for starting to crawl the given url") help="restrict crawling only to the given urls")
parser.add_option("-n", "--nofollow", dest="nofollow", action="store_true", \
help="don't follow links (for use with URLs only)")
parser.add_option("-c", "--callback", dest="callback", action="store", \
help="use the provided callback for starting to crawl the given url")
def process_options(self, args, opts): def process_options(self, args, opts):
ScrapyCommand.process_options(self, args, opts) ScrapyCommand.process_options(self, args, opts)
@ -44,20 +48,24 @@ class Command(ScrapyCommand):
urls = [a] urls = [a]
else: else:
spider = spiders.fromdomain(a) spider = spiders.fromdomain(a)
urls = spider.start_urls if hasattr(spider.start_urls, '__iter__') else [spider.start_urls] urls = spider.start_urls if hasattr(spider.start_urls, \
'__iter__') else [spider.start_urls]
if spider: if spider:
if hasattr(spider, opts.callback): if hasattr(spider, opts.callback):
requests.extend(Request(url=url, callback=getattr(spider, opts.callback)) for url in urls) requests.extend(Request(url=url, callback=getattr(spider, \
opts.callback)) for url in urls)
else: else:
log.msg('Callback %s doesnt exist in spider %s' % (opts.callback, spider.domain_name), log.ERROR) log.msg('Callback %s doesnt exist in spider %s' % \
(opts.callback, spider.domain_name), log.ERROR)
else: else:
log.msg('Cannot find spider for %s' % a, log.ERROR) log.msg('Cannot find spider for %s' % a, log.ERROR)
if requests: if requests:
args = requests args = requests
else: else:
log.msg('Cannot create any requests with the provided arguments', log.ERROR) log.msg('Cannot create any requests with the provided arguments', \
log.ERROR)
return return
scrapymanager.runonce(*args) scrapymanager.runonce(*args)