def execute(self, args, opts):
task = None
if opts.task_id:
task = Task().load(id=opts.task_id)
if opts.task_name:
task = Task().next(name=opts.task_name)
if task or len(args):
if task:
domain = task.domain
else:
domain = args[0]
spider = spiders.fromdomain(domain)
scrapymanager.configure()
if opts.child:
def _stop():
pass
# monkeypatching stop command to prevent stoping prematurely in child mode
scrapymanager.stop = _stop
if not task.locked:
task.lock()
self.crawl(spider, task)
scrapyengine.start()
else:
log.msg('You must specify atleast 1 domain', level=log.ERROR)
def run(self, args, opts):
if opts.list:
self._list_templates()
return
if opts.dump:
template_file = self._find_template(opts.template)
if template_file:
template = open(template_file, 'r')
print template.read()
return
if len(args) < 2:
return False
module = sanitize_module_name(args[0])
domain = args[1]
spider = spiders.fromdomain(domain)
if spider and not opts.force:
print "Spider '%s' already exists in module:" % domain
print " %s" % spider.__module__
sys.exit(1)
template_file = self._find_template(opts.template)
if template_file:
self._genspider(module, domain, opts.template, template_file)
def _get_spider_requests(*args):
"""Collect requests and spiders from the given arguments. Returns a dict of
spider -> list of requests
"""
spider_requests = defaultdict(list)
for arg in args:
if isinstance(arg, tuple):
request, spider = arg
spider_requests[spider] = request
elif isinstance(arg, Request):
spider = spiders.fromurl(arg.url) or BaseSpider('default')
if spider:
spider_requests[spider] += [arg]
else:
log.msg('Could not find spider for request: %s' % arg, log.ERROR)
elif isinstance(arg, BaseSpider):
spider_requests[arg] += arg.start_requests()
elif is_url(arg):
spider = spiders.fromurl(arg) or BaseSpider('default')
if spider:
for req in arg_to_iter(spider.make_requests_from_url(arg)):
spider_requests[spider] += [req]
else:
log.msg('Could not find spider for url: %s' % arg, log.ERROR)
elif isinstance(arg, basestring):
spider = spiders.fromdomain(arg)
if spider:
spider_requests[spider] += spider.start_requests()
else:
log.msg('Could not find spider for domain: %s' % arg, log.ERROR)
else:
raise TypeError("Unsupported argument: %r" % arg)
return spider_requests
