scrapy/scrapy/commands/crawl.py

52 lines
2.0 KiB
Python

from scrapy.commands import ScrapyCommand
from scrapy.utils.conf import arglist_to_dict, feed_process_params_from_cli
from scrapy.exceptions import UsageError
class Command(ScrapyCommand):
requires_project = True
def syntax(self):
return "[options] <spider>"
def short_desc(self):
return "Run a spider"
def add_options(self, parser):
ScrapyCommand.add_options(self, parser)
parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE",
help="set spider argument (may be repeated)")
parser.add_option("-o", "--output", metavar="FILE", action="append",
help="dump scraped items into FILE (use - for stdout)")
parser.add_option("-t", "--output-format", metavar="FORMAT",
help="format to use for dumping items with -o")
def process_options(self, args, opts):
ScrapyCommand.process_options(self, args, opts)
try:
opts.spargs = arglist_to_dict(opts.spargs)
except ValueError:
raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False)
if opts.output:
feeds = feed_process_params_from_cli(self.settings, opts.output, opts.output_format)
self.settings.set('FEEDS', feeds, priority='cmdline')
def run(self, args, opts):
if len(args) < 1:
raise UsageError()
elif len(args) > 1:
raise UsageError("running 'scrapy crawl' with more than one spider is no longer supported")
spname = args[0]
crawl_defer = self.crawler_process.crawl(spname, **opts.spargs)
if getattr(crawl_defer, 'result', None) is not None and issubclass(crawl_defer.result.type, Exception):
self.exitcode = 1
else:
self.crawler_process.start()
if self.crawler_process.bootstrap_failed or \
(hasattr(self.crawler_process, 'has_exception') and self.crawler_process.has_exception):
self.exitcode = 1