def run(self, args, opts):
# pass custom option to spiders
opts.spargs = {}
opts.spargs['use_proxy'] = opts.use_proxy
opts.spargs['require_js'] = opts.require_js
opts.spargs['keep_old_data'] = opts.keep_old_data
opts.spargs['crawl_all_cinemas'] = opts.crawl_all_cinemas
opts.spargs['crawl_all_movies'] = opts.crawl_all_movies
opts.spargs['crawl_booking_data'] = opts.crawl_booking_data
opts.spargs['movie_list'] = opts.movie_list
opts.spargs['cinema_list'] = opts.cinema_list
opts.spargs['date'] = opts.date
if opts.all_showing:
self.run_multiple_spiders(args, opts)
else:
Command.run(self, args, opts)
def add_options(self, parser):
Command.add_options(self, parser)
# custom options
group = OptionGroup(parser, "Custom Options")
group.add_option("--all_showing",
action="store_true",
default=False,
help="run all showing spider")
group.add_option("--use_proxy",
action="store_true",
default=False,
help="use setting's proxy when crawling")
group.add_option("--require_js",
action="store_true",
default=False,
help="use phantomjs to process page")
group.add_option("--keep_old_data",
action="store_true",
default=False,
help="keep old data when crawling")
group.add_option("--crawl_all_cinemas",
action="store_true",
default=False,
help="crawl all cinemas")
group.add_option("--crawl_all_movies",
action="store_true",
default=False,
help="crawl all movies")
group.add_option("--crawl_booking_data",
action="store_true",
default=False,
help="crawl booking data for each crawled showing")
group.add_option("--movie_list",
action="append",
default=[],
metavar="moviename",
help="crawl movie list, default is 君の名は。")
group.add_option("--cinema_list",
action="append",
default=[],
metavar="cinemaname",
help="crawl cinema list")
tomorrow = arrow.now('UTC+9').shift(days=+1)
group.add_option("--date",
default=tomorrow.format('YYYYMMDD'),
help="crawl date, default is tomorrow")
parser.add_option_group(group)
def run_crawler(argv=None, settings=None):
"""Run the scrapy crawler bounded to registered spiders.
This function is suitable for standalone scripts.
Usage::
# mimic 'scrapy crawl' command having these two spiders available
SpiderManager.register(FooSpider)
SpiderManager.register(BarSpider)
run_crawler()
"""
argv = argv or sys.argv
settings = _build_settings(settings)
# load spider manager from this module
settings.overrides.update({
'SPIDER_MANAGER_CLASS':
'%s.%s' % (__name__, SpiderManager.__name__),
})
crawler = CrawlerProcess(settings)
crawler.install()
parser = optparse.OptionParser(formatter=optparse.TitledHelpFormatter())
parser.add_option('-l',
'--list',
action='store_true',
help="List available spiders")
cmd = CrawlCommand()
settings.defaults.update(cmd.default_settings)
cmd.settings = settings
cmd.add_options(parser)
parser.usage = "%s %s" % (argv[0], cmd.syntax())
opts, args = parser.parse_args()
if opts.list:
settings.defaults.update(ListCommand.default_settings)
listcmd = ListCommand()
listcmd.set_crawler(crawler)
listcmd.run(args, opts)
sys.exit(listcmd.exitcode)
else:
cmdline._run_print_help(parser, cmd.process_options, args, opts)
cmd.set_crawler(crawler)
cmdline._run_print_help(parser, cmdline._run_command, cmd, args, opts)
sys.exit(cmd.exitcode)
def run_crawler(argv=None, settings=None):
"""Run the scrapy crawler bounded to registered spiders.
This function is suitable for standalone scripts.
Usage::
# mimic 'scrapy crawl' command having these two spiders available
SpiderManager.register(FooSpider)
SpiderManager.register(BarSpider)
run_crawler()
"""
argv = argv or sys.argv
settings = _build_settings(settings)
# load spider manager from this module
settings.overrides.update({
'SPIDER_MANAGER_CLASS': '%s.%s' % (__name__, SpiderManager.__name__),
})
crawler = CrawlerProcess(settings)
crawler.install()
parser = optparse.OptionParser(formatter=optparse.TitledHelpFormatter())
parser.add_option('-l', '--list', action='store_true',
help="List available spiders")
cmd = CrawlCommand()
settings.defaults.update(cmd.default_settings)
cmd.settings = settings
cmd.add_options(parser)
parser.usage = "%s %s" % (argv[0], cmd.syntax())
opts, args = parser.parse_args()
if opts.list:
settings.defaults.update(ListCommand.default_settings)
listcmd = ListCommand()
listcmd.set_crawler(crawler)
listcmd.run(args, opts)
sys.exit(listcmd.exitcode)
else:
cmdline._run_print_help(parser, cmd.process_options, args, opts)
cmd.set_crawler(crawler)
cmdline._run_print_help(parser, cmdline._run_command, cmd, args, opts)
sys.exit(cmd.exitcode)
def process_options(self, args, opts):
Command.process_options(self, args, opts)
def run(self, args, opts):
CrawlCommand.run(self, args, opts)
def process_options(self, args, opts):
CrawlCommand.process_options(self, args, opts)
if opts.db:
settings.overrides['FINANCEDB_ENABLED'] = True
def add_options(self, parser):
CrawlCommand.add_options(self, parser)
parser.add_option("--db", action="store_true", help="Save scraped data into application db")
