mirror of https://github.com/scrapy/scrapy.git
68 lines
2.0 KiB
Python
68 lines
2.0 KiB
Python
"""
|
|
Scrapy Shell
|
|
|
|
See documentation in docs/topics/shell.rst
|
|
"""
|
|
|
|
from threading import Thread
|
|
|
|
from scrapy.command import ScrapyCommand
|
|
from scrapy.shell import Shell
|
|
from scrapy.http import Request
|
|
from scrapy import log
|
|
from scrapy.utils.spider import spidercls_for_request, DefaultSpider
|
|
|
|
|
|
class Command(ScrapyCommand):
|
|
|
|
requires_project = False
|
|
default_settings = {'KEEP_ALIVE': True, 'LOGSTATS_INTERVAL': 0}
|
|
|
|
def syntax(self):
|
|
return "[url|file]"
|
|
|
|
def short_desc(self):
|
|
return "Interactive scraping console"
|
|
|
|
def long_desc(self):
|
|
return "Interactive console for scraping the given url"
|
|
|
|
def add_options(self, parser):
|
|
ScrapyCommand.add_options(self, parser)
|
|
parser.add_option("-c", dest="code",
|
|
help="evaluate the code in the shell, print the result and exit")
|
|
parser.add_option("--spider", dest="spider",
|
|
help="use this spider")
|
|
|
|
def update_vars(self, vars):
|
|
"""You can use this function to update the Scrapy objects that will be
|
|
available in the shell
|
|
"""
|
|
pass
|
|
|
|
def run(self, args, opts):
|
|
url = args[0] if args else None
|
|
spiders = self.crawler_process.spiders
|
|
|
|
spidercls = DefaultSpider
|
|
if opts.spider:
|
|
spidercls = spiders.load(opts.spider)
|
|
elif url:
|
|
spidercls = spidercls_for_request(spiders, Request(url),
|
|
spidercls, log_multiple=True)
|
|
crawler = self.crawler_process._create_logged_crawler(spidercls)
|
|
crawler.engine = crawler._create_engine()
|
|
crawler.engine.start()
|
|
|
|
self.crawler_process._start_logging()
|
|
self._start_crawler_thread()
|
|
|
|
shell = Shell(crawler, update_vars=self.update_vars, code=opts.code)
|
|
shell.start(url=url)
|
|
|
|
def _start_crawler_thread(self):
|
|
t = Thread(target=self.crawler_process._start_reactor,
|
|
kwargs={'stop_after_crawl': False})
|
|
t.daemon = True
|
|
t.start()
|