详解向scrapy中的spider传递参数的几种方法(2种)

scrapy crawl myspider -a category=electronics

import scrapy

class MySpider(scrapy.Spider):
  name = 'myspider'

  def __init__(self, category=None, *args, **kwargs):
    super(MySpider, self).__init__(*args, **kwargs)
    self.start_urls = ['http://www.example.com/categories/%s' % category]
    # ...

$ curl http://localhost:6800/schedule.json -d project=myproject -d spider=somespider -d setting=DOWNLOAD_DELAY=2 -d arg1=val1

def parse_page1(self, response):
  item = MyItem()
  item['main_url'] = response.url
  request = scrapy.Request("http://www.example.com/some_page.html",
               callback=self.parse_page2)
  request.meta['item'] = item
  return request

def parse_page2(self, response):
  item = response.meta['item']
  item['other_url'] = response.url
  return item