czasg / minitools Goto Github PK

from minitools.scrapy import miniSpider

class MySPider(miniSpider):
  start_urls = ['http://www.baidu.com']
  
  def parse(self, response):
    print(response.url)

if __name__ == '__main__':
  MySpider.run(__file__)

from minitools.scrapy import next_page_request
class MySpider(miniSpider):
  def parse(self, response):
    yield next_page_request(response, 'page=(\d+)')  # you need fill regex in here