googleplaySpider.py 文件源码

def parse(self, response):  
          #?? ?????? URL
          for url in response.xpath('//a[@class="see-more play-button small id-track-click apps id-responsive-see-more"]'):
              targetURL = "https://play.google.com" + url.xpath('@href')[0].extract()
              #??POST , ??? 100 ?
              yield  scrapy.FormRequest(               
                     targetURL,
                     formdata = {'start':'0',
                                 'num':'100',
                                 'numChildren':'0',
                                 'cctcss':'square-cover',
                                 'cllayout':'NORMAL',
                                 'ipf':'1',
                                 'xhr':'1',
                                 'token':'zNTXc17yBEzmbkMlpt4eKj14YOo:1458833715345'},
                    callback = self.parse_data
                 )