uuSpider.py 文件源码

def parse(self, response):
        # ?request.content ??? Element
        items = response.xpath('//form[@name="moderate"]/*/div[@class="spaceborder"]/table/tr')
        for item in items:
            url_str = 'http://www.mayattt.com/'+item.xpath('./td[@class="f_title"]/a/@href').extract()[0]
            title_str = ''
            date_str = ''
            try:
                title_str = item.xpath('./td[@class="f_title"]/a/text()').extract()[0]
                date_str = item.xpath('./td[@class="f_last"]/span/a/text()').extract()[0]
            except:
                self.logger.error('get list page failure!')
                pass
            yield Request(url_str, headers=self.headers, callback=self.parseImage, meta={'title': title_str,
                                                                                             'date': date_str})

    # ??????? ??url , ??item?