chou.py 文件源码

def show(self, response):
        # print(response)
        hxs = HtmlXPathSelector(response)
        news_list = hxs.select('//div[@id="content-list"]/div[@class="item"]')
        for new in news_list:
            # temp = new.xpath('div/div[@class="part2"]/@share-linkid').extract()
            link_id = new.xpath('*/div[@class="part2"]/@share-linkid').extract_first()
            yield Request(
                url='http://dig.chouti.com/link/vote?linksId=%s' % (link_id,),
                method='POST',
                cookies=self.cookie_dict,
                callback=self.do_favor
            )
        page_list = hxs.select('//div[@id="dig_lcpage"]//a[re:test(@href, "/all/hot/recent/\d+")]/@href').extract()
        for page in page_list:

            page_url = 'http://dig.chouti.com%s' % page
            import hashlib
            hash = hashlib.md5()
            hash.update(bytes(page_url, encoding='utf-8'))
            key = hash.hexdigest()
            if key in self.has_request_set:
                pass
            else:
                self.has_request_set[key] = page_url
                yield Request(
                    url=page_url,
                    method='GET',
                    callback=self.show
                )