問(wèn)題描述

想要爬取愛(ài)卡汽車(chē)的每個(gè)汽車(chē)的口碑，但是在翻頁(yè)問(wèn)題總是進(jìn)不去，無(wú)論是用chorme還是自帶的css selector helper抓取到的CSS PATH都無(wú)法翻頁(yè)，請(qǐng)求幫助，代碼如下

#!/usr/bin/env python# -*- encoding: utf-8 -*-# Created on 2017-03-21 12:57:03# Project: test03import refrom pyspider.libs.base_handler import *class Handler(BaseHandler): crawl_config = { } @every(minutes=24 * 60) def on_start(self):self.crawl(’http://newcar.xcar.com.cn/price/’, callback=self.index_page) @config(age=10 * 24 * 60 * 60) def index_page(self, response):for each in response.doc(’a[href^='http']’).items(): if re.match('http://newcar.xcar.com.cn/d', each.attr.href, re.U): self.crawl(each.attr.href, callback=self.list_page) def list_page(self, response):for each in response.doc(’body > p.demio_wp > p > ul > li:nth-child(6) > a’).items(): self.crawl(each.attr.href, callback=self.list_page1)def list_page1(self, response):for each in response.doc(’.review_gml_tit > .more’).items(): self.crawl(each.attr.href, callback=self.detail_page) #翻頁(yè)，問(wèn)題出在下面這里for each in response.doc(’body > p.review_main > p.review_left > p > p.review_comments > p.review_comments_dl > p.pagers > a:nth-child(2)’).items(): self.crawl(each.attr.href, callback=self.list_page1)@config(priority=2) def detail_page(self, response):return { 'branch':response.doc(’#nav_ps > em > a’).text(), 'text':response.doc(’body > p.review_main > p.review_left > p > p.review_comments > p.review_comments_dl > dl > dd’).text(), }

問(wèn)題解答

評(píng)論是 javascript 加載的。