tc.py 代码
# -*- coding: utf-8 -*-
import scrapy
from ..items import TcItem
class Tc58Spider(scrapy.Spider):
name = 'tc'
allowed_domains = ['bj.58.com']
start_urls = ['http://bj.58.com/chuzu/pn1/?PGTID=0d3090a7-0000-1fd7-9c9a-3a83d8c87059&ClickID=2']
#http://bj.58.com/chuzu/pn5/?PGTID=0d3090a7-0000-1fd7-9c9a-3a83d8c87059&ClickID=2
def parse(self, response):
for i in range(2,10):
next_url = 'http://bj.58.com/chuzu/pn{}/?PGTID=0d3090a7-0000-1fd7-9c9a-3a83d8c87059&ClickID=2'.format(i)
yield scrapy.Request(next_url, callback=self.parse_xq)
def parse_xq(self, response):
# with open('58tongcheng.html','wb') as f:
# f.write(response.body)
#/html/body/div[4]/div[1]/div[5]/div[2]/ul/li[1]/div[2]/h2/a
item=TcItem()
titles = response.x