1.案例一
a.创建项目
scrapy startproject renren_login
进入项目路径
scrapy genspider renren "renren.com"
renren.py
# -*- coding: utf-8 -*- import scrapy class RenrenSpider(scrapy.Spider): name = 'renren' allowed_domains = ['renren.com'] start_urls = ['http://renren.com/'] def start_requests(self): url="http://www.renren.com/PLogin.do" data={"email":"[email protected]","password":"1988010101"} request=scrapy.FormRequest(url,formdata=data,callback=self.parse_page) yield request def parse_page(self, response): request=scrapy.Request(url='http://www.renren.com/326282648/profile',callback=self.parse_profile) yield request def parse_profile(self,response): with open("wenliang.html","w",encoding="utf-8") as fp: fp.write(response.text)
在项目路径下创建start.py
from scrapy import cmdline cmdline.execute(["scrapy","crawl","renren"])
2.案例2