pipelines ,items里面都没有任何的输入,然后setting里面自行加上请求头和开启就好了。
# -*- coding: utf-8 -*-
import scrapy
class RenrenSpider(scrapy.Spider):
name = 'renren'
allowed_domains = ['renren.com']
start_urls = ['http://renren.com/']
def start_request(self):
url = "http://www.renren.com/SysHome.do"
data = {"email": "15831222968", "password": "970506slm"}
request = scrapy.FormRequest(url, formdata=data, callback=self.parse)
yield request
def parse(self, response):
request = scrapy.Request(
url="http://www.renren.com/928915747/newsfeed/origin",
callback=self.parse_profile
)
yield request
def parse_profile(self, response):
with open("login.html", "w", encoding="utf-8")as fp:
fp.write(response.text)