# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request,FormRequest
class IqianSpider(scrapy.Spider):
name = ‘iqian‘
allowed_domains = [‘edu.iqianxxx.com‘]
# start_urls = [‘http://edu.iqianxxx.com/‘]
headers = {‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER‘}
# 入口
def start_requests(self):
start_url = "http://edu.iqianxxx.com/index_user_login.html"
return [Request(url=start_url, meta={"cookiejar": 1}, callback=self.login)]
def login(self, response):
data = {
"number": "xxxx",
"passwd": "xxxx",
}
print("登录中...............")
return [FormRequest.from_response(response,
meta={"cookiejar": response.meta["cookiejar"]},
headers=self.headers,
formdata=data,
callback=self.next1,
)]
#需要在跳转一次,以防中间页面
def next1(self, response):
yield Request(url="http://edu.iqianxxx.com/index_user_index.html", callback=self.next2)
def next2(self, response):
print(response.url)
pass