?
scrapy中使用FormRequest向網頁提交數據
Scrapy post使用
?
如何post data：
http://httpbin.org/post
?
FormRequest : post請求
GitHub Login
借助瀏覽器分析登陸行為。
- 分析post的內容
- 先嘗試一次錯誤的登陸：
- 如下：分析：
需要post的數據有：
- token:
- utf-8:
- commit:
- login:
- password:
- 以上只有token不是固定的
- 將以上內容組裝出來。
scrapy 如下：
# -*- coding: utf-8 -*-
import scrapy
from scrapy import FormRequest, Requestclass SpiderpostSpider(scrapy.Spider):name = "spiderpost"# allowed_domains = ["httpbin.org"]# starturls = 'http://httpbin.org/post'# "oSqXgiQ0dBFn5aNywI/BLkosYQKNlKd0K4QspnZP1HLLuA/ePxcjU0RItphFoIkOfySKiLQW27AKcmjLmqPmjQ=="# "wOgMHIwtyvdS1iwLG05afiq0/+gSkFr0RjS+x6f0nP/DALNvQiBVvuKsLRVMHfDJEtfNdTga2MdmYid0OcqxwQ=="starturls='https://github.com/login'loginurls='https://github.com/session'def start_requests(self):yield Request(self.starturls, callback=self.pre_parse)def pre_parse(self, response):# print(response.url)# passform =response.xpath('//form[@action="/session"]').extract()# print(form)keys=['utf8', 'authenticity_token', 'commit']values=[]for key in keys:xpath_ = '//form[@action="/session"]//input[@name="%s"]/@value'%keyvalue = response.xpath(xpath_).extract()[0]values.append(value)# print(values)postdata=dict(zip(keys,values))postdata['login'] = 'your nanme'postdata['password']='your password'# print(postdata)yield FormRequest(self.loginurls, formdata=postdata,callback=self.login_parse)def login_parse(self,response):# print(response.url)#檢驗是否登陸成功print(response.xpath('//meta[@name="user-login"]/@content').extract()))
猜想)
