scrapy爬蟲系列之六--模擬登陸

功能點：如何發送攜帶cookie訪問登陸後的頁面，如何發送post請求登陸

爬取網站：bilibili、github

完整代碼：https://files.cnblogs.com/files/bookwed/login.zip

主要代碼：

bili.py

# -*- coding: utf-8 -*-
import scrapy
import re


class BiliSpider(scrapy.Spider):
    """直接攜帶cookie訪問登陸後的bilibili頁面"""
    name = 'bili'
    allowed_domains = ['bilibili.com']
    # 登陸後的我的主頁
    start_urls = ['https://account.bilibili.com/home/userInfo']

    def start_requests(self):
        cookies = "_uuid=738F48A9-E13A-9445-3577-3068FADC9F6A05981infoc; buvid3=5DE9F436-F051-44E1-9B97-AB53E60C3ED448999infoc;"
        cookies = {i.split("=")[0]: i.split("=")[1] for i in cookies.split("; ")}
        # 把cookies字符串放到headers裏面傳參，這種方式不行，要單獨傳cookies參數
        # headers={"Cookie": cookies}
        print(cookies)
        yield scrapy.Request(
            self.start_urls[0],
            callback=self.parse,
            cookies=cookies,
            # headers=headers
        )


    def parse(self, response):
        # 驗證是否成功
        print("*"*30)
        print(re.findall("bookwed", response.body.decode()))
        print("*"*30)

        # yield scrapy.FormRequest(
        #     "http://",
        #     headers=self,
        #     formdata=dict(),
        #     callback=self.after_login
        # )

github.py

# -*- coding: utf-8 -*-
import scrapy
import re


class GithubSpider(scrapy.Spider):
    """利用scrapy發送post請求，模擬登陸github"""
    """注意點：針對form表單有action地址的狀況，能夠直接請求action，參考github2.py"""
    name = 'github'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']

    def parse(self, response):
        authenticity_token = response.xpath("//input[@name='authenticity_token']/@value").extract_first()
        commit = response.xpath("//input[@name='commit']/@value").extract_first()
        utf8 = response.xpath("//input[@name='utf8']/@value").extract_first()
        webauthn_support = response.xpath("//input[@name='webauthn-support']/@value").extract_first()
        # login = response.xpath("//input[@name='login']/@value").extract_first()
        # password = response.xpath("//input[@name='password']/@value").extract_first()
        post_data = dict(
            login="aa@163.com",
            password="aaaaaa",
            commit=commit,
            utf8=utf8,
            authenticity_token=authenticity_token,
            webauthn_support=webauthn_support
        )
        yield scrapy.FormRequest(
            "https://github.com/session",   #發送post請求登陸接口
            formdata=post_data,
            callback=self.after_login
        )

        # 另一種發送post請求的方式：指定請求方式爲POST
        # yield scrapy.Request(
        #     "https://github.com/session",
        #     method='POST',
        #     body=
        # )

    def after_login(self,response):
        # 對於不太確認的狀況，能夠先把響應保存到本地，而後進行分析
        # with open('aa.html', 'w', encoding='utf-8') as f:
        #     f.write(response.body.decode())
        print("*"*30)
        print(re.findall('wed', response.body.decode()))
        print("*"*30)

github2.py

# -*- coding: utf-8 -*-
import scrapy
import re


class Github2Spider(scrapy.Spider):
    """對於form表單有action地址的狀況，能夠直接請求action，只用傳用戶名密碼便可"""
    name = 'github2'
    allowed_domains = ['github.com']
    start_urls = ['https://github.com/login']

    # 注意：針對網頁中有多個form的狀況，能夠經過傳參來指定form，如formname、formid、formnumber、formxpath
    def parse(self, response):
        yield scrapy.FormRequest.from_response(
            response,   # scrapy會從response中自動尋找form表單
            formdata={"login": "aa@163.com", "password": "aaaaaa"},     # key對應頁面上的name，value對應實際的值
            callback=self.after_login
        )

    def after_login(self, response):
        print("*" * 30)
        print(re.findall('wed', response.body.decode()))
        print("*" * 30)