Scrapy 爬虫框架-基于验证码登录

PIL库基本介绍

PIL：Python Imaging Library，已经是Python平台事实上的图像处理标准库了。PIL功能非常强大，但API却非常简单易用

# 加载图片
data = Image.open("../data/getcode.do.jpg")
data.show()
# 把图片转化为矩阵类型
data = np.array(data)
print(data,data.shape)

完成登录验证码识别操作

# -*- coding: utf-8 -*-
import scrapy
from scrapy import cmdline
from urllib import request
from PIL import Image


class DoubanSpiderSpider(scrapy.Spider):
    name = 'douban_spider'
    allowed_domains = ['movie.douban.com']
    # 启动url地址
    start_urls = ['http://www.renren.com/PLogin.do']

    def parse(self, response):
        formdata = {
            'email': '970138074@qq.com',
            'password': 'pythonspider'
        }
        # 获取当前的验证码地址
        img_url = response.xpath("//*[@id='verifyPic_login']/@src")
        print(img_url)
        if img_url:
            # 根据图片地址获取图片信息
            check_code = self.parse_image(img_url)
            formdata['icode'] = check_code
        yield scrapy.FormRequest(url='http://www.renren.com/PLogin.do', formdata=formdata, callback=self.after_login)

    # next(parse)
    def parse_image(self, image_url):
        # from urllib import request
        request.urlretrieve(image_url, 'check_code.png')
        image = Image.open('check_code.png')
        image.show()
        check_code = input("请输入验证码")
        return check_code

    def after_login(self, response):
        print('---->' , response.url)


if __name__ == "__main__":
    # cmdline.execute("scrapy crawl -s LOG_FILE=all.log douban_spider".split(' '))
    cmdline.execute("scrapy crawl douban_spider".split(' '))
    # cmdline.execute("scrapy crawl -o douban.csv douban_spider".split(' '))

版本二

import scrapy
from urllib import request
from PIL import Image
from lxml import etree


class RenrenSpiderSpider(scrapy.Spider):
    name = 'renren_spider'
    allowed_domains = ['renren.com']
    start_urls = ['http://www.renren.com/SysHome.do']

    def parse(self, response):
        loginForm = {
            'email':'1147040@qq.com',
            'password':'scrapy_demo1'
        }
        #img_url = etree.HTML(response.text).xpath("//*[@id='verifyPic_login']/@src")
        img_url = 'http://icode.renren.com/getcode.do?t=web_login&rnd=Math.random()'
        print(img_url)
        if img_url:
            check_code = self.__parse_image(img_url)
            loginForm['icode'] = check_code
        return scrapy.FormRequest(url='http://www.renren.com/PLogin.do',formdata=loginForm,callback=self.after_login)

    def __parse_image(self,img_url):
        request.urlretrieve(img_url,"check_code.png")
        image = Image.open('check_code.png')
        image.show()
        check_code = input('请输入验证码')
        return check_code

    def after_login(self,reponse):
        with open('renren.hmtl','w+',encoding='utf-8') as f:
            f.write(reponse.text)

————————————————

版权声明：本文为CSDN博主「lsqzedu」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。

原文链接：https://blog.csdn.net/lsqzedu/article/details/99707709