模拟登录人人网

Posted 2020-12-18 gerenboke

#编码流程：
#1.验证码的识别，获取验证码图片的文字数据
#2.对post请求进行发送（处理请求函数）
#3.对响应函数进行持久化存储

import requests
from lxml import etree
from CodeClass import YDMHttp

#1.对验证码图片进行捕获和识别
headers = {
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/47.0.2626.106 Safari/537.36‘
}

url = ‘http://www.renren.com/SysHome.do‘
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
code_img_src = etree.xpath(‘//*[@id="verifyPic_login"]/@src‘)[0]
code_img_data = requests.get(url=code_img_src,headers=headers).content
with open(‘./code.jpg‘,‘wb‘) as fp:
    fp.write(code_img_data)

#使用云打码提供的示例代码对验证码图片进行识别
result = getCodeText(‘code.jpg‘,2004)

#post请求的发送（模拟登录）
login_url = ‘‘

data = {

}
response = requests.post(url=login_url,headers=headers,data=data)
print(response.status_code)

with open(‘renren.html‘,‘w‘,encoding=‘utf-8‘) as fp:
    fp.write(login_page_text)