0


selenium 提取谷歌游览器Cookie的五种方法

纯手动提取谷歌游览器cookie

方法就是先F12打开开发者工具,然后访问要提取cookie的网站,然后在网络中选中刚才访问的请求,然后在请求头中找到cookie这一项,复制对应的值即可。
将请求以curl命令形式复制到剪切板之后,我们就可以通过代码直接提取cookie,代码如下:

import re
import pyperclip

defextractCookieByCurlCmd(curl_cmd):
    cookie_obj = re.search("-H \$?'cookie: ([^']+)'", curl_cmd, re.I)if cookie_obj:return cookie_obj.group(1)

cookie = extractCookieByCurlCmd(pyperclip.paste())print(cookie)

selenium手动登录并获取cookie

以保存B站登录cookie为例:

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.common.exceptions import NoSuchElementException
import time
import json

browser = webdriver.Chrome()
browser.get("https://passport.bilibili.com/login")
flag =Trueprint("等待登录...")while flag:try:
        browser.find_element(By.XPATH,"//div[@class='user-con signin']|//ul[@class='right-entry']""//a[@class='header-entry-avatar']")
        flag =Falseexcept NoSuchElementException as e:
        time.sleep(3)print("已登录,现在为您保存cookie...")withopen('cookie.txt','w', encoding='u8')as f:
    json.dump(browser.get_cookies(), f)
browser.close()print("cookie保存完成,游览器已自动退出...")

selenium无头模式获取非登录cookie

比如抖音这种网站想下载其中的视频,就必须要带有一个初始的cookie,但这个cookie生成的算法比较复杂,纯requests很难模拟,这时我们完全可以借助selenium来加载网页并获取cookie节省分析js的时间。
代码如下:

from selenium import webdriver
import time

defselenium_get_cookies(url='https://www.douyin.com'):"""无头模式提取目标链接对应的cookie,代码作者:小小明-代码实体"""
    start_time = time.time()
    option = webdriver.ChromeOptions()
    option.add_argument("--headless")
    option.add_experimental_option('excludeSwitches',['enable-automation'])
    option.add_experimental_option('useAutomationExtension',False)
    option.add_argument('user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36')
    option.add_argument("--disable-blink-features=AutomationControlled")print("打开无头游览器...")
    browser = webdriver.Chrome(options=option)print(f"访问{url} ...")
    browser.get(url)
    cookie_list = browser.get_cookies()# 关闭浏览器
    browser.close()
    cost_time = time.time()- start_time
    print(f"无头游览器获取cookie耗时:{cost_time:0.2f} 秒")return{row["name"]: row["value"]for row in cookie_list}print(selenium_get_cookies("https://www.douyin.com"))

打印结果如下:

打开无头游览器...
访问https://www.douyin.com ...
无头游览器获取cookie耗时:3.28 秒
{'':'douyin.com','ttwid':'1%7CZn_LJdPjHKdCy4jtBoYWL_yT3NMn7OZVTBStEzoLoQg%7C1642932056%7C80dbf668fd283c71f9aee1a277cb35f597a8453a3159805c92dfee338e70b640','AB_LOGIN_GUIDE_TIMESTAMP':'1642932057106','MONITOR_WEB_ID':'651d9eca-f155-494b-a945-b8758ae948fb','ttcid':'ea2b5aed3bb349219f7120c53dc844a033','home_can_add_dy_2_desktop':'0','_tea_utm_cache_6383':'undefined','__ac_signature':'_02B4Z6wo00f01kI39JwAAIDBnlvrNDKInu5CB.AAAPFv24','MONITOR_DEVICE_ID':'25d4799c-1d29-40e9-ab2b-3cc056b09a02','__ac_nonce':'061ed27580066860ebc87'}

获取本地谷歌游览器中的cookie

只要我们使用debug远程调试模式运行本地的谷歌游览器,再用selenium控制即可提取之前登录的cookie:

import os
import winreg
from selenium import webdriver
import time

defget_local_ChromeCookies(url, chrome_path=None):"""提取本地谷歌游览器目标链接对应的cookie,代码作者:小小明-代码实体"""if chrome_path isNone:
        key = winreg.OpenKey(winreg.HKEY_CLASSES_ROOT,r"ChromeHTML\Application")
        path = winreg.QueryValueEx(key,"ApplicationIcon")[0]
        chrome_path = path[:path.rfind(",")]
    start_time = time.time()
    command =f'"{chrome_path}" --remote-debugging-port=9222'# print(command)
    os.popen(command)
    option = webdriver.ChromeOptions()
    option.add_experimental_option("debuggerAddress","127.0.0.1:9222")
    browser = webdriver.Chrome(options=option)print(f"访问{url}...")
    browser.get(url)
    cookie_list = browser.get_cookies()# 关闭浏览器
    browser.close()
    cost_time = time.time()- start_time
    print(f"获取谷歌游览器cookie耗时:{cost_time:0.2f} 秒")return{row["name"]: row["value"]for row in cookie_list}print(get_local_ChromeCookies("https://www.douyin.com"))

谷歌游览器的启动参数加上 --remote-debugging-port=9222即可开启远程debug模式,而selenium则可以通过debuggerAddress参数连接一个现有开启远程debug模式的谷歌游览器。

直接解密cookies文件

代码块

"""
小小明的代码
CSDN主页:https://blog.csdn.net/as604049322
"""
__author__ ='小小明'
__time__ ='2022/1/23'import base64
import json
import os
import sqlite3

import win32crypt
from cryptography.hazmat.primitives.ciphers.aead import AESGCM

defload_local_key(localStateFilePath):"读取chrome保存在json文件中的key再进行base64解码和DPAPI解密得到真实的AESGCM key"withopen(localStateFilePath, encoding='u8')as f:
        encrypted_key = json.load(f)['os_crypt']['encrypted_key']
    encrypted_key_with_header = base64.b64decode(encrypted_key)
    encrypted_key = encrypted_key_with_header[5:]
    key = win32crypt.CryptUnprotectData(encrypted_key,None,None,None,0)[1]return key

defdecrypt_value(key, data):"AESGCM解密"
    nonce, cipherbytes = data[3:15], data[15:]
    aesgcm = AESGCM(key)
    plaintext = aesgcm.decrypt(nonce, cipherbytes,None).decode('u8')return plaintext

deffetch_host_cookie(host):"获取指定域名下的所有cookie"
    userDataDir = os.environ['LOCALAPPDATA']+r'\Google\Chrome\User Data'
    localStateFilePath = userDataDir +r'\Local State'
    cookiepath = userDataDir +r'\Default\Cookies'# 97版本已经将Cookies移动到Network目录下ifnot os.path.exists(cookiepath)or os.stat(cookiepath).st_size ==0:
        cookiepath = userDataDir +r'\Default\Network\Cookies'# print(cookiepath)
    sql =f"select name,encrypted_value from cookies where host_key like '%.{host}'"
    cookies ={}
    key = load_local_key(localStateFilePath)with sqlite3.connect(cookiepath)as conn:
        cu = conn.cursor()for name, encrypted_value in cu.execute(sql).fetchall():
            cookies[name]= decrypt_value(key, encrypted_value)return cookies

if __name__ =='__main__':print(fetch_host_cookie("douyin.com"))
标签: selenium

本文转载自: https://blog.csdn.net/weixin_41442949/article/details/138308939
版权归原作者 我就是我是好孩子啊 所有, 如有侵权,请联系我们删除。

“selenium 提取谷歌游览器Cookie的五种方法”的评论:

还没有评论