【selenium自动化过程中的api抓包】browsermobproxy的安装和配置

第一步

pip install browsermob-proxy

先装一个包

第二步

要求jdk1.8以上的环境变量依赖
ps：如果是刚配的环境记得，重启一下

第三步

下载java端BrowserMob-Proxy包：http://bmp.lightbody.net/

直接拿来主义（在py配置的时候要记得写上browsermob-proxy.bat地址）

实验：百度一下

比如说，我想随便抓一个js的response看看

确实可以看到一些粗略的内容，细致的js代码还需要探索一下

完整代码

from browsermobproxy import Server
from selenium import webdriver
import time
import pprint

class ProxyManger:

    __BMP = r"C:\Users\Irving\Desktop\echain\browsermob-proxy-2.1.4-bin\browsermob-proxy-2.1.4\bin\browsermob-proxy.bat"

    def __init__(self):

        self.__server = Server(ProxyManger.__BMP)
        self.__client = None

    def start_server(self):
        self.__server.start()
        return self.__server

    def start_client(self):

        self.__client = self.__server.create_proxy(params={
    "trustAllServers": "true"})
        return self.__client

    @property
    def client(self):
        return self.__client

    @property
    def server(self):
        return self.__server

if __name__=="__main__":
    # 开启Proxy
    proxy = ProxyManger()
    server = proxy.start_server()
    client = proxy.start_client()

    # 配置Proxy启动WebDriver
    options = webdriver.ChromeOptions()
    options.add_argument("--proxy-server={}".format(client.proxy))
    options.add_argument('--ignore-certificate-errors')
    options.add_argument('--headless')
    #chromePath = r"D:\AzRjN\anaconda3_7\envs\demo36\Lib\site-packages\selenium\webdriver\chrome\chromedriver.exe"
    driver = webdriver.Chrome(chrome_options=options)

    # 获取返回的内容
    client.new_har("baidu.com", options={
    'captureHeaders': True, 'captureContent': True})
    driver.get("https://www.baidu.com/")
    time.sleep(3)

    result = client.har
    print(result)

    for entry in result['log']['entries']:
        _url = entry['request']['url']
        print("请求地址：", _url)

        if "https://pss.bdstatic.com/r/www/cache/static/protocol/https/amd_modules/san/dist/san_5017f11.js" in _url:
            _response = entry['response']
            _content = _response['content']
            print("---------https://pss.bdstatic.com/r/www/cache/static/protocol/https/amd_modules/san/dist/san_5017f11.js 请求响应内容：", _response)

    server.stop()

总结

selenium一边自动化操作
browsermobproxy一边抓包