详解Selenium-webdriver绕开反爬虫机制的4种方法

mitmdump -p 8001

def response(flow): 
  if '/js/yoda.' in flow.request.url:
  for webdriver_key in ['webdriver', '__driver_evaluate', '__webdriver_evaluate', '__selenium_evaluate', '__fxdriver_evaluate', '__driver_unwrapped', '__webdriver_unwrapped', '__selenium_unwrapped', '__fxdriver_unwrapped', '_Selenium_IDE_Recorder', '_selenium', 'calledSelenium', '_WEBDRIVER_ELEM_CACHE', 'ChromeDriverw', 'driver-evaluate', 'webdriver-evaluate', 'selenium-evaluate', 'webdriverCommand', 'webdriver-evaluate-response', '__webdriverFunc', '__webdriver_script_fn', '__$webdriverAsyncExecutor', '__lastWatirAlert', '__lastWatirConfirm', '__lastWatirPrompt', '$chrome_asyncScriptInfo', '$cdc_asdjflasutopfhvcZLmcfl_' ]:
   ctx.log.info('Remove "{}" from {}.'.format(
   webdriver_key, flow.request.url
   )) 
  flow.response.text = flow.response.text.replace('"{}"'.format(webdriver_key), '"NO-SUCH-ATTR"') 
 flow.response.text = flow.response.text.replace('t.webdriver', 'false')
 flow.response.text = flow.response.text.replace('ChromeDriver', '')

mitmdump -s DriverPass.py -p 8001

 var doc = opt_doc || document;
 var key = '$cdc_asdjflasutopfhvcZLmcfl_';
 if (!(key in doc))
 doc[key] = new Cache();
 return doc[key];
}

function getPageCache(opt_doc) {
 var doc = opt_doc || document;
 var key = ‘$bobo_zhangyx_';
if (!(key in doc))
 doc[key] = new Cache();
 return doc[key];
 }

chrome.exe --remote-debugging-port=9222 

chrome_options.add_experimental_option("debuggerAddress", "127.0.0.1:9222")