如何通过selenium.py获取状态码（Python代码）

11

import json
from selenium.webdriver.chrome.webdriver import WebDriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities

chromedriver_path = "YOUR/PATH/TO/chromedriver.exe"
url = "https://selenium-python.readthedocs.io/api.html"
capabilities = DesiredCapabilities.CHROME.copy()
capabilities['goog:loggingPrefs'] = {'performance': 'ALL'}

browser = WebDriver(chromedriver_path, desired_capabilities=capabilities)

browser.get(url)
logs = browser.get_log('performance')

选项1：如果你只是想返回状态码，并且假设你想要的页面在包含 'text/html 内容类型的日志中存在的话……

def get_status(logs):
    for log in logs:
        if log['message']:
            d = json.loads(log['message'])
            try:
                content_type = 'text/html' in d['message']['params']['response']['headers']['content-type']
                response_received = d['message']['method'] == 'Network.responseReceived'
                if content_type and response_received:
                    return d['message']['params']['response']['status']
            except:
                pass

用法：

>>> get_status(logs)
200

选项2：如果你想查看相关日志中的所有状态码

def get_status_codes(logs):
    statuses = []
    for log in logs:
        if log['message']:
            d = json.loads(log['message'])
            if d['message'].get('method') == "Network.responseReceived":
                statuses.append(d['message']['params']['response']['status'])
    return statuses

用法：

>>> get_status_codes(logs)
[200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200, 200]

注意1：很多内容是基于 @Stefan Matei 的回答，不过，Chrome版本之间有一些变化，我提供了一些解析日志的思路。

注意2：['content-type'] 并不是完全可靠的。大小写可能会变化。请根据你的使用情况进行检查。

回答于 2025-04-16 由 Python大师

分享举报

16

我对Python的经验不多，这里有一个更详细的Java示例：

https://stackoverflow.com/a/39979509/5703420

这个想法是启用性能日志。这意味着在chromedriver上触发“Network.enable”。接着获取性能日志条目，并解析出“Network.responseReceived”这个信息。

    from selenium import webdriver

    from selenium.webdriver.common.desired_capabilities import DesiredCapabilities    
    # enable browser logging
    d = DesiredCapabilities.CHROME
    d['loggingPrefs'] = { 'performance':'ALL' }

    driver = webdriver.Chrome(executable_path="c:\\windows\\chromedriver.exe", service_args=["--verbose", "--log-path=D:\\temp3\\chromedriverxx.log"], desired_capabilities=d)

    driver.get('https://api.ipify.org/?format=text')

    print(driver.title)

    print(driver.page_source)

    performance_log = driver.get_log('performance')
    print (str(performance_log).strip('[]'))

    for entry in driver.get_log('performance'):
        print (entry)

输出结果会包含你网址的“Network.responseReceived”，还有页面加载时进行的其他请求，或者重定向的链接。你只需要解析这些日志条目就可以了。

'{"message":{"method":"Network.responseReceived","params":{"frameId":"9488.1","loaderId":"9488.1","requestId":"9488.1","response":{"connectionId":14,"connectionReused":false,"encodedDataLength":-1,"fromDiskCache":false,"fromServiceWorker":false,"headers":{"Connection":"keep-alive","Content-Length":"13","Content-Type":"text/plain","Date":"Wed, 12 Oct 2016 06:15:47 GMT","Server":"Cowboy","Via":"1.1 vegur"},"headersText":"HTTP/1.1 200 OK\\r\\nServer: Cowboy\\r\\nConnection: keep-alive\\r\\nContent-Type: text/plain\\r\\nDate: Wed, 12 Oct 2016 06:15:47 GMT\\r\\nContent-Length:13\\r\\nVia:1.1vegur\\r\\n\\r\\n","mimeType":"text/plain","protocol":"http/1.1","remoteIPAddress":"54.197.246.207","remotePort":443,"requestHeaders":{"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8","Accept-Encoding":"gzip, deflate, sdch, br","Accept-Language":"en-GB,en-US;q=0.8,en;q=0.6","Connection":"keep-alive","Host":"api.ipify.org","Upgrade-Insecure-Requests":"1","User-Agent":"Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36"},"requestHeadersText":"GET /?format=text HTTP/1.1\\r\\nHost: api.ipify.org\\r\\nConnection: keep-alive\\r\\nUpgrade-Insecure-Requests: 1\\r\\nUser-Agent: Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36\\r\\nAccept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8\\r\\nAccept-Encoding: gzip, deflate, sdch, br\\r\\nAccept-Language: en-GB,en-US;q=0.8,en;q=0.6\\r\\n\\r\\n","securityDetails":{"certificateId":1,"certificateValidationDetails":{"numInvalidScts":0,"numUnknownScts":0,"numValidScts":0},"cipher":"AES_128_GCM","keyExchange":"ECDHE_RSA","protocol":"TLS 1.2","signedCertificateTimestampList":[]},"securityState":"secure","status":200,"statusText":"OK","timing":{"connectEnd":320.508999997401,"connectStart":3.08100000256673,"dnsEnd":3.08100000256673,"dnsStart":0,"proxyEnd":-1,"proxyStart":-1,"pushEnd":0,"pushStart":0,"receiveHeadersEnd":465.725000001839,"requestTime":78246.775045,"sendEnd":320.995999994921,"sendStart":320.825999995577,"sslEnd":320.435000001453,"sslStart":141.675999999279,"workerReady":-1,"workerStart":-1},"url":"https://api.ipify.org/?format=text"},"timestamp":78247.242716,"type":"Document"}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}, {'timestamp': 1476252948094, 'level': 'INFO', 'message': '{"message":{"method":"Network.dataReceived","params":{"dataLength":13,"encodedDataLength":171,"requestId":"9488.1","timestamp":78247.243137}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}, {'timestamp': 1476252948094, 'level': 'INFO', 'message': '{"message":{"method":"Page.frameNavigated","params":{"frame":{"id":"9488.1","loaderId":"9488.1","mimeType":"text/plain","securityOrigin":"https://api.ipify.org","url":"https://api.ipify.org/?format=text"}}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}, {'timestamp': 1476252948095, 'level': 'INFO', 'message': '{"message":{"method":"Network.loadingFinished","params":{"encodedDataLength":171,"requestId":"9488.1","timestamp":78247.242066}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}, {'timestamp': 1476252948115, 'level': 'INFO', 'message': '{"message":{"method":"Page.loadEventFired","params":{"timestamp":78247.264169}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}, {'timestamp': 1476252948115, 'level': 'INFO', 'message': '{"message":{"method":"Page.frameStoppedLoading","params":{"frameId":"9488.1"}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}, {'timestamp': 147625298116, 'level': 'INFO', 'message': '{"message":{"method":"Page.domContentEventFired","params":{"timestamp":78247.276475}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}, {'timestamp': 1476252948122, 'level': 'INFO', 'message': '{"message":{"method":"Network.requestWillBeSent","params":{"documentURL":"https://api.ipify.org/?format=text","frameId":"9488.1","initiator":{"type":"other"},"loaderId":"9488.1","request":{"headers":{"Referer":"https://api.ipify.org/?format=text","User-Agent":"Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36"},"initialPriority":"High","method":"GET","mixedContentType":"none","url":"https://api.ipify.org/favicon.ico"},"requestId":"9488.2","timestamp":78247.280131,"type":"Other","wallTime":1476252948.11805}},"webview":"6e8a3b1d-e5aa-40fb-a695-280cbb0ee420"}'}

然后从JSON响应中获取“status”:200。你也可以解析响应的“headers”。

回答于 2025-04-16 由 Python大师

分享举报

53

这不可能。

很遗憾，Selenium 设计上并不提供这个信息。关于这个问题有很长的讨论，但简单来说就是：

Selenium 是一个浏览器模拟工具，而不一定是一个测试工具。
Selenium 在加载页面时会进行很多次 GET 和 POST 请求，如果要加一个接口来处理这些请求，会让这个工具变得复杂，而开发者并不想这样。

所以我们只能用一些变通的方法，比如：

在返回的 HTML 中查找错误信息。
使用其他工具，比如 Requests（但在 @Zeinab 的回答中可以看到这种方法的不足之处）。

回答于 2025-04-16 由 Python大师

分享举报

如何通过selenium.py获取状态码（Python代码）

14 个回答

这不可能。

撰写回答