自定义状态码

默认情况下，只要返回 2xx 或 4xx 状态码，我们就假定请求成功。但是，有时网站会在非标准 HTTPS 状态码下返回所需内容。如果你的某个目标存在这种情况，你可以指明哪些状态码对你是可接受且有价值的。添加 X-Oxylabs-Successful-Status-Codes 头，包含所有对你有效的 HTTP 响应代码。

2xx 和 4xx 仍将自动标记为成功。

网页解锁器仅统计成功提取数据的流量。失败的爬取尝试不会包含在你的流量使用计算中。上行和下行流量都会被计算在内。

代码示例

curl -k -v -x https://unblock.oxylabs.io:60000 \
-U 'USERNAME:PASSWORD' \
'https://ip.oxylabs.io/location' \
-H 'X-Oxylabs-Successful-Status-Codes: 500,501,502,503'

import requests

# 在此使用您的 Web Unblocker 凭证。
USERNAME, PASSWORD = 'YOUR_USERNAME', 'YOUR_PASSWORD'

# 定义 proxy 字典。
proxies = {
  'http': f'http://{USERNAME}:{PASSWORD}@unblock.oxylabs.io:60000',
  'https': f'https://{USERNAME}:{PASSWORD}@unblock.oxylabs.io:60000',
}

headers = {
    'X-Oxylabs-Successful-Status-Codes': '500,501,502,503'
}

response = requests.get(
    'https://ip.oxylabs.io/location',
    verify=False,  # 需要忽略证书
    proxies=proxies,
    headers=headers,
)

# 将结果页面打印到 stdout
print(response.text)

# 将返回的 HTML 保存到 result.html 文件
with open('result.html', 'w') as f:
    f.write(response.text)

import fetch from 'node-fetch';
import { HttpsProxyAgent } from 'https-proxy-agent';

const username = 'YOUR_USERNAME';
const password = 'YOUR_PASSWORD';

const agent = new HttpsProxyAgent(
  `https://${username}:${password}@unblock.oxylabs.io:60000`
);

// 我们建议接受我们的证书，而不是允许不安全的 (http) 流量
process.env['NODE_TLS_REJECT_UNAUTHORIZED'] = 0;

const headers = {
   'X-Oxylabs-Successful-Status-Codes': '500,501,502,503',
}

const response = await fetch('https://ip.oxylabs.io/location', {
  method: 'get',
  headers: headers,
  agent: agent,
});

console.log(await response.text());

<?php
$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, 'https://ip.oxylabs.io/location');
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_PROXY, 'https://unblock.oxylabs.io:60000');
curl_setopt($ch, CURLOPT_PROXYUSERPWD, 'YOUR_USERNAME' . ':' . 'YOUR_PASSWORD');
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);

curl_setopt_array($ch, [
    CURLOPT_HTTPHEADER  => [
        'X-Oxylabs-Successful-Status-Codes: 500,501,502,503'
    ]
]);

$result = curl_exec($ch);
echo $result;

if (curl_errno($ch)) {
    echo 'Error:' . curl_error($ch);
}
curl_close($ch);

package main

import (
	"crypto/tls"
	"fmt"
	"io/ioutil"
	"net/http"
	"net/url"
)

func main() {
	const Username = "YOUR_USERNAME"
	const Password = "YOUR_PASSWORD"

	proxyUrl, _ := url.Parse(
		fmt.Sprintf(
			"https://%s:%[email protected]:60000",
			Username,
			Password,
		),
	)
	customTransport := &http.Transport{Proxy: http.ProxyURL(proxyUrl)}

	// 我们建议接受我们的证书，而不是允许不安全的 (http) 流量
	customTransport.TLSClientConfig = &tls.Config{InsecureSkipVerify: true}

	client := &http.Client{Transport: customTransport}
	request, _ := http.NewRequest("GET",
		"https://ip.oxylabs.io/location",
		nil,
	)
	
	// 添加自定义 Cookie
        request.Header.Add("X-Oxylabs-Successful-Status-Codes", "500,501,502,503")
        
	request.SetBasicAuth(Username, Password)
	response, _ := client.Do(request)

	responseText, _ := ioutil.ReadAll(response.Body)
	fmt.Println(string(responseText))
}

using System;
using System.Net;
using System.Net.Http;
using System.Threading.Tasks;

namespace OxyApi
{
    class Program
    {
        static async Task Main(string[] args)
        {
            var webProxy = new WebProxy
            {
                Address = new Uri("https://unblock.oxylabs.io:60000"),
                BypassProxyOnLocal = false,
                UseDefaultCredentials = false,

                Credentials = new NetworkCredential(
                userName: "YOUR_USERNAME",
                password: "YOUR_PASSWORD"
                )
            };

            var httpClientHandler = new HttpClientHandler
            {
                Proxy = webProxy,
            };

            // 我们建议接受我们的证书，而不是允许不安全的 (http) 流量
            httpClientHandler.ClientCertificateOptions = ClientCertificateOption.Manual;
            httpClientHandler.ServerCertificateCustomValidationCallback =
                (httpRequestMessage, cert, cetChain, policyErrors) =>
                {
                    return true;
                };


            var client = new HttpClient(handler: httpClientHandler, disposeHandler: true);
            
            // 添加自定义 Cookie
            client.DefaultRequestHeaders.Add("X-Oxylabs-Successful-Status-Codes", "500,501,502,503");
            
            Uri baseUri = new Uri("https://ip.oxylabs.io/location");
            client.BaseAddress = baseUri;

            var requestMessage = new HttpRequestMessage(HttpMethod.Get, "");

            var response = await client.SendAsync(requestMessage);
            var contents = await response.Content.ReadAsStringAsync();

            Console.WriteLine(contents);
        }
    }
}

package org.example;

import org.apache.hc.client5.http.auth.AuthScope;
import org.apache.hc.client5.http.auth.CredentialsProvider;
import org.apache.hc.client5.http.classic.methods.HttpGet;
import org.apache.hc.client5.http.config.RequestConfig;
import org.apache.hc.client5.http.impl.auth.CredentialsProviderBuilder;
import org.apache.hc.client5.http.impl.classic.CloseableHttpClient;
import org.apache.hc.client5.http.impl.classic.HttpClients;
import org.apache.hc.client5.http.impl.io.PoolingHttpClientConnectionManagerBuilder;
import org.apache.hc.client5.http.ssl.NoopHostnameVerifier;
import org.apache.hc.client5.http.ssl.SSLConnectionSocketFactoryBuilder;
import org.apache.hc.client5.http.ssl.TrustAllStrategy;
import org.apache.hc.core5.http.HttpHost;
import org.apache.hc.core5.http.io.entity.EntityUtils;
import org.apache.hc.core5.http.message.StatusLine;
import org.apache.hc.core5.ssl.SSLContextBuilder;

import java.util.Arrays;
import java.util.Properties;


public class Main {

    public static void main(final String[] args)throws Exception {
        final CredentialsProvider credsProvider = CredentialsProviderBuilder.create()
                .add(new AuthScope("unblock.oxylabs.io", 60000), "USERNAME", "PASSWORD".toCharArray())
                .build();
        final HttpHost target = new HttpHost("https", "ip.oxylabs.io", 443);
        final HttpHost proxy = new HttpHost("https", "unblock.oxylabs.io", 60000);
        try (final CloseableHttpClient httpclient = HttpClients.custom()
                .setDefaultCredentialsProvider(credsProvider)
                .setProxy(proxy)
                // 我们建议接受我们的证书，而不是允许不安全的 (http) 流量
                .setConnectionManager(PoolingHttpClientConnectionManagerBuilder.create()
                        .setSSLSocketFactory(SSLConnectionSocketFactoryBuilder.create()
                                .setSslContext(SSLContextBuilder.create()
                                        .loadTrustMaterial(TrustAllStrategy.INSTANCE)
                                        .build())
                                .setHostnameVerifier(NoopHostnameVerifier.INSTANCE)
                                .build())
                        .build())
                .build()) {

            final RequestConfig config = RequestConfig.custom()
                    .build();
            final HttpGet request = new HttpGet("/location");
            request.addHeader("X-Oxylabs-Successful-Status-Codes","500,501,502,503");
            request.setConfig(config);

            System.out.println("Executing request " + request.getMethod() + " " + request.getUri() +
                    " via " + proxy + " headers: " + Arrays.toString(request.getHeaders()));

            httpclient.execute(target, request, response -> {
                System.out.println("----------------------------------------");
                System.out.println(request + "->" + new StatusLine(response));
                EntityUtils.consume(response.getEntity());
                return null;
            });
        }
    }
}

上一页请求头与 Cookie 下一页POST 请求

最后更新于1年前

这有帮助吗？

早上好

代码示例