入门

阅读快速入门指南以获得简单的 Web Unblocker 使用体验。

集成 网页解锁器 很容易，尤其是如果你之前使用过常规的代理用于网页爬取。唯一的不同是我们要求你使用 -k 或 --insecure cURL 标志（或你所选语言中的等价表达）。

要使用网页解锁器发起请求，你需要使用 unblock.oxylabs.io:60000 代理端点。见下面的 cURL 示例。你可以在其他语言中找到代码示例这里或在我们的 GitHub.

使用 ip.oxylabs.io/location 来检查你 IP 的参数——该域名提供来自四个地理定位数据库的信息：MaxMind、IP2Location、DB-IP 和 IPinfo.io。参数包括 IP 地址、提供商、国家、城市、邮政编码、ASN、组织名称、时区以及元信息（当数据库披露时）。

curl -k -x https://unblock.oxylabs.io:60000 \
-U 'USERNAME:PASSWORD' \
'https://ip.oxylabs.io/location'

import requests

# 在此使用你的网页解锁器凭据。
USERNAME, PASSWORD = 'YOUR_USERNAME', 'YOUR_PASSWORD'

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

response = requests.request(
    'GET',
    'https://ip.oxylabs.io/location',
    verify=False,  # 忽略 SSL 证书
    proxies=proxies,
)

# 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`
);

// 忽略证书
process.env['NODE_TLS_REJECT_UNAUTHORIZED'] = 0;

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

$result = curl_exec($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)}

	// 忽略证书
	customTransport.TLSClientConfig = &tls.Config{InsecureSkipVerify: true}

	client := &http.Client{Transport: customTransport}
	request, _ := http.NewRequest("GET",
		"https://ip.oxylabs.io/location",
		nil,
	)

	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,
            };

            // 忽略证书
            httpClientHandler.ClientCertificateOptions = ClientCertificateOption.Manual;
            httpClientHandler.ServerCertificateCustomValidationCallback =
                (httpRequestMessage, cert, cetChain, policyErrors) =>
                {
                    return true;
                };


            var client = new HttpClient(handler: httpClientHandler, disposeHandler: true);

            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.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;
            });
        }
    }
}

如果你观察到成功率低或检索到空内容，请尝试在请求中添加额外的 "x-oxylabs-render: html" 头部。

如果网页解锁器用于抓取依赖通过 JavaScript 加载数据的网站，请参考 JavaScript 渲染 部分。该产品并不设计为直接与无头浏览器（例如 Chromium、PhantomJS、Splash 等）及其驱动（例如 Playwright、Selenium、Puppeteer 等）一起使用。

观看下面的视频，了解在不被封锁的情况下抓取困难目标的示例：

课程

如果你想了解更多关于使用大规模获取数据的内容， 网页解锁器 - 我们建议观看本次 Scraping Experts 的课程：

Bypassing Sophisticated Anti-Bot Systemsexperts.oxylabs.io

最后更新于1个月前

这有帮助吗？

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.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; }); } } }

晚安

hashtag课程

课程