自定义解析器 (Custom Parser)

查看 Oxylabs 自定义解析器的快速入门步骤。

自定义解析器是一个免费的网页爬虫API 功能，可让你 创建解析和数据处理逻辑 这些逻辑在原始 HTML 结果上执行。你可以使用 AI 自动生成解析器，或在高级场景中手动编写它们。

有关详细说明和示例，请参阅以下页面：

快速开始通过 API 生成解析器解析器预设

手动编写指令解析函数列表

快速开始

1. 生成解析器

我们建议从我们由 AI 驱动的 OxyCopilot 工具开始，该工具允许你在不编写任何代码的情况下生成爬虫和解析器。

要访问 OxyCopilot，请登录左侧菜单中的 Oxylabs 仪表板 并选择 Scraper APIs Playground 。

按照视频中展示的步骤来 生成解析器:

以下是视频中展示的相同步骤：

输入你想要抓取和解析的 URL（或多个 URL）
指定任何参数 例如 JavaScript 渲染
编写一个提示 描述你想要解析的内容
运行 OxyCopilot

当你对生成的解析器满意后，加载指令。

2. 将解析器保存为预设

你可以通过 OxyCopilot 轻松保存生成的解析器以便日后使用。参见以下步骤：

将预设分配 到特定的 API 用户
点击 保存 (Save)
输入预设名称 以及描述（可选）

保存预设后，你可以在 API 请求中使用它。

3. 在 API 请求中使用解析器

要在网页爬虫API 中使用你的预设，请发送包含 parser_preset 参数且其值为你的预设名称的请求载荷。在下面的代码示例中，我们重用之前步骤中创建的 example_parser 预设。

curl 'https://realtime.oxylabs.io/v1/queries' \
--user 'USERNAME:PASSWORD' \
-H 'Content-Type: application/json' \
-d '{
        "source": "universal",
        "url": "https://example.com/",
        "parse": true,
        "parser_preset": "example_parser"
    }'

import requests
from pprint import pprint


# 设置要使用的解析器预设。
payload = {
    'source': 'universal',
    'url': 'https://example.com/',
    'parse': True,
    'parser_preset': 'example_parser'
}

# 获取响应。
response = requests.request(
    'POST',
    'https://realtime.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    json=payload
)

# 将美化后的响应打印到标准输出。
pprint(response.json())

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "universal",
    url: "https://example.com/",
    parse: true,
    parser_preset: "example_parser"
};

const options = {
    hostname: "realtime.oxylabs.io",
    path: "/v1/queries",
    method: "POST",
    headers: {
        "Content-Type": "application/json",
        Authorization:
            "Basic " + Buffer.from(`${username}:${password}`).toString("base64"),
    },
};

const request = https.request(options, (response) => {
    let data = "";

    response.on("data", (chunk) => {
        data += chunk;
    });

    response.on("end", () => {
        const responseData = JSON.parse(data);
        console.log(JSON.stringify(responseData, null, 2));
    });
});

request.on("error", (error) => {
    console.error("Error:", error);
});

request.write(JSON.stringify(body));
request.end();

# 您提交的整个字符串必须进行 URL 编码。

https://realtime.oxylabs.io/v1/queries?source=universal&url=https%3A%2F%2Fexample.com%2F&parse=true&parser_preset=example_parser&access_token=12345abcde

<?php

$params = array(
    'source' => 'universal',
    'url' => 'https://example.com/',
    'parse' => true,
    'parser_preset' => 'example_parser'
);

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, "https://realtime.oxylabs.io/v1/queries");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($params));
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_USERPWD, "USERNAME" . ":" . "PASSWORD");

$headers = array();
$headers[] = "Content-Type: application/json";
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

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

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

package main

import (
	"bytes"
	"encoding/json"
	"fmt"
	"io/ioutil"
	"net/http"
)

func main() {
	const Username = "USERNAME"
	const Password = "PASSWORD"

	payload := map[string]interface{}{
		"source": "universal",
		"url": "https://example.com/",
		"parse": true,
		"parser_preset": "example_parser",
	}

	jsonValue, _ := json.Marshal(payload)

	client := &http.Client{}
	request, _ := http.NewRequest("POST",
		"https://realtime.oxylabs.io/v1/queries",
		bytes.NewBuffer(jsonValue),
	)

	request.SetBasicAuth(Username, Password)
	response, _ := client.Do(request)

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

using System;
using System.Collections.Generic;
using System.Net.Http;
using System.Net.Http.Json;
using System.Threading.Tasks;

namespace OxyApi
{
    class Program
    {
        static async Task Main()
        {
            const string Username = "USERNAME";
            const string Password = "PASSWORD";

            var parameters = new {
                source = "universal",
                url = "https://example.com/",
                parse = true,
                parser_preset = "example_parser"
            };

            var client = new HttpClient();

            Uri baseUri = new Uri("https://realtime.oxylabs.io");
            client.BaseAddress = baseUri;

            var requestMessage = new HttpRequestMessage(HttpMethod.Post, "/v1/queries");
            requestMessage.Content = JsonContent.Create(parameters);

            var authenticationString = $"{Username}:{Password}";
            var base64EncodedAuthenticationString = Convert.ToBase64String(System.Text.ASCIIEncoding.UTF8.GetBytes(authenticationString));
            requestMessage.Headers.Add("Authorization", "Basic " + base64EncodedAuthenticationString);

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

            Console.WriteLine(contents);
        }
    }
}

package org.example;

import okhttp3.*;
import org.json.JSONObject;
import java.util.concurrent.TimeUnit;

public class Main implements Runnable {
    private static final String AUTHORIZATION_HEADER = "Authorization";
    public static final String USERNAME = "USERNAME";
    public static final String PASSWORD = "PASSWORD";

    public void run() {
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "universal");
        jsonObject.put("url", "https://example.com/");
        jsonObject.put("parse", true);
        jsonObject.put("parser_preset", "example_parser");

        Authenticator authenticator = (route, response) -> {
            String credential = Credentials.basic(USERNAME, PASSWORD);
            return response
                    .request()
                    .newBuilder()
                    .header(AUTHORIZATION_HEADER, credential)
                    .build();
        };

        var client = new OkHttpClient.Builder()
                .authenticator(authenticator)
                .readTimeout(180, TimeUnit.SECONDS)
                .build();

        var mediaType = MediaType.parse("application/json; charset=utf-8");
        var body = RequestBody.create(jsonObject.toString(), mediaType);
        var request = new Request.Builder()
                .url("https://realtime.oxylabs.io/v1/queries")
                .post(body)
                .build();

        try (var response = client.newCall(request).execute()) {
            if (response.body() != null) {
                try (var responseBody = response.body()) {
                    System.out.println(responseBody.string());
                }
            }
        } catch (Exception exception) {
            System.out.println("Error: " + exception.getMessage());
        }

        System.exit(0);
    }

    public static void main(String[] args) {
        new Thread(new Main()).start();
    }
}

输出示例

{
  "results": [
    {
      "content": {
        "title": "Example Domain",
        "parse_status_code": 12000
      },
      "created_at": "2025-10-24 10:04:59",
      "updated_at": "2025-10-24 10:05:00",
      "page": 1,
      "url": "https://example.com/",
      "job_id": "7387428891226308609",
      "is_render_forced": false,
      "status_code": 200,
      "type": "parsed",
      "parser_type": "preset",
      "parser_preset": "example_parser"
    }
  ]
}

获取已解析任务的 HTML 内容

你也可以通过在结果检索 URL 末尾添加 ?type=raw 来检索原始 HTML 结果。阅读更多此处.

最后更新于1个月前

这有帮助吗？

早上好

快速开始

1. 生成解析器

2. 将解析器保存为预设

3. 在 API 请求中使用解析器

获取已解析任务的 HTML 内容