一次 API 调用获取 Google 前 100 条结果

curl -X POST "https://api.brightdata.com/datasets/v3/trigger?dataset_id=gd_mfz5x93lmsjjjylob&include_errors=true" \
  -H "Authorization: Bearer ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d '[{
    "url": "https://www.google.com/",
    "keyword": "pizza",
    "language": "en",
    "country": "US",
    "start_page": 1,
    "end_page": 10
  }]'

import fetch from "node-fetch";

const API_KEY = process.env.API_KEY;
const DATASET_ID = "gd_mfz5x93lmsjjjylob";

const payload = [
  {
    url: "https://www.google.com/",
    keyword: "pizza",
    language: "en",
    country: "US",
    start_page: 1,
    end_page: 10,
  },
];

const res = await fetch(
  `https://api.brightdata.com/datasets/v3/trigger?dataset_id=${DATASET_ID}&include_errors=true`,
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Authorization: `Bearer ${API_KEY}`,
    },
    body: JSON.stringify(payload),
  }
);

const job = await res.json();
console.log(job); // 包含用于状态检查和下载的 snapshot_id

import os
import json
import requests

API_KEY = os.environ.get("API_KEY")
DATASET_ID = "gd_mfz5x93lmsjjjylob"

payload = [
    {
        "url": "https://www.google.com/",
        "keyword": "pizza",
        "language": "en",
        "country": "US",
        "start_page": 1,
        "end_page": 10
    }
]

res = requests.post(
    f"https://api.brightdata.com/datasets/v3/trigger?dataset_id={DATASET_ID}&include_errors=true",
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    },
    data=json.dumps(payload),
)

print(res.json())  # 包含用于状态检查的 snapshot_id

import fetch from "node-fetch";

const API_KEY = process.env.API_KEY;
const DATASET_ID = "gd_mfz5x93lmsjjjylob";

// 步骤 1：触发请求
const triggerRes = await fetch(
  `https://api.brightdata.com/datasets/v3/trigger?dataset_id=${DATASET_ID}&include_errors=true`,
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      Authorization: `Bearer ${API_KEY}`,
    },
    body: JSON.stringify([
      {
        url: "https://www.google.com/",
        keyword: "pizza",
        language: "en",
        country: "US",
        start_page: 1,
        end_page: 10,
      },
    ]),
  }
);

const { snapshot_id } = await triggerRes.json();

// 步骤 2：轮询完成状态
let progress;
do {
  await new Promise((resolve) => setTimeout(resolve, 5000)); // 等待 5 秒
  const progressRes = await fetch(
    `https://api.brightdata.com/datasets/v3/progress/${snapshot_id}`,
    {
      headers: { Authorization: `Bearer ${API_KEY}` },
    }
  );
  progress = await progressRes.json();
} while (progress.status !== "ready");

// 步骤 3：下载结果
const downloadRes = await fetch(
  `https://api.brightdata.com/datasets/v3/snapshot/${snapshot_id}?format=json`,
  {
    headers: { Authorization: `Bearer ${API_KEY}` },
  }
);

const results = await downloadRes.json();
console.log(results);

import os
import time
import requests

API_KEY = os.getenv("API_KEY")
DATASET_ID = "gd_mfz5x93lmsjjjylob"

# 步骤 1：触发请求
trigger_url = f"https://api.brightdata.com/datasets/v3/trigger?dataset_id={DATASET_ID}&include_errors=true"
trigger_response = requests.post(
    trigger_url,
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {API_KEY}",
    },
    json=[{
        "url": "https://www.google.com/",
        "keyword": "pizza",
        "language": "en",
        "country": "US",
        "start_page": 1,
        "end_page": 10,
    }],
)

snapshot_id = trigger_response.json()["snapshot_id"]

# 步骤 2：轮询完成状态
progress = None
while progress is None or progress["status"] != "ready":
    time.sleep(5)  # 等待 5 秒
    progress_url = f"https://api.brightdata.com/datasets/v3/progress/{snapshot_id}"
    progress_response = requests.get(
        progress_url,
        headers={"Authorization": f"Bearer {API_KEY}"},
    )
    progress = progress_response.json()

# 步骤 3：下载结果
download_url = f"https://api.brightdata.com/datasets/v3/snapshot/{snapshot_id}?format=json"
download_response = requests.get(
    download_url,
    headers={"Authorization": f"Bearer {API_KEY}"},
)

results = download_response.json()
print(results)