Baidu News

curl --request GET \
  --url https://scrapebadger.com/v1/baidu/news \
  --header 'X-API-Key: <x-api-key>'

const options = {method: 'GET', headers: {'X-API-Key': '<x-api-key>'}};

fetch('https://scrapebadger.com/v1/baidu/news', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://scrapebadger.com/v1/baidu/news",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "X-API-Key: <x-api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://scrapebadger.com/v1/baidu/news"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("X-API-Key", "<x-api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://scrapebadger.com/v1/baidu/news")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["X-API-Key"] = '<x-api-key>'

response = http.request(request)
puts response.read_body

{
  "query": "<string>",
  "page": 123,
  "total_results": 123,
  "url": "<string>",
  "results": [
    {
      "position": 123,
      "title": "<string>",
      "url": "<string>",
      "baidu_url": "<string>",
      "snippet": "<string>",
      "source": "<string>",
      "date": "<string>",
      "date_at": "<string>",
      "thumbnail": "<string>"
    }
  ]
}

GET

baidu

news

Baidu News

curl --request GET \
  --url https://scrapebadger.com/v1/baidu/news \
  --header 'X-API-Key: <x-api-key>'

const options = {method: 'GET', headers: {'X-API-Key': '<x-api-key>'}};

fetch('https://scrapebadger.com/v1/baidu/news', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://scrapebadger.com/v1/baidu/news",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "X-API-Key: <x-api-key>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://scrapebadger.com/v1/baidu/news"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("X-API-Key", "<x-api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://scrapebadger.com/v1/baidu/news")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["X-API-Key"] = '<x-api-key>'

response = http.request(request)
puts response.read_body

{
  "query": "<string>",
  "page": 123,
  "total_results": 123,
  "url": "<string>",
  "results": [
    {
      "position": 123,
      "title": "<string>",
      "url": "<string>",
      "baidu_url": "<string>",
      "snippet": "<string>",
      "source": "<string>",
      "date": "<string>",
      "date_at": "<string>",
      "thumbnail": "<string>"
    }
  ]
}

Search Baidu’s news vertical. Articles carry the publisher name, the publish date in both Baidu’s raw form and ISO 8601, and the real article URL — not a baidu.com redirect. Credits: 5

Authorization

string

required

Your ScrapeBadger API key.

Query Parameters

string

required

Search keywords, e.g. 人工智能. URL-encode as UTF-8.

integer

default:"1"

Result page, 1–76. Fixed at 10 articles per page — the news vertical has no page-size parameter.

string

default:"relevance"

Result ordering. relevance (Baidu’s default ranking) or time (most recent first).

Response

string

Echo of the requested query.

integer

The page returned.

integer

Baidu’s own reported total, when it renders one. null otherwise.

string

The baidu.com URL that was fetched.

NewsResult[]

Articles on this page.

Show NewsResult

integer

1-based rank on the page.

string

Article headline.

string

The real article URL.

string

Baidu’s tracking redirect, when the article carries one.

string

Article excerpt.

string

Publisher name, e.g. 新华网, 微信公众平台.

string

Baidu’s own date string, e.g. 2026年8月1日 or 3小时前.

string

ISO 8601 date (YYYY-MM-DD), set only when date is unambiguous.

string

Article image URL, when present.

Only position, title, query and page are guaranteed present. Every other field is nullable — Baidu’s news cards vary by publisher.

Example

curl "https://scrapebadger.com/v1/baidu/news?query=%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD&sort=time" \
  -H "X-API-Key: YOUR_API_KEY"

const res = await fetch(
  "https://scrapebadger.com/v1/baidu/news?" +
    new URLSearchParams({ query: "人工智能", sort: "time" }),
  { headers: { "X-API-Key": process.env.SCRAPEBADGER_API_KEY } },
);
const data = await res.json();

import requests

res = requests.get(
    "https://scrapebadger.com/v1/baidu/news",
    headers={"X-API-Key": "YOUR_API_KEY"},
    params={"query": "人工智能", "sort": "time"},
)
data = res.json()

Response

{
  "query": "人工智能",
  "page": 1,
  "total_results": null,
  "results": [
    {
      "position": 1,
      "title": "以科学了解咖啡的秘密",
      "url": "http://www.jgj.moa.gov.cn/kptd/202012/t20201207_6357680.htm",
      "baidu_url": null,
      "snippet": "咖啡是用经过烘焙的咖啡豆制作冲泡的饮料,与可可、茶并称为世界三大饮料,是流行于世界的主要饮品。",
      "source": "农产品质量安全监管司",
      "date": "2020年12月25日",
      "date_at": "2020-12-25",
      "thumbnail": null
    },
    {
      "position": 2,
      "title": "咖啡知识 | 咖啡知识大全",
      "url": "https://mp.weixin.qq.com/s?__biz=MzA5MzI2MzYyMQ==&mid=2247503901&idx=5",
      "baidu_url": null,
      "snippet": "豆是咖啡树果实中的种子,它们会经过采摘、干燥、烘焙等处理过程,最终被磨成粉用于冲泡咖啡...",
      "source": "微信公众平台",
      "date": "2024年8月15日",
      "date_at": "2024-08-15",
      "thumbnail": "https://t9.baidu.com/it/u=546988488,560360434&fm=217&app=126"
    }
  ],
  "url": "https://www.baidu.com/s?tn=news&word=%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD&ie=utf-8"
}

Sorting for monitoring

For a news monitor, poll with sort=time and stop at the first article you have already seen. Deduplicate on url (the real article URL), not on title — Chinese outlets syndicate the same headline across many domains, and on baidu_url, which is per-impression and changes between requests.

sort=time orders by Baidu’s own index date. Freshly indexed older articles can appear above newer ones, so date_at is the field to trust when you need a real chronology.

Errors

Status	Meaning
`422`	Anti-bot challenge — not billed. Retry; it succeeds.
`502`	Baidu returned a page without the result container. Retry.

​Authorization

​Query Parameters

​Response

​Example

​Sorting for monitoring

​Errors

Authorization

Query Parameters

Response

Example

Sorting for monitoring

Errors