网页阅读

读取并解析指定 URL 的网页内容，可选择返回格式、支持控制缓存、图片保留与摘要选项等。点击 Try it 按钮可快速试用。

POST /paas/v4/reader

网页阅读

cURL

curl --request POST \
  --url https://open.bigmodel.cn/api/paas/v4/reader \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "https://www.example.com"
}
'

import requests

url = "https://open.bigmodel.cn/api/paas/v4/reader"

payload = { "url": "https://www.example.com" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({url: 'https://www.example.com'})
};

fetch('https://open.bigmodel.cn/api/paas/v4/reader', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

HttpResponse<String> response = Unirest.post("https://open.bigmodel.cn/api/paas/v4/reader")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"https://www.example.com\"\n}")
  .asString();

package main

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

func main() {

	url := "https://open.bigmodel.cn/api/paas/v4/reader"

	payload := strings.NewReader("{\n  \"url\": \"https://www.example.com\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://open.bigmodel.cn/api/paas/v4/reader",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'url' => 'https://www.example.com'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

200

{
  "id": "<string>",
  "created": 123,
  "request_id": "<string>",
  "model": "<string>",
  "reader_result": {
    "content": "<string>",
    "description": "<string>",
    "title": "<string>",
    "url": "<string>",
    "external": {
      "stylesheet": {}
    },
    "metadata": {
      "keywords": "<string>",
      "viewport": "<string>",
      "description": "<string>",
      "format-detection": "<string>"
    }
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>"
  }
}

Authorizations

Authorization · string · header · required

标准的 HTTP Bearer 认证方式，在 API Keys 页面获取密钥。

Body

application/json

url · string · required

需要抓取的url

timeout · integer · default: 20

请求超时时间（秒），默认值 20

no_cache · boolean · default: false

是否禁用缓存（true/false），默认值 false

return_format · string · default: markdown

返回格式（如：markdown、text等），默认值 markdown

retain_images · boolean · default: true

是否保留图片（true/false），默认值 true

no_gfm · boolean · default: false

是否禁用 GitHub Flavored Markdown（true/false），默认值 false

keep_img_data_url · boolean · default: false

是否保留图片数据 URL（true/false），默认值 false

with_images_summary · boolean · default: false

是否包含图片摘要（true/false），默认值 false

with_links_summary · boolean · default: false

是否包含链接摘要（true/false），默认值 false

Response

200

application/json

业务处理成功

id · string

任务 ID

created · integer<int64>

请求创建时间，是以秒为单位的 Unix 时间戳

request_id · string

由用户端传递，需要唯一；用于区分每次请求的唯一标识符。如果用户端未提供，平台将默认生成。

model · string

模型编码

reader_result · object

网页阅读结果

Show child attributes