Map（映射）

POST /map

基于选项对多个 URL 进行映射

cURL

curl --request POST \
  --url https://api.firecrawl.dev/v2/map \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "ignoreCache": false,
  "ignoreQueryParameters": true,
  "includeSubdomains": true,
  "limit": 5000,
  "location": {
    "country": "US",
    "languages": [
      "en-US"
    ]
  },
  "search": "<string>",
  "sitemap": "include",
  "timeout": 60000,
  "url": "<string>"
}
'

import requests

url = "https://api.firecrawl.dev/v2/map"

payload = {
    "ignoreCache": False,
    "ignoreQueryParameters": True,
    "includeSubdomains": True,
    "limit": 5000,
    "location": {
        "country": "US",
        "languages": ["en-US"]
    },
    "search": "<string>",
    "sitemap": "include",
    "timeout": 60000,
    "url": "<string>"
}
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({
    ignoreCache: false,
    ignoreQueryParameters: true,
    includeSubdomains: true,
    limit: 5000,
    location: {country: 'US', languages: ['en-US']},
    search: '<string>',
    sitemap: 'include',
    timeout: 60000,
    url: '<string>'
  })
};

fetch('https://api.firecrawl.dev/v2/map', 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://api.firecrawl.dev/v2/map",
  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([
    'ignoreCache' => false,
    'ignoreQueryParameters' => true,
    'includeSubdomains' => true,
    'limit' => 5000,
    'location' => [
        'country' => 'US',
        'languages' => [
                'en-US'
        ]
    ],
    'search' => '<string>',
    'sitemap' => 'include',
    'timeout' => 60000,
    'url' => '<string>'
  ]),
  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;
}

package main

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

func main() {

	url := "https://api.firecrawl.dev/v2/map"

	payload := strings.NewReader("{\n  \"ignoreCache\": false,\n  \"ignoreQueryParameters\": true,\n  \"includeSubdomains\": true,\n  \"limit\": 5000,\n  \"location\": {\n    \"country\": \"US\",\n    \"languages\": [\n      \"en-US\"\n    ]\n  },\n  \"search\": \"<string>\",\n  \"sitemap\": \"include\",\n  \"timeout\": 60000,\n  \"url\": \"<string>\"\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))

}

HttpResponse<String> response = Unirest.post("https://api.firecrawl.dev/v2/map")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"ignoreCache\": false,\n  \"ignoreQueryParameters\": true,\n  \"includeSubdomains\": true,\n  \"limit\": 5000,\n  \"location\": {\n    \"country\": \"US\",\n    \"languages\": [\n      \"en-US\"\n    ]\n  },\n  \"search\": \"<string>\",\n  \"sitemap\": \"include\",\n  \"timeout\": 60000,\n  \"url\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.firecrawl.dev/v2/map")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"ignoreCache\": false,\n  \"ignoreQueryParameters\": true,\n  \"includeSubdomains\": true,\n  \"limit\": 5000,\n  \"location\": {\n    \"country\": \"US\",\n    \"languages\": [\n      \"en-US\"\n    ]\n  },\n  \"search\": \"<string>\",\n  \"sitemap\": \"include\",\n  \"timeout\": 60000,\n  \"url\": \"<string>\"\n}"

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

200

{
  "links": [
    {
      "url": "<string>",
      "description": "<string>",
      "title": "<string>"
    }
  ],
  "success": true
}

{
  "error": "Payment required to access this resource."
}

{
  "error": "Request rate limit exceeded. Please wait and try again later."
}

{
  "error": "An unexpected error occurred on the server."
}

您是需要 Firecrawl API 密钥的 AI 代理吗？请参见 firecrawl.dev/agent-onboarding/SKILL.md 了解自动化入门说明。

授权

Authorization · string · header · 必填

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

请求体

application/json

url · string<uri> · 必填

用于开始爬取的起始 URL

ignoreCache · boolean · 默认值: false

跳过站点地图缓存以获取最新的 URL。站点地图数据最多会被缓存 7 天；如果你刚更新了站点地图，请使用该参数。

ignoreQueryParameters · boolean · 默认值: true

不要返回包含查询参数的 URL

includeSubdomains · boolean · 默认值: true

包含此网站的子域名

limit · integer · 默认值: 5000

返回的最大链接数量

必填范围: x <= 100000

location · object

请求的地域设置。指定后，如果有可用代理，将使用相应代理，并模拟对应的语言和时区设置。若未指定，则默认为“US”。

Show child attributes

search · string

指定搜索查询，以按相关性对结果排序。示例：使用“blog”将返回在 URL 中包含单词“blog”的网址，并按相关性排序。

sitemap · enum<string> · 默认值: include

用于映射（mapping）时的 sitemap 模式。若设置为 skip，则不会使用 sitemap 来发现 URL。若设置为 only，则只会返回出现在 sitemap 中的 URL。默认值为 include，此时会同时使用 sitemap 和其他方式来发现 URL。

可用选项: skip, include, only

timeout · integer

以毫秒为单位的超时时间。默认情况下不设置超时。

响应

200

application/json

成功响应

links · object[]

Show child attributes

success · boolean