抓取单个页面并以 markdown 返回其正文内容。
curl --request POST \
--url https://api.aisa.one/apis/v1/firecrawl/scrape \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"url": "https://docs.firecrawl.dev",
"proxy": "basic",
"formats": [
"markdown"
]
}
'import requests
url = "https://api.aisa.one/apis/v1/firecrawl/scrape"
payload = {
"url": "https://docs.firecrawl.dev",
"proxy": "basic",
"formats": ["markdown"]
}
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://docs.firecrawl.dev', proxy: 'basic', formats: ['markdown']})
};
fetch('https://api.aisa.one/apis/v1/firecrawl/scrape', 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.aisa.one/apis/v1/firecrawl/scrape",
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://docs.firecrawl.dev',
'proxy' => 'basic',
'formats' => [
'markdown'
]
]),
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.aisa.one/apis/v1/firecrawl/scrape"
payload := strings.NewReader("{\n \"url\": \"https://docs.firecrawl.dev\",\n \"proxy\": \"basic\",\n \"formats\": [\n \"markdown\"\n ]\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.aisa.one/apis/v1/firecrawl/scrape")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://docs.firecrawl.dev\",\n \"proxy\": \"basic\",\n \"formats\": [\n \"markdown\"\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.aisa.one/apis/v1/firecrawl/scrape")
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 \"url\": \"https://docs.firecrawl.dev\",\n \"proxy\": \"basic\",\n \"formats\": [\n \"markdown\"\n ]\n}"
response = http.request(request)
puts response.read_body{
"success": true,
"data": {
"markdown": "<string>",
"metadata": {
"title": "<string>",
"description": "<string>",
"sourceURL": "<string>",
"statusCode": 123
}
},
"creditsUsed": 123
}搜索 API
Firecrawl 抓取
抓取一个 URL,返回它的正文 markdown。
POST
https://api.aisa.one/apis/v1
/
firecrawl
/
scrape
抓取单个页面并以 markdown 返回其正文内容。
curl --request POST \
--url https://api.aisa.one/apis/v1/firecrawl/scrape \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"url": "https://docs.firecrawl.dev",
"proxy": "basic",
"formats": [
"markdown"
]
}
'import requests
url = "https://api.aisa.one/apis/v1/firecrawl/scrape"
payload = {
"url": "https://docs.firecrawl.dev",
"proxy": "basic",
"formats": ["markdown"]
}
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://docs.firecrawl.dev', proxy: 'basic', formats: ['markdown']})
};
fetch('https://api.aisa.one/apis/v1/firecrawl/scrape', 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.aisa.one/apis/v1/firecrawl/scrape",
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://docs.firecrawl.dev',
'proxy' => 'basic',
'formats' => [
'markdown'
]
]),
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.aisa.one/apis/v1/firecrawl/scrape"
payload := strings.NewReader("{\n \"url\": \"https://docs.firecrawl.dev\",\n \"proxy\": \"basic\",\n \"formats\": [\n \"markdown\"\n ]\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.aisa.one/apis/v1/firecrawl/scrape")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"https://docs.firecrawl.dev\",\n \"proxy\": \"basic\",\n \"formats\": [\n \"markdown\"\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.aisa.one/apis/v1/firecrawl/scrape")
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 \"url\": \"https://docs.firecrawl.dev\",\n \"proxy\": \"basic\",\n \"formats\": [\n \"markdown\"\n ]\n}"
response = http.request(request)
puts response.read_body{
"success": true,
"data": {
"markdown": "<string>",
"metadata": {
"title": "<string>",
"description": "<string>",
"sourceURL": "<string>",
"statusCode": 123
}
},
"creditsUsed": 123
}抓取一个 URL,返回它的正文 markdown。
url 和 proxy 都必填 —— 计量档位下 proxy 必须是 basic —— formats 选择输出格式。返回 success 和 data,其中 markdown 是正文,metadata 是一大坨页面元信息(og: 与 twitter: 标签、statusCode、sourceURL、language)。实测抓 1 个页面约 10 秒。⚠️ URL 必须是 HTTPS,且不能指向 PDF,两者都是直接拒绝而不是尽力而为。有 URL 又要正文时用它。多个 URL 一起处理用 post_firecrawl_batch_scrape(后台任务),少量且要立刻拿到用 post_tavily_extract(同步)。要先找出 URL,用 post_firecrawl_map。授权
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
请求体
application/json