Extract
Perform advanced AI scraping to extract data from any website. Search all subdomains and combine scraped data with search results.
Code Examples
const options = {
method: 'POST',
headers: {'content-type': 'application/json', authorization: 'Bearer <TOKEN>'},
body: JSON.stringify({
config: {environment: 'production'},
pipes: [
{
pipe_id: 'website:extract:firecrawl@1',
config: {
extraction_prompt: 'Extract the company mission as well as the latest news.',
enable_full_domain_crawl: true,
enable_web_search: true,
json_schema: {
type: 'object',
required: ['company_mission', 'latest_news'],
properties: {company_mission: {type: 'string'}, latest_news: {type: 'string'}}
}
}
}
],
input: [{id: '1', company_website_url: 'Pipe0'}]
})
};
fetch('https://api.pipe0.com/v1/pipes/run', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://api.pipe0.com/v1/pipes/run"
payload = {
"config": { "environment": "production" },
"pipes": [
{
"pipe_id": "website:extract:firecrawl@1",
"config": {
"extraction_prompt": "Extract the company mission as well as the latest news.",
"enable_full_domain_crawl": True,
"enable_web_search": True,
"json_schema": {
"type": "object",
"required": ["company_mission", "latest_news"],
"properties": {
"company_mission": { "type": "string" },
"latest_news": { "type": "string" }
}
}
}
}
],
"input": [
{
"id": "1",
"company_website_url": "Pipe0"
}
]
}
headers = {
"content-type": "application/json",
"authorization": "Bearer <TOKEN>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)curl --request POST \
--url https://api.pipe0.com/v1/pipes/run \
--header 'authorization: Bearer <TOKEN>' \
--header 'content-type: application/json' \
--data '
{
"config": {
"environment": "production"
},
"pipes": [
{
"pipe_id": "website:extract:firecrawl@1",
"config": {
"extraction_prompt": "Extract the company mission as well as the latest news.",
"enable_full_domain_crawl": true,
"enable_web_search": true,
"json_schema": {
"type": "object",
"required": [
"company_mission",
"latest_news"
],
"properties": {
"company_mission": {
"type": "string"
},
"latest_news": {
"type": "string"
}
}
}
}
}
],
"input": [
{
"id": "1",
"company_website_url": "Pipe0"
}
]
}
'package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.pipe0.com/v1/pipes/run"
payload := strings.NewReader("{\"config\":{\"environment\":\"production\"},\"pipes\":[{\"pipe_id\":\"website:extract:firecrawl@1\",\"config\":{\"extraction_prompt\":\"Extract the company mission as well as the latest news.\",\"enable_full_domain_crawl\":true,\"enable_web_search\":true,\"json_schema\":{\"type\":\"object\",\"required\":[\"company_mission\",\"latest_news\"],\"properties\":{\"company_mission\":{\"type\":\"string\"},\"latest_news\":{\"type\":\"string\"}}}}}],\"input\":[{\"id\":\"1\",\"company_website_url\":\"Pipe0\"}]}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("content-type", "application/json")
req.Header.Add("authorization", "Bearer <TOKEN>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}<?php
require_once('vendor/autoload.php');
$client = new \GuzzleHttp\Client();
$response = $client->request('POST', 'https://api.pipe0.com/v1/pipes/run', [
'body' => '{"config":{"environment":"production"},"pipes":[{"pipe_id":"website:extract:firecrawl@1","config":{"extraction_prompt":"Extract the company mission as well as the latest news.","enable_full_domain_crawl":true,"enable_web_search":true,"json_schema":{"type":"object","required":["company_mission","latest_news"],"properties":{"company_mission":{"type":"string"},"latest_news":{"type":"string"}}}}}],"input":[{"id":"1","company_website_url":"Pipe0"}]}',
'headers' => [
'authorization' => 'Bearer <TOKEN>',
'content-type' => 'application/json',
],
]);
echo $response->getBody();POST /v1/pipes/run HTTP/1.1
Content-Type: application/json
Authorization: Bearer <TOKEN>
Host: api.pipe0.com
Content-Length: 448
{"config":{"environment":"production"},"pipes":[{"pipe_id":"website:extract:firecrawl@1","config":{"extraction_prompt":"Extract the company mission as well as the latest news.","enable_full_domain_crawl":true,"enable_web_search":true,"json_schema":{"type":"object","required":["company_mission","latest_news"],"properties":{"company_mission":{"type":"string"},"latest_news":{"type":"string"}}}}}],"input":[{"id":"1","company_website_url":"Pipe0"}]}