Importar conteúdo web
curl --request POST \
--url https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper \
--header 'Content-Type: application/json' \
--data '
{
"unityId": "<string>",
"datasetId": "<string>",
"folderId": "<string>",
"url": "<string>",
"limit": 123
}
'import requests
url = "https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper"
payload = {
"unityId": "<string>",
"datasetId": "<string>",
"folderId": "<string>",
"url": "<string>",
"limit": 123
}
headers = {"Content-Type": "application/json"}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({
unityId: '<string>',
datasetId: '<string>',
folderId: '<string>',
url: '<string>',
limit: 123
})
};
fetch('https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper', 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://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper",
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([
'unityId' => '<string>',
'datasetId' => '<string>',
'folderId' => '<string>',
'url' => '<string>',
'limit' => 123
]),
CURLOPT_HTTPHEADER => [
"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://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper"
payload := strings.NewReader("{\n \"unityId\": \"<string>\",\n \"datasetId\": \"<string>\",\n \"folderId\": \"<string>\",\n \"url\": \"<string>\",\n \"limit\": 123\n}")
req, _ := http.NewRequest("POST", url, payload)
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://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper")
.header("Content-Type", "application/json")
.body("{\n \"unityId\": \"<string>\",\n \"datasetId\": \"<string>\",\n \"folderId\": \"<string>\",\n \"url\": \"<string>\",\n \"limit\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n \"unityId\": \"<string>\",\n \"datasetId\": \"<string>\",\n \"folderId\": \"<string>\",\n \"url\": \"<string>\",\n \"limit\": 123\n}"
response = http.request(request)
puts response.read_body{
"message": "<string>",
"folder": {
"id": "<string>",
"name": "<string>",
"isRoot": true,
"knowLedgeBaseId": "<string>"
},
"urls": [
{}
],
"files": [
{
"id": "<string>",
"status": "<string>",
"fileName": "<string>",
"maskName": "<string>",
"url": "<string>",
"size": 123,
"extension": "<string>",
"createdAt": "<string>",
"kbFolder": {
"name": "<string>"
}
}
]
}Importar Conteúdo
Importar conteúdo web
Treine seu agente com sites da internet
POST
/
api
/
v2
/
extractor
/
upload-web-scraper
Importar conteúdo web
curl --request POST \
--url https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper \
--header 'Content-Type: application/json' \
--data '
{
"unityId": "<string>",
"datasetId": "<string>",
"folderId": "<string>",
"url": "<string>",
"limit": 123
}
'import requests
url = "https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper"
payload = {
"unityId": "<string>",
"datasetId": "<string>",
"folderId": "<string>",
"url": "<string>",
"limit": 123
}
headers = {"Content-Type": "application/json"}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': 'application/json'},
body: JSON.stringify({
unityId: '<string>',
datasetId: '<string>',
folderId: '<string>',
url: '<string>',
limit: 123
})
};
fetch('https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper', 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://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper",
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([
'unityId' => '<string>',
'datasetId' => '<string>',
'folderId' => '<string>',
'url' => '<string>',
'limit' => 123
]),
CURLOPT_HTTPHEADER => [
"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://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper"
payload := strings.NewReader("{\n \"unityId\": \"<string>\",\n \"datasetId\": \"<string>\",\n \"folderId\": \"<string>\",\n \"url\": \"<string>\",\n \"limit\": 123\n}")
req, _ := http.NewRequest("POST", url, payload)
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://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper")
.header("Content-Type", "application/json")
.body("{\n \"unityId\": \"<string>\",\n \"datasetId\": \"<string>\",\n \"folderId\": \"<string>\",\n \"url\": \"<string>\",\n \"limit\": 123\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://chat.api.toolzz.com.br/api/v2/extractor/upload-web-scraper")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n \"unityId\": \"<string>\",\n \"datasetId\": \"<string>\",\n \"folderId\": \"<string>\",\n \"url\": \"<string>\",\n \"limit\": 123\n}"
response = http.request(request)
puts response.read_body{
"message": "<string>",
"folder": {
"id": "<string>",
"name": "<string>",
"isRoot": true,
"knowLedgeBaseId": "<string>"
},
"urls": [
{}
],
"files": [
{
"id": "<string>",
"status": "<string>",
"fileName": "<string>",
"maskName": "<string>",
"url": "<string>",
"size": 123,
"extension": "<string>",
"createdAt": "<string>",
"kbFolder": {
"name": "<string>"
}
}
]
}Token de Acesso
string
Token de acesso (“Bearer” deve estar antes do token)
Descrição da requisição
Alguns sites poderão ser bloqueados e a não poderão ser usados para treinamento.
uuid
required
Identificador único da unidade associada à base de conhecimento.
uuid
required
Identificador do dataset onde o conteúdo será armazenado.
uuid
required
Identificador da pasta do dataset onde o conteúdo será armazenado.
string
required
URL da página que será processada e importada para o dataset.
number
Limite máximo de páginas ou conteúdos que serão processados a partir da URL informada.
Descrição da Resposta
Abaixo você verá a descrição da resposta da requisição após a importação de conteúdo webstring
required
Mensagem de confirmação do status da operação.
object
array
Lista das URLs que foram processadas para extração de conteúdo.
array
Lista de objetos representando os arquivos gerados a partir do conteúdo web.
Show Propriedades de cada item em files
Show Propriedades de cada item em files
string
Identificador único do arquivo gerado.
string
Estado atual do processamento (ex: PENDING, SUCCESS).
string
Nome técnico do arquivo no armazenamento interno.
string
Nome amigável ou exibido para o usuário, geralmente contendo a URL de origem.
string
Link público para acessar o conteúdo extraído.
number
Tamanho do arquivo em bytes.
string
Extensão do arquivo gerado (ex: txt).
string
Data e hora da criação do registro.