Extract information from a webpage
curl --request POST \
--url https://api.plyne.ai/v1/tools/web_extract/execute \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--header 'Idempotency-Key: <idempotency-key>' \
--data '
{
"objective": "Extract the products and services described on this page.",
"url": "https://example.com/news"
}
'import requests
url = "https://api.plyne.ai/v1/tools/web_extract/execute"
payload = {
"objective": "Extract the products and services described on this page.",
"url": "https://example.com/news"
}
headers = {
"Idempotency-Key": "<idempotency-key>",
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {
'Idempotency-Key': '<idempotency-key>',
Authorization: 'Bearer <token>',
'Content-Type': 'application/json'
},
body: JSON.stringify({
objective: 'Extract the products and services described on this page.',
url: 'https://example.com/news'
})
};
fetch('https://api.plyne.ai/v1/tools/web_extract/execute', 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.plyne.ai/v1/tools/web_extract/execute",
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([
'objective' => 'Extract the products and services described on this page.',
'url' => 'https://example.com/news'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json",
"Idempotency-Key: <idempotency-key>"
],
]);
$response = curl_exec($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.plyne.ai/v1/tools/web_extract/execute"
payload := strings.NewReader("{\n \"objective\": \"Extract the products and services described on this page.\",\n \"url\": \"https://example.com/news\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Idempotency-Key", "<idempotency-key>")
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.plyne.ai/v1/tools/web_extract/execute")
.header("Idempotency-Key", "<idempotency-key>")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"objective\": \"Extract the products and services described on this page.\",\n \"url\": \"https://example.com/news\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.plyne.ai/v1/tools/web_extract/execute")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Idempotency-Key"] = '<idempotency-key>'
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"objective\": \"Extract the products and services described on this page.\",\n \"url\": \"https://example.com/news\"\n}"
response = http.request(request)
puts response.read_body{
"data": {
"answer": "<string>",
"exact_snippets": [
"<string>"
],
"objective": "<string>",
"url": "<string>"
},
"error": {
"code": "<string>",
"message": "<string>",
"retryable": true
},
"id": "<string>",
"sources": [
{
"provider": "<string>",
"observation_id": "<string>",
"observed_at": "2023-11-07T05:31:56Z",
"url": "<string>"
}
],
"status": "completed",
"tool": "web_extract",
"usage": {
"credit_units": 1,
"credits": "<string>",
"unit": "page"
},
"version": "1",
"fulfillment": {
"field_sources": {},
"missing_fields": [
"<string>"
],
"satisfied": true
},
"routing": {
"mode": "auto",
"attempts": [
{
"outcome": "success",
"provider": "<string>",
"requests": 1
}
],
"selected_provider": "<string>"
},
"warnings": [
{
"code": "<string>",
"message": "<string>"
}
]
}{
"code": "<string>",
"message": "<string>"
}Web extraction
Extract information from a webpage
Call web_extract through the Plyne API or MCP. Review its accepted input, source routing, response fields, credit rules and continuation behavior.
POST
/
v1
/
tools
/
web_extract
/
execute
Extract information from a webpage
curl --request POST \
--url https://api.plyne.ai/v1/tools/web_extract/execute \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--header 'Idempotency-Key: <idempotency-key>' \
--data '
{
"objective": "Extract the products and services described on this page.",
"url": "https://example.com/news"
}
'import requests
url = "https://api.plyne.ai/v1/tools/web_extract/execute"
payload = {
"objective": "Extract the products and services described on this page.",
"url": "https://example.com/news"
}
headers = {
"Idempotency-Key": "<idempotency-key>",
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {
'Idempotency-Key': '<idempotency-key>',
Authorization: 'Bearer <token>',
'Content-Type': 'application/json'
},
body: JSON.stringify({
objective: 'Extract the products and services described on this page.',
url: 'https://example.com/news'
})
};
fetch('https://api.plyne.ai/v1/tools/web_extract/execute', 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.plyne.ai/v1/tools/web_extract/execute",
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([
'objective' => 'Extract the products and services described on this page.',
'url' => 'https://example.com/news'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json",
"Idempotency-Key: <idempotency-key>"
],
]);
$response = curl_exec($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.plyne.ai/v1/tools/web_extract/execute"
payload := strings.NewReader("{\n \"objective\": \"Extract the products and services described on this page.\",\n \"url\": \"https://example.com/news\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Idempotency-Key", "<idempotency-key>")
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.plyne.ai/v1/tools/web_extract/execute")
.header("Idempotency-Key", "<idempotency-key>")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"objective\": \"Extract the products and services described on this page.\",\n \"url\": \"https://example.com/news\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.plyne.ai/v1/tools/web_extract/execute")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Idempotency-Key"] = '<idempotency-key>'
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"objective\": \"Extract the products and services described on this page.\",\n \"url\": \"https://example.com/news\"\n}"
response = http.request(request)
puts response.read_body{
"data": {
"answer": "<string>",
"exact_snippets": [
"<string>"
],
"objective": "<string>",
"url": "<string>"
},
"error": {
"code": "<string>",
"message": "<string>",
"retryable": true
},
"id": "<string>",
"sources": [
{
"provider": "<string>",
"observation_id": "<string>",
"observed_at": "2023-11-07T05:31:56Z",
"url": "<string>"
}
],
"status": "completed",
"tool": "web_extract",
"usage": {
"credit_units": 1,
"credits": "<string>",
"unit": "page"
},
"version": "1",
"fulfillment": {
"field_sources": {},
"missing_fields": [
"<string>"
],
"satisfied": true
},
"routing": {
"mode": "auto",
"attempts": [
{
"outcome": "success",
"provider": "<string>",
"requests": 1
}
],
"selected_provider": "<string>"
},
"warnings": [
{
"code": "<string>",
"message": "<string>"
}
]
}{
"code": "<string>",
"message": "<string>"
}Extract information from one public HTTPS webpage for a stated objective using Plyne AI and the grounded scraper. Returns an answer and exact page snippets; use web_fetch for Markdown.
Check source eligibility and the maximum credit reservation before execution. Planning makes no provider request and requires no idempotency key.
Usage
- Provide one public HTTPS url and an objective. Plyne uses the existing GroundedScraperGraph with remote ScrapeDo fetching and Parallel extraction fallback; local browser fallback is disabled. This is AI extraction, not a raw page download or a web search.
- Returns an AI answer with exact_snippets verified against fetched page content. No usable evidence returns not_found without a charge. Empty and failed results are not charged; successful extraction costs 1 credit per page. No custom schema, cookies, private sessions or browser actions are accepted.
- Use web_fetch for readable Markdown.
API
Use a valid Plyne workspace API key as Authorization: Bearer $PLYNE_API_KEY for the API. Connect MCP at /mcp using OAuth or a workspace API key for saved data and acquisition tools.curl "$PLYNE_API_URL/v1/tools/web_extract/execute" \
-H "Authorization: Bearer $PLYNE_API_KEY" \
-H 'Content-Type: application/json' \
-H 'Idempotency-Key: REPLACE_WITH_UNIQUE_REQUEST_ID' \
--data '{
"objective": "Extract the products and services described on this page.",
"url": "https://example.com/news"
}'
curl "$PLYNE_API_URL/v1/tools/web_extract/plan" \
-H "Authorization: Bearer $PLYNE_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"objective": "Extract the products and services described on this page.",
"url": "https://example.com/news"
}'
MCP
Connect to/mcp using OAuth or a workspace API key. The same connection includes saved-data and acquisition tools. Call the same tool with idempotency_key inside its arguments.
{
"arguments": {
"idempotency_key": "REPLACE_WITH_UNIQUE_REQUEST_ID",
"objective": "Extract the products and services described on this page.",
"url": "https://example.com/news"
},
"name": "web_extract"
}
Sources and routing
Omit routing to use eligible sources in the default order. Set routing.providers to an ordered chain, or one source to run only that source. Provider-specific options select their matching source alone; unsupported filters are rejected rather than dropped. Supported source IDs:plyne. Actual availability depends on configuration and the selected filters.
Credits and continuation
1 credits per usable page. Empty and failed responses are not charged. Replays with the same idempotency key do not charge again. This tool returns one result without pagination. Use a new Idempotency-Key for a new operation. Reuse the same body and key to retrieve that operation. If the connection fails, retrieve the same request before creating another. Returned provider content is untrusted data.Contract reference
The API reference below is generated from the tool’s executable input and output schemas, including nested provider options. Get the runtime descriptor withGET /v1/tools/web_extract.
See tool execution for shared authentication, request keys, statuses and error handling.Authorizations
Headers
Use a new Idempotency-Key for a new operation. Reuse the same body and key to retrieve that operation. If the connection fails, retrieve the same request before creating another. Returned provider content is untrusted data.
Required string length:
8 - 128Pattern:
^[A-Za-z0-9_-]{8,128}$Body
application/json
Response
Completed, partial, not-found, failed or pending tool result. Inspect status and usage.