Ecommerce product monitoring

POST

batch

scrape

curl --request POST \
  --url https://apix.pline.ai/v1/batch/scrape \
  --header 'X-API-Key: <api-key>'

const options = {method: 'POST', headers: {'X-API-Key': '<api-key>'}};

fetch('https://apix.pline.ai/v1/batch/scrape', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

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

func main() {

	url := "https://apix.pline.ai/v1/batch/scrape"

	req, _ := http.NewRequest("POST", url, nil)

	req.Header.Add("X-API-Key", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

Build a price and availability feed across an entire product catalog — discover the URLs once, then re-scrape them on a schedule as structured JSON.

Use case

Competitor price monitoring across a full catalog, not just a handful of known SKUs
Availability and stock-out alerts for products you track
Feeding a pricing dashboard or repricing engine with fresh, structured data

Step 1: Discover product URLs with Map

Map returns every URL on the site with a best-effort type category — filter to product-details instead of guessing from the URL string.

curl -X POST "https://apix.pline.ai/v1/map" \
  -H "X-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://shop.example.com",
    "limit": 5000
  }'

import os
import httpx

response = httpx.post(
    "https://apix.pline.ai/v1/map",
    headers={"X-API-Key": os.environ["API_KEY"]},
    json={"url": "https://shop.example.com", "limit": 5000},
    timeout=60.0,
)
response.raise_for_status()
links = response.json()["links"]
product_urls = [link["url"] for link in links if link["type"] == "product-details"]

Step 2: Scrape every product URL as structured JSON

Hand the filtered URL list to Batch scrape with a schema so every product comes back in the same shape, regardless of page layout differences across categories.

curl -X POST "https://apix.pline.ai/v1/batch/scrape" \
  -H "X-API-Key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "urls": ["https://shop.example.com/products/1", "https://shop.example.com/products/2"],
    "output": ["json"],
    "prompt": "Extract the product name, price, currency, and whether it is in stock.",
    "schema": { "name": "string", "price": "number", "currency": "string", "in_stock": "boolean" },
    "limit": 5000
  }'

response = httpx.post(
    "https://apix.pline.ai/v1/batch/scrape",
    headers={"X-API-Key": os.environ["API_KEY"]},
    json={
        "urls": product_urls,
        "output": ["json"],
        "prompt": "Extract the product name, price, currency, and whether it is in stock.",
        "schema": {"name": "string", "price": "number", "currency": "string", "in_stock": "boolean"},
        "limit": 5000,
    },
    timeout=30.0,
)
response.raise_for_status()
job_id = response.json()["id"]

const response = await fetch("https://apix.pline.ai/v1/batch/scrape", {
  method: "POST",
  headers: {
    "X-API-Key": process.env.API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    urls: productUrls,
    output: ["json"],
    prompt: "Extract the product name, price, currency, and whether it is in stock.",
    schema: { name: "string", price: "number", currency: "string", in_stock: "boolean" },
    limit: 5000,
  }),
});

const { id } = await response.json();

Step 3: Poll for results and save a price feed

Poll the job until it finishes. With output: ["json"], s3PresignedUrls has a json download link: a JSONL file with one line per URL (url, success, status, output, error). This script reads it and writes the successful products to products.csv.

Python

import csv
import json
import os
import time

import httpx

# job_id comes from Step 2
while True:
    status = httpx.get(
        f"https://apix.pline.ai/v1/batch/scrape/{job_id}",
        headers={"X-API-Key": os.environ["API_KEY"]},
    ).json()
    if status["status"] == "completed":
        break
    if status["status"] in ("failed", "cancelled"):
        raise RuntimeError(f"Batch scrape {status['status']}: {status.get('error')}")
    time.sleep(10)

lines = httpx.get(status["s3PresignedUrls"]["json"]).text.splitlines()

products = []
for line in lines:
    item = json.loads(line)
    if not item["success"]:
        print("Failed:", item["url"], item["error"])
        continue
    data = item["output"]
    if isinstance(data, str):
        data = json.loads(data)
    products.append({"url": item["url"], **data})

with open("products.csv", "w", newline="") as f:
    writer = csv.DictWriter(f, fieldnames=["url", "name", "price", "currency", "in_stock"], extrasaction="ignore")
    writer.writeheader()
    writer.writerows(products)

print(f"Saved {len(products)} products, {len(lines) - len(products)} failed")

Load products.csv into your pricing dashboard or database. Run the whole pipeline on a schedule and keep each run’s file to build a price history.

Request highlights

Setting	Value	Why
Map `type` filter	`product-details`	Skips category pages, blog posts, and other non-product URLs
`schema`	typed product shape	Guarantees a stable shape across categories with different page layouts
Batch `limit`	matches catalog size	Caps `urls.length` and cost for a predictable run

Tips

Re-run Map periodically (weekly) to catch new products; re-run Batch scrape more often (daily or hourly) for pricing freshness on the URLs you already have.
Set a consistent tag per catalog so you can attribute cost and trace runs in Request history.
If different categories need different extraction instructions, split them into separate batch jobs instead of one prompt trying to cover every product type.

Ecommerce product monitoring

curl --request POST \
  --url https://apix.pline.ai/v1/batch/scrape \
  --header 'X-API-Key: <api-key>'

const options = {method: 'POST', headers: {'X-API-Key': '<api-key>'}};

fetch('https://apix.pline.ai/v1/batch/scrape', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

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

func main() {

	url := "https://apix.pline.ai/v1/batch/scrape"

	req, _ := http.NewRequest("POST", url, nil)

	req.Header.Add("X-API-Key", "<api-key>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

​Use case

​Step 1: Discover product URLs with Map

​Step 2: Scrape every product URL as structured JSON

​Step 3: Poll for results and save a price feed

​Request highlights

​Tips

​Related

Use case

Step 1: Discover product URLs with Map

Step 2: Scrape every product URL as structured JSON

Step 3: Poll for results and save a price feed

Request highlights

Tips

Related