Start a Batch job from a CSV file

import time
import requests

BASE = "https://async.api.zenrows.com/v1"
headers = {"X-API-Key": "YOUR_ZENROWS_API_KEY"}

# 1. Create an upload slot and map your CSV columns
slot = requests.post(
    f"{BASE}/job_inputs",
    headers=headers,
    json={
        "type": "csv",
        "csv": {"header": True, "fields": {"url": "product_url", "external_id": "sku"}},
    },
    timeout=60,
).json()

# 2. Upload the file to the presigned URL, with the headers the slot gives you
with open("products.csv", "rb") as f:
    upload = requests.put(slot["upload"]["url"], headers=slot["upload"]["headers"], data=f, timeout=120)
upload.raise_for_status()

# 3. Create the job from the uploaded file
job = requests.post(
    f"{BASE}/jobs",
    headers=headers,
    json={
        "type": "regular",
        "status": "closed",
        "file_input_id": slot["file_input_id"],
        "zenrows_params": {"mode": "auto", "response_type": "markdown"},
    },
    timeout=60,
)
job.raise_for_status()
job_id = job.json()["job_id"]
print("Submitted", job_id)

# 4. Wait for the run to finish
while True:
    run = requests.get(f"{BASE}/jobs/{job_id}", headers=headers, timeout=60).json()["latest_run"]
    if run["status"] in {"completed", "failed", "stopped"}:
        break
    time.sleep(5)
print(run["status"], run["stats"])

# 5. Each result carries the external_id from your sku column
cursor = None
while True:
    page = requests.get(
        f"{BASE}/jobs/{job_id}/results",
        headers=headers,
        params={"status": "all", "cursor": cursor},
        timeout=60,
    ).json()
    for row in page["results"]:
        print(row["external_id"], row["status"], row["url"])
    cursor = page.get("next_cursor")
    if not cursor:
        break

import { readFile } from "node:fs/promises";

const BASE = "https://async.api.zenrows.com/v1";
const headers = { "X-API-Key": "YOUR_ZENROWS_API_KEY", "Content-Type": "application/json" };

async function api(method, path, body) {
  const res = await fetch(`${BASE}${path}`, { method, headers, body: body && JSON.stringify(body) });
  if (!res.ok) throw new Error(`${res.status}: ${await res.text()}`);
  return res.json();
}

// 1. Create an upload slot and map your CSV columns
const slot = await api("POST", "/job_inputs", {
  type: "csv",
  csv: { header: true, fields: { url: "product_url", external_id: "sku" } },
});

// 2. Upload the file to the presigned URL, with the headers the slot gives you
const upload = await fetch(slot.upload.url, {
  method: slot.upload.method,
  headers: slot.upload.headers,
  body: await readFile("products.csv"),
});
if (!upload.ok) throw new Error(`Upload failed: ${upload.status}`);

// 3. Create the job from the uploaded file
const { job_id } = await api("POST", "/jobs", {
  type: "regular",
  status: "closed",
  file_input_id: slot.file_input_id,
  zenrows_params: { mode: "auto", response_type: "markdown" },
});
console.log("Submitted", job_id);

// 4. Wait for the run to finish
let run;
do {
  await new Promise((r) => setTimeout(r, 5000));
  ({ latest_run: run } = await api("GET", `/jobs/${job_id}`));
} while (!["completed", "failed", "stopped"].includes(run.status));
console.log(run.status, run.stats);

// 5. Each result carries the external_id from your sku column
let cursor;
do {
  const query = new URLSearchParams({ status: "all", ...(cursor && { cursor }) });
  const page = await api("GET", `/jobs/${job_id}/results?${query}`);
  for (const row of page.results) console.log(row.external_id, row.status, row.url);
  cursor = page.next_cursor;
} while (cursor);

# 1. Create an upload slot and map your CSV columns
slot=$(curl -s -X POST "https://async.api.zenrows.com/v1/job_inputs" \
  -H "X-API-Key: YOUR_ZENROWS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "type": "csv", "csv": { "header": true, "fields": { "url": "product_url", "external_id": "sku" } } }')

# 2. Upload the file to the presigned URL, with the Content-Type from upload.headers
curl -s -X PUT "$(echo "$slot" | jq -r '.upload.url')" \
  -H "Content-Type: $(echo "$slot" | jq -r '.upload.headers["Content-Type"]')" \
  --data-binary @products.csv

# 3. Create the job from the uploaded file
curl -s -X POST "https://async.api.zenrows.com/v1/jobs" \
  -H "X-API-Key: YOUR_ZENROWS_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"type\": \"regular\",
    \"status\": \"closed\",
    \"file_input_id\": \"$(echo "$slot" | jq -r '.file_input_id')\",
    \"zenrows_params\": { \"mode\": \"auto\", \"response_type\": \"markdown\" }
  }"

# pip install zenrows
from zenrows import ZenRowsBatchClient

client = ZenRowsBatchClient(api_key="YOUR_ZENROWS_API_KEY")

# Upload the CSV and map its columns; returns the file_input_id
file_input_id = client.upload_csv(
    "products.csv",
    header=True,
    fields={"url": "product_url", "external_id": "sku"},
)

job = client.submit_regular(
    file_input_id=file_input_id,
    zenrows_params={"mode": "auto", "response_type": "markdown"},
)
run = job.run.wait(timeout=900)
print(f"{run.stats.successful}/{run.stats.total} pages scraped")

saved = run.download_to_dir("./pages", use_external_id=True)
print(f"Saved {saved} files to ./pages")

// npm install zenrows
import { readFile } from "node:fs/promises";
import { ZenRowsBatchClient } from "zenrows";

const client = new ZenRowsBatchClient("YOUR_ZENROWS_API_KEY");

// Upload the CSV and map its columns; returns the file_input_id
const fileInputId = await client.uploadCsv(await readFile("products.csv"), {
  header: true,
  fields: { url: "product_url", external_id: "sku" },
});

const job = await client.submitRegular(undefined, fileInputId, {
  zenrowsParams: { mode: "auto", response_type: "markdown" },
});
const run = await job.run.wait();
console.log(`${run.stats.successful}/${run.stats.total} pages scraped`);

const saved = await run.downloadToDir("./pages", { useExternalId: true });
console.log(`Saved ${saved} files to ./pages`);