History

from scrapegraph_py import ScrapeGraphAI

# reads SGAI_API_KEY from env, or pass explicitly: ScrapeGraphAI(api_key="...")
sgai = ScrapeGraphAI()

# List recent scrape calls
page = sgai.history.list(service="scrape", limit=5)
for entry in page.data.data:
    print(entry.id, entry.service, entry.status, entry.elapsed_ms)

# Fetch one entry, including the full result
one = sgai.history.get("9701fc04-23de-4684-a48f-7e8fa287550b")
if one.status == "success":
    print(one.data.result)

import { ScrapeGraphAI } from "scrapegraph-js";

const sgai = ScrapeGraphAI();

// List recent scrape calls
const list = await sgai.history.list({ service: "scrape", limit: 5 });
if (list.status === "success") {
  for (const entry of list.data?.data ?? []) {
    console.log(entry.id, entry.service, entry.status);
  }
}

// Fetch one entry, including the full result
const one = await sgai.history.get("9701fc04-23de-4684-a48f-7e8fa287550b");
if (one.status === "success") {
  console.log(one.data?.result);
}

# List
curl -X GET "https://v2-api.scrapegraphai.com/api/history?service=scrape&sessionId=import&limit=5" \
  -H "SGAI-APIKEY: $SGAI_API_KEY"

# Get one
curl -X GET https://v2-api.scrapegraphai.com/api/history/9701fc04-23de-4684-a48f-7e8fa287550b \
  -H "SGAI-APIKEY: $SGAI_API_KEY"

import time
from scrapegraph_py import ScrapeGraphAI, MarkdownFormatConfig

sgai = ScrapeGraphAI()

start = sgai.crawl.start(
    "https://scrapegraphai.com/",
    formats=[MarkdownFormatConfig()],
    max_pages=5,
    max_depth=2,
)
crawl_id = start.data.id

while True:
    time.sleep(2)
    status = sgai.crawl.get(crawl_id)
    if status.data.status in ("completed", "failed"):
        break

# Pull the formatted content for every completed page
for page in status.data.pages:
    if page.status != "completed":
        continue
    entry = sgai.history.get(page.scrape_ref_id)
    md = entry.data.result.results.get("markdown", {}).get("data", [None])[0]
    print(page.url, "->", md[:80] if md else "(empty)")

import { ScrapeGraphAI } from "scrapegraph-js";

const sgai = ScrapeGraphAI();

const start = await sgai.crawl.start({
  url: "https://scrapegraphai.com/",
  formats: [{ type: "markdown" }],
  maxPages: 5,
  maxDepth: 2,
});
const crawlId = start.data.id;

let status = start.data.status;
let pages = [];
while (status === "running") {
  await new Promise((r) => setTimeout(r, 2000));
  const res = await sgai.crawl.get(crawlId);
  status = res.data.status;
  pages = res.data.pages;
}

for (const page of pages) {
  if (page.status !== "completed") continue;
  const entry = await sgai.history.get(page.scrapeRefId);
  const md = entry.data?.result?.results?.markdown?.data?.[0];
  console.log(page.url, "->", md?.slice(0, 80) ?? "(empty)");
}