Best JigsawStack Alternative for Structured Data Extraction

import os

import requests

PAGE_URL = os.environ["PAGE_URL"]  # the web page URL to extract, e.g. a pricing page

# JigsawStack: define element prompts (max 5), receive structured JSON
js_response = requests.post(
    "https://api.jigsawstack.com/v1/ai/scrape",
    headers={
        "x-api-key": os.environ["JIGSAWSTACK_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "url": PAGE_URL,
        "element_prompts": ["Plan title", "Plan price", "Plan features"],
    },
    timeout=60,
)
js_response.raise_for_status()
js_result = js_response.json()
if not js_result.get("success"):
    raise RuntimeError(f"JigsawStack scrape failed for {PAGE_URL}")

# "context" maps each element prompt to the text matched for it
structured = js_result["context"]
print(structured)

# JSON shaped by your prompts, which you define and maintain per source type

# EnConvert: one POST, clean Markdown of the page, no prompts required
ec_response = requests.post(
    "https://api.enconvert.com/v2/perceive",
    headers={
        "X-API-Key": os.environ["ENCONVERT_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "url": PAGE_URL,
        "outputs": ["markdown"],
    },
    timeout=60,
)
ec_response.raise_for_status()
perceived = ec_response.json()

# A blocked or failed read comes back without a markdown output
if perceived.get("error") or "markdown" not in perceived.get("outputs", {}):
    raise RuntimeError(
        f"Perceive failed for {PAGE_URL}: "
        f"{perceived.get('error') or perceived.get('warnings')}"
    )

# The Markdown is a signed artifact URL (valid 15 minutes). Plain GET, no API key.
markdown_response = requests.get(perceived["outputs"]["markdown"]["url"], timeout=60)
markdown_response.raise_for_status()
markdown = markdown_response.text

# No prompts or fields to define, ready to chunk and embed
print(markdown)