Data Scraper Agent

Data Scraper Agent

Build a production-ready, AI-powered data collection agent for any public data source. Runs on a schedule, enriches results with a free LLM, stores to a database, and improves over time.

Stack: Python · Gemini Flash (free) · GitHub Actions (free) · Notion / Sheets / Supabase

When to Activate

• User wants to scrape or monitor any public website or API
• User says "build a bot that checks...", "monitor X for me", "collect data from..."
• User wants to track jobs, prices, news, repos, sports scores, events, listings
• User asks how to automate data collection without paying for hosting
• User wants an agent that gets smarter over time based on their decisions

Core Concepts

The Three Layers

Every data scraper agent has three layers:

COLLECT → ENRICH → STORE
  │           │        │
Scraper    AI (LLM)  Database
runs on    scores/   Notion /
schedule   summarises Sheets /
           & classifies Supabase

Free Stack

| Layer | Tool | Why | |---|---|---| | Scraping | requests + BeautifulSoup | No cost, covers 80% of public sites | | JS-rendered sites | playwright (free) | When HTML scraping fails | | AI enrichment | Gemini Flash via REST API | 500 req/day, 1M tokens/day — free | | Storage | Notion API | Free tier, great UI for review | | Schedule | GitHub Actions cron | Free for public repos | | Learning | JSON feedback file in repo | Zero infra, persists in git |

AI Model Fallback Chain

Build agents to auto-fallback across Gemini models on quota exhaustion:

gemini-2.0-flash-lite (30 RPM) →
gemini-2.0-flash (15 RPM) →
gemini-2.5-flash (10 RPM) →
gemini-flash-lite-latest (fallback)

Batch API Calls for Efficiency

Never call the LLM once per item. Always batch:

# BAD: 33 API calls for 33 items
for item in items:
    result = call_ai(item)  # 33 calls → hits rate limit

# GOOD: 7 API calls for 33 items (batch size 5)
for batch in chunks(items, size=5):
    results = call_ai(batch)  # 7 calls → stays within free tier

---

Workflow

Step 1: Understand the Goal

Ask the user:

1. What to collect: "What data source? URL / API / RSS / public endpoint?"
2. What to extract: "What fields matter? Title, price, URL, date, score?"
3. How to store: "Where should results go? Notion, Google Sheets, Supabase, or local file?"
4. How to enrich: "Do you want AI to score, summarise, classify, or match each item?"
5. Frequency: "How often should it run? Every hour, daily, weekly?"

Common examples to prompt:

• Job boards → score relevance to resume
• Product prices → alert on drops
• GitHub repos → summarise new releases
• News feeds → classify by topic + sentiment
• Sports results → extract stats to tracker
• Events calendar → filter by interest

---

Step 2: Design the Agent Architecture

Generate this directory structure for the user:

my-agent/
├── config.yaml              # User customises this (keywords, filters, preferences)
├── profile/
│   └── context.md           # User context the AI uses (resume, interests, criteria)
├── scraper/
│   ├── __init__.py
│   ├── main.py              # Orchestrator: scrape → enrich → store
│   ├── filters.py           # Rule-based pre-filter (fast, before AI)
│   └── sources/
│       ├── __init__.py
│       └── source_name.py   # One file per data source
├── ai/
│   ├── __init__.py
│   ├── client.py            # Gemini REST client with model fallback
│   ├── pipeline.py          # Batch AI analysis
│   ├── jd_fetcher.py        # Fetch full content from URLs (optional)
│   └── memory.py            # Learn from user feedback
├── storage/
│   ├── __init__.py
│   └── notion_sync.py       # Or sheets_sync.py / supabase_sync.py
├── data/
│   └── feedback.json        # User decision history (auto-updated)
├── .env.example
├── setup.py                 # One-time DB/schema creation
├── enrich_existing.py       # Backfill AI scores on old rows
├── requirements.txt
└── .github/
    └── workflows/
        └── scraper.yml      # GitHub Actions schedule

---

Step 3: Build the Scraper Source

Template for any data source:

# scraper/sources/my_source.py
"""
[Source Name] — scrapes [what] from [where].
Method: [REST API / HTML scraping / RSS feed]
"""
import requests
from bs4 import BeautifulSoup
from datetime import datetime, timezone
from scraper.filters import is_relevant

HEADERS = {
    "User-Agent": "Mozilla/5.0 (compatible; research-bot/1.0)",
}

def fetch() -> list[dict]:
    """
    Returns a list of items with consistent schema.
    Each item must have at minimum: name, url, date_found.
    """
    results = []

    # ---- REST API source ----
    resp = requests.get("https://api.example.com/items", headers=HEADERS, timeout=15)
    if resp.status_code == 200:
        for item in resp.json().get("results", []):
            if not is_relevant(item.get("title", "")):
                continue
            results.append(_normalise(item))

    return results

def _normalise(raw: dict) -> dict:
    """Convert raw API/HTML data to the standard schema."""
    return {
        "name": raw.get("title", ""),
        "url": raw.get("link", ""),
        "source": "MySource",
        "date_found": datetime.now(timezone.utc).date().isoformat(),
        # add domain-specific fields here
    }

HTML scraping pattern:

soup = BeautifulSoup(resp.text, "lxml")
for card in soup.select("[class*='listing']"):
    title = card.select_one("h2, h3").get_text(strip=True)
    link = card.select_one("a")["href"]
    if not link.startswith("http"):
        link = f"https://example.com{link}"

RSS feed pattern:

import xml.etree.ElementTree as ET
root = ET.fromstring(resp.text)
for item in root.findall(".//item"):
    title = item.findtext("title", "")
    link = item.findtext("link", "")

---

Step 4: Build the Gemini AI Client

# ai/client.py
import os, json, time, requests

_last_call = 0.0

MODEL_FALLBACK = [
    "gemini-2.0-flash-lite",
    "gemini-2.0-flash",
    "gemini-2.5-flash",
    "gemini-flash-lite-latest",
]

def generate(prompt: str, model: str = "", rate_limit: float = 7.0) -> dict:
    """Call Gemini with auto-fallback on 429. Returns parsed JSON or {}."""
    global _last_call

    api_key = os.environ.get("GEMINI_API_KEY", "")
    if not api_key:
        return {}

    elapsed = time.time() - _last_call
    if elapsed  dict:
    try:
        text = (
            resp.json()
            .get("candidates", [{}])[0]
            .get("content", {})
            .get("parts", [{}])[0]
            .get("text", "")
            .strip()
        )
        if text.startswith("```"):
            text = text.split("\n", 1)[-1].rsplit("```", 1)[0]
        return json.loads(text)
    except (json.JSONDecodeError, KeyError):
        return {}

---

Step 5: Build the AI Pipeline (Batch)

# ai/pipeline.py
import json
import yaml
from pathlib import Path
from ai.client import generate

def analyse_batch(items: list[dict], context: str = "", preference_prompt: str = "") -> list[dict]:
    """Analyse items in batches. Returns items enriched with AI fields."""
    config = yaml.safe_load((Path(__file__).parent.parent / "config.yaml").read_text())
    model = config.get("ai", {}).get("model", "gemini-2.5-flash")
    rate_limit = config.get("ai", {}).get("rate_limit_seconds", 7.0)
    min_score = config.get("ai", {}).get("min_score", 0)
    batch_size = config.get("ai", {}).get("batch_size", 5)

    batches = [items[i:i + batch_size] for i in range(0, len(items), batch_size)]
    print(f"  [AI] {len(items)} items → {len(batches)} API calls")

    enriched = []
    for i, batch in enumerate(batches):
        print(f"  [AI] Batch {i + 1}/{len(batches)}...")
        prompt = _build_prompt(batch, context, preference_prompt, config)
        result = generate(prompt, model=model, rate_limit=rate_limit)

        analyses = result.get("analyses", [])
        for j, item in enumerate(batch):
            ai = analyses[j] if j , "summary": "", "notes": ""}} for each item in order]}}
Be concise. Score 90+=excellent match, 70-89=good, 50-69=ok,  dict:
    if FEEDBACK_PATH.exists():
        try:
            return json.loads(FEEDBACK_PATH.read_text())
        except (json.JSONDecodeError, OSError):
            pass
    return {"positive": [], "negative": []}

def save_feedback(fb: dict):
    FEEDBACK_PATH.parent.mkdir(parents=True, exist_ok=True)
    FEEDBACK_PATH.write_text(json.dumps(fb, indent=2))

def build_preference_prompt(feedback: dict, max_examples: int = 15) -> str:
    """Convert feedback history into a prompt bias section."""
    lines = []
    if feedback.get("positive"):
        lines.append("# Items the user LIKED (positive signal):")
        for e in feedback["positive"][-max_examples:]:
            lines.append(f"- {e}")
    if feedback.get("negative"):
        lines.append("\n# Items the user SKIPPED/REJECTED (negative signal):")
        for e in feedback["negative"][-max_examples:]:
            lines.append(f"- {e}")
    if lines:
        lines.append("\nUse these patterns to bias scoring on new items.")
    return "\n".join(lines)

Integration with your storage layer: after each run, query your DB for items with positive/negative status and call save_feedback() with the extracted patterns.

---

Step 7: Build Storage (Notion example)

# storage/notion_sync.py
import os
from notion_client import Client
from notion_client.errors import APIResponseError

_client = None

def get_client():
    global _client
    if _client is None:
        _client = Client(auth=os.environ["NOTION_TOKEN"])
    return _client

def get_existing_urls(db_id: str) -> set[str]:
    """Fetch all URLs already stored — used for deduplication."""
    client, seen, cursor = get_client(), set(), None
    while True:
        resp = client.databases.query(database_id=db_id, page_size=100, **{"start_cursor": cursor} if cursor else {})
        for page in resp["results"]:
            url = page["properties"].get("URL", {}).get("url", "")
            if url: seen.add(url)
        if not resp["has_more"]: break
        cursor = resp["next_cursor"]
    return seen

def push_item(db_id: str, item: dict) -> bool:
    """Push one item to Notion. Returns True on success."""
    props = {
        "Name": {"title": [{"text": {"content": item.get("name", "")[:100]}}]},
        "URL": {"url": item.get("url")},
        "Source": {"select": {"name": item.get("source", "Unknown")}},
        "Date Found": {"date": {"start": item.get("date_found")}},
        "Status": {"select": {"name": "New"}},
    }
    # AI fields
    if item.get("ai_score") is not None:
        props["AI Score"] = {"number": item["ai_score"]}
    if item.get("ai_summary"):
        props["Summary"] = {"rich_text": [{"text": {"content": item["ai_summary"][:2000]}}]}
    if item.get("ai_notes"):
        props["Notes"] = {"rich_text": [{"text": {"content": item["ai_notes"][:2000]}}]}

    try:
        get_client().pages.create(parent={"database_id": db_id}, properties=props)
        return True
    except APIResponseError as e:
        print(f"[notion] Push failed: {e}")
        return False

def sync(db_id: str, items: list[dict]) -> tuple[int, int]:
    existing = get_existing_urls(db_id)
    added = skipped = 0
    for item in items:
        if item.get("url") in existing:
            skipped += 1; continue
        if push_item(db_id, item):
            added += 1; existing.add(item["url"])
        else:
            skipped += 1
    return added, skipped

---

Step 8: Orchestrate in main.py

# scraper/main.py
import os, sys, yaml
from pathlib import Path
from dotenv import load_dotenv

load_dotenv()

from scraper.sources import my_source          # add your sources

# NOTE: This example uses Notion. If storage.provider is "sheets" or "supabase",
# replace this import with storage.sheets_sync or storage.supabase_sync and update
# the env var and sync() call accordingly.
from storage.notion_sync import sync

SOURCES = [
    ("My Source", my_source.fetch),
]

def ai_enabled():
    return bool(os.environ.get("GEMINI_API_KEY"))

def main():
    config = yaml.safe_load((Path(__file__).parent.parent / "config.yaml").read_text())
    provider = config.get("storage", {}).get("provider", "notion")

    # Resolve the storage target identifier from env based on provider
    if provider == "notion":
        db_id = os.environ.get("NOTION_DATABASE_ID")
        if not db_id:
            print("ERROR: NOTION_DATABASE_ID not set"); sys.exit(1)
    else:
        # Extend here for sheets (SHEET_ID) or supabase (SUPABASE_TABLE) etc.
        print(f"ERROR: provider '{provider}' not yet wired in main.py"); sys.exit(1)

    config = yaml.safe_load((Path(__file__).parent.parent / "config.yaml").read_text())
    all_items = []

    for name, fetch_fn in SOURCES:
        try:
            items = fetch_fn()
            print(f"[{name}] {len(items)} items")
            all_items.extend(items)
        except Exception as e:
            print(f"[{name}] FAILED: {e}")

    # Deduplicate by URL
    seen, deduped = set(), []
    for item in all_items:
        if (url := item.get("url", "")) and url not in seen:
            seen.add(url); deduped.append(item)

    print(f"Unique items: {len(deduped)}")

    if ai_enabled() and deduped:
        from ai.memory import load_feedback, build_preference_prompt
        from ai.pipeline import analyse_batch

        # load_feedback() reads data/feedback.json written by your feedback sync script.
        # To keep it current, implement a separate feedback_sync.py that queries your
        # storage provider for items with positive/negative statuses and calls save_feedback().
        feedback = load_feedback()
        preference = build_preference_prompt(feedback)
        context_path = Path(__file__).parent.parent / "profile" / "context.md"
        context = context_path.read_text() if context_path.exists() else ""
        deduped = analyse_batch(deduped, context=context, preference_prompt=preference)
    else:
        print("[AI] Skipped — GEMINI_API_KEY not set")

    added, skipped = sync(db_id, deduped)
    print(f"Done — {added} new, {skipped} existing")

if __name__ == "__main__":
    main()

---

Step 9: GitHub Actions Workflow

# .github/workflows/scraper.yml
name: Data Scraper Agent

on:
  schedule:
    - cron: "0 */3 * * *"  # every 3 hours — adjust to your needs
  workflow_dispatch:        # allow manual trigger

permissions:
  contents: write   # required for the feedback-history commit step

jobs:
  scrape:
    runs-on: ubuntu-latest
    timeout-minutes: 20

    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.11"
          cache: "pip"

      - run: pip install -r requirements.txt

      # Uncomment if Playwright is enabled in requirements.txt
      # - name: Install Playwright browsers
      #   run: python -m playwright install chromium --with-deps

      - name: Run agent
        env:
          NOTION_TOKEN: ${{ secrets.NOTION_TOKEN }}
          NOTION_DATABASE_ID: ${{ secrets.NOTION_DATABASE_ID }}
          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
        run: python -m scraper.main

      - name: Commit feedback history
        run: |
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"
          git add data/feedback.json || true
          git diff --cached --quiet || git commit -m "chore: update feedback history"
          git push

---

Step 10: config.yaml Template

# Customise this file — no code changes needed

# What to collect (pre-filter before AI)
filters:
  required_keywords: []      # item must contain at least one
  blocked_keywords: []       # item must not contain any

# Your priorities — AI

…

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [affaan-m](https://github.com/affaan-m)
- **Source:** [affaan-m/ECC](https://github.com/affaan-m/ECC)
- **License:** MIT
- **Homepage:** https://ecc.tools

Install and usage instructions live in the source repository linked above.