A Practical List of Annoying Click Tasks—and How to Automate Them with Python

from pathlib import Path
import shutil
import logging

logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(message)s")

DOWNLOADS = Path.home() / "Downloads"
CATEGORIES = {
    "Images": [".jpg", ".jpeg", ".png", ".gif", ".webp"],
    "Documents": [".pdf", ".doc", ".docx", ".txt"],
    "Archives": [".zip", ".tar", ".gz", ".rar"],
    "Code": [".py", ".js", ".ts", ".json", ".yaml", ".yml"],
}

def main():
    for file in DOWNLOADS.iterdir():
        if not file.is_file():
            continue
        
        ext = file.suffix.lower()
        for category, extensions in CATEGORIES.items():
            if ext in extensions:
                dest_dir = DOWNLOADS / category
                dest_dir.mkdir(exist_ok=True)
                dest = dest_dir / file.name
                
                # Handle duplicates
                counter = 1
                while dest.exists():
                    stem = file.stem
                    dest = dest_dir / f"{stem}_{counter}{file.suffix}"
                    counter += 1
                
                shutil.move(str(file), str(dest))
                logging.info(f"Moved {file.name} → {category}/")
                break

if __name__ == "__main__":
    main()

import httpx
from selectolax.parser import HTMLParser
from pathlib import Path
import json
from datetime import datetime

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

def scrape_hn_top() -> list[dict]:
    resp = httpx.get("https://news.ycombinator.com", headers=HEADERS, timeout=10)
    resp.raise_for_status()
    
    tree = HTMLParser(resp.text)
    items = []
    
    for row in tree.css("tr.athing"):
        title_node = row.css_first("span.titleline > a")
        if not title_node:
            continue
        items.append({
            "title": title_node.text(),
            "url": title_node.attributes.get("href", ""),
        })
    
    return items

def main():
    items = scrape_hn_top()
    output = Path(f"hn_{datetime.now().strftime('%Y-%m-%d')}.json")
    output.write_text(json.dumps(items, indent=2))
    print(f"Saved {len(items)} items → {output}")

if __name__ == "__main__":
    main()

from playwright.async_api import async_playwright
import asyncio

async def scrape_dynamic(url: str) -> str:
    async with async_playwright() as p:
        browser = await p.chromium.launch(headless=True)
        page = await browser.new_page()
        await page.goto(url, wait_until="networkidle")
        content = await page.content()
        await browser.close()
    return content

import pdfplumber
from pathlib import Path
import csv

def extract_tables_from_pdf(pdf_path: Path) -> list[list[str]]:
    """Extract all tables from a PDF into a flat list of rows."""
    all_rows: list[list[str]] = []
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            for table in page.extract_tables():
                all_rows.extend(table)
    return all_rows

def process_invoices(input_dir: Path, output_csv: Path) -> None:
    rows: list[list[str]] = []
    for pdf in sorted(input_dir.glob("invoice_*.pdf")):
        extracted = extract_tables_from_pdf(pdf)
        rows.extend(extracted)

    with output_csv.open("w", newline="") as f:
        writer = csv.writer(f)
        writer.writerows(rows)

    print(f"Processed {len(list(input_dir.glob('*.pdf')))} PDFs → {output_csv}")

import httpx
import time
import random
import logging

log = logging.getLogger(__name__)

def poll_until_done(job_id: str, api_key: str, max_retries: int = 10) -> dict:
    """Poll a job endpoint until status is 'done' or 'failed'."""
    base_url = f"https://api.example.com/jobs/{job_id}"
    headers = {"Authorization": f"Bearer {api_key}"}
    
    for attempt in range(max_retries):
        try:
            resp = httpx.get(base_url, headers=headers, timeout=15)
            resp.raise_for_status()
            data = resp.json()
            
            if data["status"] == "done":
                return data
            if data["status"] == "failed":
                raise RuntimeError(f"Job {job_id} failed: {data.get('error')}")
            
            # Still pending — back off with jitter
            wait = (2 ** attempt) + random.uniform(0, 1)
            log.info(f"Job {job_id} pending, retry {attempt + 1}/{max_retries}, wait {wait:.1f}s")
            time.sleep(wait)
            
        except httpx.HTTPStatusError as e:
            if e.response.status_code == 429:  # Rate limited
                wait = int(e.response.headers.get("Retry-After", 60))
                log.warning(f"Rate limited, waiting {wait}s")
                time.sleep(wait)
            else:
                raise
    
    raise TimeoutError(f"Job {job_id} did not complete in {max_retries} retries")

# Run downloads organizer every weekday at 6pm
0 18 * * 1-5 /usr/bin/python3 /home/user/scripts/organize_downloads.py >> /var/log/organizer.log 2>&1

# Scrape HN headlines every morning at 8am
0 8 * * * /usr/bin/python3 /home/user/scripts/scrape_headlines.py >> /var/log/scraper.log 2>&1

0 8 * * * /home/user/.local/bin/uv run /home/user/scripts/scrape_headlines.py