#!/usr/bin/env python3
import os
import sys
import time
import re
import xml.etree.ElementTree as ET
from urllib.parse import urlparse
from bs4 import BeautifulSoup
from curl_cffi import requests

TARGET_URL = "https://xkcd.com/rss.xml"
DOWNLOAD_DIR = "/mnt/archie/Pictures/Editorial Cartoons/xkcd"
MAX_STORAGE_DAYS = 30

# ==========================================
# PROXY CONFIGURATION (SINGLE PROXY)
# ==========================================
# Set to None to disable proxy and connect directly
# Format: {"http": "http://HOSTNAME:PORT", "https": "http://HOSTNAME:PORT"}
# Example: {"http": "http://127.0.0.1:8080", "https": "http://127.0.0.1:8080"}
PROXY = {"http": "http://proxydrum:8080"}

def enforce_retention_policy():
    print(f"Running automated retention validation sweep inside {DOWNLOAD_DIR}...", flush=True)
    now = time.time()
    cutoff = now - (MAX_STORAGE_DAYS * 86400)
    try:
        purged_count = 0
        for entry in os.scandir(DOWNLOAD_DIR):
            if entry.is_file():
                file_modification_time = entry.stat().st_mtime
                if file_modification_time < cutoff:
                    os.remove(entry.path)
                    purged_count += 1
        if purged_count > 0:
            print(f"[Cleanup Success]: Purged {purged_count} legacy assets older than {MAX_STORAGE_DAYS} days.", flush=True)
    except Exception as e:
        print(f"[Warning]: Automated file retention sweep encountered an issue: {e}", file=sys.stderr, flush=True)

def scrape_xkcd_rss():
    print("=== STARTING PURE PYTHON RSS EXTRACTION RUN ===", flush=True)
    print(f"[TIME]  {time.strftime('%Y-%m-%d %H:%M:%S')}", flush=True)
    if PROXY:
        print(f"[PROXY]: {PROXY.get('http', 'N/A')}", flush=True)
    else:
        print(f"[PROXY]: None (direct connection)", flush=True)
    if not os.path.exists(DOWNLOAD_DIR):
        print(f"Creating target storage directory tree structure at: {DOWNLOAD_DIR}", flush=True)
        os.makedirs(DOWNLOAD_DIR, exist_ok=True)

    browser_headers = {
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8",
        "Accept-Language": "en-US,en;q=0.9",
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
    }

    response = None
    print("Fetching RSS feed...", flush=True)
    try:
        if PROXY:
            res = requests.get(TARGET_URL, impersonate="chrome120", headers=browser_headers, proxies=PROXY, timeout=15)
        else:
            res = requests.get(TARGET_URL, impersonate="chrome120", headers=browser_headers, timeout=15)
        if res.status_code == 200:
            response = res
            print("Successfully fetched RSS raw file payload.", flush=True)
        else:
            print(f" -> Status: {res.status_code} (Rejected)", flush=True)
    except Exception as e:
        print(f" -> Connection dropped / Timeout: {e}", flush=True)

    if response is None:
        print("[CRITICAL FATAL ERROR]: Could not fetch RSS feed.", file=sys.stderr, flush=True)
        return

    try:
        root = ET.fromstring(response.content)
        items = root.findall('.//item')
        print(f"Detected {len(items)} items inside the RSS feed description structure.", flush=True)
        new_downloads_count = 0
        for index, item in enumerate(items):
            print(f"\nProcessing entry [{index + 1}/{len(items)}]...", flush=True)
            description_node = item.find('description')
            if description_node is None or not description_node.text:
                print(" -> [Parse Warning]: Target entry missing clean description markup string content. Skipping.", flush=True)
                continue
            soup = BeautifulSoup(description_node.text, 'html.parser')
            img_element = soup.find('img')
            if not img_element:
                print(" -> [Parse Warning]: Description block found but missing raw HTML img tag context element. Skipping.", flush=True)
                continue
            img_url = img_element.get('src')
            if not img_url:
                print(" -> [Parse Warning]: Could not parse out a clean target image source web link string. Skipping.", flush=True)
                continue
            if img_url.startswith('//'):
                img_url = 'https:' + img_url
            parsed_url = urlparse(img_url)
            filename = os.path.basename(parsed_url.path)
            if not filename:
                continue
            save_path = os.path.join(DOWNLOAD_DIR, filename)
            if os.path.exists(save_path):
                print(f" -> [SKIPPED]: File locally present: \"{filename}\".", flush=True)
                continue
            print(f" -> [DISCOVERY]: Fetching binary asset: {img_url}", flush=True)
            download_success = False
            try:
                if PROXY:
                    img_response = requests.get(img_url, impersonate="chrome120", headers=browser_headers, proxies=PROXY, timeout=20)
                else:
                    img_response = requests.get(img_url, impersonate="chrome120", headers=browser_headers, timeout=20)
                if img_response.status_code == 200:
                    with open(save_path, "wb") as file_writer:
                        file_writer.write(img_response.content)
                    download_success = True
                else:
                    print(f" -> Download failed (Status: {img_response.status_code}).", flush=True)
            except Exception as e:
                print(f" -> Download timed out/dropped: {e}", flush=True)

            if download_success:
                print(f" -> [SUCCESS]: Archived target locally -> {save_path}", flush=True)
                new_downloads_count += 1
            else:
                print(f" -> [DOWNLOAD ERROR]: Skipping this image.", file=sys.stderr, flush=True)
        print(f"\nProcessing queue empty. Total new assets written to storage disk: {new_downloads_count}", flush=True)
        enforce_retention_policy()
    except Exception as error:
        print(f"\n[UNHANDLED RUNTIME TRACKER EXCEPTION]: {str(error)}", file=sys.stderr, flush=True)

if __name__ == "__main__":
    scrape_xkcd_rss()