#!/usr/bin/env python3
"""
tvwish EPG Scraper - Selenium Version (for JS-rendered content)
Scrapes program schedules from tvwish.com and generates XMLTV EPG format for all configured channels.
"""

import xml.etree.ElementTree as ET
from xml.dom.minidom import parseString
from datetime import datetime, timedelta
import pytz
from pathlib import Path
import time
import re
import sys
import signal
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup

# Global exit flag
stop_flag = False

# Default config
DEFAULT_PROGRAM_DURATION = timedelta(minutes=30)
INDIA_TZ = pytz.timezone('Asia/Kolkata')

# Signal handler for graceful Ctrl+C
signal.signal(signal.SIGINT, lambda sig, frame: (print("\nInterrupted."), sys.exit(0)))

def get_channel_mapping():
    config_path = Path(__file__).parent / "tempest_config" / "tvwish.config.xml"
    print(f"[INFO] Loading config from {config_path}")
    if not config_path.exists():
        raise FileNotFoundError(f"Config file not found: {config_path}")

    tree = ET.parse(config_path)
    channel_map = {}

    for channel in tree.findall(".//channel"):
        site_id = channel.get("site_id")
        display_name = channel.text.strip() if channel.text else channel.get("xmltv_id")

        url_name = display_name.lower().replace(' ', '-')
        url_name = re.sub(r'[^a-z0-9-]', '', url_name)

        # Manual fixes
        if site_id == "20": url_name = "and-pictures"
        elif site_id == "8": url_name = "and-pictures-hd"
        elif site_id == "1377": url_name = "and-xplor-hd"

        channel_map[site_id] = {
            'xmltv_id': channel.get("xmltv_id"),
            'display_name': display_name,
            'url_name': url_name
        }

    return channel_map

def setup_driver():
    options = Options()
    options.add_argument('--headless')
    options.add_argument('--disable-gpu')
    options.add_argument('--no-sandbox')
    options.add_argument('--window-size=1920,1080')
    return webdriver.Chrome(options=options)

def parse_schedule(channel_url):
    driver = setup_driver()
    print(f"[INFO] Opening URL: {channel_url}")
    driver.get(channel_url)
    time.sleep(5)
    soup = BeautifulSoup(driver.page_source, 'html.parser')
    driver.quit()

    programs = []
    items = soup.select("div.card.schedule-item")
    print(f"[INFO] Found {len(items)} schedule items")

    current_date = datetime.now(INDIA_TZ).strftime("%d %b %Y")

    for item in items:
        try:
            time_str = item.select_one("div.card-header h3").get_text(strip=True)
            title = item.select_one("h4.text-warning").get_text(strip=True)
            desc_el = item.select_one("p.my-2")
            description = desc_el.get_text(strip=True) if desc_el else ""
            genre_tags = item.select("a.badge.bg-info")
            genre = ", ".join(g.get_text(strip=True) for g in genre_tags)

            dt = datetime.strptime(f"{current_date} {time_str}", "%d %b %Y %I:%M %p")
            start_time = INDIA_TZ.localize(dt)

            programs.append({
                "title": title,
                "description": description,
                "genre": genre,
                "start": start_time
            })
        except Exception as e:
            print(f"[WARN] Skipping item: {e}")
            continue

    programs.sort(key=lambda x: x["start"])
    for i in range(len(programs)):
        end_time = programs[i+1]["start"] if i+1 < len(programs) else programs[i]["start"] + DEFAULT_PROGRAM_DURATION
        programs[i]["end"] = end_time

    return programs

def generate_epg(channels_data):
    print("[INFO] Generating XMLTV EPG...")
    output_dir = Path(__file__).parent / "tempest_config" / "epg"
    output_file = output_dir / "tvwish_epg.xml"
    output_dir.mkdir(parents=True, exist_ok=True)

    root = ET.Element("tv", {"generator-info-name": "tvwish EPG Generator"})

    for ch_id, ch_info in channels_data.items():
        programs = ch_info['programs']
        if not programs:
            continue

        ch_elem = ET.SubElement(root, "channel", {"id": ch_info['xmltv_id']})
        ET.SubElement(ch_elem, "display-name").text = ch_info['display_name']

        for prog in programs:
            start = prog["start"].astimezone(pytz.utc).strftime("%Y%m%d%H%M%S +0000")
            end = prog["end"].astimezone(pytz.utc).strftime("%Y%m%d%H%M%S +0000")
            pr = ET.SubElement(root, "programme", {
                "start": start,
                "stop": end,
                "channel": ch_info['xmltv_id']
            })
            ET.SubElement(pr, "title", {"lang": "en"}).text = prog["title"]
            if prog["genre"]:
                ET.SubElement(pr, "category", {"lang": "en"}).text = prog["genre"]
            if prog["description"]:
                ET.SubElement(pr, "desc", {"lang": "en"}).text = prog["description"]

    xml_str = ET.tostring(root, encoding="utf-8")
    pretty = parseString(xml_str).toprettyxml()
    with open(output_file, "w", encoding="utf-8") as f:
        f.write(pretty)

    print(f"[SUCCESS] EPG written to {output_file.absolute()}")

def main():
    print("tvwish EPG Scraper - Selenium Version")
    print("====================================")

    try:
        channel_map = get_channel_mapping()
        all_channels = {}

        for site_id, info in channel_map.items():
            if stop_flag:
                break

            url = f"https://www.tvwish.com/{info['url_name']}/Channel/{site_id}/Schedule/Today"
            print(f"[INFO] Scraping: {info['display_name']} ({site_id})")
            programs = parse_schedule(url)
            if programs:
                all_channels[site_id] = {
                    'xmltv_id': info['xmltv_id'],
                    'display_name': info['display_name'],
                    'programs': programs
                }
                print(f"[INFO] {len(programs)} programs found for {info['display_name']}")
            else:
                print(f"[WARN] No programs found for {info['display_name']}")

        if all_channels:
            generate_epg(all_channels)
        else:
            print("[ERROR] No programs were extracted for any channel")

    except Exception as e:
        print(f"[FATAL] {e}")

if __name__ == '__main__':
    main()