Web Scraper to Telegram Bot

worker.js

/*

create a KV and bind to your worker -> kv_link

*/

const pageUrl = "https://ledc.ir/%D8%AE%D8%A7%D9%85%D9%88%D8%B4%DB%8C%D9%87%D8%A7%DB%8C-%D8%A8%D8%B1%D9%86%D8%A7%D9%85%D9%87-%D8%B1%DB%8C%D8%B2%DB%8C-%D8%B4%D8%AF%D9%87";
const botToken = "8478782432:AAG7afaplinQtnGgLbjgEgsAhbUQHRRYXFo";
const chatId = "@barghmire";

export default {
  async fetch(request, env, ctx) {
    return handleRequest(env, request);
  },

  async scheduled(event, env, ctx) {
    ctx.waitUntil(handleRequest(env));
  },
};


async function handleRequest(env, request = null) {

  const kv = env.kv_link;
  let dev = false;

  if (request) {
    const url = new URL(request.url);
    if (url.searchParams.get("dev") === "1") {
      dev = true;
    }
  }

 
  const url = gproxy(pageUrl); // استفاده از گوگل ترسلیت برای لود کردن صفحه

  try {
    const res = await fetch(url, {
      headers: {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115 Safari/537.36",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
        "Accept-Language": "fa-IR,fa;q=0.9,en;q=0.8"
      }
    });

    const html = await res.text();



    // شروع پردازش صفحه

    const conditions = [
      ["بروجرد", "جعفری"],
      ["بروجرد", "بهار"]
    ];



    const trMatches = [...html.matchAll(/<tr[\s\S]*?<\/tr>/gi)];
    const rows = [];

    trMatches.forEach((tr, idx) => {
      const trHtml = tr[0];
      const text = trHtml.replace(/<[^>]+>/g, " "); // متن خالص

      const matched = conditions.find(words =>
        words.every(w => text.includes(w))
      );

      if (matched) {
        const tdMatches = [...trHtml.matchAll(/<td[^>]*>([\s\S]*?)<\/td>/gi)];
        const third = tdMatches[2] ? tdMatches[2][1].replace(/<[^>]+>/g, "").trim() : null;
        rows.push({ label: matched.join(","), value: third });
      }
    });

    const date = extractPersianDate(html) || "none";

    const lastDate = await kv.get("last_date");

    if (!dev) {
      if (date == "none") {
        return new Response("try again ...", { status: 200 });
      }
      if (lastDate === date) {
        return new Response("تاریخ مشابه قبلی است، ارسال انجام نشد.", { status: 200 });
      }
    } 
    let message = date + "\n\n";

    rows.forEach(r => {
      message += `<b>${r.label}: ${r.value}</b>\n`;
    });

    // پایان پردازش صفخه







    // ارسال به تلگرام

    const telegramUrl = `https://api.telegram.org/bot${botToken}/sendMessage?chat_id=${chatId}&text=${encodeURIComponent(message)}&parse_mode=html`;
    await fetch(telegramUrl);
    await kv.put("last_date", date);

    if (dev) {
      return new Response(message+"\n"+html, { headers: { "Content-Type": "text/plain; charset=utf-8" } });
    }

    return new Response(message, { headers: { "Content-Type": "text/plain; charset=utf-8" } });

  } catch (err) {
    return new Response("Error: " + err.message, { status: 500 });
  }
}


function gproxy(url) {
  try {
    let u = new URL(url);
    u.hostname = u.hostname.replace(/\./g, "-") + ".translate.goog";
    ["_x_tr_sl=en", "_x_tr_tl=fa", "_x_tr_hl=en", "_x_tr_pto=wapp"]
      .forEach(p => { let [k, v] = p.split("="); u.searchParams.set(k, v) });
    return u.toString();
  } catch (e) { return null }
}

function extractPersianDate(text) {
  const match = text.match(/(شنبه|یکشنبه|دوشنبه|سه‌شنبه|سه شنبه|چهارشنبه|پنجشنبه|جمعه)\s+\d{4}\/\d{2}\/\d{2}/);
  return match ? match[0] : null;
}