Tghub群组频道数据采集脚本

编程代码
1

Telegram 群组/频道目录 - Tghub

image
image1920×1049 130 KB

image
image2560×1398 350 KB

群组共2958页/每页10条

image
image2560×1398 375 KB

频道共23480页/每页10条

自动采集脚本代码，使用 python 编写

import os
import re
import time
import requests

# === 配置 ===
OUTPUT_DIR = "output"
os.makedirs(OUTPUT_DIR, exist_ok=True)

FILES = {
    "群组": {
        "公开": os.path.join(OUTPUT_DIR, "public_groups.txt"),
        "私密": os.path.join(OUTPUT_DIR, "private_groups.txt")
    },
    "频道": {
        "公开": os.path.join(OUTPUT_DIR, "public_channels.txt"),
        "私密": os.path.join(OUTPUT_DIR, "private_channels.txt")
    }
}

HEADERS = {
    "User-Agent": "Mozilla/5.0"
}

# 加载历史记录
def load_existing_links(filepath):
    if os.path.exists(filepath):
        with open(filepath, "r", encoding="utf-8") as f:
            return set(line.strip() for line in f if line.strip())
    return set()

# 提取干净的 t.me 链接
def extract_telegram_links(html):
    raw_links = re.findall(r'https://t\.me/[^\s"\'<>,;]+', html)
    cleaned = set()

    for link in raw_links:
        # 去除尾部多余内容
        link = re.split(r'[&<>"\'\s]', link)[0]
        if re.match(r'^https://t\.me/[a-zA-Z0-9_+/]+$', link):
            cleaned.add(link)
    return cleaned

# 判断是否为私密链接
def is_private(link):
    return '/+J' in link or '/+/' in link or '/+-' in link or '/+' in link

# 主采集逻辑
def scrape(base_url, pages, 类型):
    public_file = FILES[类型]["公开"]
    private_file = FILES[类型]["私密"]

    existing_public = load_existing_links(public_file)
    existing_private = load_existing_links(private_file)

    new_public = set()
    new_private = set()

    for page in range(1, pages + 1):
        url = base_url.format(page)
        print(f"\n📄 [{类型}] 第 {page} 页：{url}")

        try:
            res = requests.get(url, headers=HEADERS, timeout=10)
            res.encoding = "utf-8"
            html = res.text

            links = extract_telegram_links(html)
            for link in links:
                if is_private(link):
                    if link not in existing_private:
                        new_private.add(link)
                else:
                    if link not in existing_public:
                        new_public.add(link)

            print(f"🔎 找到 {len(links)} 个链接，新增公开 {len(new_public)}, 私密 {len(new_private)}")

        except Exception as e:
            print(f"❌ 抓取失败（第 {page} 页）：{e}")

        time.sleep(0.5)  # 避免请求过快

    # 写入新链接
    if new_public:
        with open(public_file, "a", encoding="utf-8") as f:
            for link in sorted(new_public):
                f.write(link + "\n")
    if new_private:
        with open(private_file, "a", encoding="utf-8") as f:
            for link in sorted(new_private):
                f.write(link + "\n")

    print(f"\n✅ [{类型}] 新增公开 {len(new_public)} 条，新增私密 {len(new_private)} 条")

# === 主入口 ===
if __name__ == "__main__":
    print("🚀 正在抓取 TGHUB Telegram 群组与频道...\n")

    scrape("https://www.tghub.club/zh/group-list/{}", 10, "群组")
    scrape("https://www.tghub.club/zh/channel-list/{}", 10, "频道")

    print("\n🎉 所有任务完成！")

常驻运行命令：nohup python3 telegram_directory_scraper.py > output.log 2>&1 &

image
image2160×1350 451 KB