1

README.md

@@ -11,23 +11,23 @@
 
 ### **直播源（txt）：**
 ```
-https://raw.githubusercontent.com/kimwang1978/collect-tv-txt/main/merged_output.txt
+https://raw.githubusercontent.com/xuy132/collect-tv-txt/main/merged_output.txt
 ```
 直播源（txt）短链：
 ```
 http://gg.gg/tv-live-txt
 ```
 镜像源（txt）：
 ```
-https://ghproxy.net/https://raw.githubusercontent.com/kimwang1978/collect-tv-txt/main/merged_output.txt
+https://ghproxy.net/https://raw.githubusercontent.com/xuy132/collect-tv-txt/main/merged_output.txt
 ```
 镜像源（txt）短链：
 ```
 http://gg.gg/tv-live-txt-mirr
 ```
 ### **直播源（m3u）：**
 ```
-https://raw.githubusercontent.com/kimwang1978/collect-tv-txt/main/merged_output.m3u
+https://raw.githubusercontent.com/xuy132/collect-tv-txt/main/merged_output.m3u
 ```
 直播源（m3u）短链：
 ```
@@ -37,14 +37,14 @@ http://gg.gg/tv-live-m3u
 
 | 类 别  | 直播源                                       | ShortLink   |
 |-------|------------------------------------------------|------------|
-| （txt） |  https://raw.githubusercontent.com/kimwang1978/collect-tv-txt/main/merged_output.txt | http://gg.gg/tv-live-txt   |
-| （m3u） |  https://raw.githubusercontent.com/kimwang1978/collect-tv-txt/main/merged_output.m3u | http://gg.gg/tv-live-m3u   |
+| （txt） |  https://raw.githubusercontent.com/xuy132/collect-tv-txt/main/merged_output.txt | http://gg.gg/tv-live-txt   |
+| （m3u） |  https://raw.githubusercontent.com/xuy132/collect-tv-txt/main/merged_output.m3u | http://gg.gg/tv-live-m3u   |
 
 
 如果有其他定期更新稳定的源也可以留言，有时间一起加在收集列表里。
 
 ## Star History
 
-[![Star History Chart](https://api.star-history.com/svg?repos=kimwang1978/collect-tv-txt&type=Date)](https://star-history.com/#kimwang1978/collect-tv-txt&Date)
+[![Star History Chart](https://api.star-history.com/svg?repos=xuy132/collect-tv-txt&type=Date)](https://star-history.com/#xuy132/collect-tv-txt&Date)
 
 

blacklist.py

@@ -0,0 +1,245 @@
+import urllib.request
+from concurrent.futures import ThreadPoolExecutor, as_completed
+import time
+from datetime import datetime
+import os
+from urllib.parse import urlparse
+
+
+timestart = datetime.now()
+
+# 读取文件内容
+def read_txt_file(file_path):
+    skip_strings = ['#genre#']  # 定义需要跳过的字符串数组['#', '@', '#genre#'] 
+    required_strings = ['://']  # 定义需要包含的字符串数组['必需字符1', '必需字符2'] 
+
+    with open(file_path, 'r', encoding='utf-8') as file:
+        lines = [
+            line for line in file
+            if not any(skip_str in line for skip_str in skip_strings) and all(req_str in line for req_str in required_strings)
+        ]
+    return lines
+
+# 检测URL是否可访问并记录响应时间
+headers = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+}
+def check_url(url, timeout=8):
+    try:
+    	if  "://" in url:
+            start_time = time.time()
+            req = urllib.request.Request(url, headers=headers)
+            with urllib.request.urlopen(req, timeout=timeout) as response:
+                elapsed_time = (time.time() - start_time) * 1000  # 转换为毫秒
+                if response.status == 200:
+                    return elapsed_time, True
+    except Exception as e:
+        print(f"Error checking {url}: {e}")
+    return None, False
+
+# 处理单行文本并检测URL
+def process_line(line):
+    if "#genre#" in line or "://" not in line :
+        return None, None  # 跳过包含“#genre#”的行
+    parts = line.split(',')
+    if len(parts) == 2:
+        name, url = parts
+        elapsed_time, is_valid = check_url(url.strip())
+        if is_valid:
+            return elapsed_time, line.strip()
+        else:
+            return None, line.strip()
+    return None, None
+
+# 多线程处理文本并检测URL
+def process_urls_multithreaded(lines, max_workers=18):
+    blacklist =  [] 
+    successlist = []
+
+    with ThreadPoolExecutor(max_workers=max_workers) as executor:
+        futures = {executor.submit(process_line, line): line for line in lines}
+        for future in as_completed(futures):
+            elapsed_time, result = future.result()
+            if result:
+                if elapsed_time is not None:
+                    successlist.append(f"{elapsed_time:.2f}ms,{result}")
+                else:
+                    blacklist.append(result)
+    return successlist, blacklist
+
+# 写入文件
+def write_list(file_path, data_list):
+    with open(file_path, 'w', encoding='utf-8') as file:
+        for item in data_list:
+            file.write(item + '\n')
+
+# 增加外部url到检测清单，同时支持检测m3u格式url
+# urls里所有的源都读到这里。
+urls_all_lines = []
+
+def get_url_file_extension(url):
+    # 解析URL
+    parsed_url = urlparse(url)
+    # 获取路径部分
+    path = parsed_url.path
+    # 提取文件扩展名
+    extension = os.path.splitext(path)[1]
+    return extension
+
+def convert_m3u_to_txt(m3u_content):
+    # 分行处理
+    lines = m3u_content.split('\n')
+
+    # 用于存储结果的列表
+    txt_lines = []
+
+    # 临时变量用于存储频道名称
+    channel_name = ""
+
+    for line in lines:
+        # 过滤掉 #EXTM3U 开头的行
+        if line.startswith("#EXTM3U"):
+            continue
+        # 处理 #EXTINF 开头的行
+        if line.startswith("#EXTINF"):
+            # 获取频道名称（假设频道名称在引号后）
+            channel_name = line.split(',')[-1].strip()
+        # 处理 URL 行
+        elif line.startswith("http"):
+            txt_lines.append(f"{channel_name},{line.strip()}")
+
+    # 将结果合并成一个字符串，以换行符分隔
+    return '\n'.join(txt_lines)
+
+def process_url(url):
+    try:
+        # 打开URL并读取内容
+        with urllib.request.urlopen(url) as response:
+            # 以二进制方式读取数据
+            data = response.read()
+            # 将二进制数据解码为字符串
+            text = data.decode('utf-8')
+            if get_url_file_extension(url)==".m3u" or get_url_file_extension(url)==".m3u8":
+                urls_all_lines.append(convert_m3u_to_txt(text))
+            elif get_url_file_extension(url)==".txt":
+                lines = text.split('\n')
+                for line in lines:
+                    if  "#genre#" not in line and "," in line and "://" in line:
+                        #channel_name=line.split(',')[0].strip()
+                        #channel_address=line.split(',')[1].strip()
+                        urls_all_lines.append(line.strip())
+
+    except Exception as e:
+        print(f"处理URL时发生错误：{e}")
+
+
+if __name__ == "__main__":
+    # 定义要访问的多个URL
+    urls = [
+        'https://raw.githubusercontent.com/YanG-1989/m3u/main/Gather.m3u',
+        'https://raw.githubusercontent.com/iptv-org/iptv/master/streams/cn.m3u',
+        'https://gitlab.com/p2v5/wangtv/-/raw/main/wang-tvlive.txt',
+        'https://raw.githubusercontent.com/kimwang1978/tvbox/main/%E5%A4%A9%E5%A4%A9%E5%BC%80%E5%BF%83/lives/%E2%91%AD%E5%BC%80%E5%BF%83%E7%BA%BF%E8%B7%AF.txt',
+        'https://raw.githubusercontent.com/mlvjfchen/TV/main/iptv_list.txt'
+    ]
+    for url in urls:
+        print(f"处理URL: {url}")
+        process_url(url)   #读取上面url清单中直播源存入urls_all_lines
+
+    # 获取当前脚本所在的目录
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    # 获取上一层目录
+    parent_dir = os.path.dirname(current_dir)
+
+    input_file1 = os.path.join(parent_dir, 'merged_output.txt')  # 输入文件路径1
+    input_file2 = os.path.join(current_dir, 'blacklist_auto.txt')  # 输入文件路径2 
+    success_file = os.path.join(current_dir, 'whitelist_auto.txt')  # 成功清单文件路径
+    success_file_tv = os.path.join(current_dir, 'whitelist_auto_tv.txt')  # 成功清单文件路径（另存一份直接引用源）
+    blacklist_file = os.path.join(current_dir, 'blacklist_auto.txt')  # 黑名单文件路径
+
+    # 读取输入文件内容
+    lines1 = read_txt_file(input_file1)
+    lines2 = read_txt_file(input_file2)
+    lines=list(set(urls_all_lines + lines1 + lines2))
+    # 计算合并后合计个数
+    urls_hj = len(lines)
+
+    # 处理URL并生成成功清单和黑名单
+    successlist, blacklist = process_urls_multithreaded(lines)
+
+    # 给successlist, blacklist排序
+    # 定义排序函数
+    def successlist_sort_key(item):
+        time_str = item.split(',')[0].replace('ms', '')
+        return float(time_str)
+
+    successlist=sorted(set(successlist), key=successlist_sort_key)
+    blacklist=sorted(set(blacklist))
+
+    # 计算check后ok和ng个数
+    urls_ok = len(successlist)
+    urls_ng = len(blacklist)
+
+    # 把successlist整理一下，生成一个可以直接引用的源，方便用zyplayer手动check
+    def remove_prefix_from_lines(lines):
+        result = []
+        for line in lines:
+            if  "#genre#" not in line and "," in line and "://" in line:
+                parts = line.split(",")
+                result.append(",".join(parts[1:]))
+        return result
+
+
+    # 加时间戳等
+    version=datetime.now().strftime("%Y%m%d-%H-%M-%S")+",url"
+    successlist_tv = ["更新时间,#genre#"] +[version] + ['\n'] +\
+                  ["whitelist,#genre#"] + remove_prefix_from_lines(successlist)
+    successlist = ["更新时间,#genre#"] +[version] + ['\n'] +\
+                  ["RespoTime,whitelist,#genre#"] + successlist
+    blacklist = ["更新时间,#genre#"] +[version] + ['\n'] +\
+                ["blacklist,#genre#"]  + blacklist
+
+    # 写入成功清单文件
+    write_list(success_file, successlist)
+    write_list(success_file_tv, successlist_tv)
+
+    # 写入黑名单文件
+    write_list(blacklist_file, blacklist)
+
+    print(f"成功清单文件已生成: {success_file}")
+    print(f"成功清单文件已生成(tv): {success_file_tv}")
+    print(f"黑名单文件已生成: {blacklist_file}")
+
+    # 写入history
+    timenow=datetime.now().strftime("%Y%m%d_%H_%M_%S")
+    history_success_file = f'history/blacklist/{timenow}_whitelist_auto.txt'
+    history_blacklist_file = f'history/blacklist/{timenow}_blacklist_auto.txt'
+    write_list(history_success_file, successlist)
+    write_list(history_blacklist_file, successlist)
+    print(f"history成功清单文件已生成: {history_success_file}")
+    print(f"history黑名单文件已生成: {history_blacklist_file}")
+
+    # 执行的代码
+    timeend = datetime.now()
+
+    # 计算时间差
+    elapsed_time = timeend - timestart
+    total_seconds = elapsed_time.total_seconds()
+
+    # 转换为分钟和秒
+    minutes = int(total_seconds // 60)
+    seconds = int(total_seconds % 60)
+
+    # 格式化开始和结束时间
+    timestart_str = timestart.strftime("%Y%m%d_%H_%M_%S")
+    timeend_str = timeend.strftime("%Y%m%d_%H_%M_%S")
+
+    print(f"开始时间: {timestart_str}")
+    print(f"结束时间: {timeend_str}")
+    print(f"执行时间: {minutes} 分 {seconds} 秒")
+    print(f"urls_hj: {urls_hj} ")
+    print(f"  urls_ok: {urls_ok} ")
+    print(f"  urls_ng: {urls_ng} ")
+
+
+