Update 酒店源.py

py/酒店源.py

@@ -292,69 +292,67 @@ urls = [
     "https://fofa.info/result?qbase64=ImlwdHYvbGl2ZS96aF9jbi5qcyIgJiYgY291bnRyeT0iQ04iICYmIGNpdHk9Imd1aWdhbmci",  #贵港
     "https://fofa.info/result?qbase64=ImlwdHYvbGl2ZS96aF9jbi5qcyIgJiYgY291bnRyeT0iQ04iICYmIHBvcnQ9IjgxODEii",#8181
 ]
-def modify_urls(url):
-    modified_urls = []
-    ip_start_index = url.find("//") + 2
-    ip_end_index = url.find(":", ip_start_index)
-    base_url = url[:ip_start_index]
-    ip_address = url[ip_start_index:ip_end_index]
-    port = url[ip_end_index:]
-    ip_end = "/iptv/live/1000.json?key=txiptv"
-    for i in range(1, 256):
-        modified_ip = f"{ip_address[:-1]}{i}"
-        modified_url = f"{base_url}{modified_ip}{port}{ip_end}"
-        modified_urls.append(modified_url)
-    return modified_urls
-
 def is_url_accessible(url):
     try:
+        # 发送 GET 请求，设置超时时间为 3 秒
         response = requests.get(url, timeout=3)
+        # 如果响应状态码在 200 到 401 之间（包括 200 和 401），则认为 URL 可访问
         if 200 <= response.status_code <= 401:
             return url
     except requests.exceptions.RequestException:
+        # 如果请求过程中出现异常，不做任何处理，直接跳过
         pass
     return None
 
+def get_content(url):
+    try:
+        response = requests.get(url, timeout=3)
+        response.raise_for_status()
+        # 确保内容类型为HTML或文本
+        if 'text/html' in response.headers.get('Content-Type', ''):
+            return response.text
+    except requests.RequestException as e:
+        print(f"请求错误: {e}")
+    return None
+
+# 创建一个空列表用于存储结果
 results = []
 for url in urls:
+    # 发送 GET 请求获取 URL 的内容
     response = requests.get(url)
+    # 获取响应的文本内容
+    page_content = response.text
+
+def is_valid_url(url):
+    try:
+        response = requests.get(url, timeout=5)
+        if response.status_code == 200:
+            return True
+        else:
+            return False
+    except requests.RequestException:
+        return False
+
+for url in urls:
+    # 发送 GET 请求获取 URL 的内容
+    response = requests.get(url)
+    # 获取响应的文本内容
     page_content = response.text
     # 查找所有符合指定格式的网址
-    pattern = r"http://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d+"  # 设置匹配的格式,如http://8.8.8.8:8888
+    # 匹配纯域名，可能带有http://或https://前缀，但不包含端口
+    # 匹配纯数字IP地址，后面跟着端口号
+    pattern = r"(https?://[\w-]+(?:\.[\w-]+)*(?::\d+)?|\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}(?::\d+)?)"
+    # 使用正则表达式在页面内容中查找所有符合格式的 URL
     urls_all = re.findall(pattern, page_content)
-    # urls = list(set(urls_all))  # 去重得到唯一的URL列表
-    urls = set(urls_all)  # 去重得到唯一的URL列表
-    x_urls = []
-    for url in urls:  # 对urls进行处理,ip第四位修改为1,并去重
-        url = url.strip()
-        ip_start_index = url.find("//") + 2
-        ip_end_index = url.find(":", ip_start_index)
-        ip_dot_start = url.find(".") + 1
-        ip_dot_second = url.find(".", ip_dot_start) + 1
-        ip_dot_three = url.find(".", ip_dot_second) + 1
-        base_url = url[:ip_start_index]  # http:// or https://
-        ip_address = url[ip_start_index:ip_dot_three]
-        port = url[ip_end_index:]
-        ip_end = "1"
-        modified_ip = f"{ip_address}{ip_end}"
-        x_url = f"{base_url}{modified_ip}{port}"
-        x_urls.append(x_url)
-    urls = set(x_urls)  # 去重得到唯一的URL列表
-    valid_urls = []
-    #   多线程获取可用url
-    with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
-        futures = []
-        for url in urls:
-            url = url.strip()
-            modified_urls = modify_urls(url)
-            for modified_url in modified_urls:
-                futures.append(executor.submit(is_url_accessible, modified_url))
-        for future in concurrent.futures.as_completed(futures):
-            result = future.result()
-            if result:
-                valid_urls.append(result)
-    for url in valid_urls:
-        print(url)
+    # 去重得到唯一的URL列表
+    unique_urls = set(urls_all)
+    # 生成新的 URL 列表
+    new_urls = [url + "/iptv/live/1000.json?key=txiptv" for url in unique_urls]
+    # 检测新 URL 列表的有效性
+    valid_urls = [new_url for new_url in new_urls if is_valid_url(new_url)]
+    # 打印有效的 URL 列表
+    print(valid_urls)
+
 
     # 遍历网址列表,获取JSON文件并解析
     for url in valid_urls: