Update 收集.py

py/收集.py

@@ -262,7 +262,7 @@ import re
 import os
 # 定义一个包含所有要排除的关键词的列表
 excluded_keywords = [
-    'epg', 'mitv', 'udp', 'rtp', 'tsfile', 'hls', '[', 'P2p', 'p2p', 'p3p', 'P2P', 'P3p', 'P3P', '腔', '曲', '春节'
+    'epg', 'mitv', 'udp', 'rtp', '[', 'P2p', 'p2p', 'p3p', 'P2P', 'P3p', 'P3P', '腔', '曲', '春节'
 ]
 
 # 定义一个包含所有要提取的关键词的列表
@@ -339,7 +339,7 @@ with open(output_file_path, 'w', encoding='utf-8') as output_file:
                 start_time = time.time()
                 frame_count = 0
                 # 尝试捕获10秒内的帧
-                while frame_count < 30 and (time.time() - start_time) < 5:
+                while frame_count < 30 and (time.time() - start_time) < 2:
                     ret, frame = cap.read()
                     if not ret:
                         break
@@ -356,73 +356,6 @@ with open(output_file_path, 'w', encoding='utf-8') as output_file:
 for ip_key, result in detected_ips.items():
     print(f"IP Key: {ip_key}, Status: {result['status']}")
 
-#########################################################################
-# 函数：获取视频分辨率
-def get_video_resolution(video_path, timeout=0.8):
-    cap = cv2.VideoCapture(video_path)
-    if not cap.isOpened():
-        return None
-    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    cap.release()
-    return (width, height)
-# 函数：处理每一行
-def process_line(line, output_file, order_list, valid_count, invalid_count, total_lines):
-    parts = line.strip().split(',')
-    if '#genre#' in line:
-        # 如果行包含 '#genre#'，直接写入新文件
-        with threading.Lock():
-            output_file.write(line)
-            print(f"已写入genre行：{line.strip()}")
-    elif len(parts) == 2:
-        channel_name, channel_url = parts
-        resolution = get_video_resolution(channel_url, timeout=8)
-        if resolution and resolution[1] >= 720:  # 检查分辨率是否大于等于720p
-            with threading.Lock():
-                output_file.write(f"{channel_name}[{resolution[1]}p],{channel_url}\n")
-                order_list.append((channel_name, resolution[1], channel_url))
-                valid_count[0] += 1
-                print(f"Channel '{channel_name}' accepted with resolution {resolution[1]}p at URL {channel_url}.")
-        else:
-            invalid_count[0] += 1
-    with threading.Lock():
-        print(f"有效: {valid_count[0]}, 无效: {invalid_count[0]}, 总数: {total_lines}, 进度: {(valid_count[0] + invalid_count[0]) / total_lines * 100:.2f}%")
-# 函数：多线程工作
-def worker(task_queue, output_file, order_list, valid_count, invalid_count, total_lines):
-    while True:
-        try:
-            line = task_queue.get(timeout=1)
-            process_line(line, output_file, order_list, valid_count, invalid_count, total_lines)
-        except Queue.Empty:
-            break
-        finally:
-            task_queue.task_done()
-# 主函数
-def main(source_file_path, output_file_path):
-    order_list = []
-    valid_count = [0]
-    invalid_count = [0]
-    task_queue = Queue()
-    # 读取源文件
-    with open(source_file_path, 'r', encoding='utf-8') as source_file:
-        lines = source_file.readlines()
-    with open(output_file_path + '.txt', 'w', encoding='utf-8') as output_file:
-        # 创建线程池
-        with ThreadPoolExecutor(max_workers=64) as executor:
-            # 创建并启动工作线程
-            for _ in range(64):
-                executor.submit(worker, task_queue, output_file, order_list, valid_count, invalid_count, len(lines))
-            # 将所有行放入队列
-            for line in lines:
-                task_queue.put(line)
-            # 等待队列中的所有任务完成
-            task_queue.join()
-    print(f"任务完成，有效频道数：{valid_count[0]}, 无效频道数：{invalid_count[0]}, 总频道数：{len(lines)}")
-if __name__ == "__main__":
-    source_file_path = '网络收集.txt'  # 替换为你的源文件路径
-    output_file_path = '网络收集'  # 替换为你的输出文件路径,不要后缀名
-    main(source_file_path, output_file_path)
-