Update 网络收集.py

py/网络收集.py

@@ -417,6 +417,9 @@ def parse_file(input_file_path, output_file_name):
             for line in lines:
                 output_file.write(line + '\n')
             output_file.write('\n')  # 在每个小段后添加一个空行作为分隔
+    line_count = sum(len(lines) for lines in filtered_ip_or_domain_to_lines.values())
+    print(f"过滤文件完成，一共有 {line_count} 行数据。")
+
 # 调用函数并传入文件路径和输出文件名
 parse_file('2.txt', '2.txt')
 
@@ -443,8 +446,13 @@ def merge_and_filter():
 
     total_lines = len(lines)
 
+import time
+import cv2
+from tqdm import tqdm
+
 # 处理输入文件中的数据并进行检测
 with open(output_file_path, 'a', encoding='utf-8') as output_file:
+    valid_line_count = 0
     for i, line in tqdm(enumerate(lines), total=total_lines, desc="Processing", unit='line'):
         if 'genre' in line:
             output_file.write(line)
@@ -458,6 +466,7 @@ def merge_and_filter():
             if ip_key and ip_key in detected_ips:
                 if detected_ips[ip_key]['status'] == 'ok':
                     output_file.write(line)
+                    valid_line_count += 1
             elif ip_key:
                 cap = cv2.VideoCapture(url)
                 start_time = time.time()
@@ -471,8 +480,11 @@ def merge_and_filter():
                 if frame_count >= 50:
                     detected_ips[ip_key] = {'status': 'ok'}
                     output_file.write(line)
+                    valid_line_count += 1
                 else:
                     detected_ips[ip_key] = {'status': 'fail'}
+print(f"有效的总行数为：{valid_line_count}")
+
 
     # 合并任意字符加上网络收集.txt 的文件
     all_files = [f for f in os.listdir(os.getcwd()) if f.endswith('网络收集.txt')]