script/module/txt_different_find.py

# 输入文件，包含URL的内容
input_file1 = 'output10.txt'
input_file2 = 'extracted_urls.txt'

# 输出文件，用于存放提取出的不同的URL
output_file = 'different_urls.txt'

# 存放URL的集合
urls_set1 = set()
urls_set2 = set()

# 读取输入文件1中的URL
with open(input_file1, 'r') as file1:
    for line in file1:
        urls_set1.add(line.strip())

# 读取输入文件2中的URL
with open(input_file2, 'r') as file2:
    for line in file2:
        urls_set2.add(line.strip())

# 提取在extracted_urls.txt中独有的URL
different_urls = urls_set2.difference(urls_set1)

# 将提取出的不同的URL写入输出文件
with open(output_file, 'w') as output:
    for url in different_urls:
        # 每个URL单独一行
        output.write(url + '\n')

print("提取出的不同的URL已保存到输出文件中。")