Update 酒店源.py

This commit is contained in:
frxz751113
2024-08-30 03:45:49 +08:00
committed by GitHub
parent 3fe58a5576
commit 1118653ba5
+29
View File
@@ -515,6 +515,35 @@ with open("iptv.txt", 'a', encoding='utf-8') as file:
file.write(f"{channel_name},{channel_url}\n")
print("频道列表文件iptv.txt追加写入成功!")
def remove_duplicates(input_file, output_file):
# 用于存储已经遇到的URL和包含genre的行
seen_urls = set()
seen_lines_with_genre = set()
# 用于存储最终输出的行
output_lines = []
# 打开输入文件并读取所有行
with open(input_file, 'r', encoding='utf-8') as f:
lines = f.readlines()
print("去重前的行数:", len(lines))
# 遍历每一行
for line in lines:
# 使用正则表达式查找URL和包含genre的行,默认最后一行
urls = re.findall(r'[https]?[http]?[P2p]?[mitv]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', line)
genre_line = re.search(r'\bgenre\b', line, re.IGNORECASE) is not None
# 如果找到URL并且该URL尚未被记录
if urls and urls[0] not in seen_urls:
seen_urls.add(urls[0])
output_lines.append(line)
# 如果找到包含genre的行,无论是否已被记录,都写入新文件
if genre_line:
output_lines.append(line)
# 将结果写入输出文件
with open(output_file, 'w', encoding='utf-8') as f:
f.writelines(output_lines)
print("去重后的行数:", len(output_lines))
# 使用方法
remove_duplicates('iptv.txt', 'iptv.txt')
######################################################################################################################