Update GAT.py
This commit is contained in:
@@ -716,20 +716,36 @@ file_path1 = '网络收集.txt'
|
||||
file_path2 = '综合源.txt'
|
||||
append_text_between_files(file_path1, file_path2)
|
||||
|
||||
# 打开文档并读取所有行
|
||||
with open('综合源.txt', 'r', encoding="utf-8") as file:
|
||||
lines = file.readlines()
|
||||
# 使用列表来存储唯一的行的顺序
|
||||
unique_lines = []
|
||||
seen_lines = set()
|
||||
# 遍历每一行,如果是新的就加入unique_lines
|
||||
for line in lines:
|
||||
if line not in seen_lines:
|
||||
unique_lines.append(line)
|
||||
seen_lines.add(line)
|
||||
# 将唯一的行写入新的文档
|
||||
with open('综合源.txt', 'w', encoding="utf-8") as file:
|
||||
file.writelines(unique_lines)
|
||||
##############################################################对生成的文件进行网址及文本去重复,避免同一个频道出现在不同的类中
|
||||
|
||||
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]?[rtmp]?[rtsp]?[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('综合源.txt', '综合源.txt')
|
||||
|
||||
|
||||
#TXT转M3U#
|
||||
|
||||
Reference in New Issue
Block a user