littlebalalafairy/sing-box-geosite
1
0
Fork 0
mirror of https://github.com/Toperlock/sing-box-geosite.git synced 2025-06-08 01:32:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update main.py

Browse Source
This commit is contained in:
Dorae 2023-12-06 00:09:36 +08:00 committed by GitHub
parent cf5a52140e
commit cc68634df4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 30 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
main.py
View File

@ -6,12 +6,10 @@ import json
def read_csv_and_append(link):
return pd.read_csv(link, header=None, names=['pattern', 'address', 'other'], on_bad_lines='warn')
def parse_list_file(list_links, output_directory):
with open(list_links, 'r') as file:
list_links = file.read().splitlines()
def parse_list_file(link, output_directory):
with concurrent.futures.ThreadPoolExecutor() as executor:
# 使用executor.map并行处理链接
results = list(executor.map(read_csv_and_append, list_links))
results = list(executor.map(read_csv_and_append, [link]))
# 拼接为一个DataFrame
df = pd.concat(results, ignore_index=True)
@ -19,8 +17,10 @@ def parse_list_file(list_links, output_directory):
df = df[~df['pattern'].str.contains('#')].reset_index(drop=True)
# 映射字典
map_dict = {'DOMAIN-SUFFIX': 'domain_suffix', 'HOST-SUFFIX': 'domain_suffix', 'DOMAIN': 'domain', 'HOST': 'domain', 'DOMAIN-KEYWORD': 'domain_keyword',
'IP-CIDR': 'ip_cidr', 'IP-CIDR6': 'ip_cidr', 'SRC-IP-CIDR': 'source_ip_cidr', 'GEOIP': 'geoip', 'DST-PORT': 'port',
map_dict = {'DOMAIN-SUFFIX': 'domain_suffix', 'HOST-SUFFIX': 'domain_suffix', 'DOMAIN': 'domain', 'HOST': 'domain', 'host': 'domain',
'DOMAIN-KEYWORD':'domain_keyword', 'HOST-KEYWORD': 'domain_keyword', 'host-keyword': 'domain_keyword', 'IP-CIDR': 'ip_cidr',
'ip-cidr': 'ip_cidr', 'IP-CIDR6': 'ip_cidr',
'IP6-CIDR': 'ip_cidr','SRC-IP-CIDR': 'source_ip_cidr', 'GEOIP': 'geoip', 'DST-PORT': 'port',
'SRC-PORT': 'source_port', "URL-REGEX": "domain_regex"}
# 删除不在字典中的pattern
@ -31,22 +31,33 @@ def parse_list_file(list_links, output_directory):
# 替换pattern为字典中的值
df['pattern'] = df['pattern'].replace(map_dict)
# 使用 groupby 分组并转化为字典
result_dict = df.groupby('pattern')['address'].apply(list).to_dict()
# 创建自定义文件夹
os.makedirs(output_directory, exist_ok=True)
file_names = [] # 存储生成的文件名
for link in list_links:
# 使用 output_directory 拼接完整路径
file_name = os.path.join(output_directory, os.path.basename(link).split('.')[0] + '.json')
file_names.append(file_name)
with open(file_name, 'w', encoding='utf-8') as output_file:
json.dump({"version": 1, "rules": [{"pattern": key, "address": value} for key, value in result_dict.items()]}, output_file, ensure_ascii=False, indent=2)
result_rules = {"version": 1, "rules": []}
return result_dict, file_names
for pattern, addresses in df.groupby('pattern')['address'].apply(list).to_dict().items():
rule_entry = {pattern: addresses}
result_rules["rules"].append(rule_entry)
# 使用 output_directory 拼接完整路径
file_name = os.path.join(output_directory, f"{os.path.basename(link).split('.')[0]}.json")
with open(file_name, 'w', encoding='utf-8') as output_file:
json.dump(result_rules, output_file, ensure_ascii=False, indent=2)
return file_name
# 读取 links.txt 中的每个链接并生成对应的 JSON 文件
with open("../links.txt", 'r') as links_file:
links = links_file.read().splitlines()
list_of_links = "../links.txt"
output_dir = "./"
result_rules, file_names = parse_list_file(list_of_links, output_directory=output_dir)
result_file_names = []
for link in links:
result_file_name = parse_list_file(link, output_directory=output_dir)
result_file_names.append(result_file_name)
# 打印生成的文件名
# for file_name in result_file_names:
# print(file_name)