From b325ab75bfa6c5e882d642ad05d756f59eb77d82 Mon Sep 17 00:00:00 2001
From: frxz751113 <156018267+frxz751113@users.noreply.github.com>
Date: Wed, 25 Sep 2024 00:26:05 +0800
Subject: [PATCH] =?UTF-8?q?Update=20IP=E6=AF=94=E5=AF=B9.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 py/IP比对.py | 98 ++++++++++++++++++++++++++++++++--------------------
 1 file changed, 60 insertions(+), 38 deletions(-)

diff --git a/py/IP比对.py b/py/IP比对.py
index 0907184..ec925eb 100644
--- a/py/IP比对.py
+++ b/py/IP比对.py
@@ -1,47 +1,69 @@
-import re
+def extract_unique_lines(file1_path, file2_path, output_path):
+    # 用于存储两个文件中所有行的集合
+    all_lines_set = set()
+    # 用于存储两个文件中重复行的集合
+    duplicate_lines_set = set()
 
-def compare_and_write_uniques(file1_path, file2_path, output_path):
-    # 正则表达式模式，用于匹配IP地址和域名
-    ip_pattern = r'\b(?:\d{1,3}\.){3}\d{1,3}\b'
-    domain_pattern = r'\b(?:[a-zA-Z0-9-]+\.)+[a-zA-Z]{2,}\b'
-
-    # 用于存储第二个文件中的IP地址和域名集合
-    file2_ips_and_domains = set()
-
-    # 读取第二个文件，提取IP地址和域名并添加到集合
-    with open(file2_path, 'r', encoding='utf-8') as file2:
-        content2 = file2.read()
-        # 查找IP地址并添加到集合
-        ips = re.findall(ip_pattern, content2)
-        file2_ips_and_domains.update(ips)
-        # 查找域名并添加到集合
-        domains = re.findall(domain_pattern, content2)
-        file2_ips_and_domains.update(domains)
-
-    # 用于存储要写入新文件的独特IP地址和域名
-    unique_ips_and_domains = set()
-
-    # 读取第一个文件，检查IP地址和域名是否在第二个文件集合中不存在
+    # 读取第一个文件的每一行，添加到集合中
     with open(file1_path, 'r', encoding='utf-8') as file1:
-        content1 = file1.read()
-        # 查找IP地址
-        ips_in_file1 = re.findall(ip_pattern, content1)
-        for ip in ips_in_file1:
-            if ip not in file2_ips_and_domains:
-                unique_ips_and_domains.add(ip)
-        # 查找域名
-        domains_in_file1 = re.findall(domain_pattern, content1)
-        for domain in domains_in_file1:
-            if domain not in file2_ips_and_domains:
-                unique_ips_and_domains.add(domain)
+        for line in file1:
+            line = line.strip()
+            all_lines_set.add(line)
+            if line in duplicate_lines_set:
+                continue
+            duplicate_lines_set.add(line)
 
-    # 将独特的IP地址和域名写入新文件
+    # 读取第二个文件的每一行，检查是否在第一个文件中出现过，处理后添加到相应集合
+    with open(file2_path, 'r', encoding='utf-8') as file2:
+        for line in file2:
+            line = line.strip()
+            if line in all_lines_set:
+                duplicate_lines_set.add(line)
+            else:
+                all_lines_set.add(line)
+
+    # 找到不重复的行
+    unique_lines = all_lines_set - duplicate_lines_set
+
+    # 将不重复的行写入新文件
     with open(output_path, 'w', encoding='utf-8') as output_file:
-        for item in unique_ips_and_domains:
-            output_file.write(item + '\n')
+        for line in unique_lines:
+            output_file.write(line + '\n')
 
 # 示例用法
 file1_path = '无效IP.txt'
 file2_path = '网络收集.txt'
 output_path = '无效IP.txt'
-compare_and_write_uniques(file1_path, file2_path, output_path)
+extract_unique_lines(file1_path, file2_path, output_path)
+
+import re
+
+def extract_ips_and_domains(input_file_path, output_file_path):
+    # 正则表达式模式，用于匹配IP地址和域名
+    ip_pattern = r'\b(?:\d{1,3}\.){3}\d{1,3}\b'
+    domain_pattern = r'\b(?:[a-zA-Z0-9-]+\.)+[a-zA-Z]{2,}\b'
+
+    # 集合用于存储提取到的IP地址和域名，确保唯一性
+    ips_and_domains = set()
+
+    # 打开输入文件并读取内容
+    with open(input_file_path, 'r', encoding='utf-8') as input_file:
+        content = input_file.read()
+
+        # 查找IP地址并添加到集合
+        ips = re.findall(ip_pattern, content)
+        ips_and_domains.update(ips)
+
+        # 查找域名并添加到集合
+        domains = re.findall(domain_pattern, content)
+        ips_and_domains.update(domains)
+
+    # 打开输出文件并写入提取到的IP地址和域名
+    with open(output_file_path, 'w', encoding='utf-8') as output_file:
+        for item in ips_and_domains:
+            output_file.write(item + '\n')
+
+# 示例用法
+input_file_path = '无效IP.txt'
+output_file_path = '无效IP.txt'
+extract_ips_and_domains(input_file_path, output_file_path)