130 lines
3.8 KiB
Python
130 lines
3.8 KiB
Python
# -*- coding: UTF-8 -*-
|
|
'''
|
|
@Project :domainScanDemo
|
|
@File :aizhan_detector.py
|
|
@IDE :PyCharm
|
|
@Author :梦伴
|
|
@Date :2026/4/9 0:02
|
|
@explain : 爱站网检测器
|
|
'''
|
|
|
|
import requests
|
|
from curl_cffi import requests as curl_requests
|
|
import re
|
|
from app.detectors.base import BaseDetector
|
|
|
|
|
|
class AizhanDetector(BaseDetector):
|
|
"""
|
|
爱站网检测器
|
|
"""
|
|
|
|
def __init__(self):
|
|
"""
|
|
初始化爱站网检测器
|
|
"""
|
|
super().__init__()
|
|
self.url = 'https://www.aizhan.com'
|
|
self.query_url = 'https://www.aizhan.com/cha/{domain}'
|
|
|
|
def check_domain(self, domain):
|
|
"""
|
|
检测域名
|
|
|
|
:param domain: 域名
|
|
:return: dict - 检测结果
|
|
"""
|
|
try:
|
|
# 构建查询URL
|
|
query_url = self.query_url.format(domain=domain)
|
|
|
|
headers = {
|
|
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/146.0.0.0 Safari/537.36'
|
|
}
|
|
|
|
# 使用curl_cffi模拟浏览器
|
|
response = curl_requests.get(query_url, headers=headers, impersonate='chrome', timeout=10)
|
|
|
|
if response.status_code == 200:
|
|
content = response.text
|
|
|
|
# 提取标题
|
|
title = self._extract_title(content)
|
|
|
|
# 提取风险信息
|
|
risk = self._extract_risk(content)
|
|
|
|
# 检查是否包含敏感词
|
|
has_sensitive = self._check_sensitive(title, risk)
|
|
|
|
return {
|
|
'title': title,
|
|
'risk': risk,
|
|
'has_sensitive': has_sensitive
|
|
}
|
|
else:
|
|
self._log_warning(f"爱站网查询失败: {response.status_code}")
|
|
return {'title': '', 'risk': '', 'has_sensitive': False}
|
|
except Exception as e:
|
|
return self._handle_exception(e, domain)
|
|
|
|
def _extract_title(self, content):
|
|
"""
|
|
提取标题
|
|
|
|
:param content: 页面内容
|
|
:return: str - 标题
|
|
"""
|
|
try:
|
|
pattern = r'<title>(.*?)</title>'
|
|
match = re.search(pattern, content)
|
|
if match:
|
|
return match.group(1).strip()
|
|
return ''
|
|
except Exception as e:
|
|
self._handle_exception(e, 'extract_title')
|
|
return ''
|
|
|
|
def _extract_risk(self, content):
|
|
"""
|
|
提取风险信息
|
|
|
|
:param content: 页面内容
|
|
:return: str - 风险信息
|
|
"""
|
|
try:
|
|
# 这里需要根据实际页面结构调整正则表达式
|
|
pattern = r'百度网址检测：<span[^>]+>(.*?)</span>'
|
|
match = re.search(pattern, content)
|
|
if match:
|
|
return match.group(1).strip()
|
|
return ''
|
|
except Exception as e:
|
|
self._handle_exception(e, 'extract_risk')
|
|
return ''
|
|
|
|
def _check_sensitive(self, title, risk):
|
|
"""
|
|
检查是否包含敏感词
|
|
|
|
:param title: 标题
|
|
:param risk: 风险信息
|
|
:return: bool - 是否包含敏感词
|
|
"""
|
|
# 风险类型
|
|
sensitive_risks = ['低风险', '疑似色情博彩风险', '严重影响权重']
|
|
|
|
# 敏感词
|
|
sensitive_words = ['色情', '赌博', '博彩', '毒品', '暴力', '诈骗']
|
|
|
|
# 检查风险
|
|
for r in sensitive_risks:
|
|
if r in risk:
|
|
return True
|
|
|
|
# 检查标题
|
|
for word in sensitive_words:
|
|
if word in title:
|
|
return True
|
|
|
|
return False |