def checkAllow3XXDir(dirUrl):
'''
@description: 检查该目录是否都会重定向 3XX
@param {dirUrl: 输入的dirUrl,没有index.html之类的文件名}
@return: boolean
'''
randomCollect = string.ascii_letters + string.digits
randomStr1 = ''.join(random.sample(randomCollect, random.randint(20, 30)))
randomUrl1 = "%s%s.html" % (dirUrl, randomStr1)
randomStr2 = ''.join(random.sample(randomCollect, random.randint(20, 30)))
randomUrl2 = "%s%s.html" % (dirUrl, randomStr2)
# 判断是否均为3XX
try:
response1 = requests.get(randomUrl1, allow_redirects=False, timeout=3)
response2 = requests.get(randomUrl2, allow_redirects=False, timeout=3)
if response1.status_code == response2.status_code and \
300 < response1.status_code and response1.status_code < 400:
location1 = None if not "Location" in response1.headers else response1.headers[
'Location']
location2 = None if not "Location" in response2.headers else response2.headers[
'Location']
# 特殊处理下[;]/[#]/[?]的问题...
if not location1 or not location2: return None
location1 = location1.split(";")[0].split("#")[0].split("?")[0]
location2 = location2.split(";")[0].split("#")[0].split("?")[0]
# 两次随机的页面，重定向到同一个，后续不管了
if location1 and location1 == location2:
return False
except Exception as e:
print('[x] error:{}'.format(e))
tracebackLogger()
return None
return True
def getSubDirList(url):
'''
@description: 返回url的所有子路径 http://127.0.0.1/aaa/bbb/ccc/ddd.php -> aaa bbb ccc
@param {url:输入的url}
@return: 返回包含输入所有路径的list
'''
subDirList = []
# 先判断是否有协议
if not re.match(r'^https?://.+', url):
url = 'http://%s' % url
try:
# 尝试解析url
parsedUrl = urllib.parse.urlparse(url)
# 检测域名情况
if parsedUrl.netloc == '': return subDirList
# 检测域名和路径，多重路径均加入 list 中
if parsedUrl.path != '':
pathList = parsedUrl.path.split('/')
# 全是路径
if url.endswith('/'):
subDirList.extend(pathList)
# 最后一个是文件
else:
subDirList.extend(pathList[:-1])
except Exception as e:
print('[x] error:{}'.format(e))
tracebackLogger()
# 识别失败，有多少返回多少吧
pass
resultList = []
for subDir in subDirList:
if subDir == "": resultList.append(subDir)
return resultList
def _get_option(section, option):
try:
cf = ConfigParser()
cf.read(paths.CONFIG_PATH)
return cf.get(section=section, option=option)
except:
tracebackLogger()
return ''
def loadSingleDict(path):
'''
@description: 添加单个字典文件
@param {path:字典文件路径}
@return:
'''
try:
# 加载文件
with open(path) as single_file:
return single_file.read().splitlines()
except Exception as e:
tracebackLogger()
return []
def loadMultDict(path):
'''
@description: 添加多个字典文件
@param {path:字典文件路径}
@return: list:文件夹下字典文件每行的内容
'''
tmpList = []
try:
for filename in os.listdir(path):
tmpList.extend(loadSingleDict(os.path.join(path, filename)))
return tmpList
except Exception as e:
tracebackLogger()
return []
def worker(self):
'''
@description: 封包发包穷举器
@param {type}
@return:
'''
currentTaskURL = scan.taskQueue.get()
# 最新在执行的任务
scan.nowTask = currentTaskURL
scan.taskCount += 1
# 自定义 headers
headers = {}
if conf.request_headers:
for header in conf.request_headers.split(','):
k, v = header.split('=')
headers[k] = v
# 自定义 User-Agent
if conf.request_header_ua:
headers['User-Agent'] = conf.request_header_ua
# 自定义cookie
if conf.request_header_cookie:
headers['Cookie'] = conf.request_header_cookie
# 延迟请求
if conf.request_delay:
random_sleep_second = random.randint(0, abs(conf.request_delay))
time.sleep(random_sleep_second)
# 发包
try:
response = requests.request(conf.request_method,
currentTaskURL,
headers=headers,
timeout=conf.request_timeout,
verify=False,
allow_redirects=conf.redirection_302,
proxies=conf.proxy_server)
# 进入结果处理流程
self.responseHandler(currentTaskURL, response)
except requests.exceptions.Timeout as e:
# TODO:超时处理
pass
except Exception as e:
print('[x] error:{}'.format(e))
tracebackLogger()
finally:
# 更新进度
pass
def getTargetList(url):
'''
@description: 返回url的所有路径
@param {url:输入的url}
@return: 返回包含输入所有路径的list
'''
urlList = []
# 先判断是否有协议
if not re.match(r'^https?://.+', url):
url = 'http://%s' % url
try:
# 尝试解析url
parsedUrl = urllib.parse.urlparse(url)
# 检测域名情况
if parsedUrl.netloc == '': return urlList
# 检测域名和路径，多重路径均加入 list 中
if parsedUrl.path != '':
pathList = parsedUrl.path.split('/')
# 判断后缀为路径 / 文件
if pathList[-1] == '' or '.' in pathList[-1]:
pathList = pathList[:-1]
# 倒序遍历路径，添加进 list 中
for i in range(1, len(pathList))[::-1]:
targetPath = '/'.join(pathList[1:i + 1])
target = "%s://%s/%s/" % (parsedUrl.scheme, parsedUrl.netloc,
targetPath)
urlList.append(target)
# netloc 加入 list 中
target = "%s://%s/" % (parsedUrl.scheme, parsedUrl.netloc)
urlList.append(target)
except Exception as e:
print('[x] error:{}'.format(e))
tracebackLogger()
# 识别失败，有多少返回多少吧
pass
return urlList
def check404Page(url):
'''
@description: 检查404页面，收集信息
@param {url:输入的url}
@return: 返回:{"isChecked":True, "checkList":["status":200, "crc32":"xxx"]} or
{"isChecked":True, "checkList":["status":404, "crc32":""]}
'''
checkResult = {
"isChecked": False,
"checkList": [{
"status": 404,
"crc32": ""
}]
}
try:
# 随机页面
randomCollect = string.ascii_letters + string.digits
randomStr = ''.join(
random.sample(randomCollect, random.randint(20, 30)))
randomUrl = "%s%s.html" % (url, randomStr)
response = requests.get(randomUrl, timeout=3)
# 检测 status code
# 如果是 404 ，直接返回就行
if response.status_code == 404:
checkResult[
'isChecked'] = True # {"isChecked":True, "status":404, "crc32":""}
# 200的话，检查404页面的crc~
elif response.status_code == 200:
randomStr_1 = ''.join(
random.sample(randomCollect, random.randint(20, 30)))
randomUrl_1 = "%s%s.html" % (url, randomStr)
response_1 = requests.get(randomUrl_1, timeout=3)
# 替换掉可能出现的随机字符串...
path = urllib.parse.urlparse(randomUrl).path
path_1 = urllib.parse.urlparse(randomUrl).path
compText = response.text
compText_1 = response_1.text
compText = response.text.replace(path, '').replace(randomStr, '')
compText_1 = response_1.text.replace(path_1,
'').replace(randomStr_1, '')
if crc32(compText) == crc32(compText_1):
crc32Str = crc32(compText)
checkResult['isChecked'] = True
checkResult['checkList'].append({
"status": 200,
"crc32": crc32Str
})
# TODO:检查title的指定字符串？
else:
pass
# 不然就搞不定了，后续再研究是否有其他特征~
else:
pass
# 检查目录的404问题，有些网站 xxx.html 和 xxx/ 返回不一样的404...
randomUrl = "%s%s/" % (url, randomStr)
response = requests.get(randomUrl, timeout=3)
# 检测 status code
# 如果是 404 ，直接返回就行
if response.status_code == 404:
checkResult['isChecked'] = True
# 200的话，检查404页面的crc~
elif response.status_code == 200:
randomStr_1 = ''.join(
random.sample(randomCollect, random.randint(20, 30)))
randomUrl_1 = "%s%s/" % (url, randomStr)
response_1 = requests.get(randomUrl_1, timeout=3)
# 替换掉可能出现的随机字符串...
path = urllib.parse.urlparse(randomUrl).path
path_1 = urllib.parse.urlparse(randomUrl).path
compText = response.text
compText_1 = response_1.text
compText = response.text.replace(path, '').replace(randomStr, '')
compText_1 = response_1.text.replace(path_1,
'').replace(randomStr_1, '')
if crc32(compText) == crc32(compText_1):
crc32Str = crc32(compText)
checkResult['isChecked'] = True
checkResult['checkList'].append({
"status": 200,
"crc32": crc32Str
})
except Exception as e:
tracebackLogger()
return checkResult