def dark_start(target):
from dark_core.database.mysqlManger import sqlMg
from hiddenDetect import hiddenlink_obj
from dark_core.output.console import consoleLog
from dark_core.output.textFile import fileLog
from dark_core.output.logging import logger
from dark_core.profile.profile import pf
from dark_core.settings.settings import settings
from dark_core.parser.urlParser import url_object
from datetime import datetime
# 设置日志模块
if pf.getLogType() == "True":
file_path = settings.get("LOG_FILE_PATH")
datetimestrf = datetime.now().strftime("%Y-%m-%d")
domain = url_object(target).getRootDomain # 获取当前页面的根域名
file_name = file_path + domain + "_" + datetimestrf + ".log" # 检测文件名按域名_时间.log的形式加载
fileLog.set_file_name(file_name) # 设置日志文件名
logger.setOutputPlugin(fileLog)
else:
logger.setOutputPlugin(consoleLog)
# 执行检测
hidden = hiddenlink_obj(target)
hidden.init()
hidden.run()
hidden.finsh()
# 关闭相关数据库的连接和日志打印模块
sqlMg.dispose()
logger.endLogging()
def dark_start(target):
from dark_core.database.mysqlManger import sqlMg
from hiddenDetect import hiddenlink_obj
from dark_core.output.console import consoleLog
from dark_core.output.textFile import fileLog
from dark_core.output.logging import logger
from dark_core.profile.profile import pf
from dark_core.settings.settings import settings
from dark_core.parser.urlParser import url_object
from datetime import datetime
# 设置日志模块
if pf.getLogType() == 'True':
file_path = settings.get('LOG_FILE_PATH')
datetimestrf = datetime.now().strftime('%Y-%m-%d')
domain = url_object(target).getRootDomain # 获取当前页面的根域名
file_name = file_path + domain + '_' + datetimestrf + '.log' # 检测文件名按域名_时间.log的形式加载
fileLog.set_file_name(file_name) # 设置日志文件名
logger.setOutputPlugin(fileLog)
else:
logger.setOutputPlugin(consoleLog)
# 执行检测
hidden = hiddenlink_obj(target)
hidden.init()
hidden.run()
hidden.finsh()
# 关闭相关数据库的连接和日志打印模块
sqlMg.dispose()
logger.endLogging()
def __init__(self, url):
self.url = url
self.doc = None
self.html = None
try:
self.root = url_object(url).getRootDomain
except Exception, msg:
logger.error('Html parser initialization filed, please check it! Exception: %s' % msg)
def __init__(self, url):
self.url = url # 要加载快照生成快照的组件名
self.target = self.url.replace('/', '_')
self.root_target = url_object(self.url).getDomain
self.snapshot_path = settings.get('SNAPSHOT_PATH')
self._file_name = self.target + '_snapshot.html'
self._file_path = os.path.join(self.snapshot_path, self._file_name) # eg:/tmp/www.kingboxs.com_aaa_snapshot.html
self._initialized = False # 初始化标志
def __init__(self, url):
self.url = url # 要加载快照生成快照的组件名
self.target = self.url.replace('/', '_')
self.root_target = url_object(self.url).getDomain
self.snapshot_path = settings.get('SNAPSHOT_PATH')
self._file_name = self.target + '_snapshot.html'
self._file_path = os.path.join(
self.snapshot_path,
self._file_name) # eg:/tmp/www.kingboxs.com_aaa_snapshot.html
self._initialized = False # 初始化标志
def get_a_tag_link_list(self):
'''
描述： 获取包含link的所有<a>标签下的非css链接
'''
aTagLinkList = []
for link in self.get_links_from_doc:
if link[0].tag == 'a' and 'href' in link[0].keys():
href = link[0].get("href")
# print 'href:%s' %href
# 在上述的方法中已经将其中的链接转换为绝对路径
if href.startswith("http") and not href.endswith("css"):
rootDomain = url_object(href).getRootDomain # 获取每个链接的根域名
if rootDomain != self.root:
aTagLinkList.append(link[0])
return aTagLinkList
def __init__(self, obj):
self.obj = obj # 加载要进行报告生成的组件名
self.target = url_object(self.obj.url).getDomain
root_path = os.path.dirname(os.path.realpath(__file__)) # 获取当前文件的工作目录
self.reportPath = settings.get("REPORT_PATH") # 设置报告生成的根目录
self._initialized = False # 初始化标志
self._html_filepath = root_path + os.path.sep
self._style_main_filename = self._html_filepath + "main.css" # 加载的css文件位置
# These attributes hold the file pointers
self._file = None
datetimestrf = datetime.now().strftime("%Y-%m-%d")
self._file_name = self.target + "_" + datetimestrf + "_a.html"
self._file_path = os.path.join(self.reportPath, self._file_name)
def __init__(self, obj):
self.obj = obj # 加载要进行报告生成的组件名
self.target = url_object(self.obj.url).getDomain
root_path = os.path.dirname(os.path.realpath(__file__)) # 获取当前文件的工作目录
self.reportPath = settings.get('REPORT_PATH') # 设置报告生成的根目录
self._initialized = False # 初始化标志
self._html_filepath = root_path + os.path.sep
self._style_main_filename = self._html_filepath + 'main.css' # 加载的css文件位置
# These attributes hold the file pointers
self._file = None
datetimestrf = datetime.now().strftime('%Y-%m-%d')
self._file_name = self.target + '_' + datetimestrf + '_a.html'
self._file_path = os.path.join(self.reportPath, self._file_name)
def run(self):
while self.pageNum < 300:
self.curUrl = self.url % self.pageNum
print self.curUrl
self.curRequest = Requset(self.curUrl, 10)
self.curRequest.run()
doc = self.curRequest.get_doc()
infoTag = doc.xpath("//div[@class='info']/h3/a")
for info in infoTag:
try:
domainTitle = info.text
url = info.get("href")
url = url.replace("/site_", "http://").replace(".html", "/")
domain = url_object(url).getRootDomain
self.urlList.append((domain, domainTitle))
except Exception, e:
print "parse_web.rebot_obj.run: %s" % e
self.pageNum += 1
def run(self):
while self.pageNum < 300:
self.curUrl = self.url % self.pageNum
print self.curUrl
self.curRequest = Requset(self.curUrl, 10)
self.curRequest.run()
doc = self.curRequest.get_doc()
infoTag = doc.xpath("//div[@class='info']/h3/a")
for info in infoTag:
try:
domainTitle = info.text
url = info.get('href')
url = url.replace("/site_",
"http://").replace(".html", "/")
domain = url_object(url).getRootDomain
self.urlList.append((domain, domainTitle))
except Exception, e:
print 'parse_web.rebot_obj.run: %s' % e
self.pageNum += 1
