</td>
<td>
杂项测试
</td>
<td>
<font color=#FF00FF>高风险</font>
</td>
</tr>
</table>
</div>
</body>
</html>
Python程序
html_get.py
class CustomParser(HTMLParser.HTMLParser):
'''
定义一个新的HTMLParser类,覆盖用到的方法
'''
cve_list = []
sigle_cve = []
selected = ('table', 'div', 'tr', 'td', 'a','font') #需要解析的标签
selected_a = ['table/div/tr/td/a'] #需要获取标签a数据的路径
selected_font = ['table/div/tr/td/font'] #需要获取标签font数据的路径
def reset(self):
HTMLParser.HTMLParser.reset(self)
self._level_stack = []
def handle_starttag(self, tag, attrs):
if tag in CustomParser.selected:
self._level_stack.append(tag)
def handle_endtag(self, tag):
if self._level_stack and tag in CustomParser.selected and tag == self._level_stack[-1]:
self._level_stack.pop()
def handle_data(self, data):
#我们将需要获取的数据放到一个list中，同时每一个漏洞的数据会放到一个小的listz中
#如[[名称,CVE,风险],[名称，CVE,风险]],这里拿到的是全部HTML中的数据
if "/".join(self._level_stack) in CustomParser.selected_a and not CustomParser.sigle_cve:
print self._level_stack, data.decode('gbk').encode('utf-8')
CustomParser.sigle_cve.append(data.decode('gbk').encode('utf-8').strip())
elif "/".join(self._level_stack) in CustomParser.selected_a:
print self._level_stack, data.decode('gbk').encode('utf-8').strip()
CustomParser.sigle_cve.append(data.decode('gbk').encode('utf-8').strip())
elif "/".join(self._level_stack) in CustomParser.selected_font and CustomParser.sigle_cve:
print self._level_stack, data.decode('gbk').encode('utf-8').strip()
CustomParser.sigle_cve.append(data.decode('gbk').encode('utf-8').strip())
CustomParser.cve_list.append(CustomParser.sigle_cve)
CustomParser.sigle_cve = []
if __name__ == '__main__':
'''
读取，判断是否为高风险，是的打印出来
'''
try:
fd = open('test.html','r')
except Exception,error:
print error
html_string = fd.read()
ht = CustomParser()
ht.feed(html_string)
get_list = ht.cve_list
for item in get_list:
if item[-1] == '高风险':
print item
fd.close()