I want to find the span tag beween the LI tag and its attributes. Trying with beautful soap but no luck. Details of my code. Is any one point me right methodlogy
In this this code, my getId function should return me id = "0_False-2"
Any one know right method?
from BeautifulSoup import BeautifulSoup as bs
import re
html = '<ul>\
<li class="line"> </li>\
<li class="folder-open-last" id="0">\
<img style="float: left;" class="trigger" src="/media/images/spacer.gif" border="0">\
<span class="text" id="0_False">NOC</span><ul style="display: block;"><li class="line"> </li><li class="doc" id="1"><span class="active text" id="0_False-1">PNQAIPMS1</span></li><li class="line"> </li><li class="doc-last" id="2"><span class="text" id="0_False-2">PNQAIPMS2</span></li><li class="line-last"></li></ul></li><li class="line-last"></li>\
</ul>'
def getId(html, txt):
soup = bs(html)
soup.findAll('ul',recursive=False)
head = soup.contents[0]
temp = head
elements = {}
while True:
# It temp is None that means no HTML tags are available
if temp == None:
break
#print temp
if re.search('li', str( temp)) != None:
attr = str(temp.attrs).encode('ascii','ignore')
attr = attr.replace(' ', '')
attr = attr.replace('[', '')
attr = attr.replace(']', '')
attr = attr.replace(')', '')
attr = attr.replace('(', '')
attr = attr.replace('u\'', '')
attr = attr.replace('\'', '')
attr = attr.split(',')
span = str(temp.text)
if span == txt:
return attr[3]
temp = temp.next
else:
temp = temp.next
id = getId(html,"PNQAIPMS2")
print "ID = " + id