I want to find the span tag beween the LI tag and its attributes but no luck.

Question

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">&nbsp;</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">&nbsp;</li><li class="doc" id="1"><span class="active text" id="0_False-1">PNQAIPMS1</span></li><li class="line">&nbsp;</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

Answer 1

I am sure someone can show you the BS way, but here's my approach. Just plain old Python string manipulation.

html = '<ul>\
<li class="line">&nbsp;</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">&nbsp;</li><li class="doc" id="1"><span class="active text" id="0_False-1">PNQAIPMS1</span></li><li class="line">&nbsp;</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):
    for LI in html.split("</li>"):
        if "span" in LI:
            for CL in LI.split("span"):
                  if "class" in CL and "id" in CL and "text" in CL and txt in CL:
                       return CL.split("id=")[-1].split('">')[0].replace('"',"")

print "id for PNQAIPMS2: " , getId(html,"PNQAIPMS2")
print "id for NOC: ",getId(html, "NOC")
print "id for PNQAIPMS1: ",getId(html, "PNQAIPMS1")

output

$ ./python.py
id for PNQAIPMS2:  0_False-2
id for NOC:  0_False
id for PNQAIPMS1:  0_False-1