ProvoWallis wrote:
> Thanks. One more question, though.
>
> I'm not sure how to limit the scope of my search so that I'm just
> extracting the id attribute from the sections that I want. I.e., I want
> the id attributes from the forms in sections 1 and 3 but not from 2.
>
> Maybe I'm missing something.
>
If the data has closing tags this is easily achieved using a dom or sax
parser, but here is a slightly modified version, very ugly but simple.
hope this helps.
Adonis
---
from HTMLParser import HTMLParser
data = """<main-section no="1">
<form id="graphic_1.tif">
<form id="graphic_2.tif">
<main-section no="2">
<form id="graphic_3.tif">
<main-section no="3">
<form id="graphic_4.tif">
<form id="graphic_5.tif">
<form id="graphic_6.tif">
"""
class ParseForms(HTMLParser):
_section = None
_secDict = dict()
def getSection(self, key):
return self._secDict.get(str(key))
def handle_starttag(self, tag, attrs):
if tag == "form":
if not self._secDict.has_key(self._section):
self._secDict[self._section] = [dict(attrs).get('id')]
else:
self._secDict[self._section].append(dict(attrs).get('id'))
if tag == "main-section":
self._section = dict(attrs).get('no')
if __name__ == "__main__":
parser = ParseForms()
parser.feed(data)
print parser.getSection(1)
print parser.getSection(3)
--
http://mail.python.org/mailman/listinfo/python-list
