htmllib & do_meta question
Marcus Schopen
marcus.schopen at uni-bielefeld.de
Thu May 2 23:13:13 EDT 2002
Hi,
I use this for parsing a HTML File for META TAGS description and
keywords. It seems to work fine. Did I miss something or is there a
better way to do this?
Thanks
Marcus
class WPage(htmllib.HTMLParser):
def __init__(self, verbose=0):
self.description = ""
self.keywords = ""
htmllib.HTMLParser.__init__(self, formatter.NullFormatter(),
verbose)
def do_meta(self, attributes):
name = content = ""
for key, value in attributes:
if key == "name":
name = value
elif key == "content":
content = value
if string.lower(name) == "description":
self.description = string.strip(content)
elif string.lower(name) == "keywords":
self.keywords = string.strip(content)
file = open("test.html")
html = file.read()
file.close()
p = WPage()
p.feed(html)
p.close()
descr = p.description
keys = p.keywords
--
Petition for a Software Patent Free Europe
http://petition.eurolinux.org
More information about the Python-list
mailing list