How to exctract title of links
raver2046
raver2046 at gmail.com
Tue Apr 26 08:20:07 EDT 2005
here i have a link <a href="http://raver2046.ath.cx/CV/">cv network
admin</a>
how to extract "cv network admin"
here is the code i have find to exctract link but not title of link
----------------------------
import htmllib, formatter, urllib
class x(htmllib.HTMLParser):
def dump(self, tag, attrs):
#print tag,
for a, v in attrs:
if a in ['a', 'src', 'href']:
print v,
print
#def do_img(self, attrs):
# self.dump('img', attrs)
def start_a(self, attrs):
self.dump('a', attrs)
#def start_form(self, attrs):
# self.dump('form', attrs)
y = x(formatter.NullFormatter())
y.feed(urllib.urlopen('http://www.aquabase.org/fish/dump.php3').read())
y.close()
----------------------------
http://raver2046.ath.cx/CV/cv_fr.html
More information about the Python-list
mailing list