Parsing an HTML a tag

[George]

How can I parse an HTML file and collect only that the A tags. I have a
start for the code but an unable to figure out how to finish the code.
HTML_parse gets the data from the URL document. Thanks for the help

def HTML_parse(data ):
from HTMLParser import HTMLParser
parser = MyHTMLParser()

parser.feed(dat a)

class MyHTMLParser(HT MLParser):

def handle_starttag (self, tag, attrs):

def handle_endtag(s elf, tag):

def read_page(URL):
"this function returns the entire content of the specified URL
document"
import urllib
connect = urllib.urlopen( url)
data = connect.read()
connect.close()
return data

[George Sakkis]

"George" <bu*******@hotm ail.com> wrote:

I'm very new to python and I have tried to read the tutorials but I am
unable to understand exactly how I must do this problem.

Specifically, the showIPnums function takes a URL as input, calls the
read_page(url) function to obtain the entire page for that URL, and
then lists, in sorted order, the IP addresses implied in the "<A
HREF=· · ·>" tags within that page.
"""
Module to print IP addresses of tags in web file containing HTML

showIPnums('htt p://22c118.cs.uiowa .edu/uploads/easy.html') ['0.0.0.0', '128.255.44.134 ', '128.255.45.54']
showIPnums('htt p://22c118.cs.uiowa .edu/uploads/pytorg.html') ['0.0.0.0', '128.255.135.49 ', '128.255.244.57 ', '128.255.30.11' ,
'128.255.34.132 ', '128.255.44.51' , '128.255.45.53' ,
'128.255.45.54' , '129.255.241.42 ', '64.202.167.129 ']

"""

def read_page(url):
import formatter
import htmllib
import urllib

htmlp = htmllib.HTMLPar ser(formatter.N ullFormatter())
htmlp.feed(urll ib.urlopen(url) .read())
htmlp.close()

def showIPnums(URL) :
page=read_page( URL)

if __name__ == '__main__':
import doctest, sys
doctest.testmod (sys.modules[__name__])

You forgot to mention that you don't want duplicates in the result. Here's a function that passes
the doctest:

from urllib import urlopen
from urlparse import urlsplit
from socket import gethostbyname
from BeautifulSoup import BeautifulSoup

def showIPnums(url) :
"""Return the unique IPs found in the anchors of the webpage at the given
url.

showIPnums('htt p://22c118.cs.uiowa .edu/uploads/easy.html') ['0.0.0.0', '128.255.44.134 ', '128.255.45.54'] showIPnums('htt p://22c118.cs.uiowa .edu/uploads/pytorg.html')

['0.0.0.0', '128.255.135.49 ', '128.255.244.57 ', '128.255.30.11' , '128.255.34.132 ',
'128.255.44.51' , '128.255.45.53' , '128.255.45.54' , '129.255.241.42 ', '64.202.167.129 ']
"""
hrefs = set()
for link in BeautifulSoup(u rlopen(url)).fe tch('a'):
try: hrefs.add(getho stbyname(urlspl it(link["href"])[1]))
except: pass
return sorted(hrefs)
HTH,
George