htmlparser

htmlparser.py

from HTMLParser import HTMLParser
import urllib2

class MyHTMLParser(HTMLParser):
    def __init__(self):
        self.data=[]
        self.href=0
        self.linkname=''
        HTMLParser.__init__(self)

    def handle_starttag(self, tag, attrs):
        if tag == 'a':
            for name,value in attrs:
                if name == 'href':
                    self.href=1

    def handle_endtag(self,tag):
        if tag=='a':
            self.linkname=''.join(self.linkname.split())
            self.linkname=self.linkname.strip()
            if  self.linkname:
                self.data.append(self.linkname)
            self.linkname=''
            self.href=0

    def handle_data(self, data):
        if self.href:
            self.linkname+=data

    def getresult(self):
        for value in self.data:
            print value

def main():
    parser = MyHTMLParser()
    url = 'http://flickr.com'
    response = urllib2.urlopen(url)
    parser.feed(response.read())
    parser.getresult()
    parser.close()

if __name__ == '__main__':
    main()

http://stackoverflow.com/questions/753052/strip-html-from-strings-in-python

and,

https://docs.python.org/2/library/htmlparser.html