link_extractor

#-*- coding: utf-8 -*-
import urllib
from bs4 import BeautifulSoup
 
#----------------------------------------------------------------------

## Print all links from a .html
def print_type_from_site(fpath,tag1,tag2):
    f = open(fpath,'r');
    lines = f.readlines()
    for line in lines:
        soup = BeautifulSoup(line)    
        #EDIT - <a> tag + <class> name tag
        links=soup.findAll(tag1)    
        
        x=[]
        if links is not None :
            try:
                for u in links:
                    type_url = u[tag2].lower()
                    if type_url is not None:
                        l = type_url.encode('ascii','ignore')
                        print l
            except Exception, e:
                print e
        
    f.close()
#----------------------------------------------------------------------
if __name__ == "__main__":
    #EDIT
    fpath = 'index_real_.html'
    print_type_from_site(fpath,'img','src')
    print_type_from_site(fpath,'a','href')