import htmllib, formatter,re,string
import urllib, htmllib, sys

class LinksExtractor(htmllib.HTMLParser): # derive new HTML parser

   def __init__(self, formatter) :        # class constructor
      htmllib.HTMLParser.__init__(self, formatter)  # base class constructor
      self.links = []        # create an empty list for storing hyperlinks

   def start_a(self, attrs) :  # override handler of <A ...>...</A> tags
      # process the attributes
      if len(attrs) > 0 :
         
         for attr in attrs :
            if attr[0] == "href" :         # ignore all non HREF attributes
                self.links.append(attr[1]) # save the link info in the list

   def get_links(self) :     # return the list of extracted links
        return self.links


format = formatter.NullFormatter()           # create default formatter
htmlparser = LinksExtractor(format)        # create new parser object

if len(sys.argv) < 2:
    print "ERROR: Provide linklist filename"
    sys.exit(0)
if len(sys.argv) == 2:
    sys.argv = sys.argv + ['']    
allLinks = []
linklist = open(sys.argv[1],'r')
while True:
    link = linklist.readline()
    if not link:
        break
    print "now processing: " + link.rstrip()
    data = urllib.urlopen(link.rstrip())
    #if sys.argv[2] == 'see':
    #    while True:
    #        sent = data.readline()
    #        if 'a name="See_also"' in sent:
    #            htmlparser.feed(data.read())      # parse the file saving the info about links
    #            break
    #        if '</html>' in sent:
    #            print "empty link: " + link.rstrip()
    #            break
    #else:
    htmlparser.feed(data.read())      # parse the file saving the info about links
 
allLinks = htmlparser.get_links()   # get the hyperlinks list

print len(allLinks)
cleanLink= {}
for link in allLinks:   
    if not ':' in link:
        if not '#' in link:
            if link in cleanLink:
                cleanLink[link] = cleanLink[link] + 1
            else:
                cleanLink[link] = 1
    
print len(cleanLink)

sortedDict =  sorted(cleanLink.iteritems(), key=lambda (k,v):(v,k), reverse=True)
for link in sortedDict:
    print link