gistfile1.py

#!/usr/bin/python2.7

# SuperCoolPosideonShit.py!
# Now with more shit.

# Written by a really cool Debian GNU/Linux user called Tux on freenode ;)
# - http://the.leet.la

import feedparser, sys, urllib, urllib2, re, time

if len(sys.argv) <= 1:
   print "I need a URL"
   sys.exit(1)

# hardcoded atm

# Parse the feed.
# We only need to parse links.
d = feedparser.parse(sys.argv[1])

links = []
for i in d.entries:
    # we only care about edits here
    if "New user account" in i.summary:
        pass
    else:
        links.append(i.link)

# Now, mass-fetch the pages.
# We are going to impose a 0.2 second time.sleep() per fetch.

trending = []
tcount = []

for z in links:
    time.sleep(0.2)
    tmp = urllib2.urlopen(z).read()
    for match in re.finditer(r"(http|https|ftp)\://([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&amp;%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&amp;%\$#\=~_\-]+\:))*", tmp):
        tmp2 = match.group()
        if tmp2 in trending:
            s = trending.index(tmp2)
            tcount[s] = tcount[s] + 1
        else:
            trending.append(tmp2)
            tcount.append(1)

final = []

for index, url in enumerate(trending):
    if tcount[index] >= 5:
        pass
    else:
        final.append(url.split("/")[2])

for i in final:
    print i