Twitpic HTML Parser

twitpic-sync.py

#/usr/bin/env python
#-*- encode: utf-8 -*-

import HTMLParser
import urllib2
import time

class TwitpicParser(HTMLParser.HTMLParser):
    baseurl = "http://twitpic.com/photos/"
    
    def __init__(self, username):
        HTMLParser.HTMLParser.__init__(self)
        
        self.username = username
        self._phototag = False
        self._finish = False
        self.ids = list()
    
    def start(self, pagemax = None):
        i = 1
        while True:
            page = urllib2.urlopen(self.baseurl + self.username + "?page=%d" % i).read()
            self.feed(page)
            self.reset()
            
            if self._finish == True: break
            i += 1
            time.sleep(1)
        
        return self.ids
    
    def handle_starttag(self, tag, attrs):
        if tag == "div" and ("class", "user-photo") in attrs:
            self._phototag = True
        
        if self._phototag and tag == "a":
            photoid = dict(attrs)["href"][1:]
            self._phototag = False
            
            if photoid not in self.ids:
                self.ids.append(photoid)
            else:
                self._finish = True

if __name__ == "__main__":
    username = "yourname"
    p = TwitpicParser(username)
    ids = p.start()
    
    print "Total: %d" % len(ids)
    for i in ids: print i