Dribbble Parser

import numpy as np
import json
import bson
import urllib
from HTMLParser import HTMLParser
from urllib import urlopen
import re
import urllib2,cookielib

hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
       'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
       'Accept-Encoding': 'none',
       'Accept-Language': 'en-US,en;q=0.8',
       'Connection': 'keep-alive'}

class MyHTMLParser(HTMLParser):
    def __init__(self):
        HTMLParser.__init__(self)
        self.source = 0
        self.name = 0
        self.likes_count = 0
        self.views_count = 0
        self.attach = 0
        self.color = 0
        self.tags = 0
        self.tag = 0
        self.p = 0

        self.json_name = ''
        self.json_date = ''
        self.json_attachments = []
        self.json_small_link = ''
        self.json_big_link = ''
        self.json_likes_count = 0
        self.json_views_count = 0
        self.json_colors = []
        self.json_tags = []
        self.json_description = ''

    def handle_starttag(self, tag, attrs):
        if tag == 'source':
            self.source += 1
            for name, value in attrs:
                if self.source == 3 and name == 'srcset':
                    self.json_big_link = value
                if self.source == 4 and name == 'srcset':
                    self.json_small_link = value
        if tag == 'h1':
            self.name = 1
        if tag == 'span':
            for name, value in attrs:
                if name == 'class' and value == 'stats-label likes-count':
                    self.likes_count = 1
                if name == 'class' and value == 'views-count stats-num':
                    self.views_count = 1

        if tag == 'a':
            for name, value in attrs:
                if name == 'href' and '/shots?date' in value:
                    self.json_date = value[12:]
                if name == 'data-title':
                    self.attach = 1
                if name == 'href' and self.attach == 1:
                    self.attach = 0
                    self.json_attachments.append('https://dribbble.com' + value)
                if name == 'style' and 'background-color' in value:
                    self.color = 1
        if tag == 'div':
            for name, value in attrs:
                if name == 'class' and value == 'tags-section':
                    self.tags = 1
        if tag == 'strong' and self.tags == 1:
            self.tag = 1
        if tag == 'p':
            self.p += 1




    def handle_endtag(self, tag):
        if tag == 'div' and self.tags == 1:
            self.tags = 0


    def handle_data(self, data):
        if self.name == 1:
            self.name = 0
            self.json_name = data
        if self.likes_count == 1:
            self.likes_count= 0
            lines = data.split('\n')
            likes = lines[1].replace(',', '').replace(lines[1][0], '')
            self.json_likes_count = int(likes)
        if self.views_count == 1:
            self.views_count = 0
            lines = data.split('\n')
            views = lines[1].replace(',', '').replace(lines[1][0], '')
            self.json_views_count = int(views)
        if self.color == 1:
            self.color = 0
            self.json_colors.append(data)
        if self.tag == 1:
            self.tag = 0
            self.json_tags.append(data)
        if self.p == 2:
            self.p += 1
            self.json_description = data

for i in range(1):
    json_id = 3590389 + i
    site= "https://dribbble.com/shots/"+str(json_id)
    req = urllib2.Request(site, headers=hdr)
    try:
        page = urllib2.urlopen(req)
    except urllib2.HTTPError, e:
        print site
    content = page.read()
    parser = MyHTMLParser()
    parser.feed(content)
    print 'url: ', site
    print 'id: ', json_id
    print 'small_link: ', parser.json_small_link
    print 'big_link: ', parser.json_big_link
    print 'name: ', parser.json_name
    print 'likes: ', parser.json_likes_count
    print 'views: ', parser.json_views_count
    print 'date: ', parser.json_date
    print 'attach: ', parser.json_attachments
    print 'colors: ', parser.json_colors
    print 'tag: ', parser.json_tags
    print 'description: ', parser.json_description