auto download photos from fanfou 5th birthday page

fanfou_5th_photo_spider.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

#code by from1to9
#05/11/2012
#from1to9[at]gmail.com
#
#you have to make a folder by yourself named "photo" where photos will be stored in the same folder of this script
#a file named "last.txt" will be made in this folder, it keeps the start photo id, delete it and the script will download all photos again



import codecs
import json, random
import urllib, urllib2

def put_last_id(id):
	try:
		f = file("last.txt","w")
		f.write(str(id))
		f.close
	except:
		pass
	
def get_last_id():
	try:
		f = file("last.txt","r")
		rev = f.readline()
		f.close
	except:
		rev = 0
	return rev
	
	
def getURL(url):
	try:
		req = urllib2.Request(url = url)
		response = urllib2.urlopen(req)
		context = response.read()
		rev = json.loads(context.decode('utf-8'))
	except:
		rev = json.loads("{}")
	return rev
	
def savePic(url, id):
	try:
		req = urllib2.Request(url)
		response = urllib2.urlopen(req)
		context = response.read()
		f = file("photo\%s_%d.jpg" % ( id , random.randrange(0, 999) ),"wb")
		f.write(context)
		f.close()
	except:
		pass

def do_list(list, last_id):
	for photo in list:
		pid = photo["id"]
		if pid > last_id:
			savePic(photo["largeurl"], photo["user_id"])
			try:
				print "finish @%s" % photo["user_screen_name"]
			except:
				print "finish a new photo"
		
	return pid

last_id = int(get_last_id())
list = getURL( "http://5.fanfou.com/exp/ajax/photos")
if len(list) > 0:
	first_id = list["photos"][0]["id"]
	put_last_id(first_id)
	save_id = do_list(list["photos"], last_id)
	while list["has_more"] and save_id > last_id:
		if len(list) > 0:
			list = getURL( "http://5.fanfou.com/exp/ajax/photos?max_id=" + str(save_id))
			save_id = do_list(list["photos"], last_id)
print "all done"