Twitpic

twitpic_export.py

# Based on https://gist.github.com/rjmackay/aa0dfcdf9eb313361db7
# Modified to clean up filename
# pp on https://github.com/taichino/prettyprint
# Properties
#   {username} : your account user name

import urllib
import urllib2
import json
import collections
import HTMLParser
import time
import os
import re

try:
  import json
except ImportError:
  import simplejson as json

class MyEncoder (json.JSONEncoder):
    def default(self, o):
        try:
            iterable = iter(o)
        except TypeError:
            pass
        else:
            return list(iterable)

        try:
            return json.JSONEncoder.default(self, o)
        except TypeError:
            return str(o)

def pp_str(obj):
  orig = json.dumps(obj,
               indent=4,
               sort_keys=True,
               skipkeys=True,
               cls=MyEncoder)
  return eval("u'''%s'''" % orig).encode('utf-8')

def pp(obj):
  print pp_str(obj)

if __name__ == '__main__':
  # Create a parser for HTML entities
  h = HTMLParser.HTMLParser()

  # Maximum filename length
  # Last 4 characters will be .jpg or .png etc
  max_length = os.statvfs('.').f_namemax - 4

  # Target Page
  twitpic_api = "http://api.twitpic.com/2/users/show.json?username=makietan&page="

  # Get the data about the target page
  for page in range(1, 100):
    print "page " + str(page)
    twitpic_data = json.load(urllib2.urlopen(twitpic_api + str(page)))

    # Get the info about each image on the page
    twitpic_images = twitpic_data["images"]

    for item in twitpic_images:
      twitpic_id = item['short_id']
      twitpic_title = unicode(item["message"])
      # Replace / (which can't be used in a file name) with a similar looking character
      twitpic_title = twitpic_title.replace('/', u'\u2044')
      twitpic_title = twitpic_title[:max_length]
      twitpic_file_type = item["type"]
      twitpic_time = time.mktime(time.strptime(item["timestamp"], "%Y-%m-%d %H:%M:%S"))
      twitpic_file_url = "http://twitpic.com/show/full/" + twitpic_id

      twitpic_file_name = h.unescape(twitpic_title).lower().replace(" ", "-")
      twitpic_file_name = re.sub(r'[^A-Za-z-]','', twitpic_file_name)
      if (twitpic_file_name == ""):
        twitpic_file_name = twitpic_id
      twitpic_file_name = twitpic_file_name  + "_" + str(twitpic_time) + "." + twitpic_file_type
      print twitpic_file_name

      # Save the file
      urllib.urlretrieve (twitpic_file_url, twitpic_file_name)
      # Set the file time
      os.utime(twitpic_file_name,(twitpic_time, twitpic_time))

      pp(item)

簡単に上書きされてしまうのでファイル名にタイムスタンプをつけた