rjmackay · September 4, 2014 22:48 · Sep 4, 2014
diff --git a/export.py b/export.py
@@ -0,0 +1,51 @@
+# Based on http://shkspr.mobi/blog/2013/08/exporting-twitpic-images-python/
+# Modified to clean up filename
+
+import urllib
+import urllib2
+import json
+import collections
+import HTMLParser
+import time
+import os
+import re
+
+# 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=rjmackay&page="
+
+# Get the data about the target page
+for page in range(1, 100):
+  print "page " + 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 = 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 + "." + 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))