Last active
August 29, 2015 14:06
-
-
Save hugs/fa7892da03ce660c212e to your computer and use it in GitHub Desktop.
Twitpic Image and Data Archiver
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Archive your Twitpic photos and metadata | |
# | |
# A cleaned-up fork of Terence Eden's original archiver: | |
# http://shkspr.mobi/blog/2013/08/exporting-twitpic-images-python/ | |
# | |
# License: MIT | |
import urllib | |
import urllib2 | |
import json | |
import time | |
import os | |
USERNAME = "your_username_goes_here" | |
NUMBER_OF_PAGES_TO_DOWNLOAD = 5 | |
# Target Page | |
api = "https://api.twitpic.com/2/users/show.json?username=%s&page=" % USERNAME | |
# Get the data about the target page | |
for page in range(1, NUMBER_OF_PAGES_TO_DOWNLOAD+1): | |
print page | |
raw_data = urllib2.urlopen(api + str(page)) | |
json_data = json.load(raw_data) | |
# Save the page data | |
page_file = open("page-%s.json" % page,"w") | |
page_file.write(json.dumps(json_data, indent=2)) | |
page_file.close() | |
# Get the info about each image on the page | |
images = json_data["images"] | |
for item in images: | |
file_id = item["short_id"] | |
file_type = item["type"] | |
file_time = time.mktime(time.strptime(item["timestamp"], "%Y-%m-%d %H:%M:%S")) | |
file_url = "https://twitpic.com/show/full/"+file_id | |
file_name = file_id + "." + file_type | |
# Save the file | |
urllib.urlretrieve (file_url, file_name) | |
# Set the file time | |
os.utime(file_name,(file_time, file_time)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment