For the last few years I've been taking photos of my daily life and posting them on instagram. And for the last year and a halfish I've been using https://github.com/tryghost/ghost as a backend for my blog.

One of the major things that I thought was missing and really wanted to setup was cross posting from instagram on my personal blog. This includes grabbing the source images via the instagram API, storing them in S3, and creating a post.

I had written a script that would grab images and upload them to s3, and I was manually posting things every month or two. But with some down time over the recent holiday I made a poorly written end-to-end sync tool that backs up the instagram images and posts them to the blog. The script is below:

#!/usr/bin/env python

import json  
import os  
import requests

from boto.s3.connection import S3Connection  
from boto.s3.key import Key

import urllib2  
import StringIO  
import datetime

from slugify import slugify

global CONN

auth_token = 'instagram-api-token'

try:  
    AWS_ACCESS_KEY = os.environ['AWS_ACCESS_KEY']
    AWS_SECRET_KEY = os.environ['AWS_SECRET_KEY']
    AWS_BUCKET_NAME = os.environ.get('instascraper_bucket', 'bucketname')
    CONN = S3Connection(AWS_ACCESS_KEY, AWS_SECRET_KEY)
except Exception, e:  
    print 'AWS Credentials were not properly set'


def _key_name(id):  
    return 'instagram-photos/%s.png' % id


def get_ghost_token():  
    res = requests.post('http://jake.ai/ghost/api/v0.1/authentication/token', data={
        'username': 'foo@bar.com',
        'password': 'password-goes-here',
        'grant_type': 'password',
        'client_id': 'ghost-admin',
        'client_secret': 'q0f8hqf0hq'
    })

    return json.loads(res.content)['access_token']


def create_post(title, created_time, html):  
    token = get_ghost_token()

    try:
        slug = slugify(title)
    except Exception:
        slug = '(untitled)'

    pd = dict(author="1",
              featured=False,
              image=None,
              language="en_US",
              markdown=html,
              meta_description=None,
              meta_title=title,
              page=False,
              published_by=None,
              slug=slug,
              status="published",
              tags=[{
                  "id": 7,
                  "uuid": "041d5867-9bcf-4f9e-a5a5-51cf7ab541d0",
                  "name": "insta",
                  "slug": "insta",
              }],
              title=title,
              published_at=created_time)

    h = {'Authorization': 'Bearer %s' % token, 'Content-Type': 'application/json'}
    res = requests.post('http://jake.ai/ghost/api/v0.1/posts',
                        json=dict(posts=[pd]), headers=h)

class InstagramPhoto(object):  
    def __init__(self, image_dict):
        super(InstagramPhoto, self).__init__()
        self.id = image_dict.get('id')
        self.caption = None
        self.created_time = None
        if image_dict.get('caption'):
            self.caption = image_dict['caption'].get('text')
        self.instagram_image_url = image_dict['images']['standard_resolution']['url']
        self.instagram_url = image_dict.get('link')
        self.created_time = datetime.datetime.fromtimestamp(float(image_dict.get('created_time'))).strftime('%Y-%m-%d %H:%M:%S')

        self.s3_url = None

    def __repr__(self):
        return "InstagramPhoto(id=%s)" % (self.id)

    def upload_to_s3(self):
        bucket = CONN.get_bucket(AWS_BUCKET_NAME)
        if bucket.get_key(_key_name(self.id)):
            print 'This image already exists in s3: %s' % self.id
            k = Key(bucket)
            k.key = _key_name(self.id)
            self.s3_url = k.generate_url(expires_in=0, query_auth=False)
            return False
        try:
            k = Key(bucket)
            k.key = _key_name(self.id)

            file_handle = urllib2.urlopen(self.instagram_image_url)
            file_content = StringIO.StringIO(file_handle.read())
            k.set_contents_from_file(file_content)
            k.set_acl('public-read')
            self.s3_url = k.generate_url(expires_in=0, query_auth=False)
            return True
        except Exception, e:
            print 'An error occured trying to upload %s: %s' % (self.id, e)

    def post_to_blog(self):
        raw_body = '''<a href="%(instagram_url)s"><img src="%(image_url)s" class="instagram" alt="%(caption)s"></a>'''
        body = raw_body % {
            'instagram_url': self.instagram_url,
            'image_url': self.s3_url,
            'caption': self.caption
        }
        post = {'title': self.caption, 'html': body, 'status': 'draft',
                'created_time': self.created_time}

        create_post(post.get('title'), post.get('created_time'),
                    post.get('html'))


raw_images = requests.get('https://api.instagram.com/v1/users/self/media/recent', params={  
    'access_token': auth_token,
    'count': 1000
}).json()['data']

photos = [InstagramPhoto(p) for p in raw_images]

for p in photos:  
    if p.upload_to_s3():
        p.post_to_blog()