flickr_chronam.py

#!/usr/bin/env python

"""
Print out a list of links between Flickr and Chronicling America. These are newspaper pages that have had images extracted from them, that have been uploaded to Flickr by Dave Woodward.
"""

import json
import urllib

# http://www.flickr.com/services/api/keys/
key = 'REAL_FLICKR_KEY_HERE'

def newspaper_photo_ids():
    u = 'http://api.flickr.com/services/rest/?method=flickr.photosets.getPhotos&api_key=%s&photoset_id=72157619452486566&format=json&nojsoncallback=1' % key
    photos = json.loads(urllib.urlopen(u).read())
    return photos['photoset']['photo']

def flickr_url(photo_id):
    return 'http://www.flickr.com/photos/library_of_congress/%s' % photo_id

def chronam_url(photo_id):
    u = 'http://api.flickr.com/services/rest/?method=flickr.photos.getInfo&api_key=%s&photo_id=%s&format=json&nojsoncallback=1' % (key, photo_id)
    j = json.loads(urllib.urlopen(u).read())
    for tag in j['photo']['tags']['tag']:
        if 'chroniclingamerica.loc.gov' in tag['raw']:
            return tag['raw'].replace('dc:identifier=', '')
    return None

def flickr_chronam_links():
    for photo in newspaper_photo_ids():
        yield flickr_url(photo['id']), chronam_url(photo['id'])

for link in flickr_chronam_links():
    print link