get_bad_photos.py

import os
import requests
from clint.textui import progress

s = requests.session()



def iter_photos():

    r = requests.get('http://blackbox.kennethreitz.org/records/?q=metadata.service:flickr&sort=epoch:asc&size=10000')

    for record in r.json['records']:
        yield record

def iter_urls():
    for photo in iter_photos():
        yield photo['links']['src']

def iter_download():
    for url in progress.bar([f for f in iter_urls()]):

        name = url.split('/')[-1]

        if not os.path.exists(name):
            try:
                r = s.get(url)

                with open(name, 'w') as f:
                    f.write(r.content)

            except Exception:
                pass




with open('badphotos') as f:
    bad_files = f.read().split()

photos = [p for p in iter_photos()]

# urls = [p['links']['src'] for p in photos]

for bad_file in bad_files:
    print bad_file
    for photo in photos:
        if bad_file in photo['links']['src']:
            print 'found!'
            name = photo['links']['path:data'].split('/')[-1]
            r = s.get(photo['links']['path:data'])

            with open(bad_file, 'w') as f:
                f.write(r.content)






# [j for j in iter_download()]

get_my_photos.py

import os
import requests
from clint.textui import progress

s = requests.session()

def iter_photos():

    r = requests.get('http://blackbox.kennethreitz.org/records/?q=metadata.service:flickr&sort=epoch:asc&size=10000')

    for record in r.json['records']:
        yield record

def iter_urls():
    for photo in iter_photos():
        yield photo['links']['src']

def iter_download():
    for url in progress.bar([f for f in iter_urls()]):

        name = url.split('/')[-1]

        if not os.path.exists(name):
            try:
                r = s.get(url)

                with open(name, 'w') as f:
                    f.write(r.content)

            except Exception, e:
                pass


[j for j in iter_download()]