picasa.py

#!/usr/bin/python

import sys
import re
import os
import urllib
import urllib2
import gdata.photos
import gdata.photos.service

pws = gdata.photos.service.PhotosService()


def main():
    username = sys.argv[1]
    resume = ''
    l_username = False
    l_password = False
    force = False
    for arg in sys.argv:
        if arg.startswith('--resume='):
            resume = arg.split('--resume=')[1]
        if arg.startswith('--username='):
            l_username = arg.split('--username=')[1]
        if arg.startswith('--password='):
            l_password = arg.split('--password=')[1]
        if arg == '--force':
            force = True

    if l_username and l_password:
        pws.ClientLogin(l_username, l_password)
        print 'Logged in as %s.' % (username)
    else:
        print 'Logged in as anonymous.'
    print 'Grabbing %s\'s photos' % username
    albums = pws.GetUserFeed(user=username)
    for album in albums.entry:
        process_album(album, username)


def process_album(album, username):
    print 'Album named %s found, containing %s photos and ID of %s' %(album.name.text, album.numphotos.text, album.gphoto_id.text)
    album_name = album.name.text
    create_dir(album_name)
    photos = pws.GetFeed('/data/feed/api/user/%s/albumid/%s?kind=photo&imgmax=d' %(username, album.gphoto_id.text))
    for photo in photos.entry:
        #link = str(photo.GetHtmlLink()) # Returns XML
        #print "Link is ", link
        res = re.search("href=\"(.*?)\"", str(photo.GetHtmlLink()), 0)  # Pull URL of photo display page from XML
        if res.group(1) is not None:
            print res.group(1)
        else:
            print 'Could not extract link'
            return 0

        #print 'Photo title:', photo.title.text
        #print photo.GetHtmlLink



    try:
        photo = photos[0]
        print "Found some photos, continuing for %s" % (album_name)
    except IndexError:
        print 'No photos in %s' % (album_name)
        return
    gallery_link = str(photo.GetHtmlLink().href)
    text = grab_url(gallery_link)
    print "Text to match against is %s" % (text)
    # found = re.findall('"width":"(.*?)","height":"(.*?)","size":"(.*?)","commentingEnabled":"(.*?)","allowNameTags":"(.*?)","media":\{"content":\[\{"url":"https:\/\/(.*?)",', text)
    found = re.findall('https://get.google.com(.*?)', text)
    print "Matched %s" % (found)
    # url_list = []
    for object in found:
        split = object[5].split('/')
        split.append(split[5])  # extra item
        if int(object[0]) > 2048:
            size = '2048'
        else:
            size = object[0]
        split[5] = 's' + size
        url = 'https://' + '/'.join(split)
        filename = split[6]
        if os.path.isfile(filename) and (not force):
            continue
        print "found %s" % (url)
        try:
            download_image(url, album_name.lower(), filename)
        except KeyboardInterrupt:
            sys.exit(1)
        except:
            print 'Skipping: Error on %s' % (url)
        print 'Successfully grabbed %s' % (split[6])
        # url_list.append(url)
    print 'Finished %s' % (album_name)


def download_image(url, album, filename):
    img = grab_url(url)
    file = open(album + '/' + filename, 'w')
    file.write(img)
    file.close()
    print "Downloaded %s" % (filename)


def grab_url(link):
    obj = urllib.urlopen(link)
    text = obj.read()
    obj.close()
    return text


def create_dir(name):
    try:
        os.mkdir(name.lower())
    except OSError:
        pass


if __name__ == "__main__":
    main()