Download documents from Google Docs in doc, html, zip and pdf format. Note: zip=html+images

google_doc_downloader.py

import gdata.docs.data
import gdata.docs.client
import re


def print_feed(feed):
    if not feed.entry:
        print 'No entries in feed.'
    for entry in feed.entry:
        print entry.title.text.encode('UTF-8'), entry.GetDocumentType(), entry.resource_id.text
        for folder in entry.InFolders():
            print folder.title


def download(resourceId, filename="file"):
    entry = client.GetDoc(resourceId)
    for ext in ('doc', 'zip', 'html', 'pdf'):
        print ext, "..."
        client.Export(entry, "%s.%s" % (filename, ext))

def safe_title(title):
    return re.sub(r'[^a-zA-Z_-]', '', title)


def download_folder(folder_uid):
    feed = client.GetDocList(uri='/feeds/default/private/full/%s/contents' % (folder_uid))
    for entry in feed.entry:
        title=entry.title.text.encode("UTF-8")
        document_id = entry.resource_id.text
        print "Downloading", title
        download(document_id, safe_title(title))


client = gdata.docs.client.DocsClient(source='xxx-download-v1')
client.ssl = True
client.http_client.debug = False
client.ClientLogin('xxx@gmail.com', 'XXXX', client.source)

# Get all top level folders
# feed = client.GetDocList(uri='/feeds/default/private/full?showfolders=true')

# Get list of files in a folder
# feed = client.GetDocList(uri='/feeds/default/private/full/folder:0B5w0mnT5s6eINmRiYWE4YWYtOGUwZC00MTJkLWFlZjktMDJjMzE2YThjNjMx/contents')
# print_feed(feed)

test_folder_uid = "folder:0B5w0mnT5s6eINmRiYWE4YWYtOGUwZC00MTJkLWFlZjktMDJjMzE2YThjNjMx"
test_document_uid = "document:1hDGJyEUUFtMpe32zsXWMGNsTUic6HVoBI9gLjqlHq0M"

download_folder(test_folder_uid)