IronPython client to save IE sessions to RIL

rilie.py

# Read It Later IE
# Utility to post IE sessions to http://readitlaterlist.com
#
# The MIT License
# 
# Copyright (c) 2010, Atif Aziz
#
# Author(s):
#
#   Atif Aziz, http://www.raboof.com/
# 
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
# 
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
# 
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.

import sys, clr

from System import Type, Activator, StringComparison
from System.Collections.Specialized import NameValueCollection
from System.Net import WebClient
from System.Text import Encoding
from System.Text.RegularExpressions import Regex

clr.AddReference('System.Web.Extensions')
from System.Web.Script.Serialization import JavaScriptSerializer as JsonSerializer

def ie_docs():
    shell_type = Type.GetTypeFromProgID('Shell.Application')
    shell = Activator.CreateInstance(shell_type)
    result = []
    wins = shell.Windows()
    for i in range(wins.Count()):
        title = None
        try:
            document = wins.Item(i).Document()
            title = document.title
        except:
            pass
        if title is None:
            continue
        if not type(title) is str:
            continue
        href = document.location.href
        # TODO: exclude local addresses
        if not Regex.IsMatch(href, r'^(http|https)\:\/\/\S+'):
            continue
        result.append((href, title))
    return result

def main(args):

    if len(args) < 3:
        from os import getenv
        uid, pwd, apikey = getenv('RIL_UID'), getenv('RIL_PWD'), getenv('RIL_KEY')
    else:
        uid, pwd, apikey = args[:3]

    if not uid or not pwd or not apikey:
        print 'Usage: %s USERNAME PASSWORD APIKEY' % sys.argv[0]
        sys.exit(2)

    docs = ie_docs()
    for url, title in docs:
        print title
        print url
        print

    bookmarks = [{'url': url, 'title': title} for url, title in docs]

    form = NameValueCollection()
    form.Add('username', uid)
    form.Add('password', pwd)
    form.Add('apikey', apikey)

    new_json = JsonSerializer().Serialize(dict([(str(i), bkmk) for i, bkmk in zip(range(len(bookmarks)), bookmarks)]))
    form.Add('new', new_json)

    wc = WebClient()
    reply = wc.UploadValues('https://readitlaterlist.com/v2/send', 'POST', form)
    print Encoding.UTF8.GetString(reply)
    print
    print '\n'.join(['%8s = %s' % (int(wc.ResponseHeaders[k]).ToString('N0'), k[8:]) for k in wc.ResponseHeaders if k.StartsWith('X-Limit-', StringComparison.OrdinalIgnoreCase)])

if __name__ == '__main__':
    try:
        main(sys.argv[1:])
    except Exception, e:
        print >> sys.stderr, e
        sys.exit(1)