"""Download newsletters from Intellicontact.
"""
import os
import csv
import time
import traceback
from os.path import isfile

from BeautifulSoup import BeautifulSoup, Tag
from pywinauto.application import Application

BASE = r'c:\workbench\intellicontact'
FIREFOX = r"c:\program files\Mozilla Firefox\Firefox.exe %s"
URL = "http://app.intellicontact.com/icp/core/message/compose?message_id=%s"
RAW = BASE + r'\raw\%s-%s.html'
EXTRACTED = BASE + r'\extracted\%s-%s.htm'

reader = csv.reader(open('newsletters.csv'))
headers = reader.next()

for mid, postdate in reader:

    year, month, day = tuple(postdate.split('-'))

    url = URL % mid
    save_as = RAW % (month, day)
    extracted = EXTRACTED % (month, day)

    if isfile(save_as) and isfile(extracted):
        continue

    print url


    # Save the file from Firefox.
    # ===========================

    if not isfile(save_as):
        print '  =>', save_as

        app = Application().start_(FIREFOX % url)
        time.sleep(3)
        if not app.windows_(): # Firefox wasn't already running; we launched it
            app = Application().connect_(title_re=".* - Mozilla Firefox")
        firefox = app.window_(title_re=".* - Mozilla Firefox")

        firefox.TypeKeys("%FA") # File -> Save As
        while app.SaveAs.FileNameEdit.TextBlock() != save_as:
            app.SaveAs.FileNameEdit.SetEditText(save_as)
        app.SaveAs.TypeKeys("%S") # "Save" button
        firefox.TypeKeys("%FC") # File -> Close Tab


    # Wait for the file to appear before doing the next one.
    # ======================================================

    while 1:
        if isfile(save_as):
            break
        time.sleep(0.2)


    # Post-process
    # ============

    if not isfile(extracted):
        print '  =>', extracted

        soup = BeautifulSoup(open(save_as))

        content_type = Tag(soup, 'meta')
        content_type['http-equiv'] = 'Content-Type'
        content_type['content'] = 'text/html; charset=utf-8'

        try:
            text = soup.textarea.string
        except:
            print "  => ERROR FINDING CONTENT"
            traceback.print_exc()
            continue

        text = text.replace('&lt;', '<')
        text = text.replace('&gt;', '>')
        text = text.replace('&amp;', '&')
        text = text.replace('&quot;', '"')
        soup = BeautifulSoup(text)

        try:
            soup.head.insert(0, content_type)
        except:
            print "  => ERROR INSERTING Content-Type"
            traceback.print_exc()
        else:
            print "  => SUCCESS!"

        open(extracted, 'w+').write(soup.prettify())


    print