A Python script for removing duplicated messages in a Outlook folder

outlook-undup.py

import sys
import hashlib
from win32com.client import *

def getMD5(str):
    m = hashlib.md5()
    m.update(str)
    return m.hexdigest()

def getFolder(folder, path):
    if not path:
        return folder
    else:
        return getFolder(folder.Folders.Item(path[0]), path[1:])

def getFolders(folderPaths):
    app = gencache.EnsureDispatch("Outlook.Application")
    ns = app.GetNamespace("MAPI")

    folders = []
    for i in folderPaths:
        path = [j.strip() for j in i.split('/') if j.strip()]
        folders.append(getFolder(ns, i.split('/')))
    return folders

Folders = [
    u"Working/Inbox/pvcs-tracker",
]

dryRun = True
removedCount = 0
for f in getFolders(Folders):
    count = len(f.Items)
    keys = set()
    for i in range(count, 0, -1):
        msg = f.Items[i]
        subject = msg.Subject.encode('utf-8')
        digest = getMD5(msg.Body.encode('utf-8'))
        received = msg.ReceivedTime
        print >>sys.stderr, "message %6d of %6d: %s" % (count-i+1, count, digest),
        key = (subject, received, digest)
        if key in keys:
            removedCount += 1
            print >>sys.stderr, " - REMOVED"
            if not dryRun:
                msg.Delete()
        else:
            keys.add(key)
            print >>sys.stderr
print >>sys.stderr, "Done, %d messages removed." % removedCount