Answers for "Using Python to Extract Data from NSF"

Using Python to Extract Data from NSF

import win32com.client
import csv # imports the csv module
import sys # imports the sys module
import re

notesServer = "NotesServer/Certifier"
notesFile = "NotesFolder\NotesDatabase.nsf"
notesPass = "NotesPassword"

#Connect to notes database on server
notesSession = win32com.client.Dispatch('Lotus.NotesSession')
notesSession.Initialize(notesPass)
notesDatabase = notesSession.GetDatabase(notesServer,notesFile)
notesView = '(All Documents)'

notesView = notesDatabase.GetView(notesView)
notesDoc = notesView.GetFirstDocument()

#Code block used from another blog.See resources section
def makeDocumentGenerator(folderName):
 # Get folder
 folder = notesDatabase.GetView(folderName)
 if not folder:
 raise Exception('Folder "%s" not found' % folderName)
 # Get the first document
 document = folder.GetFirstDocument()
 # If the document exists,
 while document:
 # Yield it
 yield document
 # Get the next document
 document = folder.GetNextDocument(document)

#Loop through documents extracting data from listed fields and view.
for document in makeDocumentGenerator(notesView):
 try:
 crm_iencompany = document.GetItemValue('IENCompany')[0].encode('utf-8').strip()
 docID = str(document.UniversalID.strip()) #Get the document ID to make filename unique
 crm_principle = document.GetItemValue('Principle')[0].encode('utf-8').strip()
 crm_iensubject = document.GetItemValue('IENSubject')[0].encode('utf-8').strip()
 crm_ienviewphones = document.GetItemValue('IENVIEWPHONES')[0].encode('utf-8').strip()
 crm_ienviewfullname = document.GetItemValue('IENVIEWFULLNAME')[0].encode('utf-8').strip()
 crm_ienviewaddress = document.GetItemValue('IENVIEWADDRESS')[0].encode('utf-8').strip()
 crm_iensalesrep = document.GetItemValue('IENSalesRep')[0].encode('utf-8').strip()
 crm_entersendto = document.GetItemValue('EnterSendTo')[0].encode('utf-8').strip()
 crm_entercopyto = document.GetItemValue('EnterCopyTo')[0].encode('utf-8').strip()
 crm_from = document.GetItemValue('From')[0].encode('utf-8').strip()
 crm_body = document.GetItemValue('Body')[0].encode('utf-8').strip()

#Remove any characters from filename which are not valid.
 fileName = crm_iencompany + "-" + docID + ".txt"
 fileName = fileName.replace("/"," ")
 fileName = fileName.replace("\\"," ")
 fileName = fileName.replace(":"," ")
 fileName = fileName.replace("\r"," ")
 fileName = fileName.replace("\n"," ")
 fileName = fileName.rstrip('\r\n')
 fileName = fileName.rstrip('\n\r')
 fileName = fileName.rstrip('\n')
 fileName = fileName.rstrip('\r')
 cleaned_up_filename = re.sub(r'[/\\:*?"<>|]', '', fileName)

#Write to txt file.
 with open(cleaned_up_filename, 'w') as f:
 f.write("iencompany:" + crm_iencompany + "," + "\n")
 f.write("principle:" + crm_principle + "," + "\n")
 f.write("ienviewphones:" + crm_ienviewphones + "," + "\n")
 f.write("ienviewfullname:" + crm_ienviewfullname + "," + "\n")
 f.write("ienviewaddress:" + crm_ienviewaddress + "," + "\n")
 f.write("iensalesrep:" + crm_iensalesrep + "," + "\n")
 f.write("entersendto:" + crm_entersendto + "," + "\n")
 f.write("entercopyto:" + crm_entercopyto + "," + "\n")
 f.write("from:" + crm_from + "," + "\n")
 f.write("subject:" + crm_iensubject + "," + "\n")
 f.write("body:" + crm_body + "," + "\n")
 except:
 print document
 pass