Tutorial: Python & DOCX II

D. Thiebaut (talk) 04:13, 28 June 2018 (EDT)

---

The Basic Idea

• You have a csv file with a list of students taking different workshops. One field of the csv file contains the first name of the student, another field the last name, and a third field, the workshop title taken by the student.
• The python program shown here generates a Word document where each page is a diploma page, with a logo for the school, the first and last names of the student, and the workshop taken by the student.
• This is a typical Mail-Merge type problem.
• The trick used here is that the MS Word doc diplomas file, containing all the diplomas, starts with 100 (or whatever number is good for you) blank diploma pages, more than the actual number of rows in the csv file, and substitutes the student information in each page.

The CSV File

Here is an example csv file. Update to match your needs. Note that the csv file contains 4 lines, but that some of them might wrap when displayed.

students.csv

Last name,First name,Institution,Address 1,Address 2,City,zip,Country,Phone,Email,Course,misc1,misc2,misc3
Mouse, Mickey,U. of Orlando,Disney World,,"Orlando, FL",12345,USA,+1(234)567 89 00,mickeymouse@disney.com,Animation I,null,null,null
Mouse, Minie,U. of Orlando,Disney World,,"Orlando, FL",12345,USA,+1(234)567 89 00,miniemouse@disney.com,Animation II,null,null,null
Duck, Duffy,U. of Orlando,Disney World,,"Orlando, FL",12345,USA,+1(234)567 89 99,duffyduck@disney.com,Animation I,null,null,null

The MS Word template

• Here is the MS Word document containing 100 (or whatever number is larger than the number of students) blank diplomas.
• 100_diploma_TEMPLATE.docx (this file is zipped. Unzip before using)

The output MS Word file

• Here is the MS Word generated by the Python script (below).
• Diplomas_all.docx (this file is zipped. Unzip before using)

The Python Script

#! /usr/bin/env python3
# generateDiplomas.py
# D. Thiebaut
# Inspired by code provided at https://stackoverflow.com/questions/24805671/
#   how-to-use-python-docx-to-replace-text-in-a-word-document-and-save
from __future__ import print_function
import re
from docx import Document
import csv
import os

#=======================================================
# GLOBALS
#=======================================================
# the field in the csv file where the course name is saved.
# the first field is 0
COURSE_NAME_FIELD = 10

# the location of the csv file.  The program will prompt for
# it if it doesn't find it
CSV_FILE_NAME = "students.csv"

# the file where the diplomas will be saved
# by default, they will go to the Desktop
#DIPLOMAS_FILE = os.getenv("HOME") +"/Desktop/Diplomas_all.docx"
DIPLOMAS_FILE = "Diplomas_all.docx"

# TEMPLATE100 contains 100 blank diplomas with 3 strings defining
# the first name, last name, and course name that should go on each
# diploma. 
TEMPLATE100 = '100_diploma_TEMPLATE.docx'

# the list of valid course names.  These should appear in Field 10
# of the csv file.  If a student has a course name that doesn't appear
# in the list below, that student will be skipped.
courses=[ "Animation I", "Animation II" ]

#                    1         2         3
#          0123456789012345678901234567890
# define shorter version of course names, with _ instead of spaces
coursesShort = [ "_".join( k[0:24].split()[0:-1] ) for k in courses ]
          
# define course dictionary:
# key is course, value is list of participants.  Each participant is
# a list of fields, as found in the csv file
CourseParticipants = { }

#=======================================================
# FUNCTIONS
#=======================================================
def getValidFileName( prompt, defaultFileName ):
    while True:
        try:
            f=open( defaultFileName, 'r' )
            f.close()
            return defaultFileName
        except:
            print( prompt )
            defaultFileName = input()
            
        
def docx_replace_regex(doc_obj, regex , replace):
    '''searches a document (doc_obj) and locates regex,
    and replaces it with replace.  doc_obj passed by reference
    so no need to return it.
    '''
    for p in doc_obj.paragraphs:
        if regex.search(p.text):
            inline = p.runs
            # Loop added to work with runs (strings with same style)
            for i in range(len(inline)):
                if regex.search(inline[i].text):
                    text = regex.sub(replace, inline[i].text, count=1 )
                    inline[i].text = text
                    return
    
    #for table in doc_obj.tables:
    #    for row in table.rows:
    #        for cell in row.cells:
    #            docx_replace_regex(cell, regex , replace)


def generateDiploma(doc, firstName, lastName, course):
    """
    replace the next "33", "44", and "555" words in the
    word document by the first name, last name and course name
    of the next student.
    """
    docx_replace_regex(doc,
                       re.compile( r"33" ),
                       firstName )
    docx_replace_regex(doc,
                       re.compile( r"44" ),
                       lastName )
    docx_replace_regex(doc,
                       re.compile( r"555" ),
                       course )

def generateAllDiplomas( CourseParticipants ):
    '''
    Given the dictionary of all participants, substitute
    all the names and courses in the MS Word doc.
    '''
    global courses, DIPLOMAS_FILE, TEMPLATE100

    fileName = TEMPLATE100
    fileName = getValidFileName( "What is the path of the MS Word template? ",
                                 fileName )
    doc = Document( fileName )

    # for each course, generate list of participants                   
    for j, course in enumerate( CourseParticipants ):
        
        # if course not valid, skip it
        if course not in courses:
            print( "*** WARNING ***: invalid course:", course )
            continue
                
        for i,fields in enumerate( CourseParticipants[ course ] ):
            lastName,firstName, institution, address1, address2, \
                city, zip, country, phone, email, course, _,_,_ = fields

            print( "generating diploma for", firstName, lastName )
            generateDiploma( doc, firstName, lastName, course )

 
    doc.save( DIPLOMAS_FILE )
    print( "Diplomas saved in", DIPLOMAS_FILE ) 

def main():
    global CSV_FILE_NAME
    CSV_FILE_NAME = getValidFileName( "What is the full path of the csv file? ",
                                      CSV_FILE_NAME )
    
    # read the csv file and parse it
    with open( CSV_FILE_NAME, newline='' ) as csvfile:

        # create a csv reader
        csvReader = csv.reader( csvfile, delimiter=',', quotechar='"')
        for i, fields in enumerate( csvReader ):
            # skip ill formed lines
            if len( fields ) <= 5: continue

            # skip first line that contains headers
            if i==0: continue
            
            # get course from appropriate field 
            course = fields[COURSE_NAME_FIELD]

            # add new participant to list associated with his/her course
            try:        
                CourseParticipants[ course ].append( fields )
            except:
                CourseParticipants[ course ] = [ fields ]

    generateAllDiplomas( CourseParticipants ) 

main()