Checking a checkBox in .docx form with Python using docx module

Question

I am attempting to fill out a word document form with Python 2.7's docx module. I can modify text elements just fine but I am having difficulty figuring out how to check a yes or no checkbox.

How do I go about checking one the the checkboxes in the form. I have tried a few different ways but I think it all comes do to me not know how the docx xml is structured when it comes to check boxes.

Am I able to use the Bookmark property to find a specific checkbox and check it as seen in the picture below?

I have uploaded a copy of the test form to Google Drive here.

Burrows

Answer 1

Ok, so after much frustration I finally figured out how to check a checkbox. There is a element within a checkbox element that signifies if the box is checked. I am essenially able to create that element with the following function.

from docx.oxml import OxmlElement
from docx.oxml.ns import qn

def checkedElement():
    elm = OxmlElement('w:checked')
    elm.set(qn('w:val'),"true")
    return elm

I can find all checkboxes within a table cell with the following function. Since the yes is always the first checkbox in each cell I can set the index for a yes check to 0 and a no check to index 1 and then I can append the checked element within the checkbox element:

def yesNoCheck(yes_no,tableIdx,coords):
    print coords, yes_no
    if yes_no == 'y':
        index = 0
        x = doc.tables[tableIdx].cell(coords[0],coords[1])._element.xpath('.//w:checkBox')
        x[index].append(checkedElement())
    elif yes_no == 'n':
        index = 1
        x = doc.tables[tableIdx].cell(coords[0],coords[1])._element.xpath('.//w:checkBox')
        x[index].append(checkedElement())
    else:
        print "value was neither yes or no"
        pass

here is my full code that I have written so far. I have a bunch of refactoring to do but it works great as of now. There are two tables in my .docx template and dictionary table1 and table2 contain the cell row and column coordinates. This script is used to fill out a required form using data published from ESRI's Survey123.

from docx import Document
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
from docx.shared import Inches
from docx.enum.text import WD_ALIGN_PARAGRAPH
import arcpy
import datetime
import os

table1 = {
    'BusinessName':[2,3],
    'LicenseNumber':[2,14],
    'OwnerName':[3,3],
    'PhoneNumber':[3,14],
    'BusinessAddress':[4,5],
    'County':[4,14],
    'City':[5,1],
    'St':[5,8],
    'Zip':[5,15],
    'LicenceExpired':[6,1], #CheckBox
    'DateExpired':[6,15],
    'LicenceRenewal':[7,1], #CheckBox
    'NumberDisplayed':[8,1], #CheckBox
    'NameAddDisplayed':[10,1], #CheckBox
    'VehicleInfoMatches':[12,1], #CheckBox
    'DischargeValveCapped':[14,1], #CheckBox
    'DischargeValveCapChained':[15,1], #CheckBox
    'HoseDisinfectCarried':[16,1], #CheckBox
    'VehicleAndTankClean':[17,1], #CheckBox
    'FreeOfLeaks':[18,1] #CheckBox
}

table2 = {
    'LandApplyWaste':[1,1], #Yes/No CheckBox
    'LocationDescriptionAccurate':[6,1], #Yes/No CheckBox
    'LocationDescriptionAccDesc':[6,5], #text
    'Slope':[7,1], #Yes/No CheckBox
    'DistanceNearestResidence':[8,1], #Yes/No CheckBox
    'DistanceNearestWell':[9,1], #Yes/No CheckBox
    'DistanceNearestStreamLakeEtc':[10,1], #Yes/No CheckBox
    'SeptageIncorporated':[11,1], #Yes/No CheckBox
    'InjectedIncorporated':[12,3], #Yes/No CheckBox, dependent on the septage incorporated being yes
    'SeptageStabilized':[13,1], #Yes/No CheckBox
    'HowIsLimeMixed':[14,3], #text dependent on if lime was used
    'ConfiningLayerOrGroundwater':[15,1], #Yes/No CheckBox
    'ConfiningLayerOrGroundwaterDesc':[16,3], #text
    'CropGrown':[17,1], #Yes/No CheckBox
    'CropGrownHowVerified':[19,3], #text
    'LandAppCompliance':[20,1], #Yes/No CheckBox
    'AdditionalComments':[22,3],
    'SignDate':[22,13]
}

def checkedElement():
    elm = OxmlElement('w:checked')
    elm.set(qn('w:val'),"true")
    return elm

def yesNoCheck(yes_no,tableIdx,coords):
    print coords, yes_no
    if yes_no == 'y':
        index = 0
        x = doc.tables[tableIdx].cell(coords[0],coords[1])._element.xpath('.//w:checkBox')
        x[index].append(checkedElement())
    elif yes_no == 'n':
        index = 1
        x = doc.tables[tableIdx].cell(coords[0],coords[1])._element.xpath('.//w:checkBox')
        x[index].append(checkedElement())
    else:
        print "value was neither yes or no"
        pass

def disposalMethodCheck(method, locationDec):
    vals = {
        'WastewaterTreatmentFacility':[20,1],
        'LandApplication':[22,1],
        'SanitaryLandfill':[24,1],
        'SeptageLagoonOrDryingBed':[26,1]
    }
    if method != None:
        row,col = vals[method]
        checkBoxElm = doc.tables[0].cell(row,col)._element.xpath('.//w:checkBox')[0]
        print "{0} Checked!".format(method)
        checkBoxElm.append(checkedElement())
        editTxt(locationDec,0,[row,6]) 

def editTxt(text, tblIdx, coords, alignment = WD_ALIGN_PARAGRAPH.LEFT, bold=True):
    print text, coords
    field = doc.tables[tblIdx].cell(coords[0],coords[1]).paragraphs[0]
    field.text = text
    field.alignment = alignment
    field.runs[0].font.bold = bold

def addSig(sigJpgPath):
    para = doc.tables[1].row_cells(23)[0].paragraphs[0]
    para.alignment = WD_ALIGN_PARAGRAPH.CENTER
    run = para.add_run()
    run.add_picture(sigJpgPath,width=Inches(1.34),height=Inches(.35))

fc = r"E:\PumperTruckInspectionFeatureClass"
arcpy.MakeFeatureLayer_management (fc, "PumperTruckInspections")
attach = r"PumperTruckInspection__ATTACH" #Where signatures are stored

def rows_as_dicts(cursor):
    colnames = cursor.fields
    for row in cursor:
        yield dict(zip(colnames, row))

def dateString(date):
    if date != None:
        d = date.strftime('%m/%d/%Y')
        return d
    else:
        print "no date"
        return ''

def checkBusName(name):
    if name != None:
        return name
    else:
        return 'unknown'

with arcpy.da.SearchCursor(fc, '*') as sc:
    for row in rows_as_dicts(sc):
        doc = Document(r"path\to\TEMPLATE.docx")

        t = datetime.datetime.now().strftime('%Y-%m-%d')
        newDocName = checkBusName(row['BusinessName']) + t + '.docx'


        editTxt(row['BusinessName'],0,table1['BusinessName'])
        editTxt(row['LicenseNumber'],0,table1['LicenseNumber'])
        editTxt(row['OwnerName'],0,table1['OwnerName'])
        editTxt(row['PhoneNumber'],0,table1['PhoneNumber'])
        editTxt(row['BusinessAddress'],0,table1['BusinessAddress'])
        editTxt(row['County'],0,table1['County']) 
        editTxt(row['City'],0,table1['City'])
        editTxt(row['St'],0,table1['St'])
        editTxt(row['Zip'],0,table1['Zip'])
        editTxt(dateString(row['DateExpired']),0,table1['DateExpired'])
        yesNoCheck(row['LicenceExpired'],0, table1['LicenceExpired'])

        yesNoCheck(row['LicenceRenewal'],0, table1['LicenceRenewal'])
        yesNoCheck(row['NumberDisplayed'],0, table1['NumberDisplayed'])
        yesNoCheck(row['NameAddDisplayed'],0, table1['NameAddDisplayed'])
        yesNoCheck(row['VehicleInfoMatches'],0, table1['VehicleInfoMatches'])
        yesNoCheck(row['DischargeValveCapped'],0, table1['DischargeValveCapped'])
        yesNoCheck(row['DischargeValveCapChained'],0, table1['DischargeValveCapChained'])
        yesNoCheck(row['HoseDisinfectCarried'],0, table1['HoseDisinfectCarried'])
        yesNoCheck(row['VehicleAndTankClean'],0, table1['VehicleAndTankClean'])
        yesNoCheck(row['FreeOfLeaks'],0, table1['FreeOfLeaks'])
        disposalMethodCheck(row['DisposalMethod'],row['DisposalLocation'])
        if row['DisposalMethod'] == 'LandApplication':
            yesNoCheck(row['LandApplyWaste'],1,table2['LandApplyWaste'])
            yesNoCheck(row['LocationDescriptionAccurate'],1,table2['LocationDescriptionAccurate'])
            editTxt(row['LocationDescriptionAccDesc'],1,table2['LocationDescriptionAccDesc'])
            yesNoCheck(row['Slope'],1,table2['Slope'])
            yesNoCheck(row['DistanceNearestResidence'],1,table2['DistanceNearestResidence'])

            yesNoCheck(row['DistanceNearestWell'],1,table2['DistanceNearestWell'])
            yesNoCheck(row['DistanceNearestStreamLakeEtc'],1,table2['DistanceNearestStreamLakeEtc'])
            yesNoCheck(row['SeptageIncorporated'],1,table2['SeptageIncorporated'])
            yesNoCheck(row['InjectedIncorporated'],1,table2['InjectedIncorporated']) #might need a new method since its not yes/no
            yesNoCheck(row['SeptageStabilized'],1,table2['SeptageStabilized'])
            editTxt(row['HowIsLimeMixed'],1,table2['HowIsLimeMixed'])
            yesNoCheck(row['ConfiningLayerOrGroundwater'],1,table2['ConfiningLayerOrGroundwater'])
            editTxt(row['ConfiningLayerOrGroundwaterDescript'],1,table2['ConfiningLayerOrGroundwaterDescript'])
            yesNoCheck(row['CropGrown'],1,table2['CropGrown'])
            editTxt(row['CropGrownHowVerified'],1,table2['CropGrownHowVerified'])
            yesNoCheck(row['LandAppCompliance'],1,table2['LandAppCompliance'])
        editTxt(row['AdditionalComments'],1,table2['AdditionalComments'],bold=False)
        where = "REL_GLOBALID = '{0}'".format(row['GlobalID'])
        from pprint import pprint
        with arcpy.da.SearchCursor(attach,['DATA', 'ATT_NAME', 'ATTACHMENTID'],where_clause=where) as cursor:
            for r in rows_as_dicts(cursor):
                pprint(r)
                name = r['ATT_NAME']
                attachment = r['DATA']
                if name.split('_')[0] == 'InspectorSignature':
                    imagePath = os.path.join(name.split('_')[0] + "_" + )
                    open(("sig.jpeg"), 'wb').write(attachment.tobytes())
                    addSig("sig.jpeg")

                    break

        editTxt(dateString(row['SignDate']),1,table2['SignDate'],alignment = WD_ALIGN_PARAGRAPH.CENTER,bold=False)
        doc.save(newDocName)
        del doc

Burrows

Answer 2

I just created a checked checkbox in word and then recreated the xml codes. Compiled the whole in a function, you just have to pass the paragraph as an argument.

import docx
from docx import Document
from docx.shared import Inches
from docx.oxml import OxmlElement
from docx.oxml.ns import qn


def addCheckedbox(para, box_id, name):

    run = para.add_run()
    tag = run._r
    start = docx.oxml.shared.OxmlElement('w:bookmarkStart')
    start.set(docx.oxml.ns.qn('w:id'), str(box_id - 1))
    start.set(docx.oxml.ns.qn('w:name'), "_GoBack")

    run2 = para.add_run()
    tag2 = run2._r
    fld = docx.oxml.shared.OxmlElement('w:fldChar')
    fld.set(docx.oxml.ns.qn('w:fldCharType'), 'begin')


    checker = docx.oxml.shared.OxmlElement('w:checkBox')
    sizer = docx.oxml.shared.OxmlElement('w:sizeAuto')
    checkValue = docx.oxml.shared.OxmlElement('w:default')
    checkValue.set(docx.oxml.ns.qn('w:val'), '1')
    checker.append(sizer)
    checker.append(checkValue)
    start.append(checker)    
    tag.append(start)

    run3 = para.add_run()
    tag3 = run3._r
    instr = docx.oxml.OxmlElement('w:instrText')
    instr.text = 'FORMCHECKBOX'
    tag3.append(instr)

    run4 = para.add_run()
    tag4 = run4._r
    fld2 = docx.oxml.shared.OxmlElement('w:fldChar')
    fld2.set(docx.oxml.ns.qn('w:fldCharType'), 'end')
    tag4.append(fld2)

    run5 = para.add_run()
    tag5 = run5._r
    end = docx.oxml.shared.OxmlElement('w:bookmarkEnd')
    end.set(docx.oxml.ns.qn('w:id'), str(box_id))
    end.set(docx.oxml.ns.qn('w:name'), name)
    tag5.append(end)

    return

Ender

would it work with every version of word ? if the underlying xml is changed by microsoft, this solution might fail – Organicism

@Lucifer. Yes, you'll need to examine the xml when creating these functions – Nealneala

Answer 3

Here is an updated version for a newer version of Word. The key to checking/unchecking is found in the following line: checked.set(qn('w14:val'), '1'). '1' is checked and '0' is unchecked.

import docx

try:

    # Create an instance of a Word document
    doc = docx.Document()
    # Save the empty Word document
    doc.save(r"C:\My Documents\checkbox_test_document.docx")
    
except PermissionError:
    
    print("Need to close the open document")
    
try:

    # Create an instance of a Word document
    doc = docx.Document()
    # Save the empty Word document (overwrites an existing document of the same name)
    doc.save(r"C:\My Documents\checkbox_test_document.docx")

    # Create a new instance of the empty Word document that has been created
    doc = docx.Document(r"C:\My Documents\checkbox_test_document.docx")
    
# Raise an exception if a previously generated Word document is open
except PermissionError:

    print("Need to close the open document")

check1 = "text for checkbox1"
check2 = "text for checkbox2"

checklist = [check1, check2]

def add_checlist_to_docx(document, checklist_item):  
    from docx.oxml.shared import OxmlElement, qn
    
    paragraph = document.add_paragraph()
    tag = paragraph._p
    
    sdt = OxmlElement('w:sdt')
    sdtPr = OxmlElement('w:sdtPr')
    checkbox = OxmlElement('w14:checkbox')
    checked = OxmlElement('w14:checked')
    checked.set(qn('w14:val'), '1')
    checkedState = OxmlElement('w14:checkedState')
    checkedState.set(qn('w14:val'), '2612')
    checkedState.set(qn('w14:font'), 'MS Gothic')
    uncheckedState = OxmlElement('w14:uncheckedState')
    uncheckedState.set(qn('w14:val'), '2610')
    uncheckedState.set(qn('w14:font'), 'MS Gothic')

    sdtContent = OxmlElement('w:sdtContent')
    r_box = OxmlElement('w:r')
    rPr = OxmlElement('w:rPr')
    rFonts = OxmlElement('w:rFonts')
    rFonts.set(qn('w:ascii'), 'MS Gothic')
    rFonts.set(qn('w:eastAsia'), 'MS Gothic')
    rFonts.set(qn('w:hAnsi'), 'MS Gothic')
    rFonts.set(qn('w:hint'), 'eastAsia')
    t_box = OxmlElement('w:t')

    r_text = OxmlElement('w:r')
    t_text = OxmlElement('w:t')
    t_text.set(qn('xml:space'), 'preserve')
    
    checkbox.append(checked)
    checkbox.append(checkedState)
    checkbox.append(uncheckedState)
    sdtPr.append(checkbox)
    sdt.append(sdtPr)
    rPr.append(rFonts)
    t_box.text = '☐'
    r_box.append(rPr)
    r_box.append(t_box)
    sdtContent.append(r_box)
    sdt.append(sdtContent)
    tag.append(sdt)
    t_text.text = checklist_item
    r_text.append(t_text)
    tag.append(r_text)
    return
    
for check in checklist:
    add_checlist_to_docx(doc, check)

doc.save(r"C:\My Documents\checkbox_test_document.docx")

Nealneala