S73-to-csv.py

# -*- coding: utf-8 -*-

from collections import OrderedDict
from PyPDF2 import PdfReader
import os


def _getFields(obj, tree=None, retval=None, fileobj=None):
    """
    Extracts field data if this PDF contains interactive form fields.
    The *tree* and *retval* parameters are for recursive use.

    :param fileobj: A file object (usually a text file) to write
        a report to on all interactive form fields found.
    :return: A dictionary where each key is a field name, and each
        value is a :class:`Field<PyPDF2.generic.Field>` object. By
        default, the mapping name is used for keys.
    :rtype: dict, or ``None`` if form data could not be located.
    """
    fieldAttributes = {'/FT': 'Field Type', '/Parent': 'Parent', '/T': 'Field Name', '/TU': 'Alternate Field Name',
                       '/TM': 'Mapping Name', '/Ff': 'Field Flags', '/V': 'Value', '/DV': 'Default Value'}
    if retval is None:
        retval = OrderedDict()
        catalog = obj.trailer["/Root"]
        # get the AcroForm tree
        if "/AcroForm" in catalog:
            tree = catalog["/AcroForm"]
        else:
            return None
    if tree is None:
        return retval

    obj._check_kids(tree, retval, fileobj)
    for attr in fieldAttributes:
        if attr in tree:
            # Tree is a field
            obj._buildField(tree, retval, fileobj, fieldAttributes)
            break

    if "/Fields" in tree:
        fields = tree["/Fields"]
        for f in fields:
            field = f.get_object()
            obj._build_field(field, retval, fileobj, fieldAttributes)

    return retval


def get_form_fields(infile):
    infile = PdfReader(open(infile, 'rb'))
    fields = _getFields(infile)
    # for k, v in fields.items():
    #     print(k + ": " + v.get('/V', ''))
    return OrderedDict((k, v.get('/V', '').strip().replace('  ', '')) for k, v in fields.items())



if __name__ == '__main__':
    
    nextNoEmailIndex = 1
 
    for x in sorted(os.listdir()):
        if x.endswith(".pdf"):

            try:
                pdf_file_name = x

                formFields = get_form_fields(pdf_file_name)
                csvCells = []
                
                csvCells.append("Circuito") # circuit
                csvCells.append(formFields['900_11_Text_C'] + ' ' + formFields['900_12_Text_C']) # congregation
                csvCells.append(formFields['900_2_Text_C']) # first name
                csvCells.append(formFields['900_3_Text_C']) # middle name
                csvCells.append(formFields['900_1_Text_C']) # last name
                
                if formFields['900_22_CheckBox'] == "/Yes": # is female
                    csvCells.append("TRUE") 
                else:
                    csvCells.append("FALSE")

                email = formFields['900_5_Text_C'].replace(' ', '').lower()
                if email == '':
                    nextNoEmailIndex += 1
                    email = 'no-email-' + str(nextNoEmailIndex).zfill(2) + '@example.com'
                csvCells.append(email) # email
                csvCells.append('+549'+formFields['900_10_Text_C'].replace(' ', '').replace('-', '').replace('(', '').replace(')','').replace('.','')) # phone
                csvCells.append("S") # language
                
                if formFields['900_30_CheckBox'] == "/Yes": # pioneerlevel
                    csvCells.append("Special") 
                elif formFields['900_32_CheckBox'] == "/Yes":
                    csvCells.append("Regular")
                else:
                    csvCells.append("None")

                if formFields['900_34_CheckBox'] == "/Yes": # privilege
                    csvCells.append("Elder") 
                elif formFields['900_35_CheckBox'] == "/Yes":
                    csvCells.append("MinisterialServant")
                else:
                    csvCells.append("None")

                if formFields['900_38_CheckBox'] == "/Yes": # participated before: yes
                    csvCells.append("Common") #experience
                else:
                    csvCells.append("Newbie")

                csvCells.append("FALSE") # IsShiftLeader
                csvCells.append("FALSE") # IsVip
                csvCells.append("FALSE") # IsAdmin
                csvCells.append("Activate") # ImportAction
                csvCells.append("") # placeholder for concatenation of availabilities

                
                #csvCells.append(formFields['900_28_Text_C']) # partner
                csvCells.append(formFields['900_41_Text_C'])
                csvCells.append(formFields['900_42_Text_C'])
                csvCells.append(formFields['900_43_Text_C'])
                csvCells.append(formFields['900_44_Text_C'])
                csvCells.append(formFields['900_45_Text_C'])
                csvCells.append(formFields['900_46_Text_C'])
                csvCells.append(formFields['900_47_Text_C'])

                csvCells = map(lambda s: s.strip(), csvCells)
                
                print("\""+"\";\"".join(csvCells)+"\"")
            except:
                print("\""+x+"\"")

prerequisite:
pip install PyPDF2