從python或bash批量填充PDF表格

Question

我有一個PDF表格需要填寫一堆（這是一個時間表準確）。現在因爲我不想親手做這件事，所以我正在尋找一種方法來使用python腳本或者可以在bash腳本中使用的工具來填充它們。

有沒有人有這方面的經驗？

Answer 1

對於Python你需要的fdfgen lib和PDFTK

@Hugh博思韋爾的評論是100％正確的，所以我會用延長工作落實這個問題的答案。

如果你在windows中，你還需要確保python和pdftk都包含在系統路徑中（除非你想使用長文件夾名稱）。從CSV數據文件

下面的代碼來自動批量填寫的PDF表單收集：

import csv 
from fdfgen import forge_fdf 
import os 
import sys 

sys.path.insert(0, os.getcwd()) 
filename_prefix = "NVC" 
csv_file = "NVC.csv" 
pdf_file = "NVC.pdf" 
tmp_file = "tmp.fdf" 
output_folder = './output/' 

def process_csv(file): 
    headers = [] 
    data = [] 
    csv_data = csv.reader(open(file)) 
    for i, row in enumerate(csv_data): 
     if i == 0: 
     headers = row 
     continue; 
     field = [] 
     for i in range(len(headers)): 
     field.append((headers[i], row[i])) 
     data.append(field) 
    return data 

def form_fill(fields): 
    fdf = forge_fdf("",fields,[],[],[]) 
    fdf_file = open(tmp_file,"w") 
    fdf_file.write(fdf) 
    fdf_file.close() 
    output_file = '{0}{1} {2}.pdf'.format(output_folder, filename_prefix, fields[1][1]) 
    cmd = 'pdftk "{0}" fill_form "{1}" output "{2}" dont_ask'.format(pdf_file, tmp_file, output_file) 
    os.system(cmd) 
    os.remove(tmp_file) 

data = process_csv(csv_file) 
print('Generating Forms:') 
print('-----------------------') 
for i in data: 
    if i[0][1] == 'Yes': 
    continue 
    print('{0} {1} created...'.format(filename_prefix, i[1][1])) 
    form_fill(i) 

注：它不應該是火箭的手術，以找出如何定製的。初始變量聲明包含自定義配置。

在CSV中，第一行中的每列將包含PDF文件中相應字段名稱的名稱。任何在模板中沒有相應字段的列都將被忽略。

在PDF模板中，只需創建希望數據填充的可編輯字段，並確保名稱與CSV數據匹配。

對於此特定配置，只需將該文件放在與NVC.csv，NVC.pdf和名爲'output'的文件夾相同的文件夾中即可。運行它，它自動完成剩下的工作。

Answer 2

替換原文件

os.system('pdftk "original.pdf" fill_form "data.fdf" output "output.pdf"') 
os.remove("data.fdf") 
os.remove("original.pdf") 
os.rename("output.pdf","original.pdf") 

Answer 3

快得多版本，沒有PDFTK也不fdfgen需要，純Python 3.6+：

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

from collections import OrderedDict 
from PyPDF2 import PdfFileWriter, PdfFileReader 


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._checkKids(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.getObject() 
      obj._buildField(field, retval, fileobj, fieldAttributes) 

    return retval 


def get_form_fields(infile): 
    infile = PdfFileReader(open(infile, 'rb')) 
    fields = _getFields(infile) 
    return OrderedDict((k, v.get('/V', '')) for k, v in fields.items()) 


def update_form_values(infile, outfile, newvals=None): 
    pdf = PdfFileReader(open(infile, 'rb')) 
    writer = PdfFileWriter() 

    for i in range(pdf.getNumPages()): 
     page = pdf.getPage(i) 
     try: 
      if newvals: 
       writer.updatePageFormFieldValues(page, newvals) 
      else: 
       writer.updatePageFormFieldValues(page, 
               {k: f'#{i} {k}={v}' 
                for i, (k, v) in enumerate(get_form_fields(infile).items()) 
                }) 
      writer.addPage(page) 
     except Exception as e: 
      print(repr(e)) 
      writer.addPage(page) 

    with open(outfile, 'wb') as out: 
     writer.write(out) 


if __name__ == '__main__': 
    from pprint import pprint 

    pdf_file_name = '2PagesFormExample.pdf' 

    pprint(get_form_fields(pdf_file_name)) 

    update_form_values(pdf_file_name, 'out-' + pdf_file_name) # enumerate & fill the fields with their own names 
    update_form_values(pdf_file_name, 'out2-' + pdf_file_name, 
         {'my_fieldname_1': 'My Value', 
         'my_fieldname_2': 'My Another alue'}) # update the form fields