Python：从多个pdf中提取文本并粘贴到excel上

Question

我是 python 的新手，你能帮我更正这段代码吗？

我想补充两件事：

1. 对多个 pdf 进行操作，而不仅仅是一个并将内容粘贴到 A2、A3 A4 等
2. 如果可能，请在另一行 (B2,B3,B4) 中写入 pdf 文件的名称。

   提前谢谢你，这是我正在使用的代码

   import PyPDF2
   import openpyxl
   pdfFileObj = open("file.pdf", 'rb')
   pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
   pdfReader.numPages
   
   pageObj = pdfReader.getPage(0)
   mytext = pageObj.extractText()
   wb = openpyxl.load_workbook('excel.xlsx')
   sheet = wb.active
   sheet.title = 'MyPDF'
   sheet['A1'] = mytext
   
   wb.save('excel.xlsx')
   print('DONE!!')
   
   

   我已经按照建议修改了代码，循环似乎得到了所有页面！但也许我必须使用 "sheet[f'A{row}'].value = '\n'.join(output)" 因为它似乎打印了很多空格

   
   import PyPDF2
   import openpyxl
   import os
   import glob
   root_dir = "your directory"
   
   filenames = []
   # root_dir needs a trailing slash (i.e. /root/dir/)
   for filename in glob.iglob(root_dir + '**/**', recursive=True):
       if filename.lower().endswith('.pdf'):
           filenames.append(os.path.join(directory, filename))
           
   
   wb = openpyxl.load_workbook('excel.xlsx')#your file excel
   sheet = wb.active
   sheet.title = 'MyPDF'
   
   for row, filename in enumerate(filenames, start=1):
       with open(filename, 'rb') as f:
           pdfReader = PyPDF2.PdfFileReader(f)
           count=pdfReader.numPages
           pageObj = pdfReader.getPage(0)
           mytext = pageObj.extractText()
           for i in range(count): 
               page = pdfReader.getPage(i)
               output = []
               output = page.extractText() 
               print(output)
   
       sheet[f'A{row}'].value = '\n'.join(output)
       sheet[f'B{row}'].value = filename
   
   wb.save('excel.xlsx') #your file excel
   print('DONE!!')
   

Answer 1

您基本上想将您编写的读取 pdf 文件的代码放入 for 循环中，该循环遍历文件名（在这种情况下，文件名存储为 tuple）。

使用enumerate，row 循环的每次迭代递增，并从 1 开始。因此文本和文件名将被放入 A1 和 B1，然后是 A2 和 B2，依此类推。

import PyPDF2
import openpyxl

filenames = ("file.pdf", 
             "file2.pdf", 
             "file3.pdf", 
            )

wb = openpyxl.load_workbook('excel.xlsx')
sheet = wb.active
sheet.title = 'MyPDF'

for row, filename in enumerate(filenames, start=1):
    with open(filename, 'rb') as f:
        pdfReader = PyPDF2.PdfFileReader(f)
        pdfReader.numPages
        pageObj = pdfReader.getPage(0)
        mytext = pageObj.extractText()
    
    sheet[f'A{row}'].value = mytext
    sheet[f'B{row}'].value = filename

wb.save('excel.xlsx')
print('DONE!!')

---

通过遍历目录中的所有文件并检查文件名是否以 .pdf 结尾，您可以很容易地获得以 .pdf 结尾的所有文件名的列表。如果是，请使用os.path.join 为您提供完整的文件路径，并将其附加到filenames 列表中。

您也可以使用 glob 模块。

import os

filenames = []
directory = r"C:StuffPDF Files"
for filename in os.listdir(directory):
    if filename.lower().endswith(".pdf"):
        filenames.append(os.path.join(directory, filename))

---

更新代码：

import PyPDF2
import openpyxl
import os
import glob
import re
import itertools

# Used to strip characters that can't be written to a spreadsheet
# See https://stackoverflow.com/a/93029/3589122
control_chars = ''.join(map(chr, itertools.chain(range(0x00,0x20), range(0x7f,0xa0))))
control_char_re = re.compile('[%s]' % re.escape(control_chars))

def remove_control_chars(s):
    return control_char_re.sub('', s)

root_dir = 'your directory' # root_dir needs a trailing slash (i.e. /root/dir/)

filenames = (filename for filename in glob.iglob(root_dir + '/**/*.pdf', recursive=True))

wb = openpyxl.load_workbook('excel.xlsx') # your file excel
sheet = wb.active
sheet.title = 'MyPDF'

row = 1
for filename in filenames:
    with open(filename, 'rb') as f:
        try:
            pdfReader = PyPDF2.PdfFileReader(f)
            count = pdfReader.numPages
            
            output = []
            for i in range(count): 
                print(i, filename)
                page = pdfReader.getPage(i)
                output.append(page.extractText())
                #print(output)
        except Exception as e:
            print(f'Error: PyPDF2 could not read {filename}. Continuing... ({e})')
            continue
    
    sheet[f'A{row}'].value = '
'.join(remove_control_chars(output))
    sheet[f'B{row}'].value = filename
    row += 1

wb.save('excel.xlsx') #your file excel
print('DONE!!')

Answer 2

您是否尝试过超过 6/7 个文件？我在 7 pdf 时收到此错误

TypeError                                 Traceback (most recent call last)
<ipython-input-14-07fb0aa603b8> in <module>
     23         for i in range(count):
     24             page = pdfReader.getPage(i)
---> 25             output.append(page.extractText())
     26             print(output)
     27 

~naconda3libsite-packagesPyPDF2_page.py in extractText(self, Tj_sep, TJ_sep)
   1283         """
   1284         deprecate_with_replacement("extractText", "extract_text")
-> 1285         return self.extract_text(Tj_sep=Tj_sep, TJ_sep=TJ_sep)
   1286 
   1287     mediabox = _create_rectangle_accessor(PG.MEDIABOX, ())

~naconda3libsite-packagesPyPDF2_page.py in extract_text(self, Tj_sep, TJ_sep, space_width)
   1261         :return: a string object.
   1262         """
-> 1263         return self._extract_text(self, self.pdf, space_width, PG.CONTENTS)
   1264 
   1265     def extract_xform_text(

~naconda3libsite-packagesPyPDF2_page.py in _extract_text(self, obj, pdf, space_width, content_key)
   1243                     text = ""
   1244             else:
-> 1245                 process_operation(operator, operands)
   1246         output += text  # just in case of
   1247         return output

~naconda3libsite-packagesPyPDF2_page.py in process_operation(operator, operands)
   1195                 tm_matrix[5] -= TL
   1196             elif operator == b"Tj":
-> 1197                 text += operands[0].translate(cmap)
   1198             else:
   1199                 return None

TypeError: a bytes-like object is required, not 'dict'

Answer 3

我们可以通过浏览 xlsx 文件来总结 pdf 中的数据吗..在 python 中没有任何导入数据.... 我需要从详细信息可用的 excel 数据中制作一个摘要页面......例如每月每季度每年......多年来的变化等......月月，，，