它包括根据文档中的页数动态设置为每个PDF页创建一个新工作表。

import PyPDF2 as p2
import xlsxwriter

pdfFileName = "sample.pdf"
pdfFile = open(pdfFileName, 'rb')
pdfread = p2.PdfFileReader(pdfFile)
number_of_pages = pdfread.getNumPages()
workbook = xlsxwriter.Workbook('pdftoexcel.xlsx')

for page_number in range(number_of_pages):
    print(f'Sheet{page_number}')
    pageinfo = pdfread.getPage(page_number)
    rawInfo = pageinfo.extractText().split('\n')

    row = 0
    column = 0
    worksheet = workbook.add_worksheet(f'Sheet{page_number}')

    for line in rawInfo:
        worksheet.write(row, column, line)
        row += 1
workbook.close()

你可以使用PDFtoText https://github.com/jalan/pdftotext

PDF到文本保持文本格式缩进，不管你是否有表格。

一种更健壮的方法，假设有多个PDF或只有一个!

import os
from PyPDF2 import PdfFileWriter, PdfFileReader
from io import BytesIO

mydir = # specify path to your directory where PDF or PDF's are

for arch in os.listdir(mydir): 
    buffer = io.BytesIO()
    archpath = os.path.join(mydir, arch)
    with open(archpath) as f:
            pdfFileObj = open(archpath, 'rb')
            pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
            pdfReader.numPages
            pageObj = pdfReader.getPage(0) 
            ley = pageObj.extractText()
            file1 = open("myfile.txt","w")
            file1.writelines(ley)
            file1.close()
            

你可以从这里下载tika-app-xxx.jar(最新)。

然后将这个.jar文件放在python脚本文件的同一文件夹中。

然后在脚本中插入如下代码:

import os
import os.path

tika_dir=os.path.join(os.path.dirname(__file__),'<tika-app-xxx>.jar')

def extract_pdf(source_pdf:str,target_txt:str):
    os.system('java -jar '+tika_dir+' -t {} > {}'.format(source_pdf,target_txt))

该方法的优点:

更少的依赖。单个.jar文件比python包更容易管理。

开始支持。位置source_pdf可以是任何类型文档的目录。(.doc， .html， .odt等)

最新的。tika-app.jar始终先于相关版本的tika python包发布。

稳定。它比PyPDF更加稳定和维护良好(由Apache提供支持)。

劣势:

一个无头小丑是必要的。

我正在添加代码来实现这一点: 这对我来说很好:

# This works in python 3
# required python packages
# tabula-py==1.0.0
# PyPDF2==1.26.0
# Pillow==4.0.0
# pdfminer.six==20170720

import os
import shutil
import warnings
from io import StringIO

import requests
import tabula
from PIL import Image
from PyPDF2 import PdfFileWriter, PdfFileReader
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.pdfpage import PDFPage

warnings.filterwarnings("ignore")


def download_file(url):
    local_filename = url.split('/')[-1]
    local_filename = local_filename.replace("%20", "_")
    r = requests.get(url, stream=True)
    print(r)
    with open(local_filename, 'wb') as f:
        shutil.copyfileobj(r.raw, f)

    return local_filename


class PDFExtractor():
    def __init__(self, url):
        self.url = url

    # Downloading File in local
    def break_pdf(self, filename, start_page=-1, end_page=-1):
        pdf_reader = PdfFileReader(open(filename, "rb"))
        # Reading each pdf one by one
        total_pages = pdf_reader.numPages
        if start_page == -1:
            start_page = 0
        elif start_page < 1 or start_page > total_pages:
            return "Start Page Selection Is Wrong"
        else:
            start_page = start_page - 1

        if end_page == -1:
            end_page = total_pages
        elif end_page < 1 or end_page > total_pages - 1:
            return "End Page Selection Is Wrong"
        else:
            end_page = end_page

        for i in range(start_page, end_page):
            output = PdfFileWriter()
            output.addPage(pdf_reader.getPage(i))
            with open(str(i + 1) + "_" + filename, "wb") as outputStream:
                output.write(outputStream)

    def extract_text_algo_1(self, file):
        pdf_reader = PdfFileReader(open(file, 'rb'))
        # creating a page object
        pageObj = pdf_reader.getPage(0)

        # extracting extract_text from page
        text = pageObj.extractText()
        text = text.replace("\n", "").replace("\t", "")
        return text

    def extract_text_algo_2(self, file):
        pdfResourceManager = PDFResourceManager()
        retstr = StringIO()
        la_params = LAParams()
        device = TextConverter(pdfResourceManager, retstr, codec='utf-8', laparams=la_params)
        fp = open(file, 'rb')
        interpreter = PDFPageInterpreter(pdfResourceManager, device)
        password = ""
        max_pages = 0
        caching = True
        page_num = set()

        for page in PDFPage.get_pages(fp, page_num, maxpages=max_pages, password=password, caching=caching,
                                      check_extractable=True):
            interpreter.process_page(page)

        text = retstr.getvalue()
        text = text.replace("\t", "").replace("\n", "")

        fp.close()
        device.close()
        retstr.close()
        return text

    def extract_text(self, file):
        text1 = self.extract_text_algo_1(file)
        text2 = self.extract_text_algo_2(file)

        if len(text2) > len(str(text1)):
            return text2
        else:
            return text1

    def extarct_table(self, file):

        # Read pdf into DataFrame
        try:
            df = tabula.read_pdf(file, output_format="csv")
        except:
            print("Error Reading Table")
            return

        print("\nPrinting Table Content: \n", df)
        print("\nDone Printing Table Content\n")

    def tiff_header_for_CCITT(self, width, height, img_size, CCITT_group=4):
        tiff_header_struct = '<' + '2s' + 'h' + 'l' + 'h' + 'hhll' * 8 + 'h'
        return struct.pack(tiff_header_struct,
                           b'II',  # Byte order indication: Little indian
                           42,  # Version number (always 42)
                           8,  # Offset to first IFD
                           8,  # Number of tags in IFD
                           256, 4, 1, width,  # ImageWidth, LONG, 1, width
                           257, 4, 1, height,  # ImageLength, LONG, 1, lenght
                           258, 3, 1, 1,  # BitsPerSample, SHORT, 1, 1
                           259, 3, 1, CCITT_group,  # Compression, SHORT, 1, 4 = CCITT Group 4 fax encoding
                           262, 3, 1, 0,  # Threshholding, SHORT, 1, 0 = WhiteIsZero
                           273, 4, 1, struct.calcsize(tiff_header_struct),  # StripOffsets, LONG, 1, len of header
                           278, 4, 1, height,  # RowsPerStrip, LONG, 1, lenght
                           279, 4, 1, img_size,  # StripByteCounts, LONG, 1, size of extract_image
                           0  # last IFD
                           )

    def extract_image(self, filename):
        number = 1
        pdf_reader = PdfFileReader(open(filename, 'rb'))

        for i in range(0, pdf_reader.numPages):

            page = pdf_reader.getPage(i)

            try:
                xObject = page['/Resources']['/XObject'].getObject()
            except:
                print("No XObject Found")
                return

            for obj in xObject:

                try:

                    if xObject[obj]['/Subtype'] == '/Image':
                        size = (xObject[obj]['/Width'], xObject[obj]['/Height'])
                        data = xObject[obj]._data
                        if xObject[obj]['/ColorSpace'] == '/DeviceRGB':
                            mode = "RGB"
                        else:
                            mode = "P"

                        image_name = filename.split(".")[0] + str(number)

                        print(xObject[obj]['/Filter'])

                        if xObject[obj]['/Filter'] == '/FlateDecode':
                            data = xObject[obj].getData()
                            img = Image.frombytes(mode, size, data)
                            img.save(image_name + "_Flate.png")
                            # save_to_s3(imagename + "_Flate.png")
                            print("Image_Saved")

                            number += 1
                        elif xObject[obj]['/Filter'] == '/DCTDecode':
                            img = open(image_name + "_DCT.jpg", "wb")
                            img.write(data)
                            # save_to_s3(imagename + "_DCT.jpg")
                            img.close()
                            number += 1
                        elif xObject[obj]['/Filter'] == '/JPXDecode':
                            img = open(image_name + "_JPX.jp2", "wb")
                            img.write(data)
                            # save_to_s3(imagename + "_JPX.jp2")
                            img.close()
                            number += 1
                        elif xObject[obj]['/Filter'] == '/CCITTFaxDecode':
                            if xObject[obj]['/DecodeParms']['/K'] == -1:
                                CCITT_group = 4
                            else:
                                CCITT_group = 3
                            width = xObject[obj]['/Width']
                            height = xObject[obj]['/Height']
                            data = xObject[obj]._data  # sorry, getData() does not work for CCITTFaxDecode
                            img_size = len(data)
                            tiff_header = self.tiff_header_for_CCITT(width, height, img_size, CCITT_group)
                            img_name = image_name + '_CCITT.tiff'
                            with open(img_name, 'wb') as img_file:
                                img_file.write(tiff_header + data)

                            # save_to_s3(img_name)
                            number += 1
                except:
                    continue

        return number

    def read_pages(self, start_page=-1, end_page=-1):

        # Downloading file locally
        downloaded_file = download_file(self.url)
        print(downloaded_file)

        # breaking PDF into number of pages in diff pdf files
        self.break_pdf(downloaded_file, start_page, end_page)

        # creating a pdf reader object
        pdf_reader = PdfFileReader(open(downloaded_file, 'rb'))

        # Reading each pdf one by one
        total_pages = pdf_reader.numPages

        if start_page == -1:
            start_page = 0
        elif start_page < 1 or start_page > total_pages:
            return "Start Page Selection Is Wrong"
        else:
            start_page = start_page - 1

        if end_page == -1:
            end_page = total_pages
        elif end_page < 1 or end_page > total_pages - 1:
            return "End Page Selection Is Wrong"
        else:
            end_page = end_page

        for i in range(start_page, end_page):
            # creating a page based filename
            file = str(i + 1) + "_" + downloaded_file

            print("\nStarting to Read Page: ", i + 1, "\n -----------===-------------")

            file_text = self.extract_text(file)
            print(file_text)
            self.extract_image(file)

            self.extarct_table(file)
            os.remove(file)
            print("Stopped Reading Page: ", i + 1, "\n -----------===-------------")

        os.remove(downloaded_file)


# I have tested on these 3 pdf files
# url = "http://s3.amazonaws.com/NLP_Project/Original_Documents/Healthcare-January-2017.pdf"
url = "http://s3.amazonaws.com/NLP_Project/Original_Documents/Sample_Test.pdf"
# url = "http://s3.amazonaws.com/NLP_Project/Original_Documents/Sazerac_FS_2017_06_30%20Annual.pdf"
# creating the instance of class
pdf_extractor = PDFExtractor(url)

# Getting desired data out
pdf_extractor.read_pages(15, 23)

您可能希望使用经过时间验证的xPDF和派生工具来提取文本，因为pyPDF2在文本提取方面似乎仍然存在各种问题。

长的答案是，文本如何在PDF中编码有很多变化，它可能需要解码PDF字符串本身，然后可能需要与CMAP映射，然后可能需要分析单词和字母之间的距离等。

如果PDF被损坏(即显示正确的文本，但复制时产生垃圾)，并且您确实需要提取文本，那么您可能需要考虑将PDF转换为图像(使用ImageMagik)，然后使用Tesseract使用OCR从图像中获取文本。