python - 从pdf转换为文本: lines and words are broken

Question

我想通过 PyPDF2 将 pdf 文件转换为文本，但转换后的文本看起来与 PDF 文件不同。具体来说，PDF 中的一行在文本中被分成多行，单词也可能被打破。附件是我用下面的代码得到的 PDF 和文本文件。谁能帮我解决这个问题？

enter code here

import PyPDF2

def extractPdfText(filePath=''):

# Open the pdf file in read binary mode.
fileObject = open(filePath, 'rb') # rb

# Create a pdf reader .
pdfFileReader = PyPDF2.PdfFileReader(fileObject)

# Get total pdf page number.
totalPageNumber = pdfFileReader.numPages

# Print pdf total page number.
print('This pdf file contains totally ' + str(totalPageNumber) + ' pages.')

currentPageNumber = 0
text = ''

# Loop in all the pdf pages.
while(currentPageNumber < totalPageNumber ):

    # Get the specified pdf page object.
    pdfPage = pdfFileReader.getPage(currentPageNumber)

    # Get pdf page text.
    text = text + pdfPage.extractText()

    # Process next page.
    currentPageNumber += 1

    return text

pdfFilePath = 'PDF file path'

pdfText = extractPdfText(pdfFilePath)

pdf file

converted text

Answer 1

这就是我要做的。

from io import StringIO
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
import os
import sys, getopt

#converts pdf, returns its text content as a string
def convert(fname, pages=None):
    if not pages:
        pagenums = set()
    else:
        pagenums = set(pages)

    output = io.StringIO()
    manager = PDFResourceManager()
    converter = TextConverter(manager, output, laparams=LAParams())
    interpreter = PDFPageInterpreter(manager, converter)

    infile = open(fname, 'rb')
    for page in PDFPage.get_pages(infile, pagenums):
        interpreter.process_page(page)
    infile.close()
    converter.close()
    text = output.getvalue()
    output.close
    return text 

#converts all pdfs in directory pdfDir, saves all resulting txt files to txtdir
def convertMultiple(pdfDir, txtDir):
    if pdfDir == "": pdfDir = os.getcwd() + "\\" #if no pdfDir passed in 
    for pdf in os.listdir(pdfDir): #iterate through pdfs in pdf directory
        fileExtension = pdf.split(".")[-1]
        if fileExtension == "pdf":
            pdfFilename = pdfDir + pdf 
            text = convert(pdfFilename) #get string of text content of pdf
            textFilename = txtDir + pdf + ".txt"
            textFile = open(textFilename, "w") #make text file
            textFile.write(text) #write text to text file

# set paths accordingly:
pdfDir = "C://your_path_here/"
txtDir = "C://your_path_here/"
convertMultiple(pdfDir, txtDir)