从pdf转换为文本：行和单词被破坏

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，并且单词也可能被破坏。随附的PDF和我用下面的代码得到的文本文件。任何人都可以帮我解决这个问题吗？

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

我就是这样做的。

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)

Answer 2

这个答案使用encode（'utf-8'）来保持每页的输出。我不知道你需要什么输出，因为你的问题没有指明。

from PyPDF2 import PdfFileReader

def pdf_text_extractor(path):
   with open(path, 'rb') as f:
     pdf = PdfFileReader(f)

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

     currentPageNumber = 0

     while (currentPageNumber < totalPageNumber):
        page = pdf.getPage(currentPageNumber)

        text = page.extractText()
        # The encoding put each page on a single line.  
        # type is <class 'bytes'>
        print(text.encode('utf-8'))

        #################################
        # This outputs the text to a list,
        # but it doesn't keep paragraphs 
        # together 
        #################################
        # output = text.encode('utf-8')
        # split = str(output, 'utf-8').split('\n')
        # print (split)
        #################################

        # Process next page.
        currentPageNumber += 1

path = 'mypdf.pdf'
pdf_text_extractor(path)

PyPDF2和extractText（）函数的文档说明了这一点：

extractText()

Locate all text drawing commands, in the order they are provided in the 
content stream, and extract the text. This works well for some PDF files, but 
poorly for others, depending on the generator used. This will be refined in 
the future. Do not rely on the order of text coming out of this function, as 
it will change if this function is made more sophisticated.

Returns: a unicode string object.

这意味着提取文本与PDF格式的文本完全相同可能会有问题。

您可以使用tika来完成此任务，但同样不会完全干净。

from tika import parser

parse_entire_pdf = parser.from_file('mypdf.pdf', xmlContent=True)
parse_entire_pdf = parse_entire_pdf['content']
print (parse_entire_pdf)

真正的问题是 - 您打算如何使用提取的文本？