将扫描的pdf转换为文本的python代码

我有一个扫描后的PDF文件，我想从中提取文本。

我尝试使用pypdfocr进行OCR，但出现了错误：

"在通常的位置找不到ghostscript"

在搜索后，我找到了这个解决方案在Windows平台上将Ghostscript与pypdfocr链接起来，我尝试下载GhostScript并将其放入环境变量中，但仍然出现相同的错误。

我如何使用Python搜索我的扫描后的PDF文件中的文本？

谢谢。

编辑：这是我的代码示例：

import os
import sys
import re
import json
import shutil
import glob
from pypdfocr import pypdfocr_gs
from pypdfocr import pypdfocr_tesseract 
from PIL import Image
path = PATH_TO_MY_SCANNED_PDF
mainL = []
kk = {}
def new_init(self, kk):
    self.lang = 'heb'   
    self.binary = "tesseract"
    self.msgs = {
            'TS_MISSING': """ 
                无法执行%s
                请确保您已正确安装Tesseract
                """ % self.binary,
            'TS_VERSION':'Tesseract版本过旧',
            'TS_img_MISSING':'找不到指定的tiff文件',
            'TS_FAILED': 'Tesseract-OCR执行失败！',
        }
pypdfocr_tesseract.PyTesseract.__init__ = new_init  
wow = pypdfocr_gs.PyGs(kk)
tt = pypdfocr_tesseract.PyTesseract(kk)
def secFile(filename,oldfilename):
    wow.make_img_from_pdf(filename)
    files = glob.glob("X:/e206333106/ocr-114/balagan/" + '*.jpg')  
    for file in files:
        im = Image.open(file)
        im.save(file + ".tiff") 
    files = glob.glob("PATH" + '*.tiff')  
    for file in files:
        tt.make_hocr_from_pnm(file)
    pdftxt = ""    
    files = glob.glob("PATH" + '*.html') 
    for file in files:
        with open(file) as myfile:
            pdftxt = pdftxt + "#" + "".join(line.rstrip() for line in myfile)
    findNum(pdftxt,oldfilename)
    folder ="PATH"
    for the_file in os.listdir(folder):
        file_path = os.path.join(folder, the_file)
        try:
            if os.path.isfile(file_path):
                os.unlink(file_path)
        except Exception, e:
            print e
def pdf2ocr(filename):
    pdffile = filename
    os.system('pypdfocr -l heb ' + pdffile)
def ocr2txt(filename):  
    pdffile = filename
    output1 = pdffile.replace(".pdf","_ocr.txt")
    output1 = "PATH" + os.path.basename(output1)
    input1 = pdffile.replace(".pdf","_ocr.pdf")
    os.system("pdf2txt" -o  + output1 + " " + input1) 
    with open(output1) as myfile:
        pdftxt="".join(line.rstrip() for line in myfile)
    findNum(pdftxt,filename)
def findNum(pdftxt,pdffile):
    l = re.findall(r'\b\d+\b', pdftxt)
    output = open('PATH' + os.path.basename(pdffile) + '.txt', 'w')
    for i in l:
        output.write(",")
        output.write(i)
    output.close()    
def is_ascii(s):
    return all(ord(c) < 128 for c in s)
i = 0     
files = glob.glob(path + '\\*.pdf') 
print path  
print files 
for file in files:
    if file.endswith(".pdf"):
        if is_ascii(file):
            print file
            pdf2ocr(file)    
            ocr2txt(file)
        else:
            newname = "PATH" + str(i) + ".pdf"
            shutil.copyfile(file, newname)
            print newname
            secFile(newname,file)
        i = i + 1
files = glob.glob(path + '\\' + '*_ocr.pdf')         
for file in files:
    print file
    shutil.copyfile(file, "PATH" + os.path.basename(file))
    os.remove(file)