Question

我正在寻找一种从pdf文件中获取文本的方法并找到了一个pdfminer库，在github上有一个工作示例。我稍微修改它来传递参数，当我使用python执行脚本时它工作正常。但我想有一个exe文件。我使用pyinstaller来创建exe，不幸的是当我尝试运行文件时出现以下错误：

Traceback (most recent call last):
  File "onlypdfminer.py", line 5, in <module>
  File "<frozen importlib._bootstrap>", line 971, in _find_and_load
  File "<frozen importlib._bootstrap>", line 955, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 665, in _load_unlocked
  File "c:\python36-32\lib\site-    packages\PyInstaller\loader\pyimod03_importers.py", line 631, in exec_module
    exec(bytecode, module.__dict__)
  File "site-packages\pdfminer\pdfpage.py", line 10, in <module>
  File "<frozen importlib._bootstrap>", line 971, in _find_and_load
  File "<frozen importlib._bootstrap>", line 955, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 665, in _load_unlocked
  File "c:\python36-32\lib\site-packages\PyInstaller\loader\pyimod03_importers.py", line 631, in exec_module
    exec(bytecode, module.__dict__)
  File "site-packages\pdfminer\pdfdocument.py", line 12, in <module>
  File "<frozen importlib._bootstrap>", line 971, in _find_and_load
  File "<frozen importlib._bootstrap>", line 955, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 665, in _load_unlocked
  File "c:\python36-32\lib\site-packages\PyInstaller\loader\pyimod03_importers.py", line 631, in exec_module
    exec(bytecode, module.__dict__)

...

这是我的代码：

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
import argparse

parser=argparse.ArgumentParser(description='Convert PDF to txt using PyPDF2                 and pdfminer')
parser.add_argument('-i','--input',required=True)
parser.add_argument('-o','--output',required=True)

args = parser.parse_args()

def checkFile(fname):
if not os.path.exists(fname):
    sys.exit("Path "+fname+"doesn't exist")    

def usePdfMiner(fname, oPath, pages=None):
checkFile(fname)
if not pages:
    pagenums = set()
else:
    pagenums = set(pages)
try:
    output = 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
    textFile = open(oPath+"/pdf1.txt", "w")
    textFile.write(text)
except:
    pass        

if __name__ =='__main__':
usePdfMiner(args.input,args.output)

我将不胜感激任何建议

Python 3.6 - 使用pyinstaller创建exe - 错误

0 个答案: