Redirect output of a function that converts pdf to

问题:

I am using python 3. My code uses pdfminer to convert pdf to text. I want to get the output of these files in a new folder. Currently it's coming in the existing folder from which it does the conversion to .txt using pdfminer. How do I redirect the output to a different folder. I want the output in a folder called "D:\extracted_text" Code till now:

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

def convert(fname, pages=None):
   if not pages:
       pagenums = set()
   else:
       pagenums = set(pages)

   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

   savepath = 'D:/extracted_text/'
   outfile = os.path.splitext(fname)[0] + '.txt'
   comp_name = os.path.join(savepath,outfile)
   print(outfile)
   with open(comp_name, 'w', encoding = 'utf-8') as pdf_file:
       pdf_file.write(text)

   return text    



directory = glob.glob(r'D:\files\*.pdf')  

for myfiles in directory:  
     convert(myfiles)

回答1:

you can use os.path,join, you have to give your directory path and filename with extension. it will create a full url and creates a file. You can use it like below

with open(os.path.join(dir_path,fileCompleteName), "w") as file1:
        file1.write("Hello World")

In windows any of the below should work

"D:/extracted_text/"
os.path.join("/", "D:", "extracted_text", outfile)
os.path.join("D:/", "extracted_text", outfile)

Make sure directory path is exist "D:/extracted_text"

回答2:

The problem lies in line:

outfile = os.path.splitext(os.path.abspath(fname))[0] + '.txt'

If you print out outfile, you'll see that it contains the full path of your file. Replace it with:

outfile = os.path.splitext(fname)[0] + '.txt'

This should solve your problem! Note that this will break if 'D:/extracted_text/' does not exist. So either create that directory manually or programmatically using os.makedir.

EDIT: To break down the problem into smaller pieces, open a new file and run this snippet, see if it does the trick, then make the changes in the original code:

import os

fname = "some_file.pdf"
text = "Here's the extracted text"
savepath = 'D:/extracted_text/'
outfile = os.path.splitext(fname)[0] + '.txt'
print(outfile)
comp_name = os.path.join(savepath,outfile)
print(comp_name)

with open(comp_name, 'w', encoding = 'utf-8') as pdf_file:
    pdf_file.write(text)