How Read Contents Of Txt Files In Different Directories And Rename Other Files According To

I just started with Python 3 and ran into the following problem: I downloaded a good deal of PDFs from different journals for my thesis, but they are all named after their DOI and

Solution 1:

Finally got it to work:

#__author__ = 'Telefonmann'
# -*- coding: utf-8 -*-

import os, re, ntpath, shutil

for root, dirs, files in os.walk(os.getcwd()):
    for file in files: # loops through directories and files
        if file.endswith(('.txt')): # only processes txt files
            full_path = ntpath.splitdrive(ntpath.join(root, file))[1]
            # builds correct path under Win 7 (and probably other NT-systems

            with open(full_path, 'r', encoding='utf-8') as f:
                content = f.read().replace('\n', '') # remove newline

                r = re.compile('To\s*cite\s*this\s*article:\s*(.*?),\s*Journal\s*of\s*Quantitative\s*Linguistics\s*,')
                m = r.search(content)
                # finds substring inbetween "To cite this article: " and "Journal of Quantitative Linguistics,"
                # also finds typos like "Journal ofQuantitative ..."

                if m:
                    full_title = m.group(1)

            print("full_title: {0}".format(full_title))
            full_title = (full_title.replace('<','') # removes/replaces forbidden characters in Windows file names
                .replace('>','')
                .replace(':',' -')
                .replace('"','')
                .replace('/','')
                .replace('\\','')
                .replace('|','')
                .replace('?','')
                .replace('*',''))

            pdf_name = full_path.replace('txt','pdf')
            # since txt and pdf files only differ in their format extension I simply replace .txt with .pdf
            # to get the right name

            print('File: '+ file)
            print('Full Path: ' + full_path)
            print('Full Title: ' + full_title)
            print('PDF Name: ' + pdf_name)
            print('....................................')
            # for trouble shooting

            dirname = ntpath.dirname(pdf_name)
            new_path = ntpath.join(dirname, "{0}.pdf".format(full_title))

            if ntpath.exists(full_path):
                print("all paths found")
                shutil.copy(pdf_name, new_path)
                # makes a copy of the pdf file with the new name in the respective directory