我的代码使用pdfminer将pdf转换为文本。我想在一个新文件夹中获取这些文件的输出。目前,它位于现有文件夹中,使用pdfminer从该文件夹转换为.txt。如何将输出重定向到其他文件夹。到目前为止,我希望将输出保留在名为“ D:\ extracted_text”的文件夹中:
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
outfile = os.path.splitext(os.path.abspath(fname))[0] + '.txt'
print(outfile)
with open(outfile, '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)