I try to use pdfminer.six to convert multiple pdfs in a directory to multiple .txt files using python 3.6.3
I got these error: ModuleNotFoundError: No module named 'pdfminer' when run the codes below. Or, when i run pdf2txt.py filename.pdf, it gives therenv: python\r: No such file or directory
I did some research regarding the issue. I have removed the original pdfminer from my pip, currently, it has only the pdfminer.six in my pip. Also, I am running python 3.6.3 on virtualenv.
Below is the code that I run:
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, getopt
#converts pdf, returns its text content as a string
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 = file(fname, 'rb')
for page in PDFPage.get_pages(infile, pagenums):
interpreter.process_page(page)
infile.close()
converter.close()
text = output.getvalue()
output.close
return text
#converts all pdfs in directory pdfDir, saves all resulting txt files to txtdir
def convertMultiple(pdfDir, txtDir):
if pdfDir == "": pdfDir = os.getcwd() + "\\" #if no pdfDir passed in
for pdf in os.listdir(pdfDir): #iterate through pdfs in pdf directory
fileExtension = pdf.split(".")[-1]
if fileExtension == "pdf":
pdfFilename = pdfDir + pdf
text = convert(pdfFilename) #get string of text content of pdf
textFilename = txtDir + pdf + ".txt"
textFile = open(textFilename, "w") #make text file
textFile.write(text) #write text to text file
pdfDir = "../../data/raw/"
txtDir = "../../data/interim/"
convertMultiple(pdfDir, txtDir)
