Convert odt, doc, docx, pdf to text with python and some linux programs. Doesn't require Libreoffice.

document_to_text.py

from subprocess import Popen, PIPE
from docx import opendocx, getdocumenttext

#http://stackoverflow.com/questions/5725278/python-help-using-pdfminer-as-a-library
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import TextConverter
from pdfminer.layout import LAParams
from pdfminer.pdfpage import PDFPage
from cStringIO import StringIO

def convert_pdf_to_txt(path):
    rsrcmgr = PDFResourceManager()
    retstr = StringIO()
    codec = 'utf-8'
    laparams = LAParams()
    device = TextConverter(rsrcmgr, retstr, codec=codec, laparams=laparams)
    fp = file(path, 'rb')
    interpreter = PDFPageInterpreter(rsrcmgr, device)
    password = ""
    maxpages = 0
    caching = True
    pagenos=set()
    for page in PDFPage.get_pages(fp, pagenos, maxpages=maxpages, password=password,caching=caching, check_extractable=True):
        interpreter.process_page(page)
    fp.close()
    device.close()
    str = retstr.getvalue()
    retstr.close()
    return str

def document_to_text(filename, file_path):
    if filename[-4:] == ".doc":
        cmd = ['antiword', file_path]
        p = Popen(cmd, stdout=PIPE)
        stdout, stderr = p.communicate()
        return stdout.decode('ascii', 'ignore')
    elif filename[-5:] == ".docx":
        document = opendocx(file_path)
        paratextlist = getdocumenttext(document)
        newparatextlist = []
        for paratext in paratextlist:
            newparatextlist.append(paratext.encode("utf-8"))
        return '\n\n'.join(newparatextlist)
    elif filename[-4:] == ".odt":
        cmd = ['odt2txt', file_path]
        p = Popen(cmd, stdout=PIPE)
        stdout, stderr = p.communicate()
        return stdout.decode('ascii', 'ignore')
    elif filename[-4:] == ".pdf":
        return convert_pdf_to_txt(file_path)

pdfminer is too slow when reading big pdf. Command line tool pdftotext may be better.

I am looking for the package docx that contains the functions opendocx and getdocumenttext.

I don't have these functions when I do an installation with 'pip install docx'.

Are they still available on GitHub or somewhere else ?

Thanks @bufke, this was really helpful.

I find my installation of docx telling me of incompatibility issues with libxml, On trying to upgrade lxm I find it is in its latest version

Thanks a lot this helped me a lot, resolving my problem of converting doc to text

Hi. I'm trying to build a module where i can convert PDF to .docx. The PDFs contain images and formatted text. can you suggest changes in your script which will help me achieve this output.

.doc conversion not working
returns empty string only