-
-
Save TheoOliveira/20ba9a892224ab2252094d15a48a9ebe to your computer and use it in GitHub Desktop.
Convert odt, doc, docx, pdf to text with python and some linux programs. Doesn't require Libreoffice.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 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) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment