doc_ebook_checker/procesa_documentos.py

from docx import Document



import language_tool_python
import os, sys

import pdb


#un comentario de mierda sobre el nombre del fichero

fishero = "c:\\DATOS\\DOCS\\!NOM\\SPANISH\\1_MITROKHIN\\El archivo Mitrokhin - El KGB en Europa y Occidente - Christopher Andrew, Vasili Mitrokhin Z-Library-mono.docx"

checker_tool = language_tool_python.LanguageTool('es')

f = open(fishero, 'rb')
document = Document(f)

offset = 0

nroPara = 1
nroParas = len(document.paragraphs)
for para in document.paragraphs:
    start = offset
    end = start + len(para.text)
    if para.style.name == "Heading 1":        
        print(f"{para.text.replace(chr(9), " "):80s}      =>   Rango = {start} to {end}")
    else:
        text = para.text
        matches = checker_tool.check(text)
        nroMatch = 1
        for match in matches:            
            print(f"Rule[{nroMatch}]: {match.rule_id}")
            print(f"Message:     {match.message}")
            print(f"Error:      '{text[match.offset:match.offset+match.error_length]}'")
            print("Suggestions:", match.replacements)
            print("Context:    ", match.context)
            print()
            nroMatch += 1
            #if nroMatch > 3:
            #    break
        print(f"=[{nroPara:5d}/{nroParas:5d}]========================================")
    offset = end + 1
    nroPara += 1

#pdb.set_trace()
f.close()