How to summarize an article that is stored in a word document on your laptop?

[Mikedicenso87]

So I am new here.... I wrote a code in pycharm that summarizes articles online. This is the code below: it works fine. what about if I want to summarize an article that is stored in a word document on my laptop? can somebody help me with the code? Again I am using Anaconda prompt and pycharm

import tkinter as tk import nltk from textblob import TextBlob from newspaper import Article url = "https://www.news.com/index.html" article = Article(url) article.download() article.parse() article.nlp() print(f'Title: {article.title}') print(f'Authors: {article.authors}') print(f'Publication Date: {article.publish_date}') print(f'Summary: {article.summary}')

Gribouillis write Oct-06-2023, 03:42 AM:
Please post all code, output and errors (it it's entirety) between their respective tags. Refer to BBCode help topic on how to post. Use the "Preview Post" button to make sure the code is presented as you expect before hitting the "Post Reply/Thread" button.

[Pedroski55]

Word documents have metadata information. You can access that, if that is what you are looking for.

I think a word document will only have a title, author name, etc. if the author actually puts that data in the document metadata.

For personal stuff, I don't think many people will do that.

Maybe the publish date and modified date are recorded automatically.

I copied this from stackoverflow

# if you don't have it, first install python-docx module: pip3 install python-docx import docx path2file = "/home/pedro/myStuff/mydocument1.docx" def getMetaData(doc): metadata = {} prop = doc.core_properties metadata["author"] = prop.author metadata["category"] = prop.category metadata["comments"] = prop.comments metadata["content_status"] = prop.content_status metadata["created"] = prop.created metadata["identifier"] = prop.identifier metadata["keywords"] = prop.keywords metadata["last_modified_by"] = prop.last_modified_by metadata["language"] = prop.language metadata["modified"] = prop.modified metadata["subject"] = prop.subject metadata["title"] = prop.title metadata["version"] = prop.version return metadata doc = docx.Document(path2file) metadata_dict = getMetaData(doc) for item in metadata_dict.items(): print(item)

Sometimes I want to get the text from .docx files. I never needed the metadata!

[Mikedicenso87]

This code basically pulls just high level information. I will try to write a new code and will post it it when done.. Thanks so much Pedro!