Sentiment analysis of a certain paragraph from a website

Question

I have url of multiple websites in an xlsx file. I ran a loop on the xlsx file and passed the urls as an argument to the following sentiment analysis code. Now the code is providing me with the analysis of the whole website (the websites only contain text and numbers) but the problem is that I want to run the analysis only on the paragraph that starts with "Managerial function". How may I do the same? Here's my code:

article = Article(j)
article.download()
article.parse()
#nltk.download('punkt')
article.nlp()
text = article.summary
obj = TextBlob(text)
sentiment = obj.sentiment.polarity
print(round(sentiment,2))
if sentiment==0:
    print("neutral")
elif sentiment>0:
    print("positive")
elif sentiment<0:
    print("negative")

please give some text as example and a fully working code so that people can run it to provide a more accurate answer — antoine, May 29 '20 at 10:08
Btw it's "sentiment" analysis, not "sentimental". Not quite the same :) — 0buz, May 29 '20 at 11:04
Thank you for the feedbacks. I am new here and this is much appreciated. I believe I have made the necessary changes, please help. — Rohit Chayal, May 29 '20 at 11:48

score 0 · Accepted Answer · answered May 29 '20 at 12:15

Using regex, something like the below would match a paragraph starting with "Managerial function":

found=re.search(r'^(Managerial function.*\s)', full_text, re.MULTILINE)
my_paragraph=found.group(0)

, where full_text is your whole article text.

Remember to add this import first:

import re

Sentiment analysis of a certain paragraph from a website

1 Answers1