sumy_text_summarizer.py

import sumy
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
from sumy.summarizers.lex_rank import LexRankSummarizer

import requests
from bs4 import BeautifulSoup

url = 'https://en.wikipedia.org/wiki/Python_(programming_language)'

res = requests.get(url)
soup = BeautifulSoup(res.text,'html.parser')

articles = []
for i in range(len(soup.select('p'))):
    article = soup.select('p')[i].getText().strip()
    articles.append(article)
raw_data = " ".join(articles)

import re
def clean_data(data):
  text = re.sub(r"\[[0-9]*\]"," ",data)
  text = text.lower()
  text = re.sub(r'\s+'," ",text)
  text = re.sub(r","," ",text)
  return text
cleaned_article_content = clean_data(raw_data)

# For Strings
parser = PlaintextParser.from_string(cleaned_article_content,Tokenizer("english"))

summarizer = LexRankSummarizer()
#Summarize the document with 2 sentences
summary = summarizer(parser.document, 2)

for sentence in summary:
    print(sentence)