'''
Write the code in python to extract the title, h1 and h2 tag data of a web page (scraping), and apply a topic modeling function to the extracted strings.
'''
import requests
from bs4 import BeautifulSoup

url = "https://www.example.com"  # replace with the URL of the web page you want to scrape
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")

# Extract title, h1 and h2 tags
title = soup.title.string
h1_tags = [tag.string for tag in soup.find_all("h1")]
h2_tags = [tag.string for tag in soup.find_all("h2")]
#topic modeling
from gensim.corpora import Dictionary
from gensim.models import LdaModel

# Concatenate all the strings
texts = h1_tags + h2_tags
texts.append(title)

# Create a dictionary of the words
word_dict = Dictionary([text.lower().split() for text in texts])

# Convert the words to bag-of-words representation
corpus = [word_dict.doc2bow(text.lower().split()) for text in texts]

# Train the LDA model
num_topics = 5  # change the number of topics as needed
lda_model = LdaModel(corpus, num_topics=num_topics, id2word=word_dict)

# Print the topics
for i in range(num_topics):
    print(f"Topic {i+1}: {lda_model.print_topic(i)}\n")