| |
| import requests |
| from bs4 import BeautifulSoup |
| import pandas as pd |
| import gradio as gr |
|
|
| |
| def scrape_post(link): |
| response = requests.get(link) |
| soup = BeautifulSoup(response.content, 'html.parser') |
| |
| title = soup.select_one('h1').text.strip() |
| content = soup.select_one('section.entry').text.strip() |
| featured_img = soup.select_one('img.entry-image')['src'] |
| category = [a.text for a in soup.select('.entry-cat a')] |
| tags = [a.text for a in soup.select('.entry-tag a')] |
| |
| return {'title': title, 'content': content, 'featured_img': featured_img, 'category': category, 'tags': tags} |
|
|
| |
| def scrape_unwinnable_movies(): |
| base_url = 'https://unwinnable.com/category/sections/movies-tv/' |
| next_page = base_url |
| all_posts = [] |
|
|
| while next_page: |
| response = requests.get(next_page) |
| soup = BeautifulSoup(response.content, 'html.parser') |
| |
| post_links = [a['href'] for a in soup.select('.entry-title a')] |
| for link in post_links: |
| post_data = scrape_post(link) |
| all_posts.append(post_data) |
| |
| next_page_elem = soup.select_one('a.next') |
| next_page = next_page_elem['href'] if next_page_elem else None |
| |
| return pd.DataFrame(all_posts) |
|
|
| |
| def scrape_and_display(): |
| df = scrape_unwinnable_movies() |
| return gr.DataFrame.update(value=df) |
|
|
| |
| demo = gr.Interface(fn=scrape_and_display, inputs=[], outputs="dataframe", title="Unwinnable Movies Scraper") |
|
|
| |
| demo.launch() |
|
|
