Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import requests | |
| from bs4 import BeautifulSoup | |
| from urllib.parse import urljoin, urlparse | |
| from fpdf import FPDF | |
| import tempfile | |
| import re | |
| import logging | |
| logging.basicConfig(level=logging.INFO) | |
| logger = logging.getLogger(__name__) | |
| def clean_text(text): | |
| text = ''.join(char for char in text if char.isprintable()) | |
| text = re.sub(r'[^\x00-\x7F]+', ' ', text) | |
| return text | |
| def get_page_content(url): | |
| try: | |
| logger.info(f"Fetching content from: {url}") | |
| response = requests.get(url, timeout=10) | |
| response.raise_for_status() | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| content = [] | |
| main_content = soup.find('main') | |
| if main_content: | |
| for tag in ['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'li']: | |
| for element in main_content.find_all(tag): | |
| text = clean_text(element.get_text(strip=True)) | |
| if text: | |
| content.append(text) | |
| logger.info(f"Found {len(content)} content items for {url}") | |
| return content | |
| except Exception as e: | |
| logger.error(f"Error processing {url}: {str(e)}") | |
| return [f"Error processing {url}: {str(e)}"] | |
| def get_all_doc_links(url): | |
| try: | |
| response = requests.get(url, timeout=10) | |
| response.raise_for_status() | |
| soup = BeautifulSoup(response.text, 'html.parser') | |
| main_content = soup.find('main') | |
| if main_content: | |
| links = main_content.find_all('a', href=True) | |
| return [urljoin(url, link['href']) for link in links if link['href'].startswith('/docs')] | |
| return [] | |
| except Exception as e: | |
| logger.error(f"Error getting links from {url}: {str(e)}") | |
| return [] | |
| def website_to_pdf(url): | |
| base_url = "https://www.gradio.app/docs" | |
| logger.info(f"Starting to process: {base_url}") | |
| all_links = get_all_doc_links(base_url) | |
| logger.info(f"Found {len(all_links)} pages to process") | |
| pdf = FPDF() | |
| pdf.set_auto_page_break(auto=True, margin=15) | |
| pdf.add_page() | |
| pdf.set_font("Arial", size=12) | |
| for page_url in all_links: | |
| content = get_page_content(page_url) | |
| pdf.cell(0, 10, txt=page_url, ln=True) | |
| pdf.ln(5) | |
| for text in content: | |
| pdf.multi_cell(0, 10, txt=text) | |
| pdf.add_page() | |
| with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as tmp: | |
| pdf_path = tmp.name | |
| pdf.output(pdf_path) | |
| logger.info(f"PDF saved to: {pdf_path}") | |
| return pdf_path | |
| def process_url(url): | |
| try: | |
| pdf_file = website_to_pdf(url) | |
| return pdf_file | |
| except Exception as e: | |
| logger.error(f"Error in process_url: {str(e)}") | |
| return f"An error occurred: {str(e)}" | |
| iface = gr.Interface( | |
| fn=process_url, | |
| inputs=gr.Textbox(label="Enter website URL (e.g., https://www.gradio.app/docs)"), | |
| outputs=gr.File(label="Download PDF"), | |
| title="Gradio Documentation to PDF Converter", | |
| description="Enter the Gradio docs URL to convert all documentation pages into a PDF." | |
| ) | |
| if __name__ == "__main__": | |
| iface.launch() |