import streamlit as st import requests import base64 import os import asyncio from huggingface_hub import HfApi import plotly.express as px # Initialize the Hugging Face API api = HfApi() # Directory to save the downloaded and generated files HTML_DIR = "generated_html_pages" if not os.path.exists(HTML_DIR): os.makedirs(HTML_DIR) # Default list of Hugging Face usernames default_users = { "users": [ "awacke1", "rogerxavier", "jonatasgrosman", "kenshinn", "Csplk", "DavidVivancos", "cdminix", "Jaward", "TuringsSolutions", "Severian", "Wauplin", "phosseini", "Malikeh1375", "gokaygokay", "MoritzLaurer", "mrm8488", "TheBloke", "lhoestq", "xw-eric", "Paul", "Muennighoff", "ccdv", "haonan-li", "chansung", "lukaemon", "hails", "pharmapsychotic", "KingNish", "merve", "ameerazam08", "ashleykleynhans" ] } # Asynchronous function to fetch user content using Hugging Face API async def fetch_user_content(username): try: # Fetch models and datasets models = list(await asyncio.to_thread(api.list_models, author=username)) datasets = list(await asyncio.to_thread(api.list_datasets, author=username)) return { "username": username, "models": models, "datasets": datasets } except Exception as e: return {"username": username, "error": str(e)} # Fetch all users concurrently async def fetch_all_users(usernames): tasks = [fetch_user_content(username) for username in usernames] return await asyncio.gather(*tasks) # Function to download the user page using requests def download_user_page(username): url = f"https://huggingface.co/{username}" try: response = requests.get(url) response.raise_for_status() html_content = response.text html_file_path = os.path.join(HTML_DIR, f"{username}.html") with open(html_file_path, "w", encoding='utf-8') as html_file: html_file.write(html_content) return html_file_path, None except Exception as e: return None, str(e) # Function to base64 encode the HTML file def encode_html_to_base64(html_file_path): try: with open(html_file_path, "rb") as file: encoded_bytes = base64.b64encode(file.read()) encoded_str = encoded_bytes.decode('utf-8') return encoded_str, None except Exception as e: return None, str(e) # Cache the downloaded and encoded content to avoid redundant operations @st.cache_data(show_spinner=False, ttl=3600) def get_cached_base64_html(username): html_file_path, error = download_user_page(username) if error: return None, error encoded_str, encode_error = encode_html_to_base64(html_file_path) if encode_error: return None, encode_error return encoded_str, None # Streamlit app setup st.title("Hugging Face User Page Downloader 📄✨") # Text area with default list of usernames user_input = st.text_area( "Enter Hugging Face usernames (one per line):", value="\n".join(default_users["users"]), height=300 ) # Show User Content button if st.button("Show User Content"): if user_input: username_list = [username.strip() for username in user_input.split('\n') if username.strip()] # Collect statistics for Plotly graphs stats = {"username": [], "models_count": [], "datasets_count": []} st.markdown("### User Content Overview") for username in username_list: with st.container(): # Profile link st.markdown(f"**{username}** [🔗 Profile](https://huggingface.co/{username})") # Fetch models and datasets user_data = asyncio.run(fetch_user_content(username)) if "error" in user_data: st.warning(f"{username}: {user_data['error']} - Something went wrong! ⚠️") else: models = user_data["models"] datasets = user_data["datasets"] # Encode the downloaded HTML page to base64 base64_html, encode_error = get_cached_base64_html(username) if base64_html: # Provide a download link for the base64-encoded HTML b64_filename = f"{username}_base64.txt" st.download_button( label=f"📥 Download {username}'s Base64 Encoded HTML", data=base64_html, file_name=b64_filename, mime="text/plain" ) else: st.error(f"Failed to encode HTML for {username}: {encode_error}") # Add to statistics stats["username"].append(username) stats["models_count"].append(len(models)) stats["datasets_count"].append(len(datasets)) # Display models with st.expander(f"🧠 Models ({len(models)})", expanded=False): if models: for model in models: model_name = model.modelId.split("/")[-1] st.markdown(f"- [{model_name}](https://huggingface.co/{model.modelId})") else: st.markdown("No models found. 🤷‍♂️") # Display datasets with st.expander(f"📚 Datasets ({len(datasets)})", expanded=False): if datasets: for dataset in datasets: dataset_name = dataset.id.split("/")[-1] st.markdown(f"- [{dataset_name}](https://huggingface.co/datasets/{dataset.id})") else: st.markdown("No datasets found. 🤷‍♀️") st.markdown("---") # Plotly graphs to visualize the number of models and datasets each user has if stats["username"]: st.markdown("### User Content Statistics") # Number of models per user fig_models = px.bar( x=stats["username"], y=stats["models_count"], labels={'x': 'Username', 'y': 'Number of Models'}, title="Number of Models per User" ) st.plotly_chart(fig_models) # Number of datasets per user fig_datasets = px.bar( x=stats["username"], y=stats["datasets_count"], labels={'x': 'Username', 'y': 'Number of Datasets'}, title="Number of Datasets per User" ) st.plotly_chart(fig_datasets) else: st.warning("Please enter at least one username. Don't be shy! 😅") # Sidebar instructions st.sidebar.markdown(""" ## How to use: 1. The text area is pre-filled with a list of Hugging Face usernames. You can edit this list or add more usernames. 2. Click **'Show User Content'**. 3. View each user's models and datasets along with a link to their Hugging Face profile. 4. **Download a base64-encoded HTML page** for each user by clicking the download button. 5. Check out the statistics visualizations below! """)