import streamlit as st
import requests
import base64
import os
import asyncio
from huggingface_hub import HfApi
import plotly.express as px
import zipfile # Importing zipfile to handle ZIP operations
# 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)
# Directory to save the ZIP files
ZIP_DIR = "generated_zips"
if not os.path.exists(ZIP_DIR):
os.makedirs(ZIP_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)}
# 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 create a ZIP archive of the HTML files
@st.cache_resource
def create_zip_of_files(files):
zip_name = "HuggingFace_User_Pages.zip" # Renamed for clarity
zip_file_path = os.path.join(ZIP_DIR, zip_name)
with zipfile.ZipFile(zip_file_path, 'w') as zipf:
for file in files:
# Add each HTML file to the ZIP archive with its basename
zipf.write(file, arcname=os.path.basename(file))
return zip_file_path
# Function to generate a download link for the ZIP file
@st.cache_resource
def get_zip_download_link(zip_file):
with open(zip_file, 'rb') as f:
data = f.read()
b64 = base64.b64encode(data).decode()
href = f'<a href="data:application/zip;base64,{b64}" download="{os.path.basename(zip_file)}">📥 Download All HTML Pages as ZIP</a>'
return href
# Function to 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 get all HTML files for the selected users
def get_all_html_files(usernames):
html_files = []
errors = {}
for username in usernames:
html_file, error = download_user_page(username)
if html_file:
html_files.append(html_file)
else:
errors[username] = error
return html_files, errors
# Streamlit app setup
st.title("Hugging Face User Page Downloader & Zipper 📄➕📦")
# 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()]
# Fetch user content asynchronously
user_data_list = asyncio.run(fetch_all_users(username_list))
# Collect statistics for Plotly graphs
stats = {"username": [], "models_count": [], "datasets_count": []}
# List to store paths of successfully downloaded HTML files
successful_html_files = []
st.markdown("### User Content Overview")
for user_data in user_data_list:
username = user_data["username"]
with st.container():
# Profile link
st.markdown(f"**{username}** [🔗 Profile](https://huggingface.co/{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"]
# Download the user's HTML page
html_file_path, download_error = download_user_page(username)
if html_file_path:
successful_html_files.append(html_file_path)
st.success(f"✅ Successfully downloaded {username}'s page.")
else:
st.error(f"❌ Failed to download {username}'s page: {download_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("---")
# Check if there are any successfully downloaded HTML files to zip
if successful_html_files:
# Create a ZIP archive of the HTML files
zip_file_path = create_zip_of_files(successful_html_files)
# Generate a download link for the ZIP file
zip_download_link = get_zip_download_link(zip_file_path)
st.markdown(zip_download_link, unsafe_allow_html=True)
else:
st.warning("No HTML files were successfully downloaded to create a ZIP archive.")
# 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 ZIP archive** containing all the HTML pages by clicking the download link.
5. Check out the statistics visualizations below!
""")