Gemini Web Client (gemini-web-client)

A modern Python client package for automating Google Gemini Web UI using Playwright.

✨ Features

• Google Account Authentication: Login helper tool (gemini-login) to save persistent sessions securely in a local browser profile.
• Async & Sync API: Simple Python interface to send messages, stream responses, and manage multi-turn chat sessions.
• Multimodal Support: Attach images (PNG/JPG/WEBP) or documents (PDF, TXT, CSV, Python files) to your prompts.
• Image Generation Extraction: Detects inline generated images (Imagen / Gemini Web) and downloads them to disk.
• Chat History & Navigation: List past conversation threads from the Gemini sidebar and switch between chats.
• Markdown & Code Parsing: Structured response parsing for markdown code blocks (GeminiResponse.code_blocks).
• Interactive Terminal CLI: Built-in CLI runner (gemini-web) to chat directly from your shell.

🚀 Quick Start

1. Installation

Install directly from PyPI:

pip install gemini-web-client
playwright install chromium

(For local development from source):

git clone https://github.com/hpnquoc/gemini-web-client.git
cd gemini-web-client
pip install -e .
playwright install chromium

2. Login to Google Account

Run the login assistant to sign in to your Google Account once:

gemini-login

Follow the prompt to log in in the opened browser window. Your session will be saved locally to ./.user_data.

💡 Code Examples

Basic Prompt Execution

import asyncio
from gemini_web import GeminiWebClient

async def main():
    async with GeminiWebClient(headless=True) as client:
        response = await client.send_message("Explain quantum computing in simple terms.")
        print(response.text)

if __name__ == "__main__":
    asyncio.run(main())

Real-Time Response Streaming

import asyncio
from gemini_web import GeminiWebClient

async def main():
    async with GeminiWebClient(headless=True) as client:
        async for chunk in client.send_message_stream("Write a short story about an AI."):
            print(chunk, end="", flush=True)

if __name__ == "__main__":
    asyncio.run(main())

Multi-Turn Chat Session

import asyncio
from gemini_web import GeminiWebClient

async def main():
    async with GeminiWebClient(headless=True) as client:
        chat = client.start_chat()
        
        r1 = await chat.send_message("Hi, my name is Alice.")
        print(r1.text)
        
        r2 = await chat.send_message("What is my name?")
        print(r2.text)

if __name__ == "__main__":
    asyncio.run(main())

Chat History & Thread Navigation

import asyncio
from gemini_web import GeminiWebClient

async def main():
    async with GeminiWebClient(headless=True) as client:
        # List all past chats in sidebar
        chats = await client.list_chats()
        for chat in chats:
            print(f"ID: {chat['id']} | Title: {chat['title']}")

        # Switch to a specific thread
        if chats:
            await client.switch_chat(chats[0]['id'])
            turns = await client.get_conversation_turns()
            print(f"Extracted {len(turns)} messages.")

if __name__ == "__main__":
    asyncio.run(main())

🛠️ CLI Usage

Interactive Chat REPL:

gemini-web --user-data-dir ./.user_data

Login Assistant:

gemini-login --user-data-dir ./.user_data

📄 License

GNU General Public License v3.0 (GPL-3.0)