A Telegram bot designed for multi-platform content aggregation and analysis, ParseHubBot offers AI-powered summarization and inline query capabilities. It targets users who need to efficiently process and extract information from various social media and video platforms, providing a streamlined way to consume content.

How It Works

The bot leverages a modular parsing architecture to support a wide array of platforms, including TikTok, Bilibili, YouTube, Twitter, and more. Core functionality includes fetching content, optionally applying proxies for parsing and downloading, and integrating with OpenAI or other providers for AI-driven summarization of text and video transcripts. Configuration is managed via environment variables and platform-specific YAML files, allowing for granular control over proxies, API keys, and AI model parameters.

Quick Start & Requirements

• Primary install / run command: Docker is recommended via sudo sh start.sh in the project root. Alternatively, direct Python execution with uv run bot.py is supported after environment setup.
• Non-default prerequisites and dependencies:
  • Telegram API credentials (API_ID, API_HASH) and a Telegram Bot Token (BOT_TOKEN).
  • OpenAI API key (API_KEY) and optional configuration for BASE_URL, MODEL, PROMPT if AI summarization is enabled.
  • Optional proxy configurations for parsing and downloading.
  • Linux users may require libgl1-mesa-glx (Ubuntu 22/24) or libgl (ArchLinux) or mesa-libGL (CentOS) for skia-python.
  • Windows users require Microsoft Visual C++ 2015 Redistributable Update 3 RC.
  • Python 3.12 is specified for uv environment setup.
• Estimated setup time or resource footprint: Setup involves obtaining API keys and configuring environment variables. Docker simplifies deployment. Direct Python execution requires careful dependency management.
• Links:
  • Telegram API: https://my.telegram.org
  • BotFather: https://t.me/BotFather
  • OpenAI API: (Assumed, not linked)
  • Project Repo: https://github.com/z-mio/ParseHub (Implied by context)

Highlighted Details

• Supports AI summarization for fetched content, configurable via OpenAI or other transcription providers.
• Offers inline mode for seamless integration within any Telegram chat.
• Extensive platform support including TikTok, Bilibili, YouTube, Twitter, Xiaohongshu, Baidu Tieba, Facebook, Weibo, and Instagram.
• Configurable proxy settings for both content parsing and downloading, with per-platform overrides.
• Results caching mechanism to reduce redundant fetches, with a default of 24 hours.

Maintenance & Community

No specific details regarding maintainers, community channels (like Discord/Slack), sponsorships, or roadmap were found in the provided README.

Licensing & Compatibility

The license type is not explicitly stated in the provided README. Compatibility for commercial use or closed-source linking is therefore undetermined.

Limitations & Caveats

The project requires obtaining multiple third-party API keys (Telegram, potentially OpenAI/transcription services), which may incur costs. Installation on different operating systems may require specific graphics library or runtime installations. Some platform content access might necessitate providing cookies due to login requirements.