webgrab-mcp

webgrab-mcp

MCP server for web content downloading supporting videos, articles, danmaku, comments, and copy protection bypass across 1700+ sites.

Category
Visit Server

README

WebGrab - 全网最强网页内容下载处理工具

全能的网页内容下载工具:视频、文章、弹幕、评论、反复制保护绕过。

English | 中文

下载安装

无需安装 Python,开箱即用!

平台 下载
Windows WebGrab-Windows-x64.exe
macOS (Apple Silicon) WebGrab-macOS-arm64.tar.gz
Linux WebGrab-Linux-x64.tar.gz

下载后直接运行即可。也可以用 pip 安装:pip install webgrab

功能特色

功能 CLI Web UI MCP Cursor Skill OpenClaw
YouTube/通用视频下载(1700+网站) ✅ ✅ ✅ ✅ ✅
B站视频下载 ✅ ✅ ✅ ✅ ✅
B站弹幕下载(XML/JSON/CSV/ASS) ✅ ✅ ✅ ✅ ✅
B站评论下载(含楼中楼) ✅ ✅ ✅ ✅ ✅
抖音视频下载(无水印) ✅ ✅ ✅ ✅ ✅
抖音评论下载 ✅ ✅ ✅ ✅ ✅
网页文章下载(Markdown/HTML) ✅ ✅ ✅ ✅ ✅
反复制保护绕过 ✅ ✅ ✅ ✅ ✅
网页转PDF ✅ ✅ ✅ - -
m3u8流媒体下载 ✅ ✅ ✅ ✅ ✅
批量下载 ✅ ✅ ✅ - -

快速开始

安装

pip install webgrab

命令行使用

# 下载视频(支持B站、YouTube、抖音等1700+网站)
webgrab video "https://www.bilibili.com/video/BV1xx411c7mD"

# 下载B站弹幕(支持 json/csv/xml/ass 格式)
webgrab danmaku "https://www.bilibili.com/video/BV1xx411c7mD" --format ass

# 下载B站评论(含楼中楼回复)
webgrab comments "https://www.bilibili.com/video/BV1xx411c7mD" --replies --limit 200

# 下载抖音评论
webgrab comments "https://www.douyin.com/video/123456" --limit 100

# 下载文章为 Markdown
webgrab article "https://example.com/article" --format markdown

# 绕过复制保护
webgrab bypass "https://protected-site.com/article"

# 批量下载
webgrab batch "url1" "url2" "url3"

# 查看视频信息(不下载)
webgrab info "https://www.youtube.com/watch?v=xxx"

MCP 服务器(AI 助手集成)

WebGrab 提供 MCP 服务器,一次配置即可在所有主流 AI 平台使用。

安装

pip install webgrab[mcp]

配置(所有平台通用)

以下配置适用于 Claude Desktop / Cursor / Windsurf / OpenClaw / VS Code Copilot:

{
  "mcpServers": {
    "webgrab": {
      "command": "webgrab-mcp",
      "env": {
        "BILIBILI_COOKIE": "可选-用于高画质",
        "DOUYIN_COOKIE": "可选-用于评论采集"
      }
    }
  }
}

提供的工具

工具 功能
download_video 下载视频(支持画质选择)
download_audio 提取音频
download_article 下载文章(Markdown/HTML/文本)
extract_webpage 提取网页内容(不保存文件)
bypass_copy_protection 绕过复制保护
get_bilibili_danmaku 获取B站弹幕
get_bilibili_comments 获取B站评论(含楼中楼)
get_douyin_video 下载抖音视频(无水印)
get_douyin_comments 获取抖音评论
get_video_info 获取视频元数据
batch_download 批量下载
download_stream 下载m3u8流媒体

Web 服务

Docker 一键部署

git clone https://github.com/bcefghj/webgrab.git
cd webgrab
docker-compose up -d

访问 http://localhost:8000

本地开发

pip install webgrab[server]
uvicorn server.main:app --reload --host 0.0.0.0 --port 8000

油猴脚本

反复制脚本

安装 scripts/anti_copy.user.js 到 Tampermonkey,自动解除所有网页的复制限制。

视频嗅探脚本

安装 scripts/video_sniffer.user.js 到 Tampermonkey,自动检测页面中的视频/音频资源。

部署到服务器

详细的小白级部署教程请参考 部署指南,涵盖:

  • 阿里云 ECS(99元/年,含手把手教程)
  • Docker 部署
  • Render 免费部署
  • Fly.io 部署
  • GitHub Actions CI/CD

开发

git clone https://github.com/bcefghj/webgrab.git
cd webgrab
pip install -e ".[all]"
webgrab --help

许可证

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured