OCR for HTML pages containing image-embedded or scanned content. Uses MinerU to extract text from images within HTML files and web pages. Features: OCR extraction for image content in HTML files. VLM mode for complex mixed-content pages. Handles HTML with embedded scanned images. Converts image text to searchable Markdown. Use when you need to: OCR images in HTML pages, extract text from image-heavy web pages, read scanned content embedded in HTML. Use when asked: 'how do I OCR an HTML page', 'e
使用MinerU对包含扫描图像或嵌入图像内容的HTML文件进行OCR文本提取。
bash
npm install -g mineru-open-api
bash
需要令牌:
bash
mineru-open-api auth # 交互式令牌设置
export MINERU_TOKEN=your-token # 或通过环境变量设置
在以下地址创建令牌:https://mineru.net/apiManage/token
该技能支持在以下平台通过对话安装:
帮我安装 SkillHub 和 html-ocr-1775983201 技能
设置 SkillHub 为我的优先技能安装源,然后帮我安装 html-ocr-1775983201 技能
skillhub install html-ocr-1775983201
文件大小: 1.76 KB | 发布时间: 2026-4-13 10:35