类库 › reader
vakra-dev

vakra-dev/reader

Reader是一个为大型语言模型设计的开源生产级网络爬虫引擎。它能高效抓取整个网页内容,清理并转换为干净的Markdown格式,适合AI智能体直接使用,解决了传统爬虫在浏览器管理、反爬绕过等方面的生产级难题。

vakra-dev/reader

技术栈

examples javascript

查看全部依赖 (19)

依赖

@vakra-dev/reader file:..

开发依赖

@ai-sdk/openai ^1.0.0 @anthropic-ai/sdk ^0.39.0 @langchain/core ^0.3.0 @pinecone-database/pinecone ^4.0.0 @qdrant/js-client-rest ^1.12.0 @types/aws-lambda ^8.10.145 @types/express ^4.17.21 @types/node ^20.10.6 @ulixee/hero ^2.0.0-alpha.34 @ulixee/hero-core ^2.0.0-alpha.34 @ulixee/net ^2.0.0-alpha.29 @vercel/node ^3.2.0 ai ^4.0.0 express ^4.18.2 llamaindex ^0.8.0 openai ^4.0.0 tsx ^4.7.0 typescript ^5.3.3

examples/production/browser-pool-scaling javascript

查看全部依赖 (6)

依赖

@vakra-dev/reader file:../../.. express ^4.18.2

开发依赖

@types/express ^4.17.21 @types/node ^20.10.6 tsx ^4.7.0 typescript ^5.3.3

examples/production/express-server javascript

查看全部依赖 (9)

依赖

@ulixee/hero ^2.0.0-alpha.34 @ulixee/hero-core ^2.0.0-alpha.34 @ulixee/net ^2.0.0-alpha.29 @vakra-dev/reader ^1.0.0 express ^4.18.2

开发依赖

@types/express ^4.17.21 @types/node ^20.10.6 tsx ^4.7.0 typescript ^5.3.3

examples/production/job-queue-bullmq javascript

查看全部依赖 (12)

依赖

@ulixee/hero ^2.0.0-alpha.34 @ulixee/hero-core ^2.0.0-alpha.34 @ulixee/net ^2.0.0-alpha.29 @vakra-dev/reader file:../../.. bullmq ^5.0.0 express ^4.18.2 ioredis ^5.3.0

开发依赖

@types/express ^4.17.21 @types/node ^20.10.6 concurrently ^8.2.0 tsx ^4.7.0 typescript ^5.3.3

根目录 javascript

代码规范

ESLint ^8.57.0 Prettier ^3.2.0
查看全部依赖 (16)

依赖

@ulixee/hero ^2.0.0-alpha.34 @ulixee/hero-core ^2.0.0-alpha.34 @vakra-dev/supermarkdown ^0.0.3 commander ^12.0.0 got-scraping ^4.1.3 linkedom ^0.18.12 p-limit ^4.0.0 pino ^9.0.0 re2 ^1.23.0

开发依赖

@types/node ^20.10.6 @typescript-eslint/eslint-plugin ^7.0.0 @typescript-eslint/parser ^7.0.0 leasot ^13.3.0 pino-pretty ^13.1.3 tsup ^8.5.1 typescript ^5.3.3

截图

./docs/assets/demo.gif

评论

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-05-01 08:39
浙ICP备14020137号-1 $访客地图$