reworkd/AgentGPT

🌎 Add web scraping capabilities

Open

#684 创建于 2023年6月5日

在 GitHub 查看
 (2 评论) (4 反应) (0 负责人)TypeScript (34,594 star) (9,446 fork)batch import
enhancementhelp wantedjavascriptpython

描述

Currently we just do a simple Google search and summarize the descriptions of websites. We should also parse each website individual and aggregate information.

This would be a large undertaking

贡献者指南

技术栈
typescriptnodejs
领域
backenddata
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
4
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
over 1 week
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
TypeScriptweb scraping conceptsNode.js
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
25
研究方向
Review the existing Google search integration in the codebase to understand the current data flow. Examine potential scraping libraries compatible with TypeScript, such as Cheerio or Puppeteer. Assess the structure of target websites to determine parsing strategies. Consider error handling and rate limiting to avoid IP blocks. Propose a design that aggregates scraped data with existing search results.