Created
August 8, 2024 08:08
-
-
Save EdwardPrentice/2df79a94ed73ecf9394123319eea0170 to your computer and use it in GitHub Desktop.
Mattia Righetti Code Refactored
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // content-extractor.ts | |
| import $ from "jquery"; | |
| const extractContent = (selector: string, subSelector: string) => { | |
| return $(selector) | |
| .first() | |
| .find(subSelector) | |
| .map((_, el) => $(el).text().trim()) | |
| .get() | |
| .filter((text) => text.length > 0) | |
| .join("\n\n"); | |
| }; | |
| function isNotion(): boolean { | |
| return $("main.notion-page").length > 0; | |
| } | |
| function extractNotionContent() { | |
| $("main.notion-page").find(".notion-collection-page-properties").remove(); | |
| return extractContent("main.notion-page", "p, h1, h2, h3, h4, h5, h6, div, li"); | |
| } | |
| function isSubstack(): boolean { | |
| return $(".available-content").length > 0; | |
| } | |
| function extractSubstackContent() { | |
| return extractContent(".available-content", "p, h1, h2, h3, h4, h5, h6"); | |
| } | |
| function isBeehiv(): boolean { | |
| return $("#content-blocks").length > 0; | |
| } | |
| function extractBeehivContent() { | |
| return extractContent("#content-blocks", "p, h1, h2, h3, h4, h5, h6"); | |
| } | |
| function isArticle(): boolean { | |
| return $("article").length > 0; | |
| } | |
| function extractArticle() { | |
| $("article").find("style, script, div").remove(); | |
| $("article").find(".ml-form-embedContainer").remove(); | |
| return extractContent("article", "p, h1, h2, h3, h4, h5, h6, li, figure"); | |
| } | |
| function getContent() { | |
| if (isNotion()) { | |
| return extractNotionContent(); | |
| } | |
| if (isSubstack()) { | |
| return extractSubstackContent(); | |
| } | |
| if (isBeehiv()) { | |
| return extractBeehivContent(); | |
| } | |
| if (isArticle()) { | |
| return extractArticle(); | |
| } | |
| return $("main").text(); | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment