Add this function to your Apps Script project and feed it an ID to a Google Doc.
If you need this on a lot of Docs, you may want to make a new Apps Script project to use as a library. Simply copy and paste this code to the new project, go to the script that's tied to your Doc, add your new Library (the script ID), and call var html = *NameOfYourLibraryProject*.getContent(DocumentApp.getActiveDocument().getId());
| /** | |
| * Takes in a Google Doc ID, gets that doc in HTML format, cleans up the markup, and returns the resulting HTML string. | |
| * | |
| * @param {string} the id of the google doc | |
| * @param {boolean} [useCaching] enable or disable caching. default true. | |
| * @return {string} the doc's body in html format | |
| */ | |
| function getContent(id, useCaching) { | |
| if (!id) { | |
| throw "Please call this API with a valid Google Doc ID"; | |
| } | |
| if (useCaching == null) { | |
| useCaching = true; | |
| } | |
| if (typeof useCaching != "boolean") { | |
| throw "If you're going to specify useCaching, it must be boolean."; | |
| } | |
| var cache = CacheService.getScriptCache(); | |
| var cached = cache.get(id); // see if we have a cached version of our parsed html | |
| if (cached && useCaching) { | |
| var html = cached; | |
| Logger.log("Pulling doc html from cache..."); | |
| } else { | |
| Logger.log("Grabbing and parsing fresh html from the doc..."); | |
| try { | |
| var doc = DriveApp.getFileById(id); | |
| } catch (err) { | |
| throw "Please call this API with a valid Google Doc ID. " + err.message; | |
| } | |
| var docName = doc.getName(); | |
| var forDriveScope = DriveApp.getStorageUsed(); // needed to get Drive Scope requested in ScriptApp.getOAuthToken(); | |
| var url = "https://docs.google.com/feeds/download/documents/export/Export?id=" + id + "&exportFormat=html"; | |
| var param = { | |
| method: "get", | |
| headers: {"Authorization": "Bearer " + ScriptApp.getOAuthToken()}, | |
| muteHttpExceptions:true, | |
| }; | |
| var html = UrlFetchApp.fetch(url, param).getContentText(); | |
| // nuke the whole head section, including the stylesheet and meta tag | |
| html = html.replace(/<head>.*<\/head>/, ''); | |
| // remove almost all html attributes | |
| html = html.replace(/ (id|class|style|start|colspan|rowspan)="[^"]*"/g, ''); | |
| // remove all of the spans, as well as the outer html and body | |
| html = html.replace(/<(span|\/span|body|\/body|html|\/html)>/g, ''); | |
| // clearly the superior way of denoting line breaks | |
| html = html.replace(/<br>/g, '<br />'); | |
| cache.put(id, html, 900) // cache doc contents for 15 minutes, in case we get a lot of requests | |
| } | |
| Logger.log(html); | |
| return html; | |
| } |