以 HTML 格式获取 Google 文档

Question

我有一个疯狂的想法，我可以使用 Google Drive Documents 为不成熟的用户朋友建立一个网站博客来支持它。我能够创建一个 contentService 来编译文档列表。但是，我看不到将文档转换为 HTML 的方法。我知道 Google 可以在网页中渲染文档，所以我想知道是否有可能获得渲染版本以用于我的内容服务。

这可能吗？

Answer 1

你可以试试这个代码：

  function getGoogleDocumentAsHTML(){
  var id = DocumentApp.getActiveDocument().getId() ;
  var forDriveScope = DriveApp.getStorageUsed(); //needed to get Drive Scope requested
  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();
  Logger.log(html);
}

Answer 2

Node.js 解决方案

使用Google APIs Node.js Client

以下是使用 google drive 的 node.js 客户端库获取 html 格式的 google 文档的方法。

// import googleapis npm package
var google = require('googleapis');

// variables
var fileId = '<google drive doc file id>',
    accessToken = '<oauth access token>';

// oauth setup
var OAuth2 = google.auth.OAuth2,
    OAuth2Client = new OAuth2();

// set oauth credentials
OAuth2Client.setCredentials({access_token: accessToken});

// google drive setup
var drive = google.drive({version: 'v3', auth: OAuth2Client});

// download file as text/html
var buffers = [];
drive.files.export(
    {
        fileId: fileId,
        mimeType: 'text/html'
    }
)
    .on('error', function(err) {
        // handle error
    })
    .on('data', function(data) {
        buffers.push(data); // data is a buffer
    })
    .on('end', function() {
        var buffer = Buffer.concat(buffers),
            googleDocAsHtml = buffer.toString();
        console.log(googleDocAsHtml);
    });

查看Google Drive V3 download docs 了解更多语言和选项。

Answer 3

Google 文档目前具有执行此操作的功能。 只需下载到 zip(.html)，您就可以拥有一个带有 html 和图像（如果已插入）的 zip 存档

我知道这不是基于代码的解决方案，而是它的工作原理:)

Answer 4

在 GAS 中没有直接的方法来获取文档的 HTML 版本，这是一个相当古老的 enhancement request，但 Henrique Abreu 的 workaround described originally 效果很好，我一直在使用它...

授权过程中唯一烦人的事情是需要从脚本编辑器中调用，这使得在共享应用程序中使用起来很不方便（“无法使用脚本”的用户），但这只会发生一次；）。

还有一个由Romain Vialard 创建的Library，它使事情（有点）变得更容易......并添加了一些其他有趣的功能。

Answer 5

根据 Enrique 发布的想法，以下是新版 goole AOuth 的一些片段：

function exportAsHTML(){
  var forDriveScope = DriveApp.getStorageUsed(); //needed to get Drive Scope requested
  var docID = DocumentApp.getActiveDocument().getId();
  var url = "https://docs.google.com/feeds/download/documents/export/Export?id="+docID+"&exportFormat=html";
  var param = {
    method      : "get",
    headers     : {"Authorization": "Bearer " + ScriptApp.getOAuthToken()},
    muteHttpExceptions:true,
  };
  var html = UrlFetchApp.fetch(url,param).getContentText();
  return html; 

}

然后使用通常的mailApp：

function mailer(){
   var docbody = exportAsHTML();
   MailApp.sendEmail({
     to: "email@mail.com",
     subject: "document emailer",
     htmlBody:  docbody  });
}

希望新的解决方法有所帮助

京东

Answer 6

您可以使用解决方案here

/**
 * Converts a file to HTML. The Advanced Drive service must be enabled to use
 * this function.
 */
function convertToHtml(fileId) {
  var file = Drive.Files.get(fileId);
  var htmlExportLink = file.exportLinks['text/html'];
  if (!htmlExportLink) {
    throw 'File cannot be converted to HTML.';
  }
  var oAuthToken = ScriptApp.getOAuthToken();
  var response = UrlFetchApp.fetch(htmlExportLink, {
    headers:{
      'Authorization': 'Bearer ' + oAuthToken
    },
    muteHttpExceptions: true
  });
  if (!response.getResponseCode() == 200) {
    throw 'Error converting to HTML: ' + response.getContentText();
  }
  return response.getContentText();
}

作为 fileId 传递，谷歌文档的 id 并按照说明here 启用高级驱动器服务。

Answer 7

我也遇到过这个问题。 Document HTML Export 吐出的 HTML 真的很难看，所以这是我的解决方案：

/**
 * 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;

}

https://gist.github.com/xd1936/cc229d14a89e6327336177bb07ac2980

Answer 8

也许这对你有用...

function doGet() {
  var blob = DriveApp.getFileById('myFileId').getAsHTML();
  return HtmlService.createHtmlOutput(blob);
}