编程语言
首页 > 编程语言> > 在JavaScript中获取Gmail邮件正文时,删除HTML格式

在JavaScript中获取Gmail邮件正文时,删除HTML格式

作者:互联网

我想在我的Google Apps脚本中删除html格式.我目前正在搜索电子邮件并将结果打印到Google电子表格中.我想知道是否有替换文本的方法.我知道正则表达式,但我认为它不能与getBody函数一起使用.

在此问题上,我将非常感谢您的反馈或帮助.

码:

function Search() {

var sheet   = SpreadsheetApp.getActiveSheet();
var row     = 2;

// Clear existing search results
sheet.getRange(2, 1, sheet.getMaxRows() - 1, 4).clearContent();

// Which Gmail Label should be searched?
var label   = sheet.getRange("F3").getValue();

// Get the Regular Expression Search Pattern
var pattern = sheet.getRange("F4").getValue();

// Retrieve all threads of the specified label
var threads = GmailApp.search("in:" + label);

for (var i = 0; i < threads.length; i++) {

var messages = threads[i].getMessages();

for (var m = 0; m < messages.length; m++) {
 var msg = messages[m].getBody();

// Does the message content match the search pattern?
if (msg.search(pattern) !== -1) {


 // Print the message subject
 sheet.getRange(row,3).setValue(messages[m].getBody());

解决方法:

替换为:

// Print the message subject
sheet.getRange(row,3).setValue(messages[m].getBody());

有了这个:

// Print the message subject
sheet.getRange(row,3).setValue(getTextFromHtml(messages[m].getBody()));

getTextFromHtml()函数已从this answer开始改编,并增加了一些基本格式的处理(编号和项目符号列表,段落分隔符).

function getTextFromHtml(html) {
  return getTextFromNode(Xml.parse(html, true).getElement());
}

var _itemNum; // Used to lead unordered & ordered list items.

function getTextFromNode(x) {
  switch(x.toString()) {
    case 'XmlText': return x.toXmlString();
    case 'XmlElement':
      var name = x.getName().getLocalName();
      Logger.log(name);
      var pre = '';
      var post = '';
      switch (name) {
        case 'br':
        case 'p':
          pre = '';
          post = '\n';
          break;
        case 'ul':
          pre = '';
          post = '\n';
          itemNum = 0;
          break;
        case 'ol':
          pre = '';
          post = '\n';
          _itemNum = 1;
          break;
        case 'li':
          pre = '\n' + (_itemNum == 0 ? ' - ' : (' '+ _itemNum++ +'. '));
          post = '';
          break;
        default:
          pre = '';
          post = '';
          break;
      }
      return pre + x.getNodes().map(getTextFromNode).join('') + post;
    default: return '';
  }
}

标签:gmail,google-apps-script,javascript
来源: https://codeday.me/bug/20191031/1974247.html