在javascript中获取gmail邮件正文时删除html格式 [英] Remove html formatting when getting Body of a gmail message in javascript
问题描述
我想删除我的google apps脚本中的html格式。我目前正在搜索电子邮件并将结果打印到谷歌电子表格。我想知道是否有方法来替换text.I知道正则表达式,但我不认为它适用于getBody函数。
我真的很感激一些反馈或在这个问题上的一些帮助。
代码:
function Search(){
var sheet = SpreadsheetApp.getActiveSheet();
var row = 2;
//清除现有搜索结果
sheet.getRange(2,1,sheet.getMaxRows() - 1,4).clearContent();
//应该搜索哪个Gmail标签?
var label = sheet.getRange(F3)。getValue();
//获取正则表达式搜索模式
var pattern = sheet.getRange(F4)。getValue();
//检索指定标签的所有线程
var threads = GmailApp.search(in:+ label);
for(var i = 0; i< threads.length; i ++){
var messages = threads [i] .getMessages();
for(var m = 0; m var msg = messages [m] .getBody();
//邮件内容是否与搜索模式匹配?
if(msg.search(pattern)!== -1){
//打印邮件主题
sheet.getRange(row,3)。的setValue(消息[M] .getBody());
替换为:
//打印邮件主题
sheet.getRange(row,3).setValue(messages [m] .getBody());
有了这个:
//打印邮件主题
sheet.getRange(row,3).setValue(getTextFromHtml(messages [m] .getBody()));
p>
function getTextFromHtml(html){
return getTextFromNode(Xml.parse(html,true).getElement());
}
var _itemNum; //用于领导无序&有序列表项。
函数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 ='\\\
';
休息;
case'ul':
pre ='';
post ='\\\
';
itemNum = 0;
休息;
案例'ol':
pre ='';
post ='\\\
';
_itemNum = 1;
休息;
case'li':
pre ='\\\
'+(_itemNum == 0?' - ':(''+ _itemNum ++ +'。'));
post ='';
休息;
默认值:
pre ='';
post ='';
休息;
}
返回pre + x.getNodes()。map(getTextFromNode).join('')+ post;
default:return'';
}
}
I would like to remove the html formatting in my google apps script. I am currently searching the email and printing the results to a google spreadsheet. I would like to know if there is a way to replace text.I am aware of regex but I dont think it works with the getBody function.
I would really appreciate some feedback or some help on this matter.
Code:
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());
Replace this:
// Print the message subject
sheet.getRange(row,3).setValue(messages[m].getBody());
With this:
// Print the message subject
sheet.getRange(row,3).setValue(getTextFromHtml(messages[m].getBody()));
The getTextFromHtml()
function has been adapted from this answer, with the addition of handling for some basic formatting (numbered & bullet lists, paragraph breaks).
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 '';
}
}
这篇关于在javascript中获取gmail邮件正文时删除html格式的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!