Question

我正在尝试使用javascript解析srt文件。我从stackoverflow找到了一些代码，但是有一个问题。我正在逐行解析srt文件，以识别字幕，时间和字幕文本的行。但是，当代码读取字幕文本时，我的代码仅能读取一行字幕的每一行，而部分字幕包含两行或两行。

这是我的代码

var PF_SRT = function() {
                  //SRT format
                  var pattern = /(\d+)\n([\d:,]+)\s+-{2}\>\s+([\d:,]+)\n([\s\S]*?(?=\n{2}|$))/gm;
                  var _regExp;

                  var init = function() {
                    _regExp = new RegExp(pattern);
                  };
                  var parse = function(f) {
                    if (typeof(f) != "string")
                      throw "Sorry, Parser accept string only.";

                    var result = [];
                    if (f == null)
                      return _subtitles;


                    f = f.replace(/\r\n|\r|\n/g, '\n')


                    while ((matches = pattern.exec(f)) != null) {
                      result.push(toLineObj(matches));
                    }

                    return result;
                  }
                  var toLineObj = function(group) {
                    var hms_start = group[2].replace(',', ':').split(':');   

                    var hms_end = group[3].replace(',', ':').split(':');   

                    return {
                      line: group[1],
                      startTime: (+hms_start[0]) * 60 * 60 + (+hms_start[1]) * 60 + (+hms_start[2]) +'.'+ hms_start[3],
                      endTime: (+hms_end[0]) * 60 * 60 + (+hms_end[1]) * 60 + (+hms_end[2]) +'.'+ hms_end[3],
                      text: group[4]
                    };
                  }
                  init();
                  return {
                    parse: parse
                  }
                }();

// execution
// result is the entire line of srt subtitle file
PF_SRT.parse(result);

我希望

的输出

6
00:00:32,616 --> 00:00:41,496
{\a2}{\c&HFFFFFF&}{\fnTahoma} And 23 of them say forget it
you say this thing never worked 
because there's no such thing called internet in the world

到

6
00:00:32,616 --> 00:00:41,496
{\a2}{\c&HFFFFFF&}{\fnTahoma} And 23 of them say forget it<br>you say this thing never worked<br>because there's no such thing called internet in the world

Answer 1

在此行中，您会找到常见的换行字符，并用\n换行替换它们。

f = f.replace(/\r\n|\r|\n/g, '\n')

您需要对其进行修改，以用新的换行符替换HTML换行符<br>。

例如：

f = f.replace(/\r\n|\r|\n|<br>/g, '\n')

将srt文件解析为javascript数组时将/ n解析为<br/>的问题

1 个答案: