Home » Blogs » hubdog's blog

dart中html转换为文本的输出

Submitted by hubdog on Tue, 2019-04-23 23:36

dart里面没有现成的html转为text的功能,jsoup有现成的功能,可是无法移植到ios上,而且比较重,实在不值得折腾,基于dart的html库,手撸了一个html转换为text的处理

  1. class PlaintextVisitor extends TreeVisitor {
  2.   final StringBuffer _str;
  3.  
  4.   PlaintextVisitor() : _str = StringBuffer();
  5.  
  6.   String toString() => _str.toString();
  7.  
  8.   visitDocument(dom.Document node) {
  9.     visitChildren(node);
  10.   }
  11.  
  12.   visitDocumentType(dom.DocumentType node) {
  13.     visitChildren(node);
  14.   }
  15.  
  16.   visitText(dom.Text node) {
  17.     if (node.text=="\n")
  18.       return;
  19.     writeTextNodeAsHtml(_str, node);
  20.   }
  21.  
  22.   visitElement(dom.Element node) {
  23.     final tag = node.localName;
  24.     if (tag=="li")
  25.       _str.write("\n * ");
  26.     else if (tag=="dt")
  27.       _str.write("  ");
  28.     else if (tag=="p" || tag== "h1" || tag== "h2" || tag=="h3" || tag== "h4" || tag== "h5" || tag=="tr")
  29.       _str.write("\n");
  30.     if (node.nodes.isNotEmpty) {
  31.       visitChildren(node);
  32.     } else if (isVoidElement(tag)) {
  33.       return;
  34.     }
  35.     if (tag=="br" || tag== "dd" || tag=="dt" || tag== "p" || tag== "h1" || tag== "h2" || tag== "h3" || tag== "h4" || tag== "h5")
  36.       _str.write("\n");
  37.   }
  38.  
  39. }
  40. 用法
  41. import 'package:html/parser.dart' show parse;
  42. import 'package:html/dom.dart' as dom;
  43. import 'package:html/dom_parsing.dart';
  44.  
  45.       var document = parse(
  46.           htmlString);
  47.       plaintext=(PlaintextVisitor()..visit(document)).toString();

»