本文實例講述了JAVA過濾標(biāo)簽實現(xiàn)將html內(nèi)容轉(zhuǎn)換為文本的方法。分享給大家供大家參考，具體如下：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
|
/*** 把html內(nèi)容轉(zhuǎn)為文本* @param html 需要處理的html文本* @param filterTags 需要保留的html標(biāo)簽樣式* @return*/public static String trimHtml2Txt(String html, String[] filterTags){ html = html.replaceAll("\\<head>[\\s\\S]*?</head>(?i)", "");//去掉head html = html.replaceAll("\\<!--[\\s\\S]*?-->", "");//去掉注釋 html = html.replaceAll("\\<![\\s\\S]*?>", ""); html = html.replaceAll("\\<style[^>]*>[\\s\\S]*?</style>(?i)", "");//去掉樣式 html = html.replaceAll("\\<script[^>]*>[\\s\\S]*?</script>(?i)", "");//去掉js html = html.replaceAll("\\<w:[^>]+>[\\s\\S]*?</w:[^>]+>(?i)", "");//去掉word標(biāo)簽 html = html.replaceAll("\\<xml>[\\s\\S]*?</xml>(?i)", ""); html = html.replaceAll("\\<html[^>]*>|<body[^>]*>|</html>|</body>(?i)", ""); html = html.replaceAll("\\\r\n|\n|\r", " ");//去掉換行 html = html.replaceAll("\\<br[^>]*>(?i)", "\n\r"); List<String> tags = new ArrayList<String>(); List<String> s_tags = new ArrayList<String>(); List<String> halfTag = Arrays.asList(new String[]{"img","table","thead","th","tr","td"});// if(filterTags != null && filterTags.length > 0){ for (String tag : filterTags) { tags.add("<"+tag+(halfTag.contains(tag)?"":">"));//開始標(biāo)簽 if(!"img".equals(tag)) tags.add("</"+tag+">");//結(jié)束標(biāo)簽 s_tags.add("#REPLACETAG"+tag+(halfTag.contains(tag)?"":"REPLACETAG#"));//盡量替換為復(fù)雜一點的標(biāo)記,以免與顯示文本混合,如：文本中包含#td、#table等 if(!"img".equals(tag)) s_tags.add("#REPLACETAG/"+tag+"REPLACETAG#"); } } html = StringUtils.replaceEach(html, tags.toArray(new String[tags.size()]), s_tags.toArray(new String[s_tags.size()])); html = html.replaceAll("\\</p>(?i)", "\n\r"); html = html.replaceAll("\\<[^>]+>", ""); html = StringUtils.replaceEach(html,s_tags.toArray(new String[s_tags.size()]),tags.toArray(new String[tags.size()])); html = html.replaceAll("\\ ", " "); return html.trim();} |
希望本文所述對大家java程序設(shè)計有所幫助。
