提取新闻正文

public static String extractContent(String url) {
Document document = JsoupUitl.readUrl(url);
String orderHtml = document.toString().toLowerCase();
orderHtml = orderHtml.replaceAll("(?is)<!DOCTYPE.*?>", "");
orderHtml = orderHtml.replaceAll("(?is)<!--.*?-->", ""); // remove html
orderHtml = orderHtml.replaceAll("(?is)<script.*?>.*?</script>", ""); // remove
orderHtml = orderHtml.replaceAll("(?is)<style.*?>.*?</style>", ""); // remove
orderHtml = orderHtml.replaceAll("(?is)<a.*?>.*?</a>", ""); // remove
orderHtml = orderHtml.replaceAll("&.{2,5};|&#.{2,5};", "");
orderHtml = orderHtml.replaceAll("<(?!\\/?(td|tr|img|br|p)).*?>", "");
String[] eleList = orderHtml.split("\n");
StringBuffer sb = new StringBuffer();
for (String string : eleList) {
if (string.trim().length() > 20) {
if (string.contains("></p>")) {
} else {
sb.append(string);
}
}
}

orderHtml = sb.toString();
// System.out.println("=====================================");
// System.out.println(Jsoup.parse(orderHtml));
return orderHtml;

}