首页 > 代码库 > 提取新闻下一页
提取新闻下一页
package com.unbank.robotspider.util;import java.util.HashMap;import java.util.Map;import org.jsoup.nodes.Document;import org.jsoup.nodes.Element;import org.jsoup.select.Elements;public class SmartNextPageFecther { public static void main(String[] args) { String url = "http://focus.stockstar.com/SS2014061700001351.shtml"; Document document = JsoupUtil.readUrl(url); Map<Integer, String> pageList = new SmartNextPageFecther() .getNextPageUrl(document, url); for (int i = 0; i < pageList.size() + 3; i++) { String nextUrl = pageList.get(i); if (nextUrl != null) { System.out.println(nextUrl); } } } public Map<Integer, String> getNextPageUrl(Document doc, String baseurl) { Document document = doc.clone(); Map<Integer, String> map = new HashMap<Integer, String>(); Elements a_elements = document.getElementsByTag("a"); int prePageNum = 5; int pageNum = 0; for (Element e : a_elements) { String uu = e.attr("href"); uu = UrlTools.getFullUrl(baseurl, uu); if (uu == null || uu.trim().isEmpty()) { continue; } String a_text = e.text(); // 是否是下一页的 boolean bl = checkText(a_text); if (bl) { int cu = checkUrl(baseurl, uu); if (cu != -1) { pageNum = pageNum > cu ? pageNum : cu; prePageNum = prePageNum < cu ? prePageNum : cu; map.put(cu, uu); } } } if (map.size() >= 2) { // 说明是3页了 String second = null; String third = null; if (prePageNum == 0) { second = map.get(0); third = map.get(1); } else if (prePageNum == 1) { second = map.get(1); third = map.get(2); } else if (prePageNum == 2) { second = map.get(2); third = map.get(3); } String urlRule = UrlRuleUtil.getURlRule(second, third); for (int i = prePageNum; i <= pageNum; i++) { if (map.get(i) == null) { String page = UrlRuleUtil.getcheckURL(urlRule, i); map.put(i, page); } } } return map; } public boolean checkText(String text) { String[] texts = { "首页", "第一页", "下一页", "末页", "最后一页", "尾页" }; for (int i = 0; i < texts.length; i++) { if (texts[i].equals(text)) { return true; } } if (text.matches("\\d{1,2}")) { return true; } return false; } public int checkUrl(String url1, String url2) { int l1 = url1.length(); int l2 = url2.length(); if (l1 == 0 || l2 == 0) { return -1; } String longStr = l1 > l2 ? url1 : url2; String shortStr = l1 < l2 ? url1 : url2; int j = 0; StringBuffer sb = new StringBuffer(); for (int i = 0; i < longStr.length() - 1; i++) { if (longStr.charAt(i) != shortStr.charAt(j)) { sb.append(longStr.charAt(i)); } else { j++; if (j == shortStr.length()) { break; } } } if (sb.length() == 0) { return -1; } String variances = sb.toString(); String numStr = variances.replaceAll("_", "").replaceAll("=", "") .replaceAll("index", "").replaceAll("page", "") .replaceAll("p", "").replaceAll("-", ""); if (numStr.matches("\\d{1,2}")) { return Integer.valueOf(numStr); } else { return -1; } }}
声明:以上内容来自用户投稿及互联网公开渠道收集整理发布,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任,若内容有误或涉及侵权可进行投诉: 投诉/举报 工作人员会在5个工作日内联系你,一经查实,本站将立刻删除涉嫌侵权内容。