91av视频/亚洲h视频/操亚洲美女/外国一级黄色毛片 - 国产三级三级三级三级

  • 大小: 4KB
    文件類型: .zip
    金幣: 2
    下載: 0 次
    發布日期: 2021-05-09
  • 語言: 其他
  • 標簽: 爬取??

資源簡介

爬取商品詳情。

資源截圖

代碼片段和文件信息

import?org.apache.commons.lang3.StringUtils;
import?net.sf.json.JSONobject;


import?org.jsoup.Jsoup;
import?org.jsoup.nodes.Document;
import?org.jsoup.nodes.Element;
import?org.jsoup.select.Elements;

import?java.io.IOException;
import?java.net.URLEncoder;
import?java.util.*;
import?java.util.regex.Matcher;
import?java.util.regex.Pattern;

/**
?*?Created?with?Chenquan.
?*?Description:?淘寶抓包
?*?Date:?2018-12-13
?*?Time:?15:12
?*/
public?class?test?{

????public?static?void?main(String[]?args)?{
????????int?i?=?0;
????????//填寫商品詳情網站
????????String?substring?=?getParamByUrl(“https://detail.tmall.com/item.htm?spm=a1z10.10550-b.193.11.43c44d028KCTcr&id=580863947060““id“);
????????????getAll(substring);
????}

????public?static?void?getAll(String?item_id?)?{
????????try?{
????????????Thread.sleep(2000);//一個休息5s,太快會被禁
????????}?catch?(InterruptedException?e)?{
????????????e.printStackTrace();
????????}
????????System.out.println(“開始時間:“?+?new?Date());
????????Date?dateStart?=?new?Date();
????????Document?doc?=?null;
????????String?id?=?““;
????????try?{
????????????String?url?=?“https://item.taobao.com/item.htm?id=“+item_id;
????????????id?=?getParamByUrl(url?“id“);
????????????doc?=?Jsoup.connect(url).ignoreContentType(true).get();
????????}?catch?(IOException?e)?{
????????????e.printStackTrace();
????????}
????????if?(doc.baseUri().contains(“tmall“))?{
????????????System.out.println(“商品名稱:“+?doc.select(“h1[data-spm=\“1000983\“]“).text());
????????}else?{
????????????System.out.println(“商品名稱:“?+?doc.select(“h3[class=\“tb-main-title\“]“).text());
????????}
????????Elements?imgSrcElement?=?doc.select(“#J_UlThumb?>?li“);
????????for?(Element?element?:?imgSrcElement)?{
????????????String?imgSrc?=?““;
????????????if?(element.baseUri().contains(“tmall“)){
????????????????imgSrc?=?element.getElementsByTag(“img“).attr(“src“);
????????????}else{
????????????????imgSrc?=?element.getElementsByTag(“img“).attr(“data-src“);
????????????}
??????????//??imgSrc?=?imgSrc.replaceFirst(“//img.alicdn.com/imgextra/“?““);
????????????//imgSrc?=?imgSrc.substring(0?imgSrc.length()?-?10);
????????????imgSrc?=?imgSrc.replaceAll(“_60x60q90.jpg“““);?//處理掉不必要的數據
????????????//String?substring?=?imgSrc.substring(imgSrc.indexOf(“_60“)?+?3?imgSrc.lastIndexOf(“.jpg“));
????????????//String?substring?=?imgSrc.substring(0?imgSrc.lastIndexOf(“.jpg“));
????????????//String?substring?=?imgSrc.substring(0?imgSrc.lastIndexOf(“jpg_“));
????????????System.out.println(“主圖url:“?+?imgSrc);

????????}


????????//?規格參數
????????Elements?selectRules?=?doc.select(“.J_TSaleProp“);
????????List>?liHashMap?=?new?ArrayList<>();
????????for?(Element?ulElement?:?selectRules)?{
????????????String?ul?=?ulElement.getElementsByTag(“ul“).attr(“data-property“);
????????????System.out.println(“ul:“?+?ul);

????????????List?liString?=?new?ArrayList<>();

????????????for?(Element?liElement?:?ulElement.getElem

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件???????14383??2019-01-14?09:19??淘寶天貓商品詳情獲取\test.java
?????文件????????2254??2019-01-11?14:48??淘寶天貓商品詳情獲取\test1.java
?????目錄???????????0??2019-01-14?09:20??淘寶天貓商品詳情獲取\

評論

共有 條評論