溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
java spring+mybatis整合如何實現今日頭條搞笑動態圖片的爬取，相信很多沒有經驗的人對此束手無策，為此本文總結了問題出現的原因和解決方法，通過這篇文章希望你能解決這個問題。
抓取的動態圖：
數據庫：
一.此爬蟲介紹今日頭條本身就是做爬蟲的，爬取各大網站的圖片文字信息，再自己整合后推送給用戶，特別是里面的動態圖片，很有意思。在網上搜了搜，大多都是用Python來寫的，本人是學習javaweb這塊的，對正則表達式也不是很熟悉，就想著能不能換個我熟悉的方式來寫。此爬蟲使用spring+mybatis框架整合實現，使用mysql數據庫保存爬取的數據，用jsoup來操作HTML的標簽節點（完美避開正則表達式），獲取文章中動態圖片的鏈接，通過響應頭中“Content-Type”的值來判斷圖片的格式，再將圖片保存在本地。當然也可以爬取里面的文字，比如一些搞笑的黃段子，在此基礎上稍加改動就可以實現，此爬蟲只是提供一個入門的思路，更多好玩的爬蟲玩法還待大家去開發，哈哈。
核心語言：java；
核心框架：spring；
持久層框架：mybatis；
數據庫連接池：Alibaba Drui；
日志管理：Log4j；
jar包管理：maven； 。。。。
打開頭條首頁，找到點擊搞笑模塊，點擊F12,下滾后加載下一頁，發現是通過ajax請求api來獲取的數據，如下圖：
這是響應的json數據，里面的參數和值顧名思義大家都懂得。
是ajax訪問就好解決了，通過我百度谷歌各種研究后發現，ajax請求的前三個參數是不變的，改變category參數是請求不同的模塊，本列子是請求的搞笑模塊所以值為funny，max_behot_time和max_behot_time_tmp這兩個參數值是時間戳，首次請求是0，之后的值是響應json數據里面的next中的值。as和cp值是通過一段js生成的，其實就是一個加密了的時間戳而已。js代碼后面會貼。
項目搭建后之后為下圖所示的文件結構，不懂得自行谷歌 哈哈
不多說直接上核心代碼了：
public class TouTiaoCrawler {
// 搞笑板塊的api地址
public static final String FUNNY = "http://www.toutiao.com/api/pc/feed/?utm_source=toutiao&widen=1";
// 頭條首頁地址
public static final String TOUTIAO = "http://www.toutiao.com";
// 使用"spring.xml"和"spring-mybatis.xml"這兩個配置文件創建Spring上下文
static ApplicationContext ac = new ClassPathXmlApplicationContext(
"spring-mybatis.xml");
// 從Spring容器中根據bean的id取出我們要使用的funnyMapper對象
static FunnyMapper funnyMapper = (FunnyMapper) ac.getBean("funnyMapper");
// 接口訪問次數
private static int refreshCount = 0;
// 時間戳
private static long time = 0;
public static void main(String[] args) {
System.out.println("----------開始干活！-----------------");
while (true) {
crawler(time);
}
}
public static void crawler(long hottime) {// 傳入時間戳，會獲取這個時間戳的內容
refreshCount++;
System.out.println("----------第" + refreshCount + "次刷新------返回的請求時間為："
+ hottime + "----------");
String url = FUNNY + "&max_behot_time=" + hottime
+ "&max_behot_time_tmp=" + hottime;
JSONObject param = getUrlParam(); // 獲取用js代碼得到的as和cp的值
// 定義接口訪問的模塊
/*
* __all__ : 推薦 news_hot: 熱點 funny：搞笑
*/
String module = "funny";
url += "&as=" + param.get("as") + "&cp=" + param.get("cp")
+ "&category=" + module;
JSONObject json = null;
try {
json = getReturnJson(url);// 獲取json串
} catch (Exception e) {
e.printStackTrace();
}
if (json != null) {
time = json.getJSONObject("next").getLongValue("max_behot_time");
JSONArray data = json.getJSONArray("data");
for (int i = 0; i < data.size(); i++) {
try {
JSONObject obj = (JSONObject) data.get(i);
// 判斷這條文章是否已經爬過
if (funnyMapper.selectByGroupId((String) obj
.get("group_id")) != null) {
System.out
.println("----------此文章已經爬過啦！-----------------");
continue;
}
// 訪問頁面返回document對象
String url1 = TOUTIAO + "/a" + obj.getString("group_id");
Document document = getArticleInfo(url1);
System.out.println("----------成功訪問了文章：" + url1
+ "-----------------");
// 將document也存入
obj.put("document", document.toString());
// 將json對象轉換成java Entity對象
Funny funny = JSON.parseObject(obj.toString(), Funny.class);
// json入庫
funny.setBehotTime(new Date());
funnyMapper.insertSelective(funny);
} catch (Exception e) {
e.printStackTrace();
}
}
} else {
System.out.println("----------返回的json列表為空----------");
}
}
// 訪問接口，返回json封裝的數據格式
public static JSONObject getReturnJson(String url) {
try {
URL httpUrl = new URL(url);
BufferedReader in = new BufferedReader(new InputStreamReader(
httpUrl.openStream(), "UTF-8"));
String line = null;
String content = "";
while ((line = in.readLine()) != null) {
content += line;
}
in.close();
return JSONObject.parseObject(content);
} catch (Exception e) {
System.err.println("訪問失敗:" + url);
e.printStackTrace();
}
return null;
}
// 獲取網站的document對象
public static Document getArticleInfo(String url) {
try {
Connection connect = Jsoup.connect(url);
Document document;
document = connect.get();
Elements article = document.getElementsByClass("article-content");
if (article.size() > 0) {
Elements a = article.get(0).getElementsByTag("img");
if (a.size() > 0) {
for (Element e : a) {
String url2 = e.attr("src");
// 下載img標簽里面的圖片到本地
saveToFile(url2);
}
}
}
return document;
} catch (IOException e) {
System.err.println("訪問文章頁失敗:" + url + " 原因" + e.getMessage());
return null;
}
}
// 執行js獲取as和cp參數值
public static JSONObject getUrlParam() {
JSONObject jsonObject = null;
FileReader reader = null;
try {
ScriptEngineManager manager = new ScriptEngineManager();
ScriptEngine engine = manager.getEngineByName("javascript");
String jsFileName = "toutiao.js"; // 讀取js文件
reader = new FileReader(jsFileName); // 執行指定腳本
engine.eval(reader);
if (engine instanceof Invocable) {
Invocable invoke = (Invocable) engine;
Object obj = invoke.invokeFunction("getParam");
jsonObject = JSONObject.parseObject(obj != null ? obj
.toString() : null);
}
} catch (Exception e) {
e.printStackTrace();
} finally {
try {
if (reader != null) {
reader.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return jsonObject;
}
// 通過url獲取圖片并保存在本地
public static void saveToFile(String destUrl) {
FileOutputStream fos = null;
BufferedInputStream bis = null;
HttpURLConnection httpUrl = null;
URL url = null;
String uuid = UUID.randomUUID().toString();
String fileAddress = "d:\\imag/" + uuid;// 存儲本地文件地址
int BUFFER_SIZE = 1024;
byte[] buf = new byte[BUFFER_SIZE];
int size = 0;
try {
url = new URL(destUrl);
httpUrl = (HttpURLConnection) url.openConnection();
httpUrl.connect();
String Type = httpUrl.getHeaderField("Content-Type");
if (Type.equals("image/gif")) {
fileAddress += ".gif";
} else if (Type.equals("image/png")) {
fileAddress += ".png";
} else if (Type.equals("image/jpeg")) {
fileAddress += ".jpg";
} else {
System.err.println("未知圖片格式");
return;
}
bis = new BufferedInputStream(httpUrl.getInputStream());
fos = new FileOutputStream(fileAddress);
while ((size = bis.read(buf)) != -1) {
fos.write(buf, 0, size);
}
fos.flush();
System.out.println("圖片保存成功！地址：" + fileAddress);
} catch (IOException e) {
e.printStackTrace();
} catch (ClassCastException e) {
e.printStackTrace();
} finally {
try {
fos.close();
bis.close();
httpUrl.disconnect();
} catch (IOException e) {
e.printStackTrace();
} catch (NullPointerException e) {
e.printStackTrace();
}
}
}
}獲取as和cp參數的js代碼
function getParam(){
var asas;
var cpcp;
var t = Math.floor((new Date).getTime() / 1e3)
, e = t.toString(16).toUpperCase()
, i = md5(t).toString().toUpperCase();
if (8 != e.length){
asas = "479BB4B7254C150";
cpcp = "7E0AC8874BB0985";
}else{
for (var n = i.slice(0, 5), o = i.slice(-5), a = "", s = 0; 5 > s; s++){
a += n[s] + e[s];
}
for (var r = "", c = 0; 5 > c; c++){
r += e[c + 3] + o[c];
}
asas = "A1" + a + e.slice(-3);
cpcp= e.slice(0, 3) + r + "E1";
}
return '{"as":"'+asas+'","cp":"'+cpcp+'"}';
}
!function(e) {
"use strict";
function t(e, t) {
var n = (65535 & e) + (65535 & t)
, r = (e >> 16) + (t >> 16) + (n >> 16);
return r << 16 | 65535 & n
}
function n(e, t) {
return e << t | e >>> 32 - t
}
function r(e, r, o, i, a, u) {
return t(n(t(t(r, e), t(i, u)), a), o)
}
function o(e, t, n, o, i, a, u) {
return r(t & n | ~t & o, e, t, i, a, u)
}
function i(e, t, n, o, i, a, u) {
return r(t & o | n & ~o, e, t, i, a, u)
}
function a(e, t, n, o, i, a, u) {
return r(t ^ n ^ o, e, t, i, a, u)
}
function u(e, t, n, o, i, a, u) {
return r(n ^ (t | ~o), e, t, i, a, u)
}
function s(e, n) {
e[n >> 5] |= 128 << n % 32,
e[(n + 64 >>> 9 << 4) + 14] = n;
var r, s, c, l, f, p = 1732584193, d = -271733879, h = -1732584194, m = 271733878;
for (r = 0; r < e.length; r += 16)
s = p,
c = d,
l = h,
f = m,
p = o(p, d, h, m, e[r], 7, -680876936),
m = o(m, p, d, h, e[r + 1], 12, -389564586),
h = o(h, m, p, d, e[r + 2], 17, 606105819),
d = o(d, h, m, p, e[r + 3], 22, -1044525330),
p = o(p, d, h, m, e[r + 4], 7, -176418897),
m = o(m, p, d, h, e[r + 5], 12, 1200080426),
h = o(h, m, p, d, e[r + 6], 17, -1473231341),
d = o(d, h, m, p, e[r + 7], 22, -45705983),
p = o(p, d, h, m, e[r + 8], 7, 1770035416),
m = o(m, p, d, h, e[r + 9], 12, -1958414417),
h = o(h, m, p, d, e[r + 10], 17, -42063),
d = o(d, h, m, p, e[r + 11], 22, -1990404162),
p = o(p, d, h, m, e[r + 12], 7, 1804603682),
m = o(m, p, d, h, e[r + 13], 12, -40341101),
h = o(h, m, p, d, e[r + 14], 17, -1502002290),
d = o(d, h, m, p, e[r + 15], 22, 1236535329),
p = i(p, d, h, m, e[r + 1], 5, -165796510),
m = i(m, p, d, h, e[r + 6], 9, -1069501632),
h = i(h, m, p, d, e[r + 11], 14, 643717713),
d = i(d, h, m, p, e[r], 20, -373897302),
p = i(p, d, h, m, e[r + 5], 5, -701558691),
m = i(m, p, d, h, e[r + 10], 9, 38016083),
h = i(h, m, p, d, e[r + 15], 14, -660478335),
d = i(d, h, m, p, e[r + 4], 20, -405537848),
p = i(p, d, h, m, e[r + 9], 5, 568446438),
m = i(m, p, d, h, e[r + 14], 9, -1019803690),
h = i(h, m, p, d, e[r + 3], 14, -187363961),
d = i(d, h, m, p, e[r + 8], 20, 1163531501),
p = i(p, d, h, m, e[r + 13], 5, -1444681467),
m = i(m, p, d, h, e[r + 2], 9, -51403784),
h = i(h, m, p, d, e[r + 7], 14, 1735328473),
d = i(d, h, m, p, e[r + 12], 20, -1926607734),
p = a(p, d, h, m, e[r + 5], 4, -378558),
m = a(m, p, d, h, e[r + 8], 11, -2022574463),
h = a(h, m, p, d, e[r + 11], 16, 1839030562),
d = a(d, h, m, p, e[r + 14], 23, -35309556),
p = a(p, d, h, m, e[r + 1], 4, -1530992060),
m = a(m, p, d, h, e[r + 4], 11, 1272893353),
h = a(h, m, p, d, e[r + 7], 16, -155497632),
d = a(d, h, m, p, e[r + 10], 23, -1094730640),
p = a(p, d, h, m, e[r + 13], 4, 681279174),
m = a(m, p, d, h, e[r], 11, -358537222),
h = a(h, m, p, d, e[r + 3], 16, -722521979),
d = a(d, h, m, p, e[r + 6], 23, 76029189),
p = a(p, d, h, m, e[r + 9], 4, -640364487),
m = a(m, p, d, h, e[r + 12], 11, -421815835),
h = a(h, m, p, d, e[r + 15], 16, 530742520),
d = a(d, h, m, p, e[r + 2], 23, -995338651),
p = u(p, d, h, m, e[r], 6, -198630844),
m = u(m, p, d, h, e[r + 7], 10, 1126891415),
h = u(h, m, p, d, e[r + 14], 15, -1416354905),
d = u(d, h, m, p, e[r + 5], 21, -57434055),
p = u(p, d, h, m, e[r + 12], 6, 1700485571),
m = u(m, p, d, h, e[r + 3], 10, -1894986606),
h = u(h, m, p, d, e[r + 10], 15, -1051523),
d = u(d, h, m, p, e[r + 1], 21, -2054922799),
p = u(p, d, h, m, e[r + 8], 6, 1873313359),
m = u(m, p, d, h, e[r + 15], 10, -30611744),
h = u(h, m, p, d, e[r + 6], 15, -1560198380),
d = u(d, h, m, p, e[r + 13], 21, 1309151649),
p = u(p, d, h, m, e[r + 4], 6, -145523070),
m = u(m, p, d, h, e[r + 11], 10, -1120210379),
h = u(h, m, p, d, e[r + 2], 15, 718787259),
d = u(d, h, m, p, e[r + 9], 21, -343485551),
p = t(p, s),
d = t(d, c),
h = t(h, l),
m = t(m, f);
return [p, d, h, m]
}
function c(e) {
var t, n = "";
for (t = 0; t < 32 * e.length; t += 8)
n += String.fromCharCode(e[t >> 5] >>> t % 32 & 255);
return n
}
function l(e) {
var t, n = [];
for (n[(e.length >> 2) - 1] = void 0,
t = 0; t < n.length; t += 1)
n[t] = 0;
for (t = 0; t < 8 * e.length; t += 8)
n[t >> 5] |= (255 & e.charCodeAt(t / 8)) << t % 32;
return n
}
function f(e) {
return c(s(l(e), 8 * e.length))
}
function p(e, t) {
var n, r, o = l(e), i = [], a = [];
for (i[15] = a[15] = void 0,
o.length > 16 && (o = s(o, 8 * e.length)),
n = 0; 16 > n; n += 1)
i[n] = 909522486 ^ o[n],
a[n] = 1549556828 ^ o[n];
return r = s(i.concat(l(t)), 512 + 8 * t.length),
c(s(a.concat(r), 640))
}
function d(e) {
var t, n, r = "0123456789abcdef", o = "";
for (n = 0; n < e.length; n += 1)
t = e.charCodeAt(n),
o += r.charAt(t >>> 4 & 15) + r.charAt(15 & t);
return o
}
function h(e) {
return unescape(encodeURIComponent(e))
}
function m(e) {
return f(h(e))
}
function g(e) {
return d(m(e))
}
function v(e, t) {
return p(h(e), h(t))
}
function y(e, t) {
return d(v(e, t))
}
function b(e, t, n) {
return t ? n ? v(t, e) : y(t, e) : n ? m(e) : g(e)
}
"function" == typeof define && define.amd ? define("static/js/lib/md5", ["require"], function() {
return b
}) : "object" == typeof module && module.exports ? module.exports = b : e.md5 = b
}(this)我還發現了頭條有個簡約版，研究后發現這個簡約版應該更好爬一些。
訪問的格式是p+頁碼，直接讀取每頁里面的鏈接，就可以進行爬取了，就不再通過json串來獲取文章地址，也不需要傳什么限制參數，在本項目上稍加改動就可以了
看完上述內容，你們掌握java spring+mybatis整合如何實現今日頭條搞笑動態圖片的爬取的方法了嗎？如果還想學到更多技能或想了解更多相關內容，歡迎關注億速云行業資訊頻道，感謝各位的閱讀！
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
