匯入HttpClient需要的jar包

<dependency>
    <groupId>org.apache.httpcomponents</groupId>
    <artifactId>httpclient</artifactId>
    <version>4.5.12</version>
</dependency>

匯入Jsoup需要的jar包

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.13.1</version>
</dependency>

一、HttpClient 入門

常用的39個用戶代理：點我查看

public void doGetTestOne() throws IOException{

        // 獲得Http客戶端
        CloseableHttpClient httpClient = HttpClientBuilder.create().build();
        // 創建Get請求
        HttpGet httpGet = new HttpGet("http://www.grfy.net/index.htm");
        // 設定請求頭：User-Agent用戶代理（不設定個別網站訪問不了）
        httpGet.setHeader("User-Agent", "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:50.0) Gecko/20100101 Firefox/50.0");
        // 回應模型
        CloseableHttpResponse response = null;
        try {
            // 由客戶端執行(發送)Get請求
            response = httpClient.execute(httpGet);
            // 從回應模型中獲取回應物體
            HttpEntity responseEntity = response.getEntity();
            if (responseEntity != null) {
            	//獲取網頁源代碼
                String first_page = EntityUtils.toString(responseEntity, "utf-8");
            }
        } catch (ClientProtocolException e) {
            e.printStackTrace();
        } catch (ParseException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                // 釋放資源
                if (httpClient != null) {
                    httpClient.close();
                }
                if (response != null) {
                    response.close();
                }
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }

二、正則運算式實體

//創建一個存放目的資料的集合
List<String> list = new ArrayList<String>();
//撰寫正則運算式
String regex = "<a href=\"(http://.*?net)\">";
//Pattern與Matcher一起合作.
//Matcher類提供了對正則運算式的分組支持,以及對正則運算式的多次匹配支持
Pattern pattern = Pattern.compile("正則運算式");
Matcher matcher = pattern.matcher("網頁原始碼");
//將Matcher物件中的資料存盤到list中
while (matcher.find()) {
    list.add(matcher.group(1));
}
//遍歷輸出list陣列
for (String str : list) {
    if (str.length() < 30) {
        System.out.println("二級網頁：" + str);
    }
}

三、Jsoup：Java的HTML決議器

//將網頁源代碼轉化為Document物件
Document doc = Jsoup.parse(mubiao_page);
//查詢當前標簽第一個選中的第一個文本內容
String title = doc.getElementsByTag("h1").first().text();
//查詢當前選中元素上一個元素
//Elements elements = doc.getElementsByTag("dd").prevAll();
//查詢當前選中元素下一個元素
Elements elements = doc.getElementsByTag("dt").nextAll();
//獲取迭代器
Iterator it = elements.iterator();
int i = 1;
//創建Home物件
Home home = new Home();
home.setTitle(title);
//對獲取的資料進行迭代遍歷，存盤到Home中
while (it.hasNext()) {
    Element element = (Element) it.next();
    String text = element.text();
    if (i == 1) {
        home.setPrice(text);
    } else if (i == 2) {
        home.setArea(text);
    } else if (i == 3) {
        home.setName(text);
    } else if (i == 4) {
        home.setAdress(text);
    } else if (i == 5) {
        home.setMsg(text);
    } else if (i == 6) {
        home.setHight(text);
    } else if (i == 7) {
        home.setPeople(text);
    } else if (i == 8) {
        home.setPhone(text);
    }
    i = i + 1;
}

Gitee原始碼下載

點我下載：https://gitee.com/pipizi/Pc_home/tree/master/