您好,登錄后才能下訂單哦!
這篇文章主要介紹Java如何通過URL獲取公眾號(hào)文章生成HTML,文中介紹的非常詳細(xì),具有一定的參考價(jià)值,感興趣的小伙伴們一定要看完!
說明:通過公眾號(hào)URL獲取的內(nèi)容,文字可以正常顯示,但是圖片存在跨域訪問的問題,微信不允許跨域訪問公眾號(hào)圖片,所以需要將公眾號(hào)圖片從存入本地后,再上傳至OSS,然后把HTML中的圖片全部替換為自己的OSS地址就可以了
這里就需要在后臺(tái)對(duì)HTML進(jìn)行DOM的解析,需要用的Jsoup
<dependency> <groupId>com.aliyun.oss</groupId> <artifactId>aliyun-sdk-oss</artifactId> <version>2.2.3</version> </dependency> <dependency> <groupId>org.jsoup</groupId> <artifactId>jsoup</artifactId> <version>1.9.2</version> </dependency>
controller
package com.iueang.controller; import java.io.File;import java.util.HashMap;import java.util.Map; import org.jsoup.Jsoup;import org.jsoup.nodes.Document;import org.jsoup.nodes.Element;import org.jsoup.select.Elements;import org.springframework.stereotype.Controller;import org.springframework.web.bind.annotation.RequestMapping;import org.springframework.web.bind.annotation.ResponseBody; import com.iueang.util.DownLoadImg;import com.iueang.util.GetBody;import com.iueang.util.OssUtil2;import com.iueang.util.UrlUtil;@Controllerpublic class TestUrl { @RequestMapping("tohtml") public String tohtml() { return "html/index.html"; } @RequestMapping("getHtml") @ResponseBody public Map<String,String> getHtml(String url){ //獲取url文章生成文本 String html = UrlUtil.getAccess(url); String reg = "<html>(.*?)</html>"; String head=GetBody.getSubUtilSimple(html, reg); String HTTPHOST="http://yueang2.oss-cn-qingdao.aliyuncs.com/testimg/"; String newsBody=head; Document doc = Jsoup.parse(newsBody); Elements pngs = doc.select("img[data-src]"); System.out.println(pngs); for (Element element : pngs) { //獲取圖片地址 String imgUrl = element.attr("data-src"); //下載圖片到本地 String filename=DownLoadImg.downloadPicture(imgUrl); File file =new File("D:\\m2\\"+filename); //上傳至oss Boolean flag = OssUtil2.uploadFileToOss(file, "testimg/"+filename); if(flag) { file.delete(); } String newsrc =HTTPHOST + filename; element.attr("src", newsrc); } newsBody = doc.toString(); System.out.println(newsBody); Map<String,String> map=new HashMap<String, String>(); map.put("resultHtml", newsBody); return map; }}
util工具類
GetBody類
package com.iueang.util; import java.util.regex.Matcher;import java.util.regex.Pattern; public class GetBody { public static String getSubUtilSimple(String html, String reg) { Pattern pattern = Pattern.compile(reg);// 匹配的模式 Matcher m = pattern.matcher(html); while(m.find()){ return m.group(1); } return ""; } }
OssUtil類
package com.iueang.util; import java.io.File;import java.util.HashMap;import java.util.Map; import com.aliyun.oss.OSSClient;import com.aliyun.oss.model.ObjectMetadata; public class OssUtil2 { //以下幾個(gè)參數(shù)值必填,參考文章最后文檔 static String endpoint = "http://oss-cn-qingdao.aliyuncs.com"; static String accessKeyId = "oss獲取"; static String accessKeySecert = "oss獲取"; static String bucketName = "yueang2"; /** * 上傳單個(gè)文件到OSS * @param file 要上傳的文件File對(duì)象 * @param objName 上傳后的文件名,包含文件夾,比如 game/game/test.txt * @return */ public static boolean uploadFileToOss(File file, String objName) { try { OSSClient ossClient = null; try { ossClient = new OSSClient(endpoint, accessKeyId, accessKeySecert); }catch (Exception e){ e.printStackTrace(); } ObjectMetadata meta = new ObjectMetadata(); ossClient.putObject(bucketName, objName, file, meta); ossClient.shutdown(); } catch (Exception e) { e.printStackTrace(); return false; } return true; }}
DownLoadImg類
package com.iueang.util; import java.io.ByteArrayOutputStream;import java.io.DataInputStream;import java.io.File;import java.io.FileOutputStream;import java.io.IOException;import java.net.MalformedURLException;import java.net.URL;import java.util.UUID; import sun.misc.BASE64Encoder;public class DownLoadImg { public static String downloadPicture(String urlList) { String filename="iueang"+UUID.randomUUID().toString()+".png"; String path="D:/m2/"+filename; URL url = null; try { url = new URL(urlList); DataInputStream dataInputStream = new DataInputStream(url.openStream()); FileOutputStream fileOutputStream = new FileOutputStream(new File(path)); ByteArrayOutputStream output = new ByteArrayOutputStream(); byte[] buffer = new byte[1024]; int length; while ((length = dataInputStream.read(buffer)) > 0) { output.write(buffer, 0, length); } BASE64Encoder encoder = new BASE64Encoder(); String encode = encoder.encode(buffer); fileOutputStream.write(output.toByteArray()); dataInputStream.close(); fileOutputStream.close(); } catch (MalformedURLException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } System.out.println("Download返回的filname="+filename); return filename; }}
以上是“Java如何通過URL獲取公眾號(hào)文章生成HTML”這篇文章的所有內(nèi)容,感謝各位的閱讀!希望分享的內(nèi)容對(duì)大家有幫助,更多相關(guān)知識(shí),歡迎關(guān)注億速云行業(yè)資訊頻道!
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如果涉及侵權(quán)請(qǐng)聯(lián)系站長(zhǎng)郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。