我如何使用 jsoup 在 android studio 上抓取图像

分类：编程问答

如何解决我如何使用 jsoup 在 android studio 上抓取图像

我正在 android studio 上创建应用程序，我正在从下面的代码中使用的新闻网站抓取数据，我能够从网页上抓取文本并将它们放入列表中，但我想知道我如何从站点检索图像并将它们放入列表中。

片段类

final StringBuilder builder = new StringBuilder();
                ArrayList<News> webnewss = new ArrayList<>();
            

try {
                Document doc = Jsoup.connect("https://www.bbc.co.uk/search?q=little+aston&page=1").userAgent("Jsoup Scraper").get();

                String heading = "div.ssrcss-v4rel9-PromoContent.e1f5wbog0 > div.ssrcss-l100ew-PromoContentSummary.e1f5wbog1 > p.ssrcss-1uw1j0b-PromoHeadline.e1f5wbog2";
                Elements headerElements = doc.select(heading);
                ArrayList<String> headerTitles = new ArrayList<>();
                for (Element e : headerElements) {
                    headerTitles.add(e.text());
                }

                String description = "div.ssrcss-v4rel9-PromoContent.e1f5wbog0 > div.ssrcss-l100ew-PromoContentSummary.e1f5wbog1 > p:nth-child(2)";
                Elements descriptionElements = doc.select(description);
                ArrayList<String> descriptionTitles = new ArrayList<>();
                for (Element e : descriptionElements) {
                    descriptionTitles.add(e.text());
                }

                String published = "div.ssrcss-v4rel9-PromoContent.e1f5wbog0 > div.ssrcss-3r6h34-PromoContentMetadata.e1f5wbog9 > div > dl > div:nth-child(1) > dd > span > span:nth-child(2)";
                Elements publishedElements = doc.select(published);
                ArrayList<String> publishedTitles = new ArrayList<>();
                for (Element e : publishedElements) {
                    publishedTitles.add(e.text());
                }

                String url = "div.ssrcss-v4rel9-PromoContent.e1f5wbog0 > div.ssrcss-l100ew-PromoContentSummary.e1f5wbog1 > p.ssrcss-1uw1j0b-PromoHeadline.e1f5wbog2 > a";
                Elements urlElements = doc.select(url);
                ArrayList<String> urlTitles = new ArrayList<>();
                for(Element e:urlElements) {
                    urlTitles.add(e.attr("href"));

                }

                for (int i = 0; i < headerTitles.size() && i < descriptionTitles.size() && i < publishedTitles.size() && i < urlTitles.size(); i++) {
                    News news = new News(headerTitles.get(i),descriptionTitles.get(i),publishedTitles.get(i),urlTitles.get(i));
                    webnewss.add(news);
                }

            } catch (IOException e) {
                e.printStackTrace();
            }

新闻类

public class News {
    public String heading;
    public String description;
    public String published;
    public String link;
    

    public News(String heading,String description,String published,String link){
        this.heading = heading;
        this.description = description;
        this.published = published;
        this.link = link;
        
    }

列表xml

<LinearLayout xmlns:android="http://schemas.android.com/apk/res/android"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    android:orientation="vertical"
    android:gravity="center_horizontal"
    android:background="@drawable/customshape"
    >
    
    <TextView
        android:id="@+id/textNews_headingTitle"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="16dp"
        android:textColor="#000000"
        android:textStyle="bold"
        android:paddingTop="10dp"
        />

    <TextView
        android:id="@+id/textNews_heading"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="16dp"
        android:textColor="#FFFFFF"
        android:paddingBottom="2dp"/>

    <TextView
        android:id="@+id/textNews_descriptionTitle"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="16dp"
        android:textColor="#000000"
        android:textStyle="bold"/>

    <TextView
        android:id="@+id/textNews_description"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="16dp"
        android:textColor="#FFFFFF"
        android:paddingBottom="2dp"/>

    <TextView
        android:id="@+id/textNews_publishedTitle"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="16dp"
        android:textColor="#000000"
        android:textStyle="bold"/>

    <TextView
        android:id="@+id/textNews_published"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="16dp"
        android:textColor="#FFFFFF"
        android:paddingBottom="2dp"/>

    <TextView
        android:id="@+id/textNews_linkTitle"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="18dp"
        android:gravity="center"
        android:textColor="#000000"
        android:textStyle="bold"/>

    <TextView
        android:id="@+id/textNews_link"
        android:layout_width="360dp"
        android:layout_height="wrap_content"
        android:textSize="16dp"
        android:textColor="#FFFFFF"
        android:paddingBottom="10dp"/>


</LinearLayout>

适配器类

public class ScrapingAdapter extends ArrayAdapter<News> {
    private static class ViewHolder{
        TextView newsTitleHeading;
        TextView newsHeading;
        TextView newsTitleDescription;
        TextView newsDescription;
        TextView newsTitlePublished;
        TextView newsPublished;
        TextView newsTitleLink;
        TextView newsLink;
    }

    public ScrapingAdapter(Context context,ArrayList<News> newsInfo){
        super(context,R.layout.news_layout,newsInfo);
    }

    @Override

    public View getView(int position,@Nullable View view,@NonNull ViewGroup parent) {
        News scraping = getItem(position);

        ViewHolder viewHolder;
        if(view == null){
            viewHolder = new ViewHolder();
            LayoutInflater inflater = LayoutInflater.from(getContext());
            view = inflater.inflate(R.layout.news_layout,parent,false);
            viewHolder.newsTitleHeading = (TextView) view.findViewById(R.id.textNews_headingTitle);
            viewHolder.newsHeading = (TextView) view.findViewById(R.id.textNews_heading);
            viewHolder.newsTitleDescription = (TextView) view.findViewById(R.id.textNews_descriptionTitle);
            viewHolder.newsDescription = (TextView) view.findViewById(R.id.textNews_description);
            viewHolder.newsTitlePublished = (TextView) view.findViewById(R.id.textNews_publishedTitle);
            viewHolder.newsPublished = (TextView) view.findViewById(R.id.textNews_published);
            viewHolder.newsTitleLink = (TextView) view.findViewById(R.id.textNews_linkTitle);
            viewHolder.newsLink = (TextView) view.findViewById(R.id.textNews_link);
            view.setTag(viewHolder);
        } else {
            viewHolder = (ViewHolder) view.getTag();
        }

        viewHolder.newsTitleHeading.setText("Title:");
        viewHolder.newsHeading.setText(scraping.heading);
        viewHolder.newsTitleDescription.setText("Description:");
        viewHolder.newsDescription.setText(scraping.description);
        viewHolder.newsTitlePublished.setText("Date Published:");
        viewHolder.newsPublished.setText(scraping.published);
        viewHolder.newsTitleLink.setText("Click here to open link");
        view.setOnClickListener(new View.OnClickListener() {
            @Override
            public void onClick(View v) {
                //Toast.makeText(getContext(),"You clicked" + scraping.heading,Toast.LENGTH_SHORT).show();
                Intent openLinksIntent = new Intent(Intent.ACTION_VIEW,Uri.parse(scraping.link));
                getContext().startActivity(openLinksIntent);
            }
        });
        return view;

    }
}

解决方法

您可以尝试使用此方法获取图片网址。 src 将提供该页面上的所有图片网址。

ArrayList<String> imageLinkList = new ArrayList<>();
Elements e = doc.getElementsByTag("img");
for(Element el : e) {
String url = el.absUrl("src");
imageLinkList.add(url);
}

for (int i = 0; i < headerTitles.size() && i < descriptionTitles.size() && i < publishedTitles.size() && i < urlTitles.size() && imageLinkList.size(); i++) {
News news = new News(headerTitles.get(i),descriptionTitles.get(i),publishedTitles.get(i),urlTitles.get(i),imageLinkList.get(i));
webnewss.add(news);
}

public class News {
    public String heading;
    public String description;
    public String published;
    public String link;
    public String imageLink;
    

    public News(String heading,String description,String published,String link,String imageLink){
        this.heading = heading;
        this.description = description;
        this.published = published;
        this.link = link;
        this.imageLink = imageLink;
        
    }

现在您的新闻对象将有一个图片链接。在 news_layout 中添加 imageView。在适配器类中使用 Glide/Picasso 渲染。

版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 dio@foxmail.com 举报，一经查实，本站将立刻删除。

相关推荐

matplotlib报错：AttributeError: module 'backend_interagg' has no attribute 'FigureCanvas'. Did you mean: 'FigureCanvasAgg'?
使用本地python环境可以成功执行 import pandas as pd import matplotlib.pyplot as plt # 设置字体 plt.rcParams[&#39;font.sans-serif&#39;] = [&#39;SimHei&#39;] # 能正确显示负号 p
gitlab登录失败，报错：This challenge page was accidentally cached by an intermediary and is no longer available.
设置时间 控制面板
后端开发常见错误
错误1：Request method ‘DELETE‘ not supported 错误还原：controller层有一个接口，访问该接口时报错：Request method ‘DELETE‘ not supported 错误原因：没有接收到前端传入的参数，修改为如下 参考 错误2：cannot r
docker常见错误
错误1：启动docker镜像时报错：Error response from daemon: driver failed programming external connectivity on endpoint quirky_allen 解决方法：重启docker -&gt; systemctl r
idea常见错误
错误1：private field ‘xxx‘ is never assigned 按Altʾnter快捷键，选择第2项 参考：https://blog.csdn.net/shi_hong_fei_hei/article/details/88814070 错误2：启动时报错，不能找到主启动类 #
pip安装依赖失败
报错如下，通过源不能下载，最后警告pip需升级版本 Requirement already satisfied: pip in c:\users\ychen\appdata\local\programs\python\python310\lib\site-packages (22.0.4) Coll
maven常见错误
错误1：maven打包报错 错误还原：使用maven打包项目时报错如下 [ERROR] Failed to execute goal org.apache.maven.plugins:maven-resources-plugin:3.2.0:resources (default-resources)
cloud项目中常见错误
错误1：服务调用时报错 服务消费者模块assess通过openFeign调用服务提供者模块hires 如下为服务提供者模块hires的控制层接口 @RestController @RequestMapping(&quot;/hires&quot;) public class FeignControl
springboot常见错误
错误1：运行项目后报如下错误 解决方案 报错2：Failed to execute goal org.apache.maven.plugins:maven-compiler-plugin:3.8.1:compile (default-compile) on project sb 解决方案：在pom.
springmvc拦截器中使用redisTemplate报空指针异常
参考 错误原因 过滤器或拦截器在生效时，redisTemplate还没有注入 解决方案：在注入容器时就生效 @Component //项目运行时就注入Spring容器 public class RedisBean { @Resource private RedisTemplate&lt;String
vite报错：npm ERR! command C:WINDOWSsystem32cmd.exe /d /s /c C:UsersychenAppDataLocalTempnpx-dde1c848.cmd
使用vite构建项目报错 C:\Users\ychen\work&gt;npm init @vitejs/app @vitejs/create-app is deprecated, use npm init vite instead C:\Users\ychen\AppData\Local\npm-
VM VirtualBox中安装centos时报错：设置基础软件仓库时出错
参考1 参考2 解决方案 # 点击安装源 协议选择 http:// 路径填写 mirrors.aliyun.com/centos/8.3.2011/BaseOS/x86_64/os URL类型 软件库URL 其他路径 # 版本 7 mirrors.aliyun.com/centos/7/os/x86
kafka常见问题
报错1 [root@slave1 data_mocker]# kafka-console-consumer.sh --bootstrap-server slave1:9092 --topic topic_db [2023-12-19 18:31:12,770] WARN [Consumer clie
hive常见问题
错误1 # 重写数据 hive (edu)&gt; insert overwrite table dwd_trade_cart_add_inc &gt; select data.id, &gt; data.user_id, &gt; data.course_id, &gt; date_format(
装载数据时报错：Failed to execute spark task, with exception 'org.apache.hadoop.hive.ql.metadata.HiveException(Failed to create spark client.)'
错误1 hive (edu)&gt; insert into huanhuan values(1,&#39;haoge&#39;); Query ID = root_20240110071417_fe1517ad-3607-41f4-bdcf-d00b98ac443e Total jobs = 1
flume常见问题
报错1：执行到如下就不执行了，没有显示Successfully registered new MBean. [root@slave1 bin]# /usr/local/software/flume-1.9.0/bin/flume-ng agent -n a1 -c /usr/local/softwa
hadoop集群常见错误
虚拟及没有启动任何服务器查看jps会显示jps，如果没有显示任何东西 [root@slave2 ~]# jps 9647 Jps 解决方案 # 进入/tmp查看 [root@slave1 dfs]# cd /tmp [root@slave1 tmp]# ll 总用量 48 drwxr-xr-x. 2
hive常见错误
报错1 hive&gt; show databases; OK Failed with exception java.io.IOException:java.lang.RuntimeException: Error in configuring object Time taken: 0.474 se
Linux常见错误
报错1 [root@localhost ~]# vim -bash: vim: 未找到命令 安装vim yum -y install vim* # 查看是否安装成功 [root@hadoop01 hadoop]# rpm -qa |grep vim vim-X11-7.4.629-8.el7_9.x
使用sqoop一直卡在：mapreduce.Job: Running job: job_1703173956074_0001
修改hadoop配置 vi /usr/local/software/hadoop-2.9.2/etc/hadoop/yarn-site.xml # 添加如下 &lt;configuration&gt; &lt;property&gt; &lt;name&gt;yarn.nodemanager.res
pythonJavaScriptjavaHTMLPHPreactjsC#AndroidCSSNode.jssqlrpython-3.xMysqLjQueryc++pandasFlutterangularIOSdjangolinuxswifttypescript路由器JSON路由器设置无线路由器h3c华三华三路由器设置华三路由器电脑软件教程arraysdocker软件图文教程Cvue.jslaravelspring-boot