java.lang.IndexOutOfBoundsException: Invalid index 0, size is 0.. 解析文件不正确？

Question

我正在尝试制作一个在网格/列表中解析在线图片的 android 应用程序，但是我遇到了一些运行时错误。它说我为我的家犬品种解析错误。有谁知道我在哪里犯错误？我知道为什么数组会越界，但我不知道如何解决它！

我正在尝试解析 http://www.dogbreedslist.info/family-dog-breeds/ 这个网站数据.. 但我的这些部分出现运行时错误

DogActivity.class

  private class RetrieveDogsTask extends AsyncTask<String, Void, Void> {
       @Override
       protected Void doInBackground(String... urls) {
           for (String url : urls) {
            Parser parser = new Parser(url, DogsActivity.this);
            Breed.Name breedName = breed.getName();
            if (breedName == Breed.Name.HERDING_DOG_BREED) {
                dogs.add(parser.parseProfile(new Dog(url, breedName)));
            } else {
                dogs.addAll(parser.parseDogsPage(breedName,    DogsActivity.this));
            }
          }
        return null;
    }

解析器类

public class Parser {
Document doc;
Context context;
Elements dogRows;

public Parser(String url, Context context) {
    this.context = context;
    try {
        doc = Jsoup.connect(url).get();
    } catch (IOException e) {
        Log.e("Page", "Wrong URL or network problems", e);
    }

}

public ArrayList<Dog> parseDogsPage(Breed.Name breedName, Context context) {
    ArrayList<Dog> dogs = new ArrayList<>();
    try {
        Element dogContainer;
        if (breedName == Breed.Name.FAMILY_DOG_BREED) {
            dogContainer = doc.getElementsByClass("familybreed").get(0);
        } else {
            dogContainer = doc.getElementsByClass("toybreed").get(0);
        }
        Log.i("Page", "A page has been parsed successfully");
        dogRows = dogContainer.getElementsByTag("a");
        for (Element dogRow : dogRows) {
            String dogName, dogURL;
            Dog dog;
            dogURL = dogRow.getElementsByTag("a").get(0).absUrl("href");
            String dogThumbnailURL = dogRow.
                    getElementsByTag("img").get(0).absUrl("src");
            if (breedName == Breed.Name.FAMILY_DOG_BREED) {
                dogName = dogRow.getElementsByTag("span").get(0).text();
                dog = new Dog(dogName, dogURL, dogThumbnailURL, breedName);
            } else {
                dogName = dogRow.getElementsByTag("strong").get(0).text();
                Element details = dogContainer.getElementsByClass("details").get(0);
                Elements children = details.children();
                if (breedName == Breed.Name.TOY_DOG_BREED || breedName == Breed.Name.HOUND_DOG_BREED) {
                    String origin = children.get(1).text();
                    String lifespan = children.get(3).text();
                    dog= new Dog(dogName, origin , lifespan, dogURL, dogThumbnailURL, breedName);
                } else {
                    //for herding
                    String sizetype = children.get(1).text();
                    dog = new Dog(dogName, sizetype, dogThumbnailURL, dogURL, breedName);
                }
            }

            dogs.add(dog);
        }
    } catch (Exception e) {
        Log.e("Breed activity", "Wrong parsing for " + breedName, e);
    }
    return dogs;
}


public Dog parseProfile(Dog dog) {
    if (!dog.isDetailDataReady()) {
        //coaches already read the data in the coaches page
        try {
            Element dogContainer = doc.getElementById("dogscontainer");
            Element bioContainer = dogContainer.getElementById("biocontainer");
            Element bioDetails = bioContainer.getElementById("biodetails");
            dog.setOtherNames(bioDetails.getElementsByTag("h1").text());

            ArrayList<Dog.Detail> dogDetails = new ArrayList<>();
            Elements rows = bioDetails.getElementsByTag("tr");
            for (Element row : rows) {
                Elements tds = row.getElementsByTag("td");
                if (dog.getBreed() == Breed.Name.WORKING_DOG_BREED ||
                        dog.getBreed() == Breed.Name.TERRIER_DOG_BREED ||
                        dog.getBreed() == Breed.Name.HERDING_DOG_BREED) {
                    //coaches, manager and legends use th and td
                    Elements ths = row.getElementsByTag("th");
                    dogDetails.add(new Dog.Detail(ths.get(0).text(), tds.get(0).text()));
                } else {
                    //dogs use two tds
                    dogDetails.add(new Dog.Detail(tds.get(0).text(), tds.get(1).text()));
                }
            }
            dog.setDetails(dogDetails);

            Element articleText = dogContainer.getElementsByClass("dogarticletext").get(0);
            Elements paragraphs = articleText.getElementsByTag("p");
            String text = "";
            for (Element p : paragraphs) {
                text = text + "\n\n\n" + p.text();
            }
            dog.setArticleText(dog.getArticleText() + text);

            if (dog.getBreed() == Breed.Name.WORKING_DOG_BREED ||
                    dog.getBreed() == Breed.Name.TERRIER_DOG_BREED ||
                    dog.getBreed() == Breed.Name.HERDING_DOG_BREED) {

                //get main image url
                dog.setMainImageURL(bioContainer.getElementsByTag("img").get(0).absUrl("src"));
                if (dog.getBreed() == Breed.Name.WORKING_DOG_BREED) {
                    dog.setThumbnailURL(dog.getMainImageURL());
                    //only need first name
                    dog.setName(dog.getOtherNames().split(" ")[1]);
                }
            } else {
                dog.setMainImageURL(bioContainer.getElementsByClass("mainImage").get(0).absUrl("src"));
            }

        } catch (Exception e) {
            Log.e("Profile activity", "Wrong parsing for " + dog.getUrl(), e);
        }
        if (dog.getBreed() == Breed.Name.WORKING_DOG_BREED) {
            dog.setBasicDataReady(true);
        }
        dog.setDetailDataReady(true);
    }
    return dog;
}

}

RetrieveDogTask：

 private class RetrieveDogsTask extends AsyncTask<String, Void, Void> {
    @Override
    protected Void doInBackground(String... urls) {
        for (String url : urls) {
            Parser parser = new Parser(url, DogsActivity.this);
            Breed.Name breedName = breed.getName();
            if (breedName == Breed.Name.HERDING_DOG_BREED) {
                dogs.add(parser.parseProfile(new Dog(url, breedName)));
            } else {
                dogs.addAll(parser.parseDogsPage(breedName, DogsActivity.this));
            }
        }

        return null; 

Logcat：

 Wrong parsing for FAMILY_DOG_BREED
 java.lang.IndexOutOfBoundsException: Invalid index 0, size is 0
    at java.util.ArrayList.throwIndexOutOfBoundsException(ArrayList.java:255)
    at java.util.ArrayList.get(ArrayList.java:308)
  at org.jsoup.select.Elements.get(Elements.java:544)
  at com.example.shannon.popular.Parser.parseDogsPage(Parser.java:35)
           at            com.example.shannon.popular.DogsActivity$RetrieveDogsTask.doInBackground(DogsActivity.java:140)  
      at com.example.shannon.popular.DogsActivity$RetrieveDogsTask.doInBackground(DogsActivity.java:131)
       at android.os.AsyncTask$2.call(AsyncTask.java:288)
       at java.util.concurrent.FutureTask.run(FutureTask.java:237)
      at    java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1112)
      at   java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:587)
       at java.lang.Thread.run(Thread.java:818)

品种类：

public class Breed implements Serializable {
private Name name;
private String url;


Breed(Name name, String url) {
    this.name = name;
    this.url = url;
}

public Name getName() {
    return name;
}

public String getNameString(Context context) {
    String nameString = "";
    switch (name) {
        case FAMILY_DOG_BREED:
            nameString = context.getString(R.string.family_breed);
            break;
        case TOY_DOG_BREED:
            nameString = context.getString(R.string.toy_breed);
            break;
        case HOUND_DOG_BREED:
            nameString = context.getString(R.string.hound_breed);
            break;
        case TERRIER_DOG_BREED:
            nameString = context.getString(R.string.terrier_breed);
            break;
        case WORKING_DOG_BREED:
            nameString = context.getString(R.string.working_breed);
            break;
        case HERDING_DOG_BREED:
            nameString = context.getString(R.string.herding_breed);
            break;
    }
    return nameString;
}

public String getURL() {
    return url;
}

public enum Name {FAMILY_DOG_BREED, TOY_DOG_BREED, HOUND_DOG_BREED, TERRIER_DOG_BREED, WORKING_DOG_BREED, HERDING_DOG_BREED}

}

Answer 1

您可能正在对格式错误的 HTML 文档使用严格的 XML 解析器。我只是尝试对您正在解析的 URL 进行 XML 验证，但它失败了，因为 <link> 元素从未关闭（在严格的 XML 中，它应该以 </link> 标记结束，但该页面中缺少它）。 这对于 HTML 页面很常见，因为当今的浏览器倾向于自动更正这些类型的错误。

由于您使用严格的 XML 解析器，因此解析器很可能会失败。

我建议切换到不同的解析器。我会使用 PULL 解析器（例如 http://www.xmlpull.org ） - 这种技术允许使用较低级别的控制进行解析，这意味着您可以轻松地忽略 HTML 中不需要的内容 - 例如这些链接元素或其他任何内容。

所以你可以这样做：

XmlPullParser parser = XmlPullParserFactory.newInstance().newPullParser();

parser.setInput(new BufferedReader(
                    new InputStreamReader(
                        new URL("http://.....").openConnection().getInputStream()
                    )
                )
            );

while(XmlPullParser.END_DOCUMENT != parser.next()){
    if(XmlPullParser.START_TAG == parser.getEventType()){
        String tagName = parser.getName();
        if(parser.getAttributeCount() > 0 {
             // parse attributes, if needed
        }
        if(parser.nextToken() == XmlPullParser.TEXT){
             String tagValue = parser.getText()
        }
        // etc.
    }
}