How to use

DefaultExtractor

in

de.l3s.boilerpipe.extractors

protected String parse(String rawText) {
 if (StringUtils.isEmpty(rawText)) return null;
 else {
  try {
   return DefaultExtractor.INSTANCE.getText(rawText);
  } catch (BoilerpipeProcessingException e) {
   LOGGER.error(e.getMessage(), e);
   return null;
  }
 }
}

public TargetModelElasticSearch(TargetModelCbor model) {
  URL url = Urls.toJavaURL(model.url);
  String rawContent = (String) model.response.get("body");
  Page page = new Page(url, rawContent);
  page.setParsedData(new ParsedData(new PaginaURL(url, rawContent)));
  this.html = rawContent;
  this.url = model.url;
  this.retrieved = new Date(model.timestamp * 1000);
  this.words = page.getParsedData().getWords();
  this.wordsMeta = page.getParsedData().getWordsMeta();
  this.title = page.getParsedData().getTitle();
  this.domain = url.getHost();
  try {
    this.text = DefaultExtractor.getInstance().getText(page.getContentAsString());
  } catch (Exception e) {
    this.text = "";
  }
  InternetDomainName domainName = InternetDomainName.from(page.getDomainName());
  if (domainName.isUnderPublicSuffix()) {
    this.topPrivateDomain = domainName.topPrivateDomain().toString();
  } else {
    this.topPrivateDomain = domainName.toString();
  }
}

private void loadDefaultRules() {
  addTextExtractor("default-extractor"      , PAGE_CONTENT_DE_PROPERTY , DefaultExtractor.getInstance());
  addTextExtractor("article-extractor"      , PAGE_CONTENT_AE_PROPERTY , ArticleExtractor.getInstance());
  addTextExtractor("large-content-extractor", PAGE_CONTENT_LCE_PROPERTY, LargestContentExtractor.getInstance());
  addTextExtractor("canola-extractor"       , PAGE_CONTENT_CE_PROPERTY , CanolaExtractor.getInstance());
}

public TargetModelElasticSearch(Page page) {
  this.url = page.getURL().toString();
  this.retrieved = page.getFetchTime() > 0 ? new Date(page.getFetchTime()) : new Date();
  this.domain = page.getDomainName();
  this.responseHeaders = page.getResponseHeaders();
  this.topPrivateDomain = LinkRelevance.getTopLevelDomain(page.getDomainName());
  this.crawlerId = page.getCrawlerId();
  this.isRelevant = page.getTargetRelevance().isRelevant() ? "relevant" : "irrelevant";
  if (page.isHtml()) {
    String contentAsString = page.getContentAsString();
    this.html = contentAsString;
    ParsedData parsedData = page.getParsedData();
    if (parsedData != null) {
      this.words = parsedData.getWords();
      this.wordsMeta = parsedData.getWordsMeta();
      this.title = parsedData.getTitle();
    }
    if (page.getTargetRelevance() != null) {
      this.relevance = page.getTargetRelevance().getRelevance();
    }
    if (contentAsString != null) {
      try {
        this.text = DefaultExtractor.getInstance().getText(contentAsString);
      } catch (Exception e) {
        this.text = "";
      }
    }
  }
}