/* * hasArticleMetadata(CachedUrl cu) * Given the CachedUrl for the potential abstract file, using the existing * SimpleHtmlMetaTagMetadataExtractor to parse the file and * retrieve any contained metadata. If a doi or author exists, it's an article * NOT defining the Metadata Extractor here! */ private boolean hasArticleMetadata(CachedUrl cu) { MetadataTarget at = new MetadataTarget(MetadataTarget.PURPOSE_ARTICLE); ArticleMetadata am; SimpleHtmlMetaTagMetadataExtractor ext = new SimpleHtmlMetaTagMetadataExtractor(); if (cu != null && cu.hasContent()) { try { at.setFormat("text/html"); am = ext.extract(at, cu); if ((am.containsRawKey("bepress_citation_journal_title")) || (am.containsRawKey("bepress_citation_abstract_html_url")) || (am.containsRawKey("bepress_citation_doi")) || (am.containsRawKey("bepress_citation_author"))) { return true; } } catch (IOException e) { e.printStackTrace(); } } return false; // no reasonable metadata, probably a toc }