@Override public void extract(MetadataTarget target, CachedUrl cu, Emitter emitter) throws IOException { ArticleMetadata am = new SimpleHtmlMetaTagMetadataExtractor().extract(target, cu); am.cook(tagMap); String url = am.get(MetadataField.FIELD_ACCESS_URL); ArchivalUnit au = cu.getArchivalUnit(); if (url == null || url.isEmpty() || !au.makeCachedUrl(url).hasContent()) { url = cu.getUrl(); } am.replace( MetadataField.FIELD_ACCESS_URL, HttpToHttpsUtil.AuUtil.normalizeHttpHttpsFromBaseUrl(au, url)); emitter.emitMetadata(cu, am); }
@Override public ArticleMetadata extract(MetadataTarget target, CachedUrl cu) throws IOException { ArticleMetadata am = super.extract(target, cu); am.cook(tagMap); String url = am.get(MetadataField.FIELD_ACCESS_URL); if (url != null && !url.isEmpty()) { CachedUrl val = cu.getArchivalUnit().makeCachedUrl(url); if (!val.hasContent()) { am.replace(MetadataField.FIELD_ACCESS_URL, cu.getUrl()); } } else { am.replace(MetadataField.FIELD_ACCESS_URL, cu.getUrl()); } return am; }