metadata

func Extract ¶

func Extract(doc *goquery.Document, schemaOrgData interface{}, metaTags []MetaTag, baseURL string) *Metadata

Extract extracts metadata from a document JavaScript original code:

static extract(doc: Document, schemaOrgData: any, metaTags: MetaTagItem[]): DefuddleMetadata {
  let domain = '';
  let url = '';

  try {
    // Try to get URL from document location
    url = doc.location?.href || '';

    // If no URL from location, try other sources
    if (!url) {
      url = this.getMetaContent(metaTags, "property", "og:url") ||
        this.getMetaContent(metaTags, "property", "twitter:url") ||
        this.getSchemaProperty(schemaOrgData, 'url') ||
        this.getSchemaProperty(schemaOrgData, 'mainEntityOfPage.url') ||
        this.getSchemaProperty(schemaOrgData, 'mainEntity.url') ||
        this.getSchemaProperty(schemaOrgData, 'WebSite.url') ||
        doc.querySelector('link[rel="canonical"]')?.getAttribute('href') || '';
    }

    if (url) {
      try {
        domain = new URL(url).hostname.replace(/^www\./, '');
      } catch (e) {
        console.warn('Failed to parse URL:', e);
      }
    }
  } catch (e) {
    // If URL parsing fails, try to get from base tag
    const baseTag = doc.querySelector('base[href]');
    if (baseTag) {
      try {
        url = baseTag.getAttribute('href') || '';
        domain = new URL(url).hostname.replace(/^www\./, '');
      } catch (e) {
        console.warn('Failed to parse base URL:', e);
      }
    }
  }

  return {
    title: this.getTitle(doc, schemaOrgData, metaTags),
    description: this.getDescription(doc, schemaOrgData, metaTags),
    domain,
    favicon: this.getFavicon(doc, url, metaTags),
    image: this.getImage(doc, schemaOrgData, metaTags),
    published: this.getPublished(doc, schemaOrgData, metaTags),
    author: this.getAuthor(doc, schemaOrgData, metaTags),
    site: this.getSite(doc, schemaOrgData, metaTags),
    schemaOrgData,
    wordCount: 0,
    parseTime: 0
  };
}