Function extractHTMLMeta

plugin/http-getter/html_meta.go:42–85

(resp io.Reader)

}

func extractHTMLMeta(resp io.Reader) *HTMLMeta {
	tokenizer := html.NewTokenizer(resp)
	htmlMeta := new(HTMLMeta)

	for {
		tokenType := tokenizer.Next()
		if tokenType == html.ErrorToken {
			break
		} else if tokenType == html.StartTagToken || tokenType == html.SelfClosingTagToken {
			token := tokenizer.Token()
			if token.DataAtom == atom.Body {
				break
			}

			if token.DataAtom == atom.Title {
				tokenizer.Next()
				token := tokenizer.Token()
				htmlMeta.Title = token.Data
			} else if token.DataAtom == atom.Meta {
				description, ok := extractMetaProperty(token, "description")
				if ok {
					htmlMeta.Description = description
				}

				ogTitle, ok := extractMetaProperty(token, "og:title")
				if ok {
					htmlMeta.Title = ogTitle
				}

				ogDescription, ok := extractMetaProperty(token, "og:description")
				if ok {
					htmlMeta.Description = ogDescription
				}

				ogImage, ok := extractMetaProperty(token, "og:image")
				if ok {
					htmlMeta.Image = ogImage
				}
			}
		}
	}

	return htmlMeta
}

func extractMetaProperty(token html.Token, prop string) (content string, ok bool) {
	content, ok = "", false