distiller

type LogFlag uint

type Options struct {
	// Flags to specify which info to dump to log.
	LogFlags LogFlag

	// Original URL of the page, which is used in the heuristics in detecting
	// next/prev page links. Will be ignored if Option is used in ApplyForURL.
	OriginalURL *nurl.URL

	// Set to true to skip process for finding pagination.
	SkipPagination bool

	// Algorithm to use for next page detection.
	PaginationAlgo PaginationAlgo
}

type PaginationAlgo uint

type Result struct {
	// URL is the URL of the processed page.
	URL string

	// Title is the title of the processed page.
	Title string

	// MarkupInfo is the metadata of the page. The metadata is extracted following three markup
	// specifications: OpenGraphProtocol, IEReadingView and SchemaOrg. For now, OpenGraph protocol
	// takes precedence because it uses specific meta tags and hence the fastest. The other
	// specifications is used as fallback in case some metadata not found.
	MarkupInfo data.MarkupInfo

	// TimingInfo is the record of the time it takes to do each step in the process of content extraction.
	TimingInfo data.TimingInfo

	// PaginationInfo contains link to previous and next partial page. This is useful for long article or
	// that may be partitioned into several partial pages by its webmaster.
	PaginationInfo data.PaginationInfo

	// WordCount is the count of words within document.
	WordCount int

	// Node is the *html.Node which contain the distilled content.
	Node *html.Node

	// Text is the string which contains the distilled content in text format.
	Text string

	// ContentImages is list of image URLs that used within the distilled content.
	ContentImages []string
}