readability

type Content struct {
	Title       string
	Description string
	Content     string
	Author      string
	Images      []Image
}

type Image struct {
	URL  string
	Size *fastimage.ImageSize
}

type Option struct {
	// RetryLength is minimum length for a page description.
	// It will retry to extract page description with more liberal rule
	// if extracted description length is less than this value.
	RetryLength int

	// MinTextLength is minimum length of an inner text for a tag.
	// If a tag has short inner text (length is less than MinTextLength),
	// the text will be discarded from the page description candidates.
	MinTextLength int

	// RemoveUnlikelyCandidates is a flag whether to remove some tags
	// if they are considered relatively unimportant.
	RemoveUnlikelyCandidates bool

	// WeightClasses is a flag whether to give more/less weight to some tags
	// if they contain some positive/negative words in id/class value.
	WeightClasses bool

	// CleanConditionally is a flag whether to remove some tags
	// using various rules in conditionalCleanReason().
	CleanConditionally bool

	// RemoveEmptyNodes is a flag whether to remove some tags which have empty inner text.
	RemoveEmptyNodes bool

	// MinImageWidth is the minimum width (pixel) for choosing images.
	MinImageWidth uint32

	// MinImageHeight is the minimum height (pixel) for choosing images.
	MinImageHeight uint32

	// MaxImageCount is the maximum number of images for a web page.
	MaxImageCount int

	// CheckImageSize is the flag for check image's size or not
	CheckImageSize bool

	// CheckImageLoopCount is the number of images for parallel requests to fetch the image size.
	// For example, if this value is set to 10,
	// the first 10 image sources in img tag will be requested.
	CheckImageLoopCount uint

	// ImageRequestTimeout is timeout(ms) for a single image request.
	ImageRequestTimeout uint

	// IgnoreImageFormat is an array of strings for ignoring some images.
	// If an image URL contains at least one of strings in this array, the image will be ignored.
	IgnoreImageFormat []string

	// DescriptionAsPlainText is a flag whether to strip all tags in a description value.
	DescriptionAsPlainText bool

	// DescriptionExtractionTimeout is timeout(ms) for extracting description for a page.
	DescriptionExtractionTimeout uint
}