extractor

Documentation

Index

• type ExtractOptions
• type ExtractResult
• type Extractor
  • func New(cfg *config.Config) *Extractor
  • func (e *Extractor) Extract(ctx context.Context, url string, opts ExtractOptions) (*ExtractResult, error)

Types

type ExtractOptions

type ExtractOptions struct {
	Format          string
	IncludeMetadata bool
	UseJS           *bool // nil = auto, true = force, false = disable
	Timeout         time.Duration
}

type ExtractResult

type ExtractResult struct {
	URL            string
	Title          string
	Content        string
	UsedJavaScript bool
	ProcessingTime time.Duration
	ContentLength  int
	Metadata       map[string]string
}

type Extractor

type Extractor struct {
	// contains filtered or unexported fields
}

func New

func New(cfg *config.Config) *Extractor

func (*Extractor) Extract

func (e *Extractor) Extract(ctx context.Context, url string, opts ExtractOptions) (*ExtractResult, error)