go-extractor/readability.go

package extractor

import (
	"bytes"
	"context"
	"net/url"

	"github.com/go-shiori/go-readability"
)

func Readability(_ context.Context, doc Document) (Article, error) {
	data, err := doc.Content()
	if err != nil {
		return Article{}, err
	}

	u, err := url.Parse(doc.URL())

	if err != nil {
		return Article{}, err
	}

	a, err := readability.FromReader(bytes.NewBufferString(data), u)

	if err != nil {
		return Article{}, err
	}

	pubTime := ""

	if a.PublishedTime != nil {
		pubTime = a.PublishedTime.Format("2006-01-02T15:04:05Z")
	}
	return Article{
		Title:         a.Title,
		Content:       a.Content,
		TextContent:   a.TextContent,
		Length:        a.Length,
		Excerpt:       a.Excerpt,
		Byline:        a.Byline,
		SiteName:      a.SiteName,
		Lang:          a.Language,
		PublishedTime: pubTime,
	}, nil

}