Files
go-extractor/readability.go
Steve Dudenhoeffer c1a5814732
All checks were successful
CI / build (pull_request) Successful in 46s
CI / test (pull_request) Successful in 48s
CI / vet (pull_request) Successful in 1m50s
feat: add ReadabilityWithOptions for DOM cleanup before extraction
Sites with infinite scroll (e.g. The Verge) load additional articles
into the DOM, which get included in readability extraction. Add
ReadabilityOptions.RemoveSelectors to strip elements by CSS selector
before parsing, avoiding the need to reimplement the readability
pipeline downstream.

Closes #60

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-19 01:09:28 +00:00

90 lines
2.4 KiB
Go

package extractor
import (
"bytes"
"context"
"fmt"
"net/url"
"strings"
"github.com/PuerkitoBio/goquery"
"github.com/go-shiori/go-readability"
)
// ReadabilityOptions configures the readability extraction process.
type ReadabilityOptions struct {
// RemoveSelectors is a list of CSS selectors for elements to remove from
// the DOM before readability extraction. This is useful for stripping
// infinite-scroll content, related articles, or other elements that
// pollute the extracted article.
RemoveSelectors []string
}
// Readability extracts article content from a document using the readability algorithm.
func Readability(_ context.Context, doc Document) (Article, error) {
return ReadabilityWithOptions(context.Background(), doc, ReadabilityOptions{})
}
// ReadabilityWithOptions extracts article content from a document, applying
// the provided options before extraction. Use RemoveSelectors to strip
// elements (e.g. infinite-scroll articles) from the DOM before parsing.
func ReadabilityWithOptions(_ context.Context, doc Document, opts ReadabilityOptions) (Article, error) {
data, err := doc.Content()
if err != nil {
return Article{}, err
}
u, err := url.Parse(doc.URL())
if err != nil {
return Article{}, err
}
if len(opts.RemoveSelectors) > 0 {
data, err = removeSelectors(data, opts.RemoveSelectors)
if err != nil {
return Article{}, fmt.Errorf("failed to clean DOM: %w", 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
}
// removeSelectors parses HTML and removes all elements matching the given CSS selectors.
func removeSelectors(html string, selectors []string) (string, error) {
doc, err := goquery.NewDocumentFromReader(strings.NewReader(html))
if err != nil {
return "", fmt.Errorf("failed to parse HTML: %w", err)
}
for _, sel := range selectors {
doc.Find(sel).Remove()
}
result, err := doc.Html()
if err != nil {
return "", fmt.Errorf("failed to serialize HTML: %w", err)
}
return result, nil
}