added archive, megamillions, and powerball site logic

This commit is contained in:
2024-12-23 03:18:50 -05:00
parent 5e924eb3f9
commit 567a9f9212
19 changed files with 1412 additions and 118 deletions

View File

@@ -1,25 +1,26 @@
package extractor
import (
"bytes"
"context"
"net/url"
"github.com/go-shiori/go-readability"
)
type Readability struct {
Extractor
}
func Readability(_ context.Context, doc Document) (Article, error) {
data, err := doc.Content()
if err != nil {
return Article{}, err
}
var _ Extractor = Readability{}
func (r Readability) Extract(_ context.Context, src Source) (Article, error) {
u, err := url.Parse(src.URL())
u, err := url.Parse(doc.URL())
if err != nil {
return Article{}, err
}
a, err := readability.FromReader(src.Reader(), u)
a, err := readability.FromReader(bytes.NewBufferString(data), u)
if err != nil {
return Article{}, err