added archive, megamillions, and powerball site logic
This commit is contained in:
@@ -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
|
||||
|
Reference in New Issue
Block a user