blob: 619d8a4004fa88142ab816589b6c3b3fee705592 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
package findlinks
import (
"fmt"
"io"
"strings"
"golang.org/x/net/html"
"golang.org/x/net/html/atom"
)
// A Link encapsulates the data harvested from a link.
type Link struct {
Href string
Text string
}
// findLinks consumes the given [io.Reader], scraping it of anchor
// tags. Each anchor tag is "unmarshalled" into a [Link]. The
// resulting slice of Links is returned, along with an error.
func FindLinks(r io.Reader) ([]Link, error) {
doc, err := html.Parse(r)
if err != nil {
return nil, fmt.Errorf("can't parse html reader: %w", err)
}
var links []Link
for n := range doc.Descendants() {
trimmedData := strings.TrimSpace(n.Data)
if n.Type == html.TextNode && trimmedData != "" {
fmt.Printf("Data: %s\n", trimmedData)
for anc := range n.Ancestors() {
fmt.Printf("\tAncestor: %v\n", anc.Data)
}
continue
}
if n.Type == html.ElementNode && n.DataAtom == atom.A {
var link Link
// Scan the href.
for _, a := range n.Attr {
if a.Key == "href" {
link.Href = a.Val
}
}
// FIXME: for now, only scan for hrefs.
links = append(links, link)
}
}
return links, nil
}
|
