func ExampleParse() {
s := `<p>Links:</p><ul><li><a href="foo">Foo</a><li><a href="/bar/baz">BarBaz</a></ul>`
doc, err := html.Parse(strings.NewReader(s))
if err != nil {
log.Fatal(err)
}
var f func(*html.Node)
f = func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "a" {
for _, a := range n.Attr {
if a.Key == "href" {
fmt.Println(a.Val)
break
}
}
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
f(c)
}
}
f(doc)
// Output:
// foo
// /bar/baz
}
// Parse the html while handling the charset
func ParseHTML(r io.Reader, cs string) (*html.Node, error) {
var err error
if cs == "" {
// attempt to guess the charset of the HTML document
r, err = charset.NewReader(r, "")
if err != nil {
return nil, err
}
} else {
// let the user specify the charset
e, name := charset.Lookup(cs)
if name == "" {
return nil, fmt.Errorf("'%s' is not a valid charset", cs)
}
r = transform.NewReader(r, e.NewDecoder())
}
return html.Parse(r)
}
