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
}
func getAnExcuse() (*Excuse, error) {
var endpointURL *url.URL
endpointURL, err := url.Parse("http://www.programmerexcuses.com/")
if err != nil {
return nil, err
}
content, err := utils.GetContent(endpointURL.String(), nil)
if err != nil {
return nil, err
}
doc, err := html.Parse(strings.NewReader(string(content)))
if err != nil {
return nil, err
}
var excuseText string
var f func(*html.Node, bool)
f = func(n *html.Node, canExtractText bool) {
// Extract text content if node is a TextNode
if canExtractText && n.Type == html.TextNode {
excuseText = n.Data
}
// Tell whether text content can be extracted or not.
// Here, we will recursively traverse for 'a' ElementNode.
canExtractText = canExtractText || (n.Type == html.ElementNode && n.Data == "a")
for c := n.FirstChild; c != nil; c = c.NextSibling {
f(c, canExtractText)
}
}
f(doc, false)
return &Excuse{Text: excuseText, Response: "true"}, err
}