// NewDocumentFromReader returns a Document from a generic reader.
// It returns an error as second value if the reader's data cannot be parsed
// as html. It does *not* check if the reader is also an io.Closer, so the
// provided reader is never closed by this call, it is the responsibility
// of the caller to close it if required.
func NewDocumentFromReader(r io.Reader) (*Document, error) {
root, e := html.Parse(r)
if e != nil {
return nil, e
}
return newDocument(root, nil), nil
}
func MustParseHTML(doc string) *html.Node {
dom, err := html.Parse(strings.NewReader(doc))
if err != nil {
panic(err)
}
return dom
}
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 TestNewDocument(t *testing.T) {
if f, e := os.Open("./testdata/page.html"); e != nil {
t.Error(e.Error())
} else {
defer f.Close()
if node, e := html.Parse(f); e != nil {
t.Error(e.Error())
} else {
doc = NewDocumentFromNode(node)
}
}
}
func loadDoc(page string) *Document {
var f *os.File
var e error
if f, e = os.Open(fmt.Sprintf("./testdata/%s", page)); e != nil {
panic(e.Error())
}
defer f.Close()
var node *html.Node
if node, e = html.Parse(f); e != nil {
panic(e.Error())
}
return NewDocumentFromNode(node)
}
// NewDocumentFromResponse is another Document constructor that takes an http response as argument.
// It loads the specified response's document, parses it, and stores the root Document
// node, ready to be manipulated. The response's body is closed on return.
func NewDocumentFromResponse(res *http.Response) (*Document, error) {
if res == nil {
return nil, errors.New("Response is nil pointer")
}
defer res.Body.Close()
// Parse the HTML into nodes
root, e := html.Parse(res.Body)
if e != nil {
return nil, e
}
// Create and fill the document
return newDocument(root, res.Request.URL), nil
}
func TestSelectors(t *testing.T) {
for _, test := range selectorTests {
s, err := Compile(test.selector)
if err != nil {
t.Errorf("error compiling %q: %s", test.selector, err)
continue
}
doc, err := html.Parse(strings.NewReader(test.HTML))
if err != nil {
t.Errorf("error parsing %q: %s", test.HTML, err)
continue
}
matches := s.MatchAll(doc)
if len(matches) != len(test.results) {
t.Errorf("wanted %d elements, got %d instead", len(test.results), len(matches))
continue
}
for i, m := range matches {
got := nodeString(m)
if got != test.results[i] {
t.Errorf("wanted %s, got %s instead", test.results[i], got)
}
}
firstMatch := s.MatchFirst(doc)
if len(test.results) == 0 {
if firstMatch != nil {
t.Errorf("MatchFirst: want nil, got %s", nodeString(firstMatch))
}
} else {
got := nodeString(firstMatch)
if got != test.results[0] {
t.Errorf("MatchFirst: want %s, got %s", test.results[0], got)
}
}
}
}