feat: add NewDocumentFromReaderWithOptions
goquery calls html.Parse, so callers cannot reach the parse options that golang.org/x/net/html has since grown. The one that matters is ParseOptionEnableScripting(false): with scripting assumed enabled the contents of a noscript element are parsed as raw text and no selector can reach inside it. Add a constructor taking html.ParseOption values. Existing constructors are untouched. Refs #139
This commit is contained in:
1 parent
8592be9b0e
commit
3701788802
2 files changed
+55
No files matched your search
@@ -56,6 +56,24 @@ func NewDocumentFromReader(r io.Reader) (*Document, error) {
|
||||
return newDocument(root, nil), nil
|
||||
}
|
||||
|
||||
// NewDocumentFromReaderWithOptions is like NewDocumentFromReader, with the
|
||||
// parse options of the html package.
|
||||
//
|
||||
// The option that usually matters is html.ParseOptionEnableScripting(false),
|
||||
// which makes <noscript> content reachable by selectors:
|
||||
//
|
||||
// doc, err := goquery.NewDocumentFromReaderWithOptions(r,
|
||||
// html.ParseOptionEnableScripting(false))
|
||||
//
|
||||
// The options apply to this parse only.
|
||||
func NewDocumentFromReaderWithOptions(r io.Reader, opts ...html.ParseOption) (*Document, error) {
|
||||
root, e := html.ParseWithOptions(r, opts...)
|
||||
if e != nil {
|
||||
return nil, e
|
||||
}
|
||||
return newDocument(root, nil), nil
|
||||
}
|
||||
|
||||
// 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.
|
||||
|
||||
Reference in new issue
Block a user