Lightweight and forgiving HTML parser and DOM.
The parser was inspired by htmlparse2 by fb55
HTML Entity parsing and decoding are both optional. The current parser interface is based on callbacks. It can also output compact HTML, and can do basic validation.
Creating the DOM from source:
auto doc = createDocument(`<html><body> </body></html>`);
writeln(doc.root.outerHTML);Creating/mutating DOM manually:
auto doc = createDocument();
doc.root.html = `<body> </body>`;
auto container = doc.createElement("div", doc.root.firstChild);
container.attr("class", "container");
container.html = "<p>moo!</p>";
auto app = appender!string;
doc.root.outerHTML(app);Compacting HTML:
auto doc = createDocument!(DOMCreateOptions.none)("<html>\n<body attr="a" attr="a b c"> abc </body>\n</html>");
writeln(doc.root.compactHTML);QuerySelector interface:
if (auto p = doc.querySelector("p:nth-of-type(2)"))
p.text = "mooo";
foreach(p; doc.querySelectorAll("p")) {
p.text = "mooo";
}Example parser usage:
auto builder = DOMBuilder();
parseHTML(`<html><body> </body></html>`, builder);Example handler:
struct DOMBuilder {
void onText(const(char)[] data) {}
void onSelfClosing() {}
void onOpenStart(const(char)[] data) {}
void onOpenEnd(const(char)[] data) {}
void onClose(const(char)[] data) {}
void onAttrName(const(char)[] data) {}
void onAttrEnd() {}
void onAttrValue(const(char)[] data) {}
void onComment(const(char)[] data) {}
void onDeclaration(const(char)[] data) {}
void onProcessingInstruction(const(char)[] data) {}
void onCDATA(const(char)[] data) {}
// the following are required if ParseEntities is set
void onNamedEntity(const(char)[] data) {}
void onNumericEntity(const(char)[] data) {}
void onHexEntity(const(char)[] data) {}
// required only if DecodeEntities is set
void onEntity(const(char)[] data, const(char)[] decoded) {}
void onDocumentEnd() {}
}- implement range-based interface for parser
- implement a basic validation mode
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent