htmlquery
htmlquery is a Go library that allows you to parse and extract data from HTML documents using XPath expressions. It provides a simple and intuitive API for traversing and querying the HTML tree structure, and it is built on top of the popular Goquery library.
Example Use
package main
import (
"fmt"
"log"
"github.com/antchfx/htmlquery"
)
func main() {
// Parse the HTML string
doc, err := htmlquery.Parse([]byte(`
<html>
<body>
<h1>Hello, World!</h1>
<ul>
<li>Item 1</li>
<li>Item 2</li>
<li>Item 3</li>
</ul>
</body>
</html>
`))
if err != nil {
log.Fatal(err)
}
// Extract the text of the first <h1> element
h1 := htmlquery.FindOne(doc, "//h1")
fmt.Println(htmlquery.InnerText(h1)) // "Hello, World!"
// Extract the text of all <li> elements
lis := htmlquery.Find(doc, "//li")
for _, li := range lis {
fmt.Println(htmlquery.InnerText(li))
}
// "Item 1"
// "Item 2"
// "Item 3"
}