Skip to content

xpathvshtmlquery

MIT 13 2 699
58.1 thousand (month) Jun 08 2019 v1.3.3(8 months ago)
760 1 8 MIT
Feb 07 2019 58.1 thousand (month) v1.3.4(8 months ago)

xpath is a library for Go that allows you to use XPath expressions to select elements from an HTML document. It is built on top of the html package in the Go standard library, and provides a way to select elements from an HTML document using XPath expressions, which are more powerful and expressive than CSS selectors.

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"
  "github.com/antchfx/xpath"
  "golang.org/x/net/html"
  "strings"
)

func main() {
  // Create an HTML string
  html := `<html>
        <body>
          <div id="content">
            <p>Hello, World!</p>
            <a href="http://example.com">Example</a>
          </div>
        </body>
      </html>`

  // Parse the HTML string into a node tree
  doc, err := html.Parse(strings.NewReader(html))
  if err != nil {
    fmt.Println("Error:", err)
    return
  }

  // Compile the XPath expression
  expr, err := xpath.Compile("//p")
  if err != nil {
    fmt.Println("Error:", err)
    return
  }

  // Use the Evaluate method to select elements from the document
  nodes, err := expr.Evaluate(xpath.NodeNavigator(doc))
  if err != nil {
    fmt.Println("Error:", err)
    return
  }
  if nodes.MoveNext() {
    fmt.Println(nodes.Current().Value())
    // > Hello, World!
  }
}
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"
}

Alternatives / Similar


Was this page helpful?