Skip to content

cascadiavshtmlquery

BSD-2-Clause 2 1 698
58.1 thousand (month) Feb 20 2018 Start(6 years ago)
739 1 8 MIT
Feb 07 2019 58.1 thousand (month) v1.3.3(20 days ago)

cascadia is a library for Go that provides a CSS selector engine, allowing you to use CSS selectors to select elements from an HTML document.

It is built on top of the html package in the Go standard library, and provides a more efficient and powerful way to select elements from an HTML document.

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/andybalholm/cascadia"
  "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 CSS selector
  sel, err := cascadia.Compile("p")
  if err != nil {
    fmt.Println("Error:", err)
    return
  }

  // Use the Selector.Match method to select elements from the document
  matches := sel.Match(doc)
  if len(matches) > 0 {
    fmt.Println(matches[0].FirstChild.Data)
    // > 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?