Skip to content

htmlqueryvschopper

MIT 8 1 693
58.1 thousand (month) Feb 07 2019 v1.3.0(1 year, 2 months ago)
22 3 1 MIT
0.6.0(11 months ago) Jul 24 2014 820 (month)

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.

Chopper is a tool to extract elements from HTML by preserving ancestors and CSS rules.

Compared to other HTML parsers Chopper is designed to retain original HTML tree but eliminate elements that do not match parsing rules. Meaning, we can parse HTML elements and keep thei structure for machine learning or other tasks where data structure is needed as well as the data value.

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"
}
HTML = """
<html>
  <head>
    <title>Test</title>
  </head>
  <body>
    <div id="header"></div>
    <div id="main">
      <div class="iwantthis">
        HELLO WORLD
        <a href="/nope">Do not want</a>
      </div>
    </div>
    <div id="footer"></div>
  </body>
</html>
"""

CSS = """
div { border: 1px solid black; }
div#main { color: blue; }
div.iwantthis { background-color: red; }
a { color: green; }
div#footer { border-top: 2px solid red; }
"""

extractor = Extractor.keep('//div[@class="iwantthis"]').discard('//a')
html, css = extractor.extract(HTML, CSS)

# will result in:
html
"""
<html>
  <body>
    <div id="main">
      <div class="iwantthis">
        HELLO WORLD
      </div>
    </div>
  </body>
</html>"""

css
"""
div{border:1px solid black;}
div#main{color:blue;}
div.iwantthis{background-color:red;}
"""

Alternatives / Similar