Golang parse HTML, extract all content with tags

by

This can be solved by recursively finding the body node, using the html package, and subsequently render the html, starting from that node.

package main

import (
    "bytes"
    "errors"
    "fmt"
    "golang.org/x/net/html"
    "io"
    "strings"
)

func Body(doc *html.Node) (*html.Node, error) {
    var body *html.Node
    var crawler func(*html.Node)
    crawler = func(node *html.Node) {
        if node.Type == html.ElementNode && node.Data == "body" {
            body = node
            return
        }
        for child := node.FirstChild; child != nil; child = child.NextSibling {
            crawler(child)
        }
    }
    crawler(doc)
    if body != nil {
        return body, nil
    }
    return nil, errors.New("Missing <body> in the node tree")
}

func renderNode(n *html.Node) string {
    var buf bytes.Buffer
    w := io.Writer(&buf)
    html.Render(w, n)
    return buf.String()
}

func main() {
    doc, _ := html.Parse(strings.NewReader(htm))
    bn, err := Body(doc)
    if err != nil {
        return
    }
    body := renderNode(bn)
    fmt.Println(body)
}

const htm = `<!DOCTYPE html>
<html>
<head>
    <title></title>
</head>
<body>
    body content
    <p>more content</p>
</body>
</html>`

Leave a Comment