parse.go

package main

import (
	"fmt"
	"os"

	"golang.org/x/net/html"
)

// WEB Scraping com Go!

func main() {
	// res, err := http.Get("https://www.google.com/")
	// if err != nil {
	// 	log.Fatal(err)
	// }
	// defer res.Body.Close()

	// input := res.Body
	input, _ := os.Open("index.html")

	node, _ := html.Parse(input)

	var acessa func(*html.Node)
	acessa = func(n *html.Node) {

		if n.Type == html.ElementNode && n.Data == "a" {
			// lê o conteúdo da tag atual
			fmt.Print(n.FirstChild.Data + " -> ")
			for _, a := range n.Attr {
				if a.Key == "href" {
					fmt.Println(a.Val)
				}
			}
		}

		for next := n.FirstChild; next != nil; next = next.NextSibling {
			acessa(next)
		}
	}

	acessa(node)
}