gopl-zh.github.com/vendor/gopl.io/ch5/links/links.go

68 lines
1.4 KiB
Go
Raw Normal View History

2015-12-09 07:57:17 +00:00
// Copyright © 2016 Alan A. A. Donovan & Brian W. Kernighan.
// License: https://creativecommons.org/licenses/by-nc-sa/4.0/
// See page 138.
//!+Extract
// Package links provides a link-extraction function.
package links
import (
"fmt"
"net/http"
"golang.org/x/net/html"
)
// Extract makes an HTTP GET request to the specified URL, parses
// the response as HTML, and returns the links in the HTML document.
func Extract(url string) ([]string, error) {
resp, err := http.Get(url)
if err != nil {
return nil, err
}
if resp.StatusCode != http.StatusOK {
resp.Body.Close()
return nil, fmt.Errorf("getting %s: %s", url, resp.Status)
}
doc, err := html.Parse(resp.Body)
resp.Body.Close()
if err != nil {
return nil, fmt.Errorf("parsing %s as HTML: %v", url, err)
}
var links []string
visitNode := func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "a" {
for _, a := range n.Attr {
if a.Key != "href" {
continue
}
link, err := resp.Request.URL.Parse(a.Val)
if err != nil {
continue // ignore bad URLs
}
links = append(links, link.String())
}
}
}
forEachNode(doc, visitNode, nil)
return links, nil
}
//!-Extract
// Copied from gopl.io/ch5/outline2.
func forEachNode(n *html.Node, pre, post func(n *html.Node)) {
if pre != nil {
pre(n)
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
forEachNode(c, pre, post)
}
if post != nil {
post(n)
}
}