mirror of
https://github.com/gopl-zh/gopl-zh.github.com.git
synced 2024-11-28 09:09:07 +00:00
70 lines
1.5 KiB
Go
70 lines
1.5 KiB
Go
// Copyright © 2016 Alan A. A. Donovan & Brian W. Kernighan.
|
|
// License: https://creativecommons.org/licenses/by-nc-sa/4.0/
|
|
|
|
// See page 125.
|
|
|
|
// Findlinks2 does an HTTP GET on each URL, parses the
|
|
// result as HTML, and prints the links within it.
|
|
//
|
|
// Usage:
|
|
// findlinks url ...
|
|
package main
|
|
|
|
import (
|
|
"fmt"
|
|
"net/http"
|
|
"os"
|
|
|
|
"golang.org/x/net/html"
|
|
)
|
|
|
|
// visit appends to links each link found in n, and returns the result.
|
|
func visit(links []string, n *html.Node) []string {
|
|
if n.Type == html.ElementNode && n.Data == "a" {
|
|
for _, a := range n.Attr {
|
|
if a.Key == "href" {
|
|
links = append(links, a.Val)
|
|
}
|
|
}
|
|
}
|
|
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
|
links = visit(links, c)
|
|
}
|
|
return links
|
|
}
|
|
|
|
//!+
|
|
func main() {
|
|
for _, url := range os.Args[1:] {
|
|
links, err := findLinks(url)
|
|
if err != nil {
|
|
fmt.Fprintf(os.Stderr, "findlinks2: %v\n", err)
|
|
continue
|
|
}
|
|
for _, link := range links {
|
|
fmt.Println(link)
|
|
}
|
|
}
|
|
}
|
|
|
|
// findLinks performs an HTTP GET request for url, parses the
|
|
// response as HTML, and extracts and returns the links.
|
|
func findLinks(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)
|
|
}
|
|
return visit(nil, doc), nil
|
|
}
|
|
|
|
//!-
|