gopl.io/ch5/title3/title.go

100 lines
2.1 KiB
Go

// Copyright © 2016 Alan A. A. Donovan & Brian W. Kernighan.
// License: https://creativecommons.org/licenses/by-nc-sa/4.0/
// See page 153.
// Title3 prints the title of an HTML document specified by a URL.
package main
import (
"fmt"
"net/http"
"os"
"strings"
"golang.org/x/net/html"
)
// 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)
}
}
//!+
// soleTitle returns the text of the first non-empty title element
// in doc, and an error if there was not exactly one.
func soleTitle(doc *html.Node) (title string, err error) {
type bailout struct{}
defer func() {
switch p := recover(); p {
case nil:
// no panic
case bailout{}:
// "expected" panic
err = fmt.Errorf("multiple title elements")
default:
panic(p) // unexpected panic; carry on panicking
}
}()
// Bail out of recursion if we find more than one non-empty title.
forEachNode(doc, func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "title" &&
n.FirstChild != nil {
if title != "" {
panic(bailout{}) // multiple title elements
}
title = n.FirstChild.Data
}
}, nil)
if title == "" {
return "", fmt.Errorf("no title element")
}
return title, nil
}
//!-
func title(url string) error {
resp, err := http.Get(url)
if err != nil {
return err
}
// Check Content-Type is HTML (e.g., "text/html; charset=utf-8").
ct := resp.Header.Get("Content-Type")
if ct != "text/html" && !strings.HasPrefix(ct, "text/html;") {
resp.Body.Close()
return fmt.Errorf("%s has type %s, not text/html", url, ct)
}
doc, err := html.Parse(resp.Body)
resp.Body.Close()
if err != nil {
return fmt.Errorf("parsing %s as HTML: %v", url, err)
}
title, err := soleTitle(doc)
if err != nil {
return err
}
fmt.Println(title)
return nil
}
func main() {
for _, arg := range os.Args[1:] {
if err := title(arg); err != nil {
fmt.Fprintf(os.Stderr, "title: %v\n", err)
}
}
}