بناء زاحف الويب باستخدام Go لاكتشاف العناوين المكررة

go get golang.org/x/net...

package html
type Node struct {
Type                    NodeType
Data                    string
Attr                    []Attribute
FirstChild, NextSibling *node
}
type NodeType int32
const (
ErrorNode NodeType = iota
TextNode
DocumentNode
ElementNode
CommentNode
DoctypeNode
)
type Attribute struct {
Key, Val string
}
func Parse(r io.Reader) (*Node, error)

http://localhost:1313/go-filesystem-structure/ -> Filesystem Structure of a Go project
http://localhost:1313/golang-measure-time/ -> Measuring execution time in a Go program
http://localhost:1313/go-tutorial-fortune/ -> Go CLI tutorial: fortune clone
http://localhost:1313/go-tutorial-lolcat/ -> Build a Command Line app with Go: lolcat

// analyze given a url and a basurl, recoursively scans the page
// following all the links and fills the `visited` map
func analyze(url, baseurl string, visited *map[string]string) {
	page, err := parse(url)
	if err != nil {
		fmt.Printf("Error getting page %s %s\n", url, err)
		return
	}
	title := pageTitle(page)
	(*visited)[url] = title
<span style="color:#75715e">//recursively find links
	links := pageLinks(nil, page)
for _, link := range links {
if (*visited)[link] == “” && strings.HasPrefix(link, baseurl) {
analyze(link, baseurl, visited)
}
}
}

// pageTitle given a reference to a html.Node, scans it until it
// finds the title tag, and returns its value
func pageTitle(n *html.Node) string {
	var title string
	if n.Type == html.ElementNode && n.Data == "title" {
		return n.FirstChild.Data
	}
	for c := n.FirstChild; c != nil; c = c.NextSibling {
		title = pageTitle(c)
		if title != "" {
			break
		}
	}
	return title
}

// pageLinks will recursively scan a `html.Node` and will return
// a list of links found, with no duplicates
func pageLinks(links []string, n *html.Node) []string {
	if n.Type == html.ElementNode && n.Data == "a" {
		for _, a := range n.Attr {
			if a.Key == "href" {
				if !sliceContains(links, a.Val) {
					links = append(links, a.Val)
				}
			}
		}
	}
	for c := n.FirstChild; c != nil; c = c.NextSibling {
		links = pageLinks(links, c)
	}
	return links
}

// sliceContains returns true if `slice` contains `value`
func sliceContains(slice []string, value string) bool {
	for _, v := range slice {
		if v == value {
			return true
		}
	}
	return false
}

// parse given a string pointing to a URL will fetch and parse it
// returning an html.Node pointer
func parse(url string) (*html.Node, error) {
	r, err := http.Get(url)
	if err != nil {
		return nil, fmt.Errorf("Cannot get page")
	}
	b, err := html.Parse(r.Body)
	if err != nil {
		return nil, fmt.Errorf("Cannot parse page")
	}
	return b, err
}

import (
	"flag"
//...
)
func main() {
var url string
var dup bool
flag.StringVar(&url, “url”, “”, “the url to parse”)
flag.BoolVar(&dup, “dup”, false, “if set, check for duplicates”)
flag.Parse()
<span style="color:#66d9ef">if</span> <span style="color:#a6e22e">url</span> <span style="color:#f92672">==</span> <span style="color:#e6db74">""</span> {
	<span style="color:#a6e22e">flag</span>.<span style="color:#a6e22e">PrintDefaults</span>()
	<span style="color:#a6e22e">os</span>.<span style="color:#a6e22e">Exit</span>(<span style="color:#ae81ff">1</span>)
}

<span style="color:#a6e22e">visited</span> <span style="color:#f92672">:=</span> <span style="color:#66d9ef">map</span>[<span style="color:#66d9ef">string</span>]<span style="color:#66d9ef">string</span>{}
<span style="color:#a6e22e">analyze</span>(<span style="color:#a6e22e">url</span>, <span style="color:#a6e22e">url</span>, <span style="color:#f92672">&amp;</span><span style="color:#a6e22e">visited</span>)
<span style="color:#66d9ef">for</span> <span style="color:#a6e22e">link</span>, <span style="color:#a6e22e">title</span> <span style="color:#f92672">:=</span> <span style="color:#66d9ef">range</span> <span style="color:#a6e22e">visited</span> {
	<span style="color:#a6e22e">fmt</span>.<span style="color:#a6e22e">Printf</span>(<span style="color:#e6db74">"%s -&gt; %s\n"</span>, <span style="color:#a6e22e">link</span>, <span style="color:#a6e22e">title</span>)
}

<span style="color:#66d9ef">if</span> <span style="color:#a6e22e">dup</span> {
	<span style="color:#a6e22e">checkDuplicates</span>(<span style="color:#f92672">&amp;</span><span style="color:#a6e22e">visited</span>)
}
}

// checkDuplicates scans the visited map for pages with duplicate titles
// and writes a report
func checkDuplicates(visited *map[string]string) {
	found := false
	uniques := map[string]string{}
	fmt.Printf("\nChecking duplicates..\n")
	for link, title := range *visited {
		if uniques[title] == "" {
			uniques[title] = link
		} else {
			found = true
			fmt.Printf("Duplicate title \"%s\" in %s but already found in %s\n", title, link, uniques[title])
		}
	}
<span style="color:#66d9ef">if</span> !<span style="color:#a6e22e">found</span> {
	<span style="color:#a6e22e">fmt</span>.<span style="color:#a6e22e">Println</span>(<span style="color:#e6db74">"No duplicates were found 😇"</span>)
}
}