golang抓取网页并分析页面包含的链接方法

git clone https://github.com/golang/net

package main
 
import (
 "os"
 "net/http"
 "fmt"
 "io/ioutil"
)
 
func main() {
 for _, url := range os.Args[1:] {
 resp, err := http.Get(url)
 if err != nil {
  fmt.Fprintf(os.Stderr, "fetch: %v\n", err)
 }
 b, err := ioutil.ReadAll(resp.Body)
 resp.Body.Close()
 if err != nil {
  fmt.Fprintf(os.Stderr, "fetch: reading %s: %v\n", url, err)
  os.Exit(1)
 }
 fmt.Printf("%s",b)
 }
}

go build test.com\justin\demo\fetch

package main
 
import (
 "os"
 "fmt"
 "golang.org/x/net/html"
)
 
func main() {
 doc, err := html.Parse(os.Stdin)
 if err != nil {
 fmt.Fprint(os.Stderr, "findlinks: %v\n", err)
 os.Exit(1)
 }
 for _, link := range visit(nil, doc) {
 fmt.Println(link)
 }
}
 
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
}

go build test.com\justin\demo\findlinks

fetch.exe https://www.qq.com | findlinks.exe