Last active
August 29, 2015 14:16
-
-
Save 7yan00/dbb8a6db45a0d086abb3 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package main | |
import ( | |
"fmt" | |
"net/url" | |
"strings" | |
"github.com/PuerkitoBio/goquery" | |
) | |
var stock = []string{} | |
var base string = "http://golang.org/" | |
func main() { | |
doc, _ := goquery.NewDocument(base) | |
var result []*url.URL | |
doc.Find("a").Each(func(_ int, s *goquery.Selection) { | |
target, _ := s.Attr("href") | |
base, _ := url.Parse(base) | |
targets, _ := url.Parse(target) | |
result = append(result, base.ResolveReference(targets)) | |
}) | |
results := GetUrl(result) | |
fmt.Println(results) | |
for len(results) > 0 { | |
results = GetUrl(results) | |
fmt.Println(results) | |
} | |
} | |
func GetUrl(urls []*url.URL) []*url.URL { | |
sorceUrl := []*url.URL{} | |
L: | |
for _, urrrl := range urls { | |
urrl := urrrl.String() | |
for e := 0; e < len(stock); e++ { | |
if urrl == stock[e] { | |
continue L | |
} | |
} | |
if !strings.Contains(urrl, base) { | |
break | |
} | |
stock = append(stock, urrl) | |
doc, _ := goquery.NewDocument(urrl) | |
var results []*url.URL | |
doc.Find("a").Each(func(_ int, s *goquery.Selection) { | |
target, _ := s.Attr("href") | |
base, _ := url.Parse(urrl) | |
targets, _ := url.Parse(target) | |
results = append(results, base.ResolveReference(targets)) | |
sorceUrl = append(sorceUrl, results...) | |
}) | |
} | |
return sorceUrl | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment