Skip to content

Instantly share code, notes, and snippets.

@nmiano1111
Last active October 22, 2016 18:12
Show Gist options
  • Select an option

  • Save nmiano1111/6e11f966a994622c0fb79df89f349aed to your computer and use it in GitHub Desktop.

Select an option

Save nmiano1111/6e11f966a994622c0fb79df89f349aed to your computer and use it in GitHub Desktop.
package main
import (
"fmt"
"sync"
)
type Fetcher interface {
// Fetch returns the body of URL and
// a slice of URLs found on that page.
Fetch(url string) (body string, urls []string, err error)
}
var used = make(map[string]int)
var mux = sync.Mutex{}
// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func Crawl(url string, depth int, fetcher Fetcher, c chan string) {
defer close(c)
if depth <= 0 {
return
}
body, urls, err := fetcher.Fetch(url)
if err != nil {
fmt.Println(err)
return
}
if used[url] == 0 {
mux.Lock()
used[url]++
mux.Unlock()
c <- fmt.Sprintf("found: %s %q\n", url, body)
}
rs := make([]chan string, len(urls))
for i, u := range urls {
rs[i] = make(chan string)
go Crawl(u, depth-1, fetcher, rs[i])
}
for i := range rs {
for s := range rs[i] {
c <- s
}
}
return
}
func main() {
ch := make(chan string)
go Crawl("http://golang.org/", 4, fetcher, ch)
for r := range ch {
fmt.Print(r)
}
}
// fakeFetcher is Fetcher that returns canned results.
type fakeFetcher map[string]*fakeResult
type fakeResult struct {
body string
urls []string
}
func (f fakeFetcher) Fetch(url string) (string, []string, error) {
if res, ok := f[url]; ok {
return res.body, res.urls, nil
}
return "", nil, fmt.Errorf("not found: %s", url)
}
// fetcher is a populated fakeFetcher.
var fetcher = fakeFetcher{
"http://golang.org/": &fakeResult{
"The Go Programming Language",
[]string{
"http://golang.org/pkg/",
"http://golang.org/cmd/",
},
},
"http://golang.org/pkg/": &fakeResult{
"Packages",
[]string{
"http://golang.org/",
"http://golang.org/cmd/",
"http://golang.org/pkg/fmt/",
"http://golang.org/pkg/os/",
},
},
"http://golang.org/pkg/fmt/": &fakeResult{
"Package fmt",
[]string{
"http://golang.org/",
"http://golang.org/pkg/",
},
},
"http://golang.org/pkg/os/": &fakeResult{
"Package os",
[]string{
"http://golang.org/",
"http://golang.org/pkg/",
},
},
}
@nmiano1111
Copy link
Author

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment