Created
May 2, 2019 10:48
-
-
Save tai2/b67cfa0b61ab6b468981c277a6c87078 to your computer and use it in GitHub Desktop.
Exercise: Web Crawler https://tour.golang.org/concurrency/10
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" | |
"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 mux sync.Mutex | |
type UrlLocks map[string]*sync.Mutex | |
func (locks UrlLocks) Lock(url string) (first bool){ | |
mux.Lock() | |
defer mux.Unlock() | |
lock, ok := locks[url] | |
if ok { | |
first = false | |
} else { | |
first = true | |
lock = &sync.Mutex{} | |
locks[url] = lock | |
} | |
lock.Lock() | |
return | |
} | |
func (locks UrlLocks) Unlock(url string) { | |
mux.Lock() | |
defer mux.Unlock() | |
lock := locks[url] | |
lock.Unlock() | |
} | |
var urlLocks UrlLocks = UrlLocks{} | |
func terminate(quit chan int) { | |
quit <- 0 | |
} | |
// Crawl uses fetcher to recursively crawl | |
// pages starting with url, to a maximum of depth. | |
func Crawl(url string, depth int, fetcher Fetcher, quit chan int) { | |
defer terminate(quit) | |
if depth <= 0 { | |
return | |
} | |
first := urlLocks.Lock(url) | |
if !first { | |
urlLocks.Unlock(url) | |
return | |
} | |
body, urls, err := fetcher.Fetch(url) | |
if err != nil { | |
fmt.Println(err) | |
urlLocks.Unlock(url) | |
return | |
} | |
fmt.Printf("found: %s %q %v\n", url, body, urls) | |
urlLocks.Unlock(url) | |
quits := make([](chan int), len(urls)) | |
for i, u := range urls { | |
quits[i] = make(chan int) | |
go Crawl(u, depth-1, fetcher, quits[i]) | |
} | |
for i := 0; i < len(urls); i++ { | |
<- quits[i] | |
} | |
} | |
func main() { | |
quit := make(chan int) | |
go Crawl("https://golang.org/", 4, fetcher, quit) | |
<- quit | |
} | |
// 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{ | |
"https://golang.org/": &fakeResult{ | |
"The Go Programming Language", | |
[]string{ | |
"https://golang.org/pkg/", | |
"https://golang.org/cmd/", | |
}, | |
}, | |
"https://golang.org/pkg/": &fakeResult{ | |
"Packages", | |
[]string{ | |
"https://golang.org/", | |
"https://golang.org/cmd/", | |
"https://golang.org/pkg/fmt/", | |
"https://golang.org/pkg/os/", | |
}, | |
}, | |
"https://golang.org/pkg/fmt/": &fakeResult{ | |
"Package fmt", | |
[]string{ | |
"https://golang.org/", | |
"https://golang.org/pkg/", | |
}, | |
}, | |
"https://golang.org/pkg/os/": &fakeResult{ | |
"Package os", | |
[]string{ | |
"https://golang.org/", | |
"https://golang.org/pkg/", | |
}, | |
}, | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment