Last active
December 10, 2017 12:37
-
-
Save reiinakano/5d71df8770a0c1d41b9e21e5e20a992a to your computer and use it in GitHub Desktop.
Quick solution to A Tour of Go Web Crawler Exercise https://tour.golang.org/concurrency/10
This file contains hidden or 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" | |
| "time" | |
| ) | |
| 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) | |
| } | |
| type SafeCache struct { | |
| entry map[string]int | |
| mux sync.Mutex | |
| } | |
| func (c *SafeCache) inCache(url string) bool { | |
| c.mux.Lock() | |
| _, ok := c.entry[url] | |
| c.mux.Unlock() | |
| return ok | |
| } | |
| func (c *SafeCache) addCache(url string) { | |
| c.mux.Lock() | |
| c.entry[url] = 1 | |
| c.mux.Unlock() | |
| } | |
| // Crawl uses fetcher to recursively crawl | |
| // pages starting with url, to a maximum of depth. | |
| func Crawl(url string, depth int, fetcher Fetcher, c SafeCache) { | |
| // TODO: Fetch URLs in parallel. | |
| // This implementation doesn't do either: | |
| if depth <= 0 { | |
| return | |
| } | |
| if c.inCache(url) { | |
| return | |
| } | |
| c.addCache(url) | |
| body, urls, err := fetcher.Fetch(url) | |
| if err != nil { | |
| fmt.Println(err) | |
| return | |
| } | |
| fmt.Printf("found: %s %q\n", url, body) | |
| for _, u := range urls { | |
| go Crawl(u, depth-1, fetcher, c) | |
| } | |
| return | |
| } | |
| func main() { | |
| c := SafeCache{entry: make(map[string]int)} | |
| Crawl("http://golang.org/", 4, fetcher, c) | |
| time.Sleep(time.Second) // Not best way to wait for crawling to finish. | |
| } | |
| // 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/", | |
| }, | |
| }, | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment