Last active
January 31, 2020 18:56
-
-
Save liyzcj/40cd4cf14962dbb6bb03e05914863227 to your computer and use it in GitHub Desktop.
A Tour of Go: Exercise: Web Crawler
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" | |
| // "time" | |
| ) | |
| const fetching = "fetching" | |
| 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 Cache struct { | |
| mu sync.Mutex | |
| v map[string]bool | |
| } | |
| var cache = &Cache{v: make(map[string]bool)} | |
| var wg sync.WaitGroup | |
| func (ch *Cache) CheckIfFetched(url string) bool { | |
| ch.mu.Lock() | |
| defer ch.mu.Unlock() | |
| _, ok := ch.v[url] | |
| if ok == false { | |
| ch.v[url] = true | |
| return false | |
| } | |
| return true | |
| } | |
| // Crawl uses fetcher to recursively crawl | |
| // pages starting with url, to a maximum of depth. | |
| func Crawl(url string, depth int, fetcher Fetcher) { | |
| // TODO: Fetch URLs in parallel. | |
| // TODO: Don't fetch the same URL twice. | |
| // This implementation doesn't do either: | |
| if depth <= 0 { | |
| wg.Done() | |
| return | |
| } | |
| if cache.CheckIfFetched(url) { | |
| wg.Done() | |
| return | |
| } | |
| body, urls, err := fetcher.Fetch(url) | |
| if err != nil { | |
| fmt.Println(err) | |
| wg.Done() | |
| return | |
| } | |
| fmt.Printf("found: %s %q\n", url, body) | |
| for _, u := range urls { | |
| wg.Add(1) | |
| go Crawl(u, depth-1, fetcher) | |
| } | |
| wg.Done() | |
| return | |
| } | |
| func main() { | |
| wg.Add(1) | |
| go Crawl("https://golang.org/", 4, fetcher) | |
| wg.Wait() | |
| // time.Sleep(time.Second) | |
| } | |
| // 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