Created
July 21, 2021 17:50
-
-
Save sbuckle/577852a3b7b197029cabb1bdf2b3281b to your computer and use it in GitHub Desktop.
Exercise: Web Crawler 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" | |
| ) | |
| 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.RWMutex | |
| v map[string]bool | |
| } | |
| func (c *Cache) Set(url string) { | |
| c.mu.Lock() | |
| c.v[url] = true | |
| c.mu.Unlock() | |
| } | |
| func (c *Cache) Get(url string) bool { | |
| c.mu.RLock() | |
| defer c.mu.RUnlock() | |
| return c.v[url] | |
| } | |
| var cache = newCache() | |
| // Crawl uses fetcher to recursively crawl | |
| // pages starting with url, to a maximum of depth. | |
| func Crawl(url string, depth int, fetcher Fetcher) { | |
| if depth <= 0 { | |
| return | |
| } | |
| if cache.Get(url) { | |
| return | |
| } | |
| body, urls, err := fetcher.Fetch(url) | |
| if err != nil { | |
| fmt.Println(err) | |
| return | |
| } | |
| fmt.Printf("found: %s %q\n", url, body) | |
| cache.Set(url) | |
| var wg sync.WaitGroup | |
| for _, u := range urls { | |
| wg.Add(1) | |
| go func(url string) { | |
| Crawl(url, depth-1, fetcher) | |
| wg.Done() | |
| }(u) | |
| } | |
| wg.Wait() | |
| return | |
| } | |
| func newCache() Cache { | |
| return Cache{ | |
| v: make(map[string]bool), | |
| } | |
| } | |
| func main() { | |
| Crawl("https://golang.org/", 4, fetcher) | |
| } | |
| // 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