Last active
August 30, 2021 05:47
-
-
Save Version2beta/190378e9dd41642dd911b8e112b05700 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" | |
"math/rand" | |
"sync" | |
"time" | |
) | |
const logging = true | |
type Fetcher interface { | |
Fetch(url string) (body string, urls []string, err error) | |
} | |
type Fetched struct { | |
Pages map[string]string | |
Broken map[string]error | |
Fetcher Fetcher | |
mu sync.Mutex | |
numCrawlers int | |
maxConcurrency int | |
} | |
func log(s string) { | |
if logging { | |
println(s) | |
} | |
} | |
func (f *Fetched) Inc() int { | |
f.mu.Lock() | |
f.numCrawlers++ | |
if f.numCrawlers > f.maxConcurrency { | |
f.maxConcurrency = f.numCrawlers | |
} | |
f.mu.Unlock() | |
return f.numCrawlers | |
} | |
func (f *Fetched) Dec() int { | |
f.mu.Lock() | |
f.numCrawlers-- | |
f.mu.Unlock() | |
return f.numCrawlers | |
} | |
func (f *Fetched) Update(url string, body string, err error) { | |
f.mu.Lock() | |
if body != "" { | |
f.Pages[url] = body | |
} else { | |
f.Broken[url] = err | |
} | |
f.mu.Unlock() | |
return | |
} | |
func (f *Fetched) Fetch(url string, depth int) { | |
myCrawlerNum := f.Inc() | |
defer f.Dec() | |
_, exists := f.Pages[url] | |
if exists { | |
log(fmt.Sprintf("[%v] Skipped %s", myCrawlerNum, url)) | |
} else { | |
body, urls, err := f.Fetcher.Fetch(url) | |
f.Update(url, body, err) | |
for _, u := range urls { | |
go f.Fetch(u, depth-1) | |
} | |
log(fmt.Sprintf("[%v] Fetched %s", myCrawlerNum, url)) | |
} | |
return | |
} | |
func (f *Fetched) Report() { | |
fmt.Println("\n# Found:") | |
for k, v := range f.Pages { | |
fmt.Printf("- %s: %s\n", k, v) | |
} | |
fmt.Println("\n# Not found:") | |
for k, v := range f.Broken { | |
fmt.Printf("- %s: %s\n", k, v) | |
} | |
fmt.Printf("\nConcurrency: %v", f.maxConcurrency) | |
return | |
} | |
func Crawl(url string, depth int, fetcher Fetcher) { | |
f := &Fetched{ | |
Fetcher: fetcher, | |
Pages: make(map[string]string), | |
Broken: make(map[string]error), | |
} | |
go f.Fetch(url, depth) | |
for f.numCrawlers > 0 || f.maxConcurrency == 0 { | |
time.Sleep(250 * time.Millisecond) | |
} | |
f.Report() | |
return | |
} | |
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) { | |
time.Sleep(time.Duration(rand.Intn(100)+80) * time.Millisecond) | |
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