Webcrawler in Go

Question

I\'m trying to build a web crawler in Go where I would like to specify the max number of concurrent workers. They will all be working as long as there are link to explore in

Answer 1

I wrote a solution utilizing the mutual exclusion (Mutex) function of Go.

When it runs on the concurrency, it may be important to restrict only one instance access the url map at a time. I believe I implemented it as written below. Please feel free to try this out. I would appreciate your feedback as I will be learn from your comments as well.

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)
}




// ! SafeUrlBook helps restrict only one instance access the central url map at a time. So that no redundant crawling should occur.
type SafeUrlBook struct {
    book map[string]bool
    mux  sync.Mutex
    }

func (sub *SafeUrlBook) doesThisExist(url string) bool {
    sub.mux.Lock()
    _ , key_exists := sub.book[url]
    defer sub.mux.Unlock()
    
    if key_exists {
    return true
    }  else { 
    sub.book[url] = true
    return false 
    }  
}
// End SafeUrlBook


// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
// Note that now I use safeBook (SafeUrlBook) to keep track of which url has been visited by a crawler.
func Crawl(url string, depth int, fetcher Fetcher, safeBook SafeUrlBook) {
    if depth <= 0 {
        return
    }
    
    
    exist := safeBook.doesThisExist(url)
    if exist { fmt.Println("Skip", url) ; return }
    
    
    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 {
        Crawl(u, depth-1, fetcher, safeBook)
    }
    return
}

func main() {
    safeBook := SafeUrlBook{book: make(map[string]bool)}
    Crawl("https://golang.org/", 4, fetcher, safeBook)
}

// 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/",
        },
    },
}