Exercise: Web Crawler

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)
}

// 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:
    type CachedData struct {
        body string
        urls []string
    }
    cached_urls_data := make(map[string]CachedData)
    var mutex sync.Mutex

    var walk func(url string, depth int, ch chan string)
    walk = func(url string, depth int, ch chan string) {
        defer close(ch)
        if depth <= 0 {
            return
        }

        var body string
        var urls []string
        var err error

        mutex.Lock()
        cached_data, was_stored := cached_urls_data[url]
        mutex.Unlock()

        if !was_stored {
            body, urls, err = fetcher.Fetch(url)
            if err != nil {
                ch <- err.Error()
                return
            }

            mutex.Lock()
            cached_urls_data[url] = CachedData{body, urls}
            mutex.Unlock()
        } else {
            urls = cached_data.urls
            body = cached_data.body
        }

        ch <- fmt.Sprintf("found: %s %q", url, body)

        results := make([]chan string, len(urls))
        for i, u := range urls {
            results[i] = make(chan string)
            go walk(u, depth-1, results[i])
        }
        for _, channel := range results {
            for res := range channel {
                ch <- res
            }
        }
    }

    ch := make(chan string)
    go walk(url, depth, ch)
    for found := range ch {
        fmt.Println(found)
    }
}

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/",
        },
    },
}