parse_songlist.go

package main

import (
	"bufio"
	"fmt"
	"net/http"
	"os"
	"strings"
	"sync"

	"golang.org/x/net/html"
)

func getMetaTags(document *html.Node) map[string]string {
	meta := map[string]string{}
	var f func(*html.Node)
	f = func(n *html.Node) {
		if n.Type == html.ElementNode && n.Data == "meta" {
			// Meta tags will have multiple attributes, name, property and content.
			var k, v string
			for _, attr := range n.Attr {
				switch attr.Key {
				case "property":
					k = attr.Val
					break
				case "content":
					v = attr.Val
					break
				}
			}

			if k == "" || v == "" {
				return
			}

			meta[k] = v
		}

		for c := n.FirstChild; c != nil; c = c.NextSibling {
			f(c)
		}
	}

	f(document)
	return meta
}

type Task struct {
	Link          string
	Title, Artist string
	Error         error
}

func startWorker(inputCh <-chan string, outputCh chan<- Task) {
	for url := range inputCh {
		task := Task{Link: url}
		resp, err := http.Get(url)
		if err != nil {
			task.Error = err
			outputCh <- task
		}

		defer resp.Body.Close()

		doc, err := html.Parse(resp.Body)
		if err != nil {
			task.Error = err
			outputCh <- task
		}

		meta := getMetaTags(doc)
		task.Title = meta["twitter:title"]
		// Spotify uses an emdot to split artist from the rest.
		task.Artist = strings.TrimSpace(strings.Split(meta["twitter:description"], "·")[0])
		outputCh <- task
	}
}

func main() {
	inputCh := make(chan string, 100)
	outputCh := make(chan Task)

	go func() {
		scanner := bufio.NewScanner(os.Stdin)
		for scanner.Scan() {
			inputCh <- scanner.Text()
		}

		close(inputCh)
	}()

	var wg sync.WaitGroup
	for i := 0; i < 100; i++ {
		wg.Add(1)
		go func() {
			startWorker(inputCh, outputCh)
			wg.Done()
		}()
	}

	go func() {
		wg.Wait()
		close(outputCh)
	}()

	for response := range outputCh {
		if response.Error != nil {
			fmt.Printf("[ERR] %s - %s", response.Link, response.Error)
			continue
		}

		fmt.Printf("%s - %s\n", response.Artist, response.Title)
	}
}