initial commit: collect the book info

Signed-off-by: Vincent Batts <vbatts@hashbangbash.com>

go.mod

@@ -0,0 +1,5 @@
+module git.thisco.de/vbatts/book-fetch
+
+go 1.16
+
+require github.com/PuerkitoBio/goquery v1.6.1

go.sum

@@ -0,0 +1,10 @@
+github.com/PuerkitoBio/goquery v1.6.1 h1:FgjbQZKl5HTmcn4sKBgvx8vv63nhyhIpv7lJpFGCWpk=
+github.com/PuerkitoBio/goquery v1.6.1/go.mod h1:GsLWisAFVj4WgDibEWF4pvYnkVQBpKBKeU+7zCJoLcc=
+github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo=
+github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20200202094626-16171245cfb2 h1:CCH4IOTTfewWjGOlSp+zGcjutRKlBEZQ6wTn8ozI/nI=
+golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=

main.go

@@ -0,0 +1,61 @@
+package main
+
+import (
+	"fmt"
+	"log"
+	"net/http"
+	"strings"
+
+	"github.com/PuerkitoBio/goquery"
+)
+
+type Book struct {
+	URL   string
+	Title string
+	Files []string
+}
+
+func BookScrape(bookURL string) (*Book, error) {
+	// Request the HTML page.
+	res, err := http.Get(bookURL)
+	if err != nil {
+		return nil, err
+	}
+	defer res.Body.Close()
+	if res.StatusCode != 200 {
+		return nil, fmt.Errorf("status code error: %d %s", res.StatusCode, res.Status)
+	}
+
+	// Load the HTML document
+	doc, err := goquery.NewDocumentFromReader(res.Body)
+	if err != nil {
+		return nil, err
+	}
+	/*
+		<audio class="wp-audio-shortcode" id="audio-24287-11" preload="none" style="width: 100%;" controls="controls"><source class="lazy lazy-hidden" type="audio/mpeg" src="https://ipaudio.club/wp-content/uploads/GOLN/Water%20Dancer%20(Ta%20Nehisi%20Coates)/11.mp3?_=11" /><a href="https://ipaudio.club/wp-content/uploads/GOLN/Water%20Dancer%20(Ta%20Nehisi%20Coates)/11.mp3">https://ipaudio.club/wp-content/uploads/GOLN/Water%20Dancer%20(Ta%20Nehisi%20Coates)/11.mp3</a></audio>
+	*/
+
+	b := Book{}
+	b.URL = bookURL
+
+	// Find the review items
+	doc.Find(".lazy-hidden").Each(func(i int, s *goquery.Selection) {
+		//title := s.Find("source").Text()
+		if src, exists := s.Attr("src"); exists && strings.Contains(src, ".mp3") {
+			fmt.Println(i, src)
+			b.Files = append(b.Files, src)
+		}
+	})
+	doc.Find("title").Each(func(i int, s *goquery.Selection) {
+		b.Title = s.Text()
+	})
+	return &b, nil
+}
+
+func main() {
+	b, err := BookScrape("https://goldenaudiobooks.com/the-water-dancer-oprahs-book-club-audiobook/")
+	if err != nil {
+		log.Fatal(err)
+	}
+	fmt.Println(b)
+}