Fix/IMDB and comando-filmes date detection (#26)

* chg: fix: data and imdb detection * chg: fix: improve IMDB detection * chg: feat: add more audio strings
2024-12-13 12:45:17 -03:00
parent 88d6d506bf
commit dc3cb3be92
5 changed files with 174 additions and 26 deletions
--- a/api/bludv.go
+++ b/api/bludv.go
@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"net/http"
 	"net/url"
-	"regexp"
 	"slices"
 	"strings"
 	"time"
@@ -187,10 +186,9 @@ func getTorrentsBluDV(ctx context.Context, i *Indexer, link string) ([]schema.In
 	imdbLink := ""
 	article.Find("div.content a").Each(func(i int, s *goquery.Selection) {
 		link, _ := s.Attr("href")
-		re := regexp.MustCompile(`https://www.imdb.com/title/(tt\d+)`)
-		matches := re.FindStringSubmatch(link)
-		if len(matches) > 0 {
-			imdbLink = matches[0]
+		_imdbLink, err := getIMDBLink(link)
+		if err == nil {
+			imdbLink = _imdbLink
 		}
 	})

--- a/api/comando_torrents.go
+++ b/api/comando_torrents.go
@@ -163,19 +163,11 @@ func getTorrents(ctx context.Context, i *Indexer, link string) ([]schema.Indexed
 	// div itemprop="datePublished"
 	datePublished := strings.TrimSpace(article.Find("div[itemprop=\"datePublished\"]").Text())
 	// pattern: 10 de setembro de 2021
-	re := regexp.MustCompile(`(\d{2}) de (\w+) de (\d{4})`)
-	matches := re.FindStringSubmatch(datePublished)
-	var date time.Time
-	if len(matches) > 0 {
-		day := matches[1]
-		month := matches[2]
-		year := matches[3]
-		datePublished = fmt.Sprintf("%s-%s-%s", year, replacer.Replace(month), day)
-		date, err = time.Parse("2006-01-02", datePublished)
-		if err != nil {
-			return nil, err
-		}
+	date, err := parseLocalizedDate(datePublished)
+	if err != nil {
+		return nil, err
 	}
+
 	magnets := textContent.Find("a[href^=\"magnet\"]")
 	var magnetLinks []string
 	magnets.Each(func(i int, s *goquery.Selection) {
@@ -217,10 +209,9 @@ func getTorrents(ctx context.Context, i *Indexer, link string) ([]schema.Indexed
 	imdbLink := ""
 	article.Find("a").Each(func(i int, s *goquery.Selection) {
 		link, _ := s.Attr("href")
-		re := regexp.MustCompile(`https://www.imdb.com/title/(tt\d+)`)
-		matches := re.FindStringSubmatch(link)
-		if len(matches) > 0 {
-			imdbLink = matches[0]
+		_imdbLink, err := getIMDBLink(link)
+		if err == nil {
+			imdbLink = _imdbLink
 		}
 	})

@@ -293,6 +284,40 @@ func getTorrents(ctx context.Context, i *Indexer, link string) ([]schema.Indexed
 	return indexedTorrents, nil
 }

+func getIMDBLink(link string) (string, error) {
+	var imdbLink string
+	re := regexp.MustCompile(`https://www.imdb.com(/[a-z]{2})?/title/(tt\d+)/?`)
+
+	matches := re.FindStringSubmatch(link)
+	if len(matches) > 0 {
+		imdbLink = matches[0]
+	} else {
+		return "", fmt.Errorf("no imdb link found")
+	}
+	return imdbLink, nil
+}
+
+func parseLocalizedDate(datePublished string) (time.Time, error) {
+	re := regexp.MustCompile(`(\d{1,2}) de (\w+) de (\d{4})`)
+	matches := re.FindStringSubmatch(datePublished)
+	if len(matches) > 0 {
+		day := matches[1]
+		// append 0 to single digit day
+		if len(day) == 1 {
+			day = fmt.Sprintf("0%s", day)
+		}
+		month := matches[2]
+		year := matches[3]
+		datePublished = fmt.Sprintf("%s-%s-%s", year, replacer.Replace(month), day)
+		date, err := time.Parse("2006-01-02", datePublished)
+		if err != nil {
+			return time.Time{}, err
+		}
+		return date, nil
+	}
+	return time.Time{}, nil
+}
+
 func stableUniq(s []string) []string {
 	var uniq []map[string]interface{}
 	m := make(map[string]map[string]interface{})
--- a/api/comando_torrents_test.go
+++ b/api/comando_torrents_test.go
@@ -3,6 +3,7 @@ package handler
 import (
 	"reflect"
 	"testing"
+	"time"

 	"github.com/felipemarinho97/torrent-indexer/schema"
 )
@@ -77,3 +78,115 @@ Servidor Via: Torrent
 		})
 	}
 }
+
+func Test_parseLocalizedDate(t *testing.T) {
+	type args struct {
+		datePublished string
+	}
+	tests := []struct {
+		name    string
+		args    args
+		want    time.Time
+		wantErr bool
+	}{
+		{
+			name: "should return date",
+			args: args{
+				datePublished: "12 de outubro de 2022",
+			},
+			want:    time.Date(2022, 10, 12, 0, 0, 0, 0, time.UTC),
+			wantErr: false,
+		},
+		{
+			name: "should return date single digit",
+			args: args{
+				datePublished: "1 de outubro de 2022",
+			},
+			want:    time.Date(2022, 10, 1, 0, 0, 0, 0, time.UTC),
+			wantErr: false,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := parseLocalizedDate(tt.args.datePublished)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("parseDate() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			if !reflect.DeepEqual(got, tt.want) {
+				t.Errorf("parseDate() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
+
+func Test_getIMDBLink(t *testing.T) {
+	type args struct {
+		link string
+	}
+	tests := []struct {
+		name    string
+		args    args
+		want    string
+		wantErr bool
+	}{
+		{
+			name: "should return imdb link",
+			args: args{
+				link: "https://www.imdb.com/title/tt1234567",
+			},
+			want:    "https://www.imdb.com/title/tt1234567",
+			wantErr: false,
+		},
+		{
+			name: "should return imdb link when end with /",
+			args: args{
+				link: "https://www.imdb.com/title/tt1234567/",
+			},
+			want:    "https://www.imdb.com/title/tt1234567/",
+			wantErr: false,
+		},
+		{
+			name: "should return imdb link when end with /",
+			args: args{
+				link: "https://www.imdb.com/title/tt1234567/",
+			},
+			want:    "https://www.imdb.com/title/tt1234567/",
+			wantErr: false,
+		},
+		{
+			name: "should return imdb link when it has a language",
+			args: args{
+				link: "https://www.imdb.com/pt/title/tt18722864/",
+			},
+			want: "https://www.imdb.com/pt/title/tt18722864/",
+		},
+		{
+			name: "should return imdb link when it has a language",
+			args: args{
+				link: "https://www.imdb.com/pt/title/tt34608980/",
+			},
+			want: "https://www.imdb.com/pt/title/tt34608980/",
+		},
+		{
+			name: "should return error when link is invalid",
+			args: args{
+				link: "https://www.google.com",
+			},
+			want:    "",
+			wantErr: true,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := getIMDBLink(tt.args.link)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("getIMDBLink() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			if got != tt.want {
+				t.Errorf("getIMDBLink() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}
--- a/api/torrent_dos_filmes.go
+++ b/api/torrent_dos_filmes.go
@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"net/http"
 	"net/url"
-	"regexp"
 	"slices"
 	"strings"
 	"time"
@@ -186,10 +185,9 @@ func getTorrentsTorrentDosFilmes(ctx context.Context, i *Indexer, link string) (
 	imdbLink := ""
 	article.Find("div.content a").Each(func(i int, s *goquery.Selection) {
 		link, _ := s.Attr("href")
-		re := regexp.MustCompile(`https://www.imdb.com/title/(tt\d+)`)
-		matches := re.FindStringSubmatch(link)
-		if len(matches) > 0 {
-			imdbLink = matches[0]
+		_imdbLink, err := getIMDBLink(link)
+		if err == nil {
+			imdbLink = _imdbLink
 		}
 	})

--- a/schema/audio.go
+++ b/schema/audio.go
@@ -35,6 +35,8 @@ const (
 	AudioHindi       = "Hindi"
 	AudioFarsi       = "Persa"
 	AudioMalay       = "Malaio"
+	AudioDutch       = "Holandês"
+	AudioDutch2      = "Holandes"
 )

 var AudioList = []Audio{
@@ -66,6 +68,10 @@ var AudioList = []Audio{
 	AudioThai2,
 	AudioTurkish,
 	AudioHindi,
+	AudioFarsi,
+	AudioMalay,
+	AudioDutch,
+	AudioDutch2,
 }

 func (a Audio) String() string {
@@ -139,6 +145,14 @@ func (a Audio) toTag() string {
 		return "tur"
 	case AudioHindi:
 		return "hin"
+	case AudioFarsi:
+		return "fas"
+	case AudioMalay:
+		return "msa"
+	case AudioDutch:
+		return "nld"
+	case AudioDutch2:
+		return "nld"
 	default:
 		return ""
 	}