Add bitchute extractor

.github/workflows/stream_bitchute.yml

@@ -0,0 +1,31 @@
+name: bitchute
+
+on:
+  push:
+    paths:
+      - "extractors/bitchute/*.go"
+      - ".github/workflows/stream_bitchute.yml"
+  pull_request:
+    paths:
+      - "extractors/bitchute/*.go"
+      - ".github/workflows/stream_bitchute.yml"
+  schedule:
+    # run ci weekly
+    - cron: "0 0 * * 0"
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        go: ["1.22"]
+        os: [ubuntu-latest]
+    name: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-go@v5
+        with:
+          go-version: ${{ matrix.go }}
+
+      - name: Test
+        run: go test -timeout 5m -race -coverpkg=./... -coverprofile=coverage.txt github.com/iawia002/lux/extractors/bitchute

app/register.go

@@ -4,6 +4,7 @@ import (
 	_ "github.com/iawia002/lux/extractors/acfun"
 	_ "github.com/iawia002/lux/extractors/bcy"
 	_ "github.com/iawia002/lux/extractors/bilibili"
+	_ "github.com/iawia002/lux/extractors/bitchute"
 	_ "github.com/iawia002/lux/extractors/douyin"
 	_ "github.com/iawia002/lux/extractors/douyu"
 	_ "github.com/iawia002/lux/extractors/eporner"

extractors/bitchute/bitchute.go

@@ -0,0 +1,103 @@
+package bitchute
+
+import (
+	"compress/flate"
+	"compress/gzip"
+	"fmt"
+	"io"
+	"net/http"
+	"regexp"
+	"strings"
+
+	"github.com/pkg/errors"
+
+	"github.com/iawia002/lux/extractors"
+	"github.com/iawia002/lux/request"
+)
+
+func init() {
+	extractors.Register("bitchute", New())
+}
+
+type extractor struct{}
+
+// New returns a bitchute extractor.
+func New() extractors.Extractor {
+	return &extractor{}
+}
+
+// Extract is the main function to extract the data.
+func (e *extractor) Extract(u string, option extractors.Options) ([]*extractors.Data, error) {
+	regVideoID := regexp.MustCompile(`/video/([^?/]+)`)
+	matchVideoID := regVideoID.FindStringSubmatch(u)
+	if len(matchVideoID) < 2 {
+		return nil, errors.New("Invalid video URL: Missing video ID parameter")
+	}
+	embedURL := fmt.Sprintf("https://www.bitchute.com/api/beta9/embed/?videoID=%s", matchVideoID[1])
+
+	res, err := request.Request(http.MethodGet, embedURL, nil, nil)
+	if err != nil {
+		return nil, errors.WithStack(err)
+	}
+	defer res.Body.Close() // nolint
+
+	var reader io.ReadCloser
+	switch res.Header.Get("Content-Encoding") {
+	case "gzip":
+		reader, _ = gzip.NewReader(res.Body)
+	case "deflate":
+		reader = flate.NewReader(res.Body)
+	default:
+		reader = res.Body
+	}
+	defer reader.Close() // nolint
+
+	b, err := io.ReadAll(reader)
+	if err != nil {
+		return nil, errors.WithStack(err)
+	}
+
+	// There is also an API that provides meta data
+	// POST https://api.bitchute.com/api/beta9/video {"video_id": <video_id>}
+	html := string(b)
+	regMediaURL := regexp.MustCompile(`media_url\s*=\s*['|"](https:\/\/[^.]+\.bitchute\.com\/.*\.mp4)`)
+	matchMediaURL := regMediaURL.FindStringSubmatch(html)
+	if len(matchMediaURL) < 2 {
+		return nil, errors.New("Could not extract media URL from page")
+	}
+	mediaURL := matchMediaURL[1]
+
+	regVideoName := regexp.MustCompile(`(?m)video_name\s*=\s*["|']\\?"?(.*)["|'];?$`)
+	matchVideoName := regVideoName.FindStringSubmatch(html)
+	if len(matchVideoName) < 2 {
+		return nil, errors.New("Could not extract media name from page")
+	}
+	videoName := strings.ReplaceAll(matchVideoName[1], `\"`, "")
+
+	streams := make(map[string]*extractors.Stream, 1)
+	size, err := request.Size(mediaURL, u)
+	if err != nil {
+		return nil, errors.WithStack(err)
+	}
+	streams["Default"] = &extractors.Stream{
+		Parts: []*extractors.Part{
+			{
+				URL:  mediaURL,
+				Size: size,
+				Ext:  "mp4",
+			},
+		},
+		Size:    size,
+		Quality: "Default",
+	}
+
+	return []*extractors.Data{
+		{
+			Site:    "Bitchute bitchute.com",
+			Title:   videoName,
+			Type:    extractors.DataTypeVideo,
+			Streams: streams,
+			URL:     u,
+		},
+	}, nil
+}

extractors/bitchute/bitchute_test.go

@@ -0,0 +1,39 @@
+package bitchute
+
+import (
+	"testing"
+
+	"github.com/iawia002/lux/extractors"
+	"github.com/iawia002/lux/test"
+)
+
+func TestDownload(t *testing.T) {
+	tests := []struct {
+		name string
+		args test.Args
+	}{
+		{
+			name: "video test 1",
+			args: test.Args{
+				URL:   "https://www.bitchute.com/video/C17naZ6WlWPo",
+				Title: "Everybody Dance Now",
+				Size:  1794720,
+			},
+		},
+		{
+			name: "video test 2",
+			args: test.Args{
+				URL:   "https://www.bitchute.com/video/HFgoUz6HrvQd",
+				Title: "Bear Level 1",
+				Size:  971698,
+			},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			data, err := New().Extract(tt.args.URL, extractors.Options{})
+			test.CheckError(t, err)
+			test.Check(t, tt.args, data[0])
+		})
+	}
+}