add sync.Source.download_media master flag, add manual import existing media command with docs, resolves #24

README.md

@@ -196,6 +196,14 @@ $ docker logs --follow tubesync
 ```
 
 
+# Advanced usage guides
+
+Once you're happy using TubeSync there are some advanced usage guides for more complex
+and less common features:
+
+![Import existing media into TubeSync](https://github.com/meeb/tubesync/blob/main/docs/import-existing-media.md)
+
+
 # Warnings
 
 ### 1. Index frequency

docs/import-existing-media.md

@@ -0,0 +1,78 @@
+# TubeSync
+
+## Advanced usage guide - importing existing media
+
+This is a new feature in v0.9 of TubeSync and later. It allows you to mark existing
+downloaded media as "downloaded" in TubeSync. You can use this feature if, for example,
+you already have an extensive catalogue of downloaded media which you want to mark
+as downloaded into TubeSync so TubeSync doesn't re-download media you already have.
+
+## Requirements
+
+Your existing downloaded media MUST contain the unique ID. For YouTube videos, this is
+means the YouTube video ID MUST be in the filename.
+
+Supported extensions to be imported are .m4a, .ogg, .mkv, .mp3, .mp4 and .avi. Your
+media you want to import must end in one of these file extensions.
+
+## Caveats
+
+As TubeSync does not probe media and your existing media may be re-encoded or in
+different formats to what is available in the current media metadata there is no way
+for TubeSync to know what codecs, resolution, bitrate etc. your imported media is in.
+Any manually imported existing local media will display blank boxes for this
+information on the TubeSync interface as it's unavailable.
+
+## Steps
+
+### 1. Add your source to TubeSync
+
+Add your source to TubeSync, such as a YouTube channel. **Make sure you untick the
+"download media" checkbox.**
+
+This will allow TubeSync to index all the available media on your source, but won't
+start downloading any media.
+
+### 2. Wait
+
+Wait for all the media on your source to be indexed. This may take some time.
+
+### 3. Move your existing media into TubeSync
+
+You now need to move your existing media into TubeSync. You need to move the media
+files into the correct download directories created by TubeSync. For example, if you
+have downloaded videos for a YouTube channel "TestChannel", you would have added this
+as a source called TestChannel and in a directory called test-channel in Tubesync. It
+would have a download directory created on disk at:
+
+`/path/to/downloads/test-channel`
+
+You would move all of your pre-existing videos you downloaded outside of TubeSync for
+this channel into this directory.
+
+In short, your existing media needs to be moved into the correct TubeSync source
+directory to be detected.
+
+This is required so TubeSync can known which Source to link the media to.
+
+### 4. Run the batch import command
+
+Execute the following Django command:
+
+`./manage.py import-existing-media`
+
+When deploying TubeSync inside a container, you can execute this with:
+
+`docker exec -ti tubesync python3 /app/manage.py import-existing-media`
+
+This command will log what its doing to the terminal when you run it.
+
+Internally, `import-existing-media` looks for the unique media key (for YouTube, this
+is the YouTube video ID) in the filename and detects the source to link it to based
+on the directory the media file is inside.
+
+
+### 5. Re-enable downloading at the source
+
+Edit your source and re-enable / tick the "download media" option. This will allow
+TubeSync to download any missing media you did not manually import.

tubesync/sync/admin.py

@@ -7,7 +7,7 @@ class SourceAdmin(admin.ModelAdmin):
 
     ordering = ('-created',)
     list_display = ('uuid', 'name', 'source_type', 'last_crawl',
-                    'has_failed')
+                    'download_media', 'has_failed')
     readonly_fields = ('uuid', 'created')
     search_fields = ('uuid', 'key', 'name')
 

tubesync/sync/management/commands/import-existing-media.py

@@ -0,0 +1,55 @@
+import os
+from pathlib import Path
+from django.core.management.base import BaseCommand, CommandError
+from common.logger import log
+from sync.models import Source, Media
+
+
+class Command(BaseCommand):
+
+    help = ('Scans download media directories for media not yet downloaded and ',
+            'marks them as downloaded')
+    extra_extensions = ['mp3', 'mp4', 'avi']
+
+    def handle(self, *args, **options):
+        log.info('Building directory to Source map...')
+        dirmap = {}
+        for s in Source.objects.all():
+            dirmap[s.directory_path] = s
+        log.info(f'Scanning sources...')
+        file_extensions = list(Source.EXTENSIONS) + self.extra_extensions
+        for sourceroot, source in dirmap.items():
+            media = list(Media.objects.filter(source=source, downloaded=False,
+                                              skip=False))
+            if not media:
+                log.info(f'Source "{source}" has no missing media')
+                continue
+            log.info(f'Scanning Source "{source}" directory for media to '
+                     f'import: {sourceroot}, looking for {len(media)} '
+                     f'undownloaded and unskipped items')
+            on_disk = []
+            for (root, dirs, files) in os.walk(sourceroot):
+                rootpath = Path(root)
+                for filename in files:
+                    filepart, ext = os.path.splitext(filename)
+                    if ext.startswith('.'):
+                        ext = ext[1:]
+                    ext = ext.strip().lower()
+                    if ext not in file_extensions:
+                        continue
+                    on_disk.append(str(rootpath / filename))
+            filemap = {}
+            for item in media:
+                for filepath in on_disk:
+                    if item.key in filepath:
+                        # The unique item key is in the file name on disk, map it to
+                        # the undownloaded media item
+                        filemap[filepath] = item
+                        continue
+            for filepath, item in filemap.items():
+                log.info(f'Matched on-disk file: {filepath} '
+                         f'to media item: {item.source} / {item}')
+                item.media_file.name = filepath
+                item.downloaded = True
+                item.save()
+        log.info('Done')

tubesync/sync/migrations/0009_auto_20210218_0442.py

@@ -0,0 +1,30 @@
+# Generated by Django 3.1.6 on 2021-02-18 04:42
+
+import django.core.files.storage
+from django.db import migrations, models
+import sync.models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('sync', '0008_source_download_cap'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='source',
+            name='download_media',
+            field=models.BooleanField(default=True, help_text='Download media from this source, if not selected the source will only be indexed', verbose_name='download media'),
+        ),
+        migrations.AlterField(
+            model_name='media',
+            name='media_file',
+            field=models.FileField(blank=True, help_text='Media file', max_length=200, null=True, storage=django.core.files.storage.FileSystemStorage(location='/home/meeb/Repos/github.com/meeb/tubesync/tubesync/downloads'), upload_to=sync.models.get_media_file_path, verbose_name='media file'),
+        ),
+        migrations.AlterField(
+            model_name='source',
+            name='media_format',
+            field=models.CharField(default='{yyyymmdd}_{source}_{title}_{key}_{format}.{ext}', help_text='File format to use for saving files, detailed options at bottom of page.', max_length=200, verbose_name='media format'),
+        ),
+    ]

tubesync/sync/models.py

@@ -101,6 +101,11 @@ class Source(models.Model):
         (FALLBACK_NEXT_BEST_HD, _('Get next best resolution but at least HD'))
     )
 
+    EXTENSION_M4A = 'm4a'
+    EXTENSION_OGG = 'ogg'
+    EXTENSION_MKV = 'mkv'
+    EXTENSIONS = (EXTENSION_M4A, EXTENSION_OGG, EXTENSION_MKV)
+
     # Fontawesome icons used for the source on the front end
     ICONS = {
         SOURCE_TYPE_YOUTUBE_CHANNEL: '<i class="fab fa-youtube"></i>',
@@ -216,6 +221,11 @@ class Source(models.Model):
         default=IndexSchedule.EVERY_6_HOURS,
         help_text=_('Schedule of how often to index the source for new media')
     )
+    download_media = models.BooleanField(
+        _('download media'),
+        default=True,
+        help_text=_('Download media from this source, if not selected the source will only be indexed')
+    )
     download_cap = models.IntegerField(
         _('download cap'),
         choices=CapChoices.choices,
@@ -334,13 +344,13 @@ class Source(models.Model):
         '''
         if self.is_audio:
             if self.source_acodec == self.SOURCE_ACODEC_MP4A:
-                return 'm4a'
+                return self.EXTENSION_M4A
             elif self.source_acodec == self.SOURCE_ACODEC_OPUS:
-                return 'ogg'
+                return self.EXTENSION_OGG
             else:
                 raise ValueError('Unable to choose audio extension, uknown acodec')
         else:
-            return 'mkv'
+            return self.EXTENSION_MKV
 
     @classmethod
     def create_url(obj, source_type, key):
@@ -564,14 +574,18 @@ class Media(models.Model):
     STATE_SCHEDULED = 'scheduled'
     STATE_DOWNLOADING = 'downloading'
     STATE_DOWNLOADED = 'downloaded'
+    STATE_SKIPPED = 'skipped'
+    STATE_DISABLED_AT_SOURCE = 'source-disabled'
     STATE_ERROR = 'error'
     STATES = (STATE_UNKNOWN, STATE_SCHEDULED, STATE_DOWNLOADING, STATE_DOWNLOADED,
-              STATE_ERROR)
+              STATE_SKIPPED, STATE_DISABLED_AT_SOURCE, STATE_ERROR)
     STATE_ICONS = {
         STATE_UNKNOWN: '<i class="far fa-question-circle" title="Unknown download state"></i>',
         STATE_SCHEDULED: '<i class="far fa-clock" title="Scheduled to download"></i>',
         STATE_DOWNLOADING: '<i class="fas fa-download" title="Downloading now"></i>',
         STATE_DOWNLOADED: '<i class="far fa-check-circle" title="Downloaded"></i>',
+        STATE_SKIPPED: '<i class="fas fa-exclamation-circle" title="Skipped"></i>',
+        STATE_DISABLED_AT_SOURCE: '<i class="fas fa-stop-circle" title="Media downloading disabled at source"></i>',
         STATE_ERROR: '<i class="fas fa-exclamation-triangle" title="Error downloading"></i>',
     }
 
@@ -1177,6 +1191,10 @@ class Media(models.Model):
                 return self.STATE_ERROR
             else:
                 return self.STATE_SCHEDULED
+        if self.skip:
+            return self.STATE_SKIPPED
+        if not self.source.download_media:
+            return self.STATE_DISABLED_AT_SOURCE
         return self.STATE_UNKNOWN
 
     def get_download_state_icon(self, task=None):

tubesync/sync/signals.py

@@ -136,7 +136,8 @@ def media_post_save(sender, instance, created, **kwargs):
     if not instance.media_file_exists:
         instance.downloaded = False
         instance.media_file = None
-    if not instance.downloaded and instance.can_download and not instance.skip:
+    if (not instance.downloaded and instance.can_download and not instance.skip
+        and instance.source.download_media):
         delete_task_by_media('sync.tasks.download_media', (str(instance.pk),))
         verbose_name = _('Downloading media for "{}"')
         download_media(

tubesync/sync/tasks.py

@@ -308,6 +308,17 @@ def download_media(media_id):
         log.warn(f'Download task triggeredd media: {media} (UUID: {media.pk}) but it '
                  f'is now marked to be skipped, not downloading')
         return
+    if media.downloaded and media.media_file:
+        # Media has been marked as downloaded before the download_media task was fired,
+        # skip it
+        log.warn(f'Download task triggeredd media: {media} (UUID: {media.pk}) but it '
+                 f'has already been marked as downloaded, not downloading again')
+        return
+    if not media.source.download_media:
+        log.warn(f'Download task triggeredd media: {media} (UUID: {media.pk}) but the '
+                 f'source {media.source} has since been marked to not download media, '
+                 f'not downloading')
+        return
     filepath = media.filepath
     log.info(f'Downloading media: {media} (UUID: {media.pk}) to: "{filepath}"')
     format_str, container = media.download_media()

tubesync/sync/templates/sync/media-item.html

@@ -64,8 +64,14 @@
         <td class="hide-on-small-only">Fallback</td>
         <td><span class="hide-on-med-and-up">Fallback<br></span><strong>{{ media.source.get_fallback_display }}</strong></td>
       </tr>
+      {% if not media.source.download_media %}
+      <tr title="Is media marked to be downloaded at the source?">
+        <td class="hide-on-small-only">Source download?</td>
+        <td><span class="hide-on-med-and-up">Source download?<br></span><strong>{% if media.source.download_media %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
+      </tr>
+      {% endif %}
       {% if media.skip %}
-      <tr title="Has the media been downloaded?">
+      <tr title="Is the media marked to be skipped?">
         <td class="hide-on-small-only">Skipping?</td>
         <td><span class="hide-on-med-and-up">Skipping?<br></span><strong>{% if media.skip %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
       </tr>

tubesync/sync/templates/sync/media.html

@@ -24,6 +24,8 @@
             {% else %}
               {% if m.skip %}
               <span class="error-text"><i class="fas fa-times" title="Skipping media"></i> Skipped</span>
+              {% elif not m.source.download_media %}
+              <span class="error-text"><i class="fas fa-times" title="Not downloading media for this source"></i> Disabled at source</span>
               {% elif not m.has_metadata %}
               <i class="far fa-clock" title="Waiting for metadata"></i> Fetching metadata
               {% elif m.can_download %}

tubesync/sync/templates/sync/source.html

@@ -61,6 +61,10 @@
         <td class="hide-on-small-only">Index schedule</td>
         <td><span class="hide-on-med-and-up">Index schedule<br></span><strong>{{ source.get_index_schedule_display }}</strong></td>
       </tr>
+      <tr title="Download media from this source">
+        <td class="hide-on-small-only">Download media?</td>
+        <td><span class="hide-on-med-and-up">Download media?<br></span><strong>{% if source.download_media %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
+      </tr>
       <tr title="When then source was created locally in TubeSync">
         <td class="hide-on-small-only">Created</td>
         <td><span class="hide-on-med-and-up">Created<br></span><strong>{{ source.created|date:'Y-m-d H:i:s' }}</strong></td>

tubesync/sync/views.py

@@ -274,9 +274,9 @@ class AddSourceView(CreateView):
     template_name = 'sync/source-add.html'
     model = Source
     fields = ('source_type', 'key', 'name', 'directory', 'media_format',
-              'index_schedule', 'download_cap', 'delete_old_media', 'days_to_keep',
+              'index_schedule', 'download_media', 'download_cap', 'delete_old_media',
-              'source_resolution', 'source_vcodec', 'source_acodec', 'prefer_60fps',
+              'days_to_keep', 'source_resolution', 'source_vcodec', 'source_acodec',
-              'prefer_hdr', 'fallback', 'copy_thumbnails', 'write_nfo')
+              'prefer_60fps', 'prefer_hdr', 'fallback', 'copy_thumbnails', 'write_nfo')
     errors = {
         'invalid_media_format': _('Invalid media format, the media format contains '
                                   'errors or is empty. Check the table at the end of '
@@ -365,9 +365,9 @@ class UpdateSourceView(UpdateView):
     template_name = 'sync/source-update.html'
     model = Source
     fields = ('source_type', 'key', 'name', 'directory', 'media_format',
-              'index_schedule', 'download_cap', 'delete_old_media', 'days_to_keep',
+              'index_schedule', 'download_media', 'download_cap', 'delete_old_media',
-              'source_resolution', 'source_vcodec', 'source_acodec', 'prefer_60fps',
+              'days_to_keep', 'source_resolution', 'source_vcodec', 'source_acodec',
-              'prefer_hdr', 'fallback', 'copy_thumbnails', 'write_nfo')
+              'prefer_60fps', 'prefer_hdr', 'fallback', 'copy_thumbnails', 'write_nfo')
     errors = {
         'invalid_media_format': _('Invalid media format, the media format contains '
                                   'errors or is empty. Check the table at the end of '