bump to v0.9

.github/FUNDING.yml

@@ -0,0 +1 @@
+github: [meeb]

Pipfile.lock

@@ -39,11 +39,11 @@
         },
         "django": {
             "hashes": [
-                "sha256:2d78425ba74c7a1a74b196058b261b9733a8570782f4e2828974777ccca7edf7",
-                "sha256:efa2ab96b33b20c2182db93147a0c3cd7769d418926f9e9f140a60dca7c64ca9"
+                "sha256:169e2e7b4839a7910b393eec127fd7cbae62e80fa55f89c6510426abf673fe5f",
+                "sha256:c6c0462b8b361f8691171af1fb87eceb4442da28477e12200c40420176206ba7"
             ],
             "index": "pypi",
-            "version": "==3.1.5"
+            "version": "==3.1.6"
         },
         "django-appconf": {
             "hashes": [
@@ -172,10 +172,10 @@
         },
         "pytz": {
             "hashes": [
-                "sha256:16962c5fb8db4a8f63a26646d8886e9d769b6c511543557bc84e9569fb9a9cb4",
-                "sha256:180befebb1927b16f6b57101720075a984c019ac16b1b7575673bea42c6c3da5"
+                "sha256:83a4a90894bf38e243cf052c8b58f381bfe9a7a483f6a9cab140bc7f702ac4da",
+                "sha256:eb10ce3e7736052ed3623d49975ce333bcd712c7bb19a58b9e2089d4057d0798"
             ],
-            "version": "==2020.5"
+            "version": "==2021.1"
         },
         "rcssmin": {
             "hashes": [
@@ -225,10 +225,10 @@
         },
         "urllib3": {
             "hashes": [
-                "sha256:19188f96923873c92ccb987120ec4acaa12f0461fa9ce5d3d0772bc965a39e08",
-                "sha256:d8ff90d979214d7b4f8ce956e80f4028fc6860e4431f731ea4a8c08f23f99473"
+                "sha256:1b465e494e3e0d8939b50680403e3aedaa2bc434b7d5af64dfd3c958d7f5ae80",
+                "sha256:de3eedaad74a2683334e282005cd8d7f22f4d55fa690a2a1020a416cb0a47e73"
             ],
-            "version": "==1.26.2"
+            "version": "==1.26.3"
         },
         "whitenoise": {
             "hashes": [
@@ -240,11 +240,11 @@
         },
         "youtube-dl": {
             "hashes": [
-                "sha256:8f421ca8394d2529e06225e44ec66538d2a28f6f340c03065776894bf3d24ea6",
-                "sha256:acf74701a31b6c3d06f9d4245a46ba8fb6c378931681177412043c6e8276fee7"
+                "sha256:b390cddbd4d605bd887d0d4063988cef0fa13f916d2e1e3564badbb22504d754",
+                "sha256:e7d48cd42f3081e1e0064e69f31f2856508ef31c0fc80eeebd8e70c6a031a24d"
             ],
             "index": "pypi",
-            "version": "==2021.1.16"
+            "version": "==2021.2.10"
         }
     },
     "develop": {}

README.md

@@ -22,7 +22,7 @@ hopefully, quite reliable.
 # Latest container image
 
 ```yaml
-ghcr.io/meeb/tubesync:v0.8
+ghcr.io/meeb/tubesync:v0.9
 ```
 
 **NOTE: the `:latest` tag does exist, but will contain in-development commits and may
@@ -102,7 +102,7 @@ Finally, download and run the container:
 
 ```bash
 # Pull a versioned image
-$ docker pull ghcr.io/meeb/tubesync:v0.8
+$ docker pull ghcr.io/meeb/tubesync:v0.9
 # Start the container using your user ID and group ID
 $ docker run \
   -d \
@@ -113,7 +113,7 @@ $ docker run \
   -v /some/directory/tubesync-config:/config \
   -v /some/directory/tubesync-downloads:/downloads \
   -p 4848:4848 \
-  ghcr.io/meeb/tubesync:v0.8
+  ghcr.io/meeb/tubesync:v0.9
 ```
 
 Once running, open `http://localhost:4848` in your browser and you should see the
@@ -125,7 +125,7 @@ Alternatively, for Docker Compose, you can use something like:
 
 ```yaml
   tubesync:
-    image: ghcr.io/meeb/tubesync:v0.8
+    image: ghcr.io/meeb/tubesync:v0.9
     container_name: tubesync
     restart: unless-stopped
     ports:
@@ -196,6 +196,16 @@ $ 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)
+
+![Sync or create missing metadata files](https://github.com/meeb/tubesync/blob/main/docs/create-missing-metadata.md)
+
+
 # Warnings
 
 ### 1. Index frequency

config/root/etc/cont-init.d/10-tubesync

@@ -19,8 +19,8 @@ chown -R app:app /app/common/static && \
 chmod -R 0750 /app/common/static && \
 chown -R app:app /app/static && \
 chmod -R 0750 /app/static && \
-find /app -type f -exec chmod 640 {} \; && \
-chmod +x /app/healthcheck.py
+find /app -type f ! -iname healthcheck.py -exec chmod 640 {} \; && \
+chmod 0755 /app/healthcheck.py
 
 # Run migrations
 exec s6-setuidgid app \

docs/create-missing-metadata.md

@@ -0,0 +1,37 @@
+# TubeSync
+
+## Advanced usage guide - creating missing metadata
+
+This is a new feature in v0.9 of TubeSync and later. It allows you to create or
+re-create missing metadata in your TubeSync download directories for missing `nfo`
+files and thumbnails.
+
+If you add a source with "write NFO files" or "copy thumbnails" disabled, download
+some media and then update the source to write NFO files or copy thumbnails then
+TubeSync will not automatically retroactively attempt to copy or create your missing
+metadata files. You can use a special one-off command to manually write missing
+metadata files to the correct locations.
+
+## Requirements
+
+You have added a source without metadata writing enabled, downloaded some media, then
+updated the source to enable metadata writing.
+
+## Steps
+
+### 1. Run the batch metadata sync command
+
+Execute the following Django command:
+
+`./manage.py sync-missing-metadata`
+
+When deploying TubeSync inside a container, you can execute this with:
+
+`docker exec -ti tubesync python3 /app/manage.py sync-missing-metadata`
+
+This command will log what its doing to the terminal when you run it.
+
+Internally, this command loops over all your sources which have been saved with
+"write NFO files" or "copy thumbnails" enabled. Then, loops over all media saved to
+that source and confirms that the appropriate thumbnail files have been copied over and
+the NFO file has been written if enabled.

docs/import-existing-media.md

@@ -0,0 +1,81 @@
+# 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.
+
+Note that TubeSync will still get screenshots write `nfo` files etc. for files you
+manually import if enabled at the source level.

tubesync/common/utils.py

@@ -19,7 +19,7 @@ def append_uri_params(uri, params):
 def clean_filename(filename):
     if not isinstance(filename, str):
         raise ValueError(f'filename must be a str, got {type(filename)}')
-    to_scrub = '<>\/:*?"|'
+    to_scrub = '<>\/:*?"|%'
     for char in to_scrub:
         filename = filename.replace(char, '')
     filename = ''.join([c for c in filename if ord(c) > 30])

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/management/commands/sync-missing-metadata.py

@@ -0,0 +1,34 @@
+import os
+from shutil import copyfile
+from django.core.management.base import BaseCommand, CommandError
+from django.db.models import Q
+from common.logger import log
+from sync.models import Source, Media
+from sync.utils import write_text_file
+
+
+class Command(BaseCommand):
+
+    help = 'Syncs missing metadata (such as nfo files) if source settings are updated'
+
+    def handle(self, *args, **options):
+        log.info('Syncing missing metadata...')
+        sources = Source.objects.filter(Q(copy_thumbnails=True) | Q(write_nfo=True))
+        for source in sources.order_by('name'):
+            log.info(f'Finding media for source: {source}')
+            for item in Media.objects.filter(source=source, downloaded=True):
+                log.info(f'Checking media for missing metadata: {source} / {item}')
+                thumbpath = item.thumbpath
+                if not thumbpath.is_file():
+                    if item.thumb:
+                        log.info(f'Copying missing thumbnail from: {item.thumb.path} '
+                                 f'to: {thumbpath}')
+                        copyfile(item.thumb.path, thumbpath)
+                    else:
+                        log.error(f'Tried to copy missing thumbnail for {item} but '
+                                  f'the thumbnail has not been downloaded')
+                nfopath = item.nfopath
+                if not nfopath.is_file():
+                    log.info(f'Writing missing NFO file: {nfopath}')
+                    write_text_file(nfopath, item.nfoxml)
+        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>',
@@ -113,6 +118,12 @@ class Source(models.Model):
         SOURCE_TYPE_YOUTUBE_CHANNEL_ID: 'https://www.youtube.com/channel/{key}',
         SOURCE_TYPE_YOUTUBE_PLAYLIST: 'https://www.youtube.com/playlist?list={key}',
     }
+    # Format used to create indexable URLs
+    INDEX_URLS = {
+        SOURCE_TYPE_YOUTUBE_CHANNEL: 'https://www.youtube.com/c/{key}/videos',
+        SOURCE_TYPE_YOUTUBE_CHANNEL_ID: 'https://www.youtube.com/channel/{key}/videos',
+        SOURCE_TYPE_YOUTUBE_PLAYLIST: 'https://www.youtube.com/playlist?list={key}',
+    }
     # Callback functions to get a list of media from the source
     INDEXERS = {
         SOURCE_TYPE_YOUTUBE_CHANNEL: get_youtube_media_info,
@@ -210,6 +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,
@@ -328,23 +344,32 @@ 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):
         url = obj.URLS.get(source_type)
         return url.format(key=key)
 
+    @classmethod
+    def create_index_url(obj, source_type, key):
+        url = obj.INDEX_URLS.get(source_type)
+        return url.format(key=key)
+
     @property
     def url(self):
         return Source.create_url(self.source_type, self.key)
 
+    @property
+    def index_url(self):
+        return Source.create_index_url(self.source_type, self.key)
+
     @property
     def format_summary(self):
         if self.source_resolution == Source.SOURCE_RESOLUTION_AUDIO:
@@ -437,25 +462,10 @@ class Source(models.Model):
         indexer = self.INDEXERS.get(self.source_type, None)
         if not callable(indexer):
             raise Exception(f'Source type f"{self.source_type}" has no indexer')
-        response = indexer(self.url)
-
-        # Account for nested playlists, such as a channel of playlists of playlists
-        def _recurse_playlists(playlist):
-            videos = []
-            if not playlist:
-                return videos
-            entries = playlist.get('entries', [])
-            for entry in entries:
-                if not entry:
-                    continue
-                subentries = entry.get('entries', [])
-                if subentries:
-                    videos = videos + _recurse_playlists(entry)
-                else:
-                    videos.append(entry)
-            return videos
-
-        return _recurse_playlists(response)
+        response = indexer(self.index_url)
+        if not isinstance(response, dict):
+            return []
+        return response.get('entries', [])
 
 
 def get_media_thumb_path(instance, filename):
@@ -481,6 +491,12 @@ class Media(models.Model):
         Source.SOURCE_TYPE_YOUTUBE_CHANNEL_ID: 'https://www.youtube.com/watch?v={key}',
         Source.SOURCE_TYPE_YOUTUBE_PLAYLIST: 'https://www.youtube.com/watch?v={key}',
     }
+    # Callback functions to get a list of media from the source
+    INDEXERS = {
+        Source.SOURCE_TYPE_YOUTUBE_CHANNEL: get_youtube_media_info,
+        Source.SOURCE_TYPE_YOUTUBE_CHANNEL_ID: get_youtube_media_info,
+        Source.SOURCE_TYPE_YOUTUBE_PLAYLIST: get_youtube_media_info,
+    }
     # Maps standardised names to names used in source metdata
     METADATA_FIELDS = {
         'upload_date': {
@@ -558,14 +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>',
     }
 
@@ -904,6 +924,10 @@ class Media(models.Model):
             'hdr': display_format['hdr'],
         }
 
+    @property
+    def has_metadata(self):
+        return self.metadata is not None
+
     @property
     def loaded_metadata(self):
         try:
@@ -976,8 +1000,12 @@ class Media(models.Model):
     def votes(self):
         field = self.get_metadata_field('upvotes')
         upvotes = self.loaded_metadata.get(field, 0)
+        if not isinstance(upvotes, int):
+            upvotes = 0
         field = self.get_metadata_field('downvotes')
         downvotes = self.loaded_metadata.get(field, 0)
+        if not isinstance(downvotes, int):
+            downvotes = 0
         return upvotes + downvotes
 
     @property
@@ -1163,6 +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):
@@ -1180,6 +1212,16 @@ class Media(models.Model):
         # Return the download paramaters
         return format_str, self.source.extension
 
+    def index_metadata(self):
+        '''
+            Index the media metadata returning a dict of info.
+        '''
+        indexer = self.INDEXERS.get(self.source.source_type, None)
+        if not callable(indexer):
+            raise Exception(f'Meida with source type f"{self.source.source_type}" '
+                            f'has no indexer')
+        return indexer(self.url)
+
 
 class MediaServer(models.Model):
     '''

tubesync/sync/signals.py

@@ -8,8 +8,9 @@ from background_task.models import Task
 from common.logger import log
 from .models import Source, Media, MediaServer
 from .tasks import (delete_task_by_source, delete_task_by_media, index_source_task,
-                    download_media_thumbnail, map_task_to_instance,
-                    check_source_directory_exists, download_media, rescan_media_server)
+                    download_media_thumbnail, download_media_metadata,
+                    map_task_to_instance, check_source_directory_exists,
+                    download_media, rescan_media_server)
 from .utils import delete_file
 
 
@@ -93,16 +94,27 @@ def task_task_failed(sender, task_id, completed_task, **kwargs):
 def media_post_save(sender, instance, created, **kwargs):
     # Triggered after media is saved, Recalculate the "can_download" flag, this may
     # need to change if the source specifications have been changed
-    post_save.disconnect(media_post_save, sender=Media)
-    if instance.get_format_str():
-        if not instance.can_download:
-            instance.can_download = True
-            instance.save()
-    else:
-        if instance.can_download:
-            instance.can_download = False
-            instance.save()
-    post_save.connect(media_post_save, sender=Media)
+    if instance.metadata:
+        post_save.disconnect(media_post_save, sender=Media)
+        if instance.get_format_str():
+            if not instance.can_download:
+                instance.can_download = True
+                instance.save()
+        else:
+            if instance.can_download:
+                instance.can_download = False
+                instance.save()
+        post_save.connect(media_post_save, sender=Media)
+    # If the media is missing metadata schedule it to be downloaded
+    if not instance.metadata:
+        log.info(f'Scheduling task to download metadata for: {instance.url}')
+        verbose_name = _('Downloading metadata for "{}"')
+        download_media_metadata(
+            str(instance.pk),
+            priority=10,
+            verbose_name=verbose_name.format(instance.pk),
+            remove_existing_tasks=True
+        )
     # If the media is missing a thumbnail schedule it to be downloaded
     if not instance.thumb_file_exists:
         instance.thumb = None
@@ -124,7 +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

@@ -179,30 +179,6 @@ def index_source_task(source_id):
         except Media.DoesNotExist:
             media = Media(key=key)
         media.source = source
-        media.metadata = json.dumps(video)
-        upload_date = media.upload_date
-        # Media must have a valid upload date
-        if upload_date:
-            media.published = timezone.make_aware(upload_date)
-        else:
-            log.error(f'Media has no upload date, skipping: {source} / {media}')
-            continue
-        # If the source has a download cap date check the upload date is allowed
-        max_cap_age = source.download_cap_date
-        if max_cap_age:
-            if media.published < max_cap_age:
-                # Media was published after the cap date, skip it
-                log.warn(f'Media: {source} / {media} is older than cap age '
-                         f'{max_cap_age}, skipping')
-                continue
-        # If the source has a cut-off check the upload date is within the allowed delta
-        if source.delete_old_media and source.days_to_keep > 0:
-            delta = timezone.now() - timedelta(days=source.days_to_keep)
-            if media.published < delta:
-                # Media was published after the cutoff date, skip it
-                log.warn(f'Media: {source} / {media} is older than '
-                         f'{source.days_to_keep} days, skipping')
-                continue
         try:
             media.save()
             log.info(f'Indexed media: {source} / {media}')
@@ -234,6 +210,56 @@ def check_source_directory_exists(source_id):
         source.make_directory()
 
 
+@background(schedule=0)
+def download_media_metadata(media_id):
+    '''
+        Downloads the metadata for a media item.
+    '''
+    try:
+        media = Media.objects.get(pk=media_id)
+    except Media.DoesNotExist:
+        # Task triggered but the media no longer exists, do nothing
+        log.error(f'Task download_media_metadata(pk={media_id}) called but no '
+                  f'media exists with ID: {media_id}')
+        return
+    source = media.source
+    metadata = media.index_metadata()
+    media.metadata = json.dumps(metadata)
+    upload_date = media.upload_date
+    # Media must have a valid upload date
+    if upload_date:
+        media.published = timezone.make_aware(upload_date)
+    else:
+        log.error(f'Media has no upload date, skipping: {source} / {media}')
+        media.skip = True
+    # If the source has a download cap date check the upload date is allowed
+    max_cap_age = source.download_cap_date
+    if max_cap_age:
+        if media.published < max_cap_age:
+            # Media was published after the cap date, skip it
+            log.warn(f'Media: {source} / {media} is older than cap age '
+                     f'{max_cap_age}, skipping')
+            media.skip = True
+    # If the source has a cut-off check the upload date is within the allowed delta
+    if source.delete_old_media and source.days_to_keep > 0:
+        delta = timezone.now() - timedelta(days=source.days_to_keep)
+        if media.published < delta:
+            # Media was published after the cutoff date, skip it
+            log.warn(f'Media: {source} / {media} is older than '
+                     f'{source.days_to_keep} days, skipping')
+            media.skip = True
+    # Check we can download the media item
+    if not media.skip:
+        if media.get_format_str():
+            media.can_download = True
+        else:
+            media.can_download = False
+    # Save the media
+    media.save()
+    log.info(f'Saved {len(media.metadata)} bytes of metadata for: '
+             f'{source} / {media_id}')
+
+
 @background(schedule=0)
 def download_media_thumbnail(media_id, url):
     '''
@@ -282,6 +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>
@@ -109,7 +115,7 @@
       {% else %}
       <tr title="Can the media be downloaded?">
         <td class="hide-on-small-only">Can download?</td>
-        <td><span class="hide-on-med-and-up">Can download?<br></span><strong>{% if youtube_dl_format %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
+        <td><span class="hide-on-med-and-up">Can download?<br></span><strong>{% if media.can_download %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
       </tr>
       {% endif %}
       <tr title="The available media formats">

tubesync/sync/templates/sync/media.html

@@ -24,8 +24,12 @@
             {% 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 %}
-              <i class="far fa-clock" title="Waiting to download or downloading"></i> {{ m.published|date:'Y-m-d' }}
+              <i class="far fa-clock" title="Waiting to download or downloading"></i> Downloading
               {% else %}
               <span class="error-text"><i class="fas fa-exclamation-triangle" title="No matching formats to download"></i> No matching formats</span>
               {% endif %}

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',
-              'source_resolution', 'source_vcodec', 'source_acodec', 'prefer_60fps',
-              'prefer_hdr', 'fallback', 'copy_thumbnails', 'write_nfo')
+              'index_schedule', 'download_media', 'download_cap', 'delete_old_media',
+              'days_to_keep', 'source_resolution', 'source_vcodec', 'source_acodec',
+              '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',
-              'source_resolution', 'source_vcodec', 'source_acodec', 'prefer_60fps',
-              'prefer_hdr', 'fallback', 'copy_thumbnails', 'write_nfo')
+              'index_schedule', 'download_media', 'download_cap', 'delete_old_media',
+              'days_to_keep', 'source_resolution', 'source_vcodec', 'source_acodec',
+              '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 '

tubesync/sync/youtube.py

@@ -37,7 +37,8 @@ def get_media_info(url):
         'skip_download': True,
         'forcejson': True,
         'simulate': True,
-        'logger': log
+        'logger': log,
+        'extract_flat': True,
     })
     response = {}
     with youtube_dl.YoutubeDL(opts) as y:

tubesync/tubesync/settings.py

@@ -6,7 +6,7 @@ CONFIG_BASE_DIR = BASE_DIR
 DOWNLOADS_BASE_DIR = BASE_DIR
 
 
-VERSION = 0.8
+VERSION = 0.9
 SECRET_KEY = ''
 DEBUG = False
 ALLOWED_HOSTS = []
@@ -114,6 +114,9 @@ Disallow: /
 '''.strip()
 
 
+X_FRAME_OPTIONS = 'SAMEORIGIN'
+
+
 HEALTHCHECK_FIREWALL = True
 HEALTHCHECK_ALLOWED_IPS = ('127.0.0.1',)
 
@@ -149,7 +152,7 @@ YOUTUBE_DEFAULTS = {
 }
 
 
-MEDIA_FORMATSTR_DEFAULT = '{yyyymmdd}_{source}_{title}_{key}_{format}.{ext}'
+MEDIA_FORMATSTR_DEFAULT = '{yyyy_mm_dd}_{source}_{title}_{key}_{format}.{ext}'
 
 
 try: