Option to list category names

jwb-index

@@ -64,14 +64,12 @@ p.add_argument('--download-subtitles', action='store_true',
                help='download VTT subtitle files')
 p.add_argument('--exclude', metavar='CODE', dest='exclude_categories',
                action=action_factory(lambda x: tuple(x.split(','))),
-               help='comma separated list of categories to exclude')
+               help='comma separated list of categories to skip (sub-categories will also be skipped)')
 p.add_argument('--filter', '-f', dest='filter_categories', metavar='CODE',
                action=action_factory(lambda x: tuple(x.split(','))),
                help='comma separated list of categories to extract (use with --latest)')
 p.add_argument('--fix-broken', action='store_true', dest='overwrite_bad',
                help='check existing files and re-download them if they are broken')
-p.add_argument('--forever', action='store_true', dest='stream_forever',
-               help='re-run program when the last video finishes')
 p.add_argument('--free', type=int, metavar='MiB', dest='keep_free',
                action=action_factory(lambda x: x * 1024 * 1024),  # MiB to B
                help='disk space in MiB to keep free (warning: deletes old MP4 files, use separate folder!)')
@@ -87,9 +85,11 @@ p.add_argument('--languages', '-L', nargs=0, action=action_factory(print_languag
                help='display a list of valid language codes')
 p.add_argument('--latest', action='store_const', const=['LatestVideos'],
                dest='include_categories',
-               help='index the "Latest Videos" section')
+               help='index the "Latest Videos" category')
 p.add_argument('--limit-rate', '-R', metavar='RATE', dest='rate_limit',
                help='maximum download rate, passed to curl (default: 1m = 1 megabyte/s, 0 = no limit)')
+p.add_argument('--list-categories', '-C', nargs='?', const=True, metavar='CODE', dest='print_category',
+               help='print a list of (sub) category names')
 p.add_argument('--mode', '-m',
                choices=['filesystem', 'html', 'html_tree', 'm3u', 'm3u_multi', 'm3u_tree', 'run', 'stdout', 'txt'],
                help='output mode (see wiki)')
@@ -109,12 +109,20 @@ p.add_argument('--since', metavar='YYYY-MM-DD', dest='min_date',
                help='only index media newer than this date')
 p.add_argument('--sort',
                choices=['newest', 'oldest', 'name', 'random'],
-               help='sort lines in output files')
+               help='sort output')
 p.add_argument('positional_arguments', nargs='*', metavar='DIR|FILE|COMMAND',
                help='where to send output (depends on mode)')
 
 s = p.parse_args(namespace=Settings())
 
+# Quick print of categories list
+if s.print_category:
+    # Ugly: may be str even if it should be bool
+    if isinstance(s.print_category, str):
+        s.include_categories = s.print_category.split(',')
+        s.print_category = True
+    parse_broadcasting(s)
+    exit()
 # Required arguments
 if not (s.mode or s.download or s.download_subtitles or s.import_dir):
     msg('please use --mode or --download')
@@ -142,7 +150,7 @@ elif len(s.positional_arguments) > 1:
     msg('unexpected argument: {}'.format(s.positional_arguments[1]))
     exit(1)
 
-# Paths
+# Check / set paths
 if not os.path.isdir(s.work_dir):
     msg('not a directory: ' + s.work_dir)
     exit(1)
@@ -160,7 +168,7 @@ if s.import_dir:
     exit()
 
 # Some heads-up
-if s.quiet < 1:
+if s.quiet < 1 and not s.print_category:
     if s.download and s.curl_path is not None and s.rate_limit != '0':
         msg('note: download rate limit is active')
     if not s.safe_filenames and (s.mode not in ('', 'stdout') or s.friendly_filenames):

jwlib/common.py

@@ -38,6 +38,7 @@ class Settings:
     include_categories = ('VideoOnDemand',)
     exclude_categories = ('VODSJJMeetings',)
     filter_categories = ()
+    print_category = False
 
     # Disk space check stuff
     keep_free = 0  # bytes

jwlib/parse.py

@@ -138,8 +138,8 @@ def parse_broadcasting(s: Settings):
     queue = list(s.include_categories)
     for key in queue:
 
-        url = 'https://data.jw-api.org/mediator/v1/categories/{L}/{c}?detailed=1&clientType=www'
-        url = url.format(L=s.lang, c=key)
+        url = 'https://data.jw-api.org/mediator/v1/categories/{L}/{c}?detailed={d}&clientType=www'
+        url = url.format(L=s.lang, c=key, d=int(not s.print_category))
 
         try:
             with urllib.request.urlopen(url) as j_raw:  # j as JSON
@@ -156,9 +156,19 @@ def parse_broadcasting(s: Settings):
         cat.home = cat.key in s.include_categories
 
         if s.quiet < 1:
-            msg('indexing: {} ({})'.format(cat.key, cat.name))
+            if s.print_category:
+                if key == 'LatestVideos':
+                    msg('Categories linked to the latest videos:')
+                else:
+                    msg('Sub-categories of {}:'.format(key))
+            else:
+                msg('indexing: {} ({})'.format(cat.key, cat.name))
 
         for j_sub in j['category'].get('subcategories', []):
+
+            if s.print_category:
+                print(j_sub['key'])
+                continue
             sub = Category()
             sub.key = j_sub['key']
             sub.name = j_sub['name']
@@ -175,9 +185,15 @@ def parse_broadcasting(s: Settings):
 
         for j_media in j['category'].get('media', []):
             # Skip videos marked as hidden
-            if 'tags' in j['category']['media']:
-                if 'WebExclude' in j['category']['media']['tags']:
-                    continue
+            if 'tags' in j_media.get('tags', []):
+                continue
+
+            if s.print_category and key == 'LatestVideos':
+                if s.quiet < 1:
+                    print('{} -> {}'.format(j_media['primaryCategory'], j_media['title']))
+                else:
+                    print(j_media['primaryCategory'])
+                continue
 
             # Apply category filter
             if s.filter_categories and j_media['primaryCategory'] not in s.filter_categories: