From a16268b2e9dff80ccb4ee398bda493e040554a84 Mon Sep 17 00:00:00 2001
From: girst <tobi@isticktoit.net>
Date: Wed, 15 Dec 2021 20:29:47 +0100
Subject: [PATCH] implement /watch?show=meta to get metadata removed from
 ANDROID api

---
 app/youtube/__init__.py | 10 ++++++--
 app/youtube/lib.py      | 56 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+), 2 deletions(-)

diff --git a/app/youtube/__init__.py b/app/youtube/__init__.py
index 62dd1e1..e2ef6b0 100644
--- a/app/youtube/__init__.py
+++ b/app/youtube/__init__.py
@@ -78,7 +78,8 @@ def watch():
     }
 
     video_id = request.args.get('v')
-    video_url, stream_map, metadata, error, errdetails = get_video_info(video_id)
+    show = request.args.get("show")
+    video_url, stream_map, metadata, error, errdetails = get_video_info(video_id, metaOnly=(show == 'meta'))
 
     proxy_on = getattr(g, 'proxy_on', None)
     proxy_msg = {
@@ -130,7 +131,6 @@ def watch():
                 Please try again in 30 seconds.
             """)
 
-    show = request.args.get("show")
     if show == "raw":
         if error:
             msg = errdetails if error=='player' else f"{error.upper()}: {errdetails}"
@@ -154,6 +154,12 @@ def watch():
             reverse=True
         )),{}).get('url')
         return redirect(stream)
+    elif show == "meta":
+        # this is the subset of (useful) keys that are not present in the
+        # Android API response. the special key '_' contains ready-to-use
+        # parsed versions of that data.
+        parsed = microformat_parser(metadata)
+        return {'microformat': metadata.get('microformat'),'cards':metadata.get('cards'), '_':parsed}
     else:
         if error and not metadata: # e.g. malformed, private/deleted video, ...
             return render_template('video-error.html.j2', video_id=video_id,
diff --git a/app/youtube/lib.py b/app/youtube/lib.py
index afcf8a2..0c83d91 100644
--- a/app/youtube/lib.py
+++ b/app/youtube/lib.py
@@ -62,3 +62,59 @@ def channel_exists(feed_id):
         feed_type: feed_id,
     })
     return r.ok
+
+def microformat_parser(metadata):
+    """ parses additional metadata only available with get_video_info(metaOnly=True) """
+    meta2 = metadata.get('microformat',{}).get('playerMicroformatRenderer',{})
+    all_countries = """AD AE AF AG AI AL AM AO AQ AR AS AT AU AW AX AZ BA BB BD
+        BE BF BG BH BI BJ BL BM BN BO BQ BR BS BT BV BW BY BZ CA CC CD CF CG CH
+        CI CK CL CM CN CO CR CU CV CW CX CY CZ DE DJ DK DM DO DZ EC EE EG EH ER
+        ES ET FI FJ FK FM FO FR GA GB GD GE GF GG GH GI GL GM GN GP GQ GR GS GT
+        GU GW GY HK HM HN HR HT HU ID IE IL IM IN IO IQ IR IS IT JE JM JO JP KE
+        KG KH KI KM KN KP KR KW KY KZ LA LB LC LI LK LR LS LT LU LV LY MA MC MD
+        ME MF MG MH MK ML MM MN MO MP MQ MR MS MT MU MV MW MX MY MZ NA NC NE NF
+        NG NI NL NO NP NR NU NZ OM PA PE PF PG PH PK PL PM PN PR PS PT PW PY QA
+        RE RO RS RU RW SA SB SC SD SE SG SH SI SJ SK SL SM SN SO SR SS ST SV SX
+        SY SZ TC TD TF TG TH TJ TK TL TM TN TO TR TT TV TW TZ UA UG UM US UY UZ
+        VA VC VE VG VI VN VU WF WS YE YT ZA ZM ZW""".split()
+    whitelisted = sorted(meta2.get('availableCountries',[]))
+    blacklisted = sorted(set(all_countries) - set(whitelisted))
+    regions = (
+        'all' if not blacklisted else
+        'none' if not whitelisted else
+        f"not in {' '.join(blacklisted)}" if len(blacklisted) < len(whitelisted) else
+        f"only in {' '.join(whitelisted)}"
+    )
+    try:
+        poster = sorted(meta2['thumbnail']['thumbnails'], key=lambda t: t['width'], reverse=True)[0]['url']
+    except: poster = None
+    infocards = prepare_infocards(metadata)
+    endcards = prepare_endcards(metadata)
+    # combine cards to weed out duplicates. for videos and playlists prefer
+    # infocards, for channels and websites prefer endcards, as those have more
+    # information than the other.
+    # if the card type is not in ident, we use the whole card for comparison
+    # (otherwise they'd all replace each other)
+    ident = { # ctype -> ident
+        'VIDEO': 'video_id',
+        'PLAYLIST': 'playlist_id',
+        'CHANNEL': 'channel_id',
+        'WEBSITE': 'url',
+        'POLL': 'question',
+    }
+    getident = lambda c: c['content'].get(ident.get(c['type']), c)
+    mkexclude = lambda cards, types: [getident(c) for c in cards if c['type'] in types]
+    exclude = lambda cards, without: [c for c in cards if getident(c) not in without]
+
+    allcards = exclude(infocards, mkexclude(endcards,  ['CHANNEL','WEBSITE'])) + \
+               exclude(endcards,  mkexclude(infocards, ['VIDEO','PLAYLIST']))
+
+    return {
+        'published': meta2.get('publishDate'),
+        #'uploaded': meta2.get('uploadDate'),
+        #'infocards': infocards,
+        #'endcards': endcards,
+        'all_cards': allcards,
+        'poster': poster,
+        'regions': regions,
+    }
-- 
2.39.3