From e117cb75e0b83b3332a6b69921efc8db084e6599 Mon Sep 17 00:00:00 2001
From: Skullheadx <94652084+Skullheadx@users.noreply.github.com>
Date: Mon, 14 Oct 2024 02:09:23 -0400
Subject: [PATCH] caption

---
 ytdl/__pycache__/funcmodule.cpython-312.pyc | Bin 1731 -> 4611 bytes
 ytdl/funcmodule.py                          |  91 ++++++++++++--------
 2 files changed, 57 insertions(+), 34 deletions(-)

diff --git a/ytdl/__pycache__/funcmodule.cpython-312.pyc b/ytdl/__pycache__/funcmodule.cpython-312.pyc
index ca8b44a2d96b38f7a434c9bb262f6543bea4ec1e..f0891d8d30b073321d920d525a3b92dca624be12 100644
GIT binary patch
literal 4611
zcmX@j%ge>Uz`$U<g(sbnmx19ihy%k+P{wB;1_p-d3@HpLj5!QZ5SlTH5zJ?bVgl35
zQOqd}DNH#mxvWvFxolBvj0`EvEeuiYDJ(4vQ5-3(EeuhdDQqnaQCyXbn(Qw@M*C?p
z-C~c-FAXV8O1;Gqkds)MlUZDn%m|W$VpawQ24)5ZhR?IWPN-pUVTg5QV5ntGVXR>+
zV<=|q;V6NtuVGvbW!Ey*FlE7<4>bxzxiG{EGceRL*Dz#(Oa=)d;TmR`eny5KQ5J?8
zhAeg@X($t63nN31J4jV9gC>*TEsg@H2Q*oVSQr=>ZgG`mrljV_mlov|-(pKFC`ipq
zxy4qLnwwvis>yPTH77GKyZ9Chh`PmCaElqF4x~>(K|$e{zKd0iduB;SX;MsOerZW*
zQmSrBetBL_equ^$QA}k?N={5#X<l+}eoARhs$N0mExzQ8)a2}Vm>Y`t85kHi85kIf
zy%-o68W?U1h<32t;1-=Ba*12^j)24rk;!}=jyJ?5rq@iVnZSHQKy*6KM4lPJR|OP5
zFf&M~Jm3-R_v!SRA##;R?gKZ2px6f<1|Go%pU<E`K#3uclff~R1CF5-##%<C7-4{g
zXbMwy3<E=vWDR2qa}_Tr25T5nSgIr#7-|{tsAuevOku5INM}f4Tf|tyD9OOUkj7NS
z#=sEFpvmr61d8I!7t9O{FF_HX4sslWL%%~6o2s5+nrg8o%PodmjNZ2xeQz;3X)@ko
zPE0D+WV*$iSDJf^GdD3kFSDdHCAAo2ih@EBA1KoJk}}id^Gb8$)AEaQ6HAJu7#J9Y
zLE-2P4#yh;f(@Q`xOh8~yEP`HT;h_t!67&yu#>NY^9BcZM_DIt2lE$J25vrx{ADhw
z4{QuPA`^-)$>?w3yeMOJLCpFhxAg@U>mmUL1_qRX1SLptKw3Zp(uE;b1QJkLAm4#K
zhahSgQ<zqRT+RRr!X7bbLS**S<haGCe~Z!T7NgcJM*CZgO1BtoZZX>3Vyr0wc|?=(
z7JE@@K~7?FswUGdj<n32)V##p)LV?1DB-}9mRS)GlPpqaU|^62g@Q6T6mIjHb}-%$
zmcA~md{J0=f#ZUr%fecn93Pk&_{<(~3pe;<`c4#<k-xBk$`Wi*Udvd+m<0*}geSqQ
z)nJl=fsvsE6h>fP3P>#*n2AEnW|+$aOLB}1C7>Jtmak#V0+(}O4xGs1g)`xd6s9%s
zVgP1R3QM*N14A*p7efjw%r#9Q7m#6Q7AR-JZG$jU*kCqg2|`4WNtlhbOz8|M?28y{
znNv7wSyC8kSyB8agsca`hM5X+e^GP|vkOCP7z0BsTMb(cV-^-2S)h1=Xoiz8`@zMn
z0(N~hY@n=}B@WjFXOw^>z`Pp9EG#hwbK@FL7>kjihOL%0g{hW>ks*(f1v%Eau$zGz
z>orUS+`*Iu%GF>uAqbf5DNJj)Vfl)Yp+pv@B1;a&LeMpgSqcaqj0H0(O9>`|pljKY
z!h;E4c+6%<;hD=+%Tb~V(_O=n!V7bmDMKx14QCc8U&5rJbPYSqenwDD&5*(X)5FM6
z!&0;?g)fCaMIc46h9gA~#Vz>4L?}fVNiE)ZOcAMJoz0LUI+wYMfq?-OGbv&z;z+s)
z_<Al=idc$74P%xD)I&%V)HKN&#w;x)VJH(SD^;Qk6=0}g%+iCg5i~4(Ql#N7lp)rA
zDY76vDRSu|wOo1aDSRY^At=P<QxsC<Qv?Qoh>#o}!nIr_hOjWsGJ>%XbPX3Q+!+~4
zOkv_#W-u0luHhh7C5kKYq+c@3BO#3=Os`~6W-w$ZW-Mo7WQb&7WME{Nz}U09f;p0*
zoKaKJuS&!%wIn$sGcR4CxTGjGF;^iizepiOlkpZ;eqK&xd}3)zW<I!0Qzhk>uaH=l
zn3<E9l#{9emVoLh2DM^}G}&%3W#`{w%1XS&RF!dyDK)Q(B~dRsA4I0+xoI-qVlBxm
z$w{q}b%8b;LAD~B1GZa}sR&fO+~O_H&Mb&et;j4c$;?ZyV$sVgNWaBYo^*>XEiJbo
zHNA>eHzz;8;1;7{6_aje6|-(xS`}AuX%g6uV%sVv1&u0JO}*lxk}6K!+|-i9l*E$6
zDmJjRZ54ZBQAuWTiER~YN@7W>Z52myer|4RUWsiLn?hM;YI$)Lr*3gZeo;wkaY+@6
zUT%R&6_ajd6^m|eV!<s&15KGCP^;jU5TuC<4VKKD%#zAmtOZ4xc_l^qpr#vhPHNsQ
zc1Xw;-(pM4%qdANy2X)Sl#*H$pHz8^B`2}C<Q7MAVnIn}eqQk{mh9BZ;#(ZBb~U(>
zb4ws4H7&6;rv%>ixy4bGT3DJ|TvB|CIX$)H7H>&LX>L+pVrCAgWq*r3IX|x?HLv6r
zOMXFW-YwShqRf)iTWpD?B^miew|ELllX5bPGvYxW2e&0}v4VYk3lw?<Mfu68#l^Rn
zi%RouG36H*fto9t+(q0V-!N5{+~NU8SUki_w*;XskI%?VElMm(&H%OgA)bLm9jG^v
zn3sNwG5Hn?C<1N?A>0aU%H3j21GzajH!&}z7-SKsy8*?J7O+5iYDs)zUP?SXV8R#}
z7!*ORKRsqpU*Zm@zyy(Q*#@T%Tnw!2*I6VlvPfQGk-o#id4We^fzWb^g%S(6E^ujI
zVbOWQ&DT-XU)5Q4onPT1zrqTa3;YU~`3)~~8*K=@#BFwgCFFud$Yqw03*2Tmghi)Y
zO|-f$ta4FUWdq9vVU^3mrq_k-E(+W2D7`G~dR^G-qOjLxVV?${PaF)Aj*J&rL~n>n
zHTd1&=5KJh!_L)V)NkEseVJW+hT<i5>Dz)z9ga8n1tvI6_nzo|T}0)gh{|OVwM+bJ
zHw1*Hb5G=+;W&}+x`6sc0rfRGJB;>Q?6kP7=W;<n{fdC=4RMJHEH@NYC-B`A5dFZ-
zAf)_-hk=#r0*~ejrS%#sHC9Mn;4-<wVtRu`0OI>4HXC@Z8~9!{@V%_;cOfq60w_R|
zzkr(l{WhI8GnlSRXk3)gxXi72o!jstw_$_J9T|-kGS@Y&FKSv}ma(}YZM!4nf~3<0
z7O^{=ychTs7N}g|R9|6ugM+i5y_0<cOAqgNW(F>ek8BJaVh?ykZtw_C2)@B1a6w4r
z29LlLof$RP<!vs?+guj1y}=_mA!-TFilFroD<du|nC&pyk+LJ~fawKG&x;D47v#Mz
z2z%e)5uahUL}x|Kb$!Q+`i_^CoGvIjUyyVGiJLDlT5h?}a)I^*Nj(tXbb-)v`GxWq
z6bvs&8i52XmiTQj+HSGY;<Ad(j*5#a?iZ9jE=YRb;1R#WBQZnfx}^3+N$tx#IxEU9
z@|fP>5%?g<E6ml&{y~9(R}|B+5HAQ#aK6C<CaCW)9Ig`Q5$5V(|02b}%HQtS=r_Uq
z3XAj?HU?JqcF#u73w#P!SQPKDuz@%|IWugoOIuu&wz$k^d4<IaA#60?Vy4AqK9v<h
zD_mBXZ4kYnZhn!^{3?sZcW*`pE{%(v>c5J47#J9iDGB-NGN09D^)+YL<i5p{o|B(c
z1nN%~c``6C6ghyhJ7+;9sF$CXSphEWz#|CYPCU5O0GCZgpnSNJ0o=EOWK|BE+<edg
zfL&1(1E_z*z)-Boz`*c<nURt4HUsx<2F}|If{z*a?=z@>Vq<3%{3OE4X!A*cnNj33
Lk252qCD<qc<N4#k

delta 450
zcmZoxIn2v<nwOW0fq{Wx<}#l2$($ScqFE+)GjkekV_;yI&QQV#k^<oxhSgAZEn_-E
z3gaTiTBZ_akPHadFlMn#4&anFX3BP9U??&I@j>FK*o7fhiGiV(xr7}iUc;EhF<FsO
zSc^Fe><E}RgkH@Ap&1!^R9F})87dhxnf)g3;Fe1$0?BBy6@eUZi#aDX?-oaLVnIn}
zeqQk{)`FtUypmh2C7C5Tskb<D67$mIlk-zjHCc+d85kIDF;$k_5`?Ob&&W(IN-Rpw
zsJz7v6)I+7U|^Wc$tP29%D}*&$iTo*?8Cso(7<qqQ(%Hfw`_ycCn*L=N5%^*qIcN2
zI*j_QJFPFXi_cKJ#4de9TylE#l<E%mJ3N9Dl%{J;)R^IZT}Jn!jP6w)y^qWc63QQ#
z88~E$1Q-|?G`VlFr03)(-D1iwzQt8snp9AfpPX7;e2b$fwXig`xP-BIa)+QQqv_;z
af>K;I3=9mQ@GsVwd`VD)Ly%D)YzP2k1#2S!

diff --git a/ytdl/funcmodule.py b/ytdl/funcmodule.py
index bb45b47..81f8319 100644
--- a/ytdl/funcmodule.py
+++ b/ytdl/funcmodule.py
@@ -36,42 +36,65 @@ def get_and_download(link):
     #     print(f"{yt.title} is already downloaded")
     #     return
 
-    # yt.check_availability()
-    # print(f"Fetching stream for {yt.title}")
-    #
-    # assert len(yt.streams.filter(only_audio=True)) > 0, "No available audio streams"
-    # audio_stream = yt.streams.filter(only_audio=True).order_by("abr").last()
+    yt.check_availability()
+    print(f"Fetching stream for {yt.title}")
+
+    assert len(yt.streams.filter(only_audio=True)) > 0, "No available audio streams"
+    audio_stream = yt.streams.filter(only_audio=True).order_by("abr").last()
 
 
     # hierarchy:
     caption_hierarchy = ["ko", "ja", "zh", "en", "a.ko", "a.en"]
+    caption_exists = False
+    lang = None
     if len(yt.captions) > 0:
-        for caption in yt.captions:
-            print(yt.title, caption.lang_code)
-    # print(f"Downloading audio stream for {yt.title}")
-    # audio_stream.download(filename=fix_filename(audio_stream.default_filename), skip_existing=True)
-    #
-    # # create thumbnail file
-    # data = requests.get(yt.thumbnail_url).content
-    # thumbnail_filename = f'{fix_filename(audio_stream.title)}.jpg'
-    # with open(thumbnail_filename, 'wb') as f:
-    #     f.write(data)
-    #
-    # command = [
-    #     'ffmpeg',
-    #     '-i', fix_filename(audio_stream.default_filename),
-    #     '-i', thumbnail_filename,
-    #     '-map', '0',
-    #     '-map', '1',
-    #     '-metadata', f'title={fix_filename(audio_stream.title)}',
-    #     '-metadata', f'artist={yt.author}',
-    #     '-metadata', f'date={yt.publish_date}',
-    #     '-metadata', f'comment={big_num_format(yt.views) + " views"}',
-    #     fix_filename(audio_stream.title) + ".mp4",
-    #     '-y'
-    # ]
-    # subprocess.run(command)
-    #
-    # # clean up tmp files
-    # os.remove(thumbnail_filename)
-    # os.remove(fix_filename(audio_stream.default_filename))
+        for c in caption_hierarchy:
+            if c in yt.captions.keys():
+                yt.captions[c].download(title=fix_filename(yt.title))
+                lang = c
+                caption_exists = True
+                break
+    print(f"Downloading audio stream for {yt.title}")
+    audio_stream.download(filename=fix_filename(audio_stream.default_filename), skip_existing=True)
+
+    # create thumbnail file
+    data = requests.get(yt.thumbnail_url).content
+    thumbnail_filename = f'{fix_filename(audio_stream.title)}.jpg'
+    with open(thumbnail_filename, 'wb') as f:
+        f.write(data)
+
+    if caption_exists:
+        command = [
+            'ffmpeg',
+            '-loop', '1',
+            '-i', thumbnail_filename,
+            '-i', fix_filename(audio_stream.default_filename),
+            '-vf', f'subtitles={fix_filename(yt.title) + f" ({lang}).srt"}',
+            '-metadata', f'title={fix_filename(audio_stream.title)}',
+            '-metadata', f'artist={yt.author}',
+            '-metadata', f'date={yt.publish_date}',
+            '-metadata', f'comment={big_num_format(yt.views) + " views"}',
+            '-shortest',
+            fix_filename(audio_stream.title) + ".mp4",
+            '-y'
+        ]
+    else:
+        command = [
+            'ffmpeg',
+            '-i', fix_filename(audio_stream.default_filename),
+            '-i', thumbnail_filename,
+            '-map', '0',
+            '-map', '1',
+            '-metadata', f'title={fix_filename(audio_stream.title)}',
+            '-metadata', f'artist={yt.author}',
+            '-metadata', f'date={yt.publish_date}',
+            '-metadata', f'comment={big_num_format(yt.views) + " views"}',
+            fix_filename(audio_stream.title) + ".mp4",
+            '-y'
+        ]
+    subprocess.run(command)
+
+    # clean up tmp files
+    os.remove(thumbnail_filename)
+    os.remove(fix_filename(audio_stream.default_filename))
+    os.remove(fix_filename(yt.title) + f" ({lang}).srt")
-- 
2.54.0