From 72a6a7bef661d4801872d57b4c127962da475a58 Mon Sep 17 00:00:00 2001 From: qo-op Date: Thu, 4 Jun 2020 06:23:22 +0200 Subject: [PATCH] CopyLaRadio sbotc zenyta command --- .../artist_song_to_sbotc_zenyta.sh | 38 + zen/_CopyLaRadio/bip.wav | Bin 0 -> 14488 bytes zen/_CopyLaRadio/copy.sh | 99 + zen/_CopyLaRadio/install_osb-studio.sh | 10 + .../libradio/FIP autour de llectro.php | 75 + zen/_CopyLaRadio/libradio/Nova zz.php | 1 + .../libradio/fipelectro-midfi.mp3.php | 1 + zen/_CopyLaRadio/libradio/radionova.php | 74 + zen/_CopyLaRadio/libradio/simple_html_dom.php | 2808 +++++++++++++++++ zen/_CopyLaRadio/parle.sh | 12 + zen/_CopyLaRadio/sbotc.sh | 3 + zen/_CopyLaRadio/sbotc_zenyta.sh | 2 + zen/_CopyLaRadio/watch.sh | 212 ++ 13 files changed, 3335 insertions(+) create mode 100755 zen/_CopyLaRadio/artist_song_to_sbotc_zenyta.sh create mode 100644 zen/_CopyLaRadio/bip.wav create mode 100755 zen/_CopyLaRadio/copy.sh create mode 100755 zen/_CopyLaRadio/install_osb-studio.sh create mode 100644 zen/_CopyLaRadio/libradio/FIP autour de llectro.php create mode 120000 zen/_CopyLaRadio/libradio/Nova zz.php create mode 120000 zen/_CopyLaRadio/libradio/fipelectro-midfi.mp3.php create mode 100644 zen/_CopyLaRadio/libradio/radionova.php create mode 100644 zen/_CopyLaRadio/libradio/simple_html_dom.php create mode 100755 zen/_CopyLaRadio/parle.sh create mode 100755 zen/_CopyLaRadio/sbotc.sh create mode 100755 zen/_CopyLaRadio/sbotc_zenyta.sh create mode 100755 zen/_CopyLaRadio/watch.sh diff --git a/zen/_CopyLaRadio/artist_song_to_sbotc_zenyta.sh b/zen/_CopyLaRadio/artist_song_to_sbotc_zenyta.sh new file mode 100755 index 0000000..f5e4c0b --- /dev/null +++ b/zen/_CopyLaRadio/artist_song_to_sbotc_zenyta.sh @@ -0,0 +1,38 @@ +#!/bin/bash +ARTIST=$1 +SONG=$2 + +echo ' + __ + __ _____ ______________ ___ __ / / + / / / / _ \/ ___/ ___/ __ `/ / / / / / + / /_/ / __(__ |__ ) /_/ / /_/ / /_/ + \__, /\___/____/____/\__,_/\__, / (_) +/____/ /____/ + +identifying' +echo $ARTIST +echo $SONG +# WHOAMI=$(sbotc whoami | jq -r .id) +# sbotc query.read '{"query":[{"$filter":{"value":{"author": "'"$WHOAMI"'", "content":{"type":"zenyta"}}}}]}' | jq -r .value?.content?.text | tail -n 1 +# this command is reagularly is run in cron_MINUTE.sh so your stations then take cae to miammiam.sh your youtube search +# +# We must transform that input information into link to copy from +# We are going to use youtube-dl dry run. + +# http://golly.sourceforge.net/ +# [@Christian Bundy](@+oaWWDs8g73EZFUMfW37R/ULtFEjwKN/DczvdYihjbU=.ed25519) +# thanks for your security hole spotting.. +# I know that this could become a badly used account... + +# It will be introduced as a learning account. (being able to regenerate). +# the above algo rythm is calibrated on the "game of life" mixed with angel problem solution. +# will it produce "speeders shapings" i hope... +# %EDlmG9QW2U2wYnvIIKf//GrDxYoQWGL/Jk3Nw0obi8M=.sha256 +# http://golly.sourceforge.net/ +mysearch="$ARTIST $SONG" +youtube-dl --default-search ytsearch1: --download-archive /home/pi/.ytdl.list --continue --no-overwrites --metadata-from-title "$artist - %(title)s" --add-metadata --embed-thumbnail --ignore-errors -f m4a --extract-audio -o "/home/pi/.zen/music/${artist}/${song}/%(id)s.%(title)s.%(uploader_id)s.%(ext)s" "$mysearch" >> /tmp/youtube-dl.log 2>&1 + +# Finaly this is made directly.... +# so it is not put on ipfs... zenTag must attach contracts... + diff --git a/zen/_CopyLaRadio/bip.wav b/zen/_CopyLaRadio/bip.wav new file mode 100644 index 0000000000000000000000000000000000000000..1028cd4e4cf479df658fa5eb32b08ba519f0a639 GIT binary patch literal 14488 zcmYj&bwE_#6Yn;Sgi5EhNOwzj*9M)tVEeVdcI($J*j~Cjl}5T71e69TrG(9Q{k`|c z+rwq=o_p>&b861ad}e%I935YofIvYf107;dU6dCBfk0po1a$i|aI*mc!9YTw=!lCE zea66V;KSmuICKt!BMdqO;s)^o7Xriu;sKtpIcyGx!vvnOfV;nC|8Vv=5TLHVCAfj> z@Ap1up92H(puj!se`V-EeS4g3Ab%hD4+H8t1YC3u7@&g=)CU9J{riD~wm82ze>l59 zX$FTEcv}!8{J#VRN-}^JSwIb7ApdXue>ev~ZCd~>9F8D}AE1;EDD{7zLV?y{|D%8h zcwZ270F?Sm!7rfx9pDZGVghu-fzlx0`619AK*b(s6X+ET=mQ9(4mtr^=lld{VQ{KJ z6`%}I4(KE3J!le0Xdr#yeB^j=-2T^tzj;g$1GEA91!@H~ff7MyfDt_eas#=7szIMY zAwYRDhsG)3mxEs_BlHiDOZgK8#hQa;dKF9zh0vrjh=2UU|*+cAG z>>KQ_oOX@?loz@WW5DttSr9yj#CgJb$O!}mfKG6KCC|FPacv`JEqbkW|a!7x%7HS7-JCZa0$bMDdH zBe@nZb68AZOyF&&TTUwr%M0m*G=g`HZ_QoRo2q9{UpzhQHtAM1S2sr>ejxJJ3DkKi zxhvfde;9sM=cHPZv!WEs7|K@UU~UV~(;$ zdEfKCH)}R+mNJkvK%9r3-#GdEq}8z1u-iwMkJ4Y|zD{e6Y0XA0MyaZ+s87~R)NFqI z{gHcycP7?7(%tNo)hSP9SLNUuRLxub8+`kZ&L5xb-`fYFk!Uh6h4)GJ{p`8arPNkX zGbkc7DwHdnJG>ZCfC$P#=Co(DX4JCl*g^im{vvLN-0W5zRyT>O#5a}iE5FJ$$@yTt zvGyJg9xf}+D=-S2Qdm`3Wi4eX)sE@HSQr``%JdxTkxDv}^t10*UxWDsA$&xANZq*Js6PB-^heD})k!@k6Q}XSp~MXJEcKH5;`*0KFO$T+iGPFIKx{fu zov3sC=lE}D-_Gu&bW(oMXXsoQ1m;Q9v#4mka6V=>D;q)MqK)ql@1y*}{7!hPdLCYv zTz`;!FFB|PT~sDnDtRQ~NW!k~j_;Gz=c`_LS3IN`QCuljE|wma9%gA~Z3gOP^q9Ui ze@kwowkeoMnT(vBIy+@PYM#?m(1U#+_kO=^w=G>SORpomHGD>HUM{LUqP+KG??>7K zZ6VAn%nO+iobW*IpC}^HHfcsMBiMBK z_weP=%8^my*koOF_Gl3JBY)w1HUqC+_U6|$>UYusxHZ0lFJFn4w=!O*FI?d)7ts5=ObZ|IJjcDU@4O*mx$C2(A8|y zY70vWPkKN2cJQ*vWfM1)J1R;vLbSZ7qG*;pL%#R>!SAzvXZ>8FoueHNJ08v|&M2;= zR8lyb?9DT7XWb?}Cp^J>kiB?X9PLQKkpj{o(jl8j>&Wzgw1Aqu+P&zM=oHlgrGlUQ zYy71_`9a?;<}5nX7qY zd@z@kFDc)zyI03ZVkDJKl})8Pq&t}6OmS*zs%i!G1@)!L<;mwK&rkMR_gdQrI|du^ z8t_`=SmpH4x@php&*-<2_mRINRwFokP=0i7U~VbxGc9&MazDTa=~LvE?z1~J_ zAvTw^lsp%IEPg5WMy#lhpwGzq_&PtCkK9($R#JJS`p7hD3iaIRnbDKJr+u@ZzJKcK z?CBIY6f@LMFi3c8`p7h_KfGT*SugoU=e5qqI?r@0(8lOFsRb#iN|{PKqBXH{`O7lW zBhX_rb}JSv1Cse#*;t3fmvuA!diuBQ$?RfyDf~si^8i;{PutiZkw4<`3HVpFFKb7XN0is%*W&dZ^&Ck* zC_mB(DFn+}>)Hy13WZVh2pX=5(3EMBYMD)%PbwWP9Nn=#uvWs!<04N)o=|U5Z&AW4 z;3Y>DM#Ig}W;#e6WVKL@kZ++^VGtEfeYW#xhbKTVpewR9a#(0W=yl!Sq~ z4k;Md7}Zn|DhZ-@SRCCo$<2*RiFMr8;swnN&@x7L__IWr?&zX6R(<-0r^9?Lu%RpaxI_R1=a( zT6|`_tiFW4UpKOQiZDVD9XL7wH-H+P4ZaXOa&+h@vm9Iz0gU7J`u_SMFJ7Uth|ORUT`L{~CYC z`JS`?ocG*m;(6lem%%Sb<;CTVFnSo2R*05Dn|#}L(oT}Zh{VV}t2Blx8g=> z12yw^=I;^rA@|E(SG}malwB5;P5oK0S`a53C2SsL6SWD@8M+(3Ymj1)@}Tg3VY*xbu$D4S@Tx`5h%4z3O^ zvE0MCW*Jr)mK;+K1Ia=rhkOe8m+J=C9x(atnXZ}kEN9jc9}%Adr$Q&~pSnMvksp)e z0QuBh#zck@!;VpOmv^6CSy(Bh6j1)FdQ&waF)D#TaiL1|%Jd?7!g?_H5PW<;u7A~J z(c}kq5t|Nl@>0(~J$Zy&0$=~3{#E@2eFRDnbxZt`cujd@xfbOFWpe%7x~{jrw_c2P z%!c@;xNLSgv!>5+A2Eg)LnBQy?Ij@NdGUMl>qO{AXa#Er57B$+ zlW9NFclue*b^;FH&ZTua)c;nGVK@CBT`?$L}VS7>g$f<}a3;{#n zZRBs%SJ75!z%*l|)Wy`Ln&g|Zk~5MuCXY{Ew!dV5I6*YwvBq-^RwKPJ9iNTA{q4rL zi&j^xoRKcbFafjxH7_%7jW$C&e{l1_8fk=_kNg>VSKy`qPd;CMTS{xnuRoiAh~5aoDc49YUFZtf^jo*ye)S?(r3@R z;yvg#n3j~CwAeA<@zLO;!MVf>iJ9i9<^uym15c8lC4cXj?D(a*rc*xNZA&4-{76N6(Oft$0WIM~~rw1Z))Aaq{sE z^cFf>F+*{`hFQ~x@4~0dq|e-T{?|DMi^U2l2`JsKc~J9#@QzSBQ!_)grP&$<8V5Qd z91%-d%UO+SwP`3$29<1#!lJ$jeBmL*AYq)V0ODyt2a=!-LmH%LN#Ks^$FCeB~ZQyxkRCk?Fjua0?* zd9}v2$9|LeCNWwzT&7PpCa11aR(G8Doa=q+eLgVWF+Qf^Q=N0{bHKb1-eVERBIc0u z$Sg(%gOW;3J(+8rJHtK0T@zRzSZb4Rg9h|-W-=prp>Dp8t;$h-jC+hDJ5U^ir-i34 z;?LtB)jzH;Rw_~2K>tE#s;8^lH#;?ZB)cSE8oxF^d2-?;Zvt0>v8K5utQp+QNM8mwNaLr~@73)&1vv(pMwvzJ2>up)mH#$>kv2z5*gLi7 z?d9c_`2Iwu9&_Uv>(#%-(NR>@lymS+r`_(ouZwh`Y3&r zpsAoKWC%8NCMhwAzg?*PmflUh@q}*)C<}~5>|pqyQL;tyO8Zj#yw;-D9I$?&a!|Rn z>Wu0jLLlMF!i|M$w^FyV_{#Vr@}lyX>agm&#M{K2h1>euZK=!<}k0p|ADC)85wa|QCZGVH)x)Jj(>)IrafbhF&9IKA@qLk`}{!h zz9IsPz}|DY=kk8;!<;fviTL=-voH7LZp)oQpF!(rX=<&st+m-D+a}8l%MT}6ezF|L zP2eu*T-51p>uK}G`{JdCrH0i^)J-&z>PW2UDbcm!m0|>yhr0KB>$ksOke_(8STrE& z9OfzEE%`-Vr?&s<`laHg>{jTR=b5pWy%(Mml9E-BQ&4@V>d=|U(~$)MMFBVWZtj(( zl&9<#{3(zZkQDF)WCv+WG0WEz?P_?=^q%sr^8JR#4I%_S0(ClbI?*BCAsQQt#i(Lb*Xq~mJqccf%&E*NOKVGO zyCAzD8lW>v=gH)4rEaATGlm#np z6(k++*68ju>M}Z(D4+PB$!n8Sz45)zlHMdWc75&&(~HrY!VF`^rKhEBE3GT7h$o3R zR<5r|cu9Nd#cRdeNjph%Rlq9#AzmhaTK=$n+WD;Wpnsn~l7r!lrH!N=WYM#(a$n`9 zhttFD(e~&MtoJP4G~F~@c0zV7q6QHV6c{9Af5_f*#&hN>{u;iwwx?EDRaljVOT`sC z7CHuhM}B{Ze}Lbp{Z&gkMm%;tscKCI^v==F8?k*uAkk@Mrl?!@j|k za#V5<+0g7yP(1WG<_YEw=04^yOavyGBb9R!&;iuI>R?4b1wR)@H^GuGP?YLXwWIcBwqRS_U%l!3tbIaiQffm%Q$hBj%tP=fo+w7(pFoj) zk^SP-;#BcM@xn-f2!W@;&w`h%7Oi%_?R>K&SQ8At8h+(yax^D^eLZlp@8s&l#srx_ zAn1QJ`f8?btlo@i!%$R`RcacV8#)M$1nwU~Kk5LRDg(>Lx~e*P;2G1G~E0>*nG5uot7GsM6_67Ss zc75b}bX|P?I7N+et>WK`|D>Kt$;8RVo%TBI6|m;F=1uXVJg&H3aaa7IxG-7}{mpRF z5Z#aN|BC;L_wM!VH8M6eK9QiFuw%S${H*VB-yi%wzPP8f=Ptl!6Vd0;-=s#QK2+hW z4pI0iwySolR8N}cx7hJmOKEHAy~^E6Foi>2Tv=JEa4L1u^3(M*}qyEMo@-Gu1IbnA|C+{$S@8r$6BDc%togq6Q>zuhjNm_x9RFfdZqtn$z-^z{ zJn^LEc}oMn4v!uS8GB*=%={tpDe|Y#lF;d*vqg3(_9?gb{@r^X_$shI>T}ep(1ws# zp+{jWt)0fT3*X)H-1hwYIk|1KJxm>=-YLFS+;O<`@Q0Z9G0*&;`=8!AwZ*1zDCsIViT>HHF`8DAMA$u-&PSQcb;Y(mm zU@NQzW{_o=m79^B@f`9JawzmrD0diF*mc+q7&()anVf;oa0WYrT?1SL2u^sX^~H_F zNMa-rRgJ7}kZ+W~h`oqSaL2lzT|B>NN;DycREJjE$Xd(pVfHW&bRX(I?R?gGI{9?6 z!=T-ugoTuaVxnwftA2+*q7&Ykot&90Gr52_l3b+bR2LgChsYfXt#(pk0v5pUbZoY!JL-_1h|9GHUWB;ReB?*{a#XA8S@rlU4Hs>`yEey2|IqnnoxQOgue(b~@ia-@X)Ef~{ApS3BEywo!$s zLKK`9oKCX-WPLg4Qjj2@FyDpzbNQ<2YU$mK4n}YAKyX%gdUy(73ZG5BZN5jkOZqT< zoc_yu!`s%?*0q0qVEqvF5LLQDs-jO~K!Oo-5CifCdsEga>%bpHxI(C+6tF=OP|2uO z!!^T>{*L}0d=LJ3k4Dds;i%zXSy|Xr%=B9Sh5j~tFMg?erdvu+Uhh5n7200fS^6&? zfC0|EuPd!9l^*3DcjE5F)yve$q*T$Wu92^irB-BCt~yt^cy)j!zEF@0Uj@Mc!S}J;CJTXI>Lz)|{8?B%5pYbANB4f?g&DKf@N(r&r zvD$;JL#?a$pZKKFq|sHgpJqeI5#*%sgfO@mT1=&pX^lJ0J08Hg(~j1Q9ugT45iAxe z{!W{wec1l6-QdyS@yYX(XZcR~&J3ViRTq6J0zeZHiD>C)g#ej=&Yj*Ji4?Jv>7wsN zRYH|QUPv!wrg@gR;+Vo%3%&*4*V@-g)23-d6JQC>)(+O|qrXR408c7vEpJuVRMCvV z#9-zW7Zrz@G8ORu1=(^O^1n{KXf#QKuqkJPcng=~`bo8iMnMGMSrIhk@vwc&?SKYTL zrZVP|*l96`GWRkgsy=mQV|K$8upJxw82j8mcyK^YrKGmyf6dnv)E4xL^o*LqUSja9N|o%%%?fea%SN(aJxYJz;(Mdy9=}b%!(3)h~H~xYws!FQhts7 zfJFcd_v-A;*+F72v9-3X7BG1!)??~1;wQvU+;4r*8jcUe-yXX?hO|N32qy3*3~7yP zCAGe8l_#hWRz~MX1I^LqiYPf0S{N-XS0q=IMoXpj?Dp=e1*!%PL=8kW2sa2nEP7ZZ zlOmgPVduh5vuA^6CLrfO*uJ}6My;Sq6-yO612%tn3|Gu`|EvDQZSwY2+EtoWu~l)u zaKEq@$_sVMJkh*xqLi{oNeKy-J%kJ;k1jB>i zn%SD!kW6^y0{91*j7i0Kg}R3>!WZEO*^F%OOwY_80G?js_r>q3(^aQGOM6QZq$tvV z)z7L6fKLC3+lzB`cX9Vw_FdK|>yzcH<*O~Ft)wf^W#}c{72V9P^e%n8A%0|Fc%ag( z(hQscNr*HEH&E(U>2Alj;!FE0`b!Oq4Es=hs06W7VoPQ7Wqp((itMK3=5Ze_p9eAb zV#wlD@jK>6|m(*^ky=r>e6hJ@`^ry6^w(NH70PPBEpkb(y)s)#3Nr)m0eH-|e zV0FssMey_B4E`+s|MLIKXQeVyU(?^yPX%LxLn6W=05O|CD?c;8J+(8Hv`^T7bvn;o)Tf9@8JC-Z9)4R|6$;O=x8YP>eRi;`deN^e_HfjUqV(ek; zJK!;}2k85P-F)5QhLMIY3C;=irVXZB{lEHmlm8^kbV+w9>#FDmU;;4FGSM>e%+GKL90GqWe{H8im%=5?KbStveoe<#hgLg)pSq8^j_q6TTc-f}m7kW6 z)-2$IV1>8BbC1GC2h7IIR*?%xJ7FhbwIbD`Xj&A_WY>K6VZgnBps3)ex596Q-HY6d zFf)N+)D{|Wz}+e_O|Y5&n~6kRFu z7YY_SiWEhn%`xVrQS#_T{002?*6*!2ZLGFE&KVbN6>4>A^wMZOz8t^N@~6e&xD{Z3 z+D5l3HY--vR@KTA6^IVAcC&p>{Z5#8OgxtoLaDO0y4IQKNYtFsnvt@Vu-y#!9pH$t zM{H#O&c2gzD{wKs%{At2#HiG({642osZ2lh$??c0yQT?7rH*T1I1fqb5O%(DSY9 z+kMN2mV7}xL0|al_^#z&%CAhVP3=2qKWGZ-2-*(c2-oE|;GfT%%hO8LO8xm~<7=3NFhn8}Qlh zGoF-8GF~!S%5=+g3y%wn>yqt}^{w`)wkJ7|)D~42c^w2CV*SGX)WBL`X69bzhwS9+ z5Ab*J&5(_dv*-)x4$xPSWTt$kMz%_JDl{D$>L232Xt!V|HZL(RMB*pa)HK$39dkYQ zDE?VI$(i6B2;j^VVhT~eMyIAvZa@x-hM?b^czxnp`^|O_f(v14556F!S)Sh_O!q&Vgz}wi#+0Yj0rJuwGVPR@0-?qv?bU!d&Z2Yt-@B z;|^$Bw7+7YqH~>7oiE9c6gr2QQ*c&x-iq6ZD?CZBJJq|@qq1YNDsjqjR_@mB+$)F`1cis9Tdi5`Cgm>m0QC?xqC2EJ);-;=L(m}f z4h#$gngy7x83qpl($8 z)cPm_I(e-`y@YDHYIy~@jEq_fS(9^>c6IV~@wH-DGC*mdv`cxH^S<$q^K&A>QCL(Q zDu>TJ$jP6SUFPc|?|LAC+5Y18S`(s(KS$p+hoI1Q}E!^DS)0geHVdsBN; z=6G{_K7hk7DK9FAhJ=QQXozZ@X+G5~L69MgO%6^b+Y{~m5&{xNH2MLIQLU*D&{3+t zReqybrCRL+{x;_Y{t>ueaIfG)+K03;Krc!P{ut~V;TN&Mzr^oS;8?JhwwV@m;D5mI zVtLKF&bR__<>p@=TUk+60h5GC5@RSanO>=0avR4swg7vjXN7;o%F)@QBgkpwJ)`SJ z7YDBoz9qgOB6~5t&4$f}UDz(HxQUpF^?=nt6S0}N+Oyo_rt6`53WY;Gk$xuq`tz&L ziPY27wVx|L9Xy;pcha<|Y>b^6 z6USS%TkQd#f}!z|aUTmWi;u|nNVX72II$R8ERiOYc4Gg;{$SuxV0L6)q?eGF(2b(2 zMZ9T(Y1Mn>dq!RsUQCZ2kKyfa+wCb$Dfy+PrTIrPk2FWOM!)rY>1Vucv3)V+Y>E_s zFTq6NqBCRIZt!6vURij!0q4<{&@cq0Au7VbCyde z^P7c#BFG4U}=)_gJM%-QA3kWla;|pV7hgCfW0){{ek$N`0wzo zVUz{hVjuShN7bk4pXff(oe9uhIaD^3Z(L+-iZ(=(#b{z?6{Z!)l;D)C-#NdHe2si- zqCZDp6T2biUEy6Jkjj_(^w)pC)ZJ9vioMIdW9iX!@eJ{dr$x_-Mh*=g@{aV2LyS9E4Ei`e@?DU zz9GFMiL?l}IH^0T?_>5c4^^M2o@q*KvL@M(f_?=4uynL^huDB@5`s4FV@N3jJ z(lY{FwFVpknc`C4#l9!TPmC*Z6}WNZN#l+F)&AooEs{x}QJ<{7to~`hmfIrrRcgL! zz6uP0>_cn)YhS$TyvkyWV>hI>q_(Oys<>!;w35~QRh;t~XL&zKKL#7ZG0fD;yqtF< z?+Nci-ofzU@CT^-C=B3}Dga=Q6M2()O@PtPDabWw$#%*1@yz3y9pV=8T*LW>2Gv^C zDeMfE0uUED6E$;(beE*qpwKX+G_2GVQWv75X{agJBGYp5uM9Hrbwbxp-|lO|*M!6q zr%(LTaqY&wI@Co2SyY;&vCci|Se8UZQu@;HYb?bF8Spn7`YW^VTkPk9w}; zT*)udP0<2$5!%_@(R^-rVVDTu^~3F>?MVG#{h`ExM7AZz^6l{3VPybgbZhr)hiiki zHA8hmEfh@^E51~HX(BWcjx8uIOu0?FMc~458pkw_9RR*BQN##h*<9tEqJx5iGcY#x z@RM-QEZ;18#%@Llv>X~5h7P+Db_1~EU4~IIQ!<}tJjo~nSAc1OUy3K$3)s57lKy&QTq^sLw!F>*1bc#b$jRQaX)YX$JT z48jIrKZ+%bEf*~ojR3lyARzlCd%pEt_uKY^9&q*>sV&s8+~M3uhaMmL4fx?ipdwM% z_OI`|P+h41=HATB7RV9c!*F3lP98ZaKOsL64loON6JOH>t#exCr%O-Yw!d#*Jzg^I z{|WPHt6{CdUBgS`Quw8C12sK0zdB@H@~3y74yM>sY-hUj!_!YsSE*O2f2vKYt@&8< z(Q(pw(%a6%?mp%brkk&wZz5|dE0`KUg)tG#%#e%_z8IbuM?NRMt65jF8UUXS7z4ua z3kV9pdn9=Xt_iO(@l3o}>EY5TscEV2xM|!^-!6))n^I zq{d{VXQ0RAgXsspE}kwKQw7tOGmU4^W*9Tgp5r|WALc)(bg6Y+F}!SeKKxAhhV+*7 zU*F4^r1&Jy6^|8$FWvVbk)9|kD3E z9-U6$B5^&9eiD5z{6Y9*&SMTAuY{4Fnfx=7ZqjZKzTf?>^-1qjz!$GCV#?CW&m$g3(6rLEFipWto$q?y8II_W2swy4 zOr9G*_gv>cox;Za#-HzhzBe5)8v$E`tQEtQ!YV|{M7DwR@fzVO!EncDM*zSCvalK0 z-@@C%e{%lh3=sQ?cX#gZ-0{2Zmk6ZK+f~~y2`>pwxsJIbqGO^7xOm(Pvz^|Lrp`6-W`5t1o#A-8dw;Voi9FLf3oQ${~*sG{5{wE zo#yRkDq!Dhk8Fz+R5_%wTK%(H=Dpne@~Pq}h&#ev{G#YZkS<);pjof^&D&RR9on7S zUmbsOoI8*&a8z+vajNe}UvX7I)z8hf&2ReS`Z3mV)|Uh>3%nkBH8kJ8&>sIQ{?||G zC21}tZly=?hww8?XO|LJ5?2J^LU0F32T4y+FHy4t(}QLJW4gU|XN?M>KuM9vD} z1P-$#Sb95}JD7vWgCb}y^aB@x3kn1{;F(0`HhqUqVUyTOP$lRRWC79&_~LIL>>TJb zb(oouT*xBVJl9#Sb6j8`Fhc4;@?d|LzFR~uq9dV5D1w`t+X?Of=jQNo1Q~pccqW$F z55xoz;K}e*ND2hPfH4IB@c&63yMOJa~1fv{kh7`HHY zHlzTuda!bk^ylLr9QzD=2eFCB;Ue9_rddEnXp@& zdmJGqFVltP$r=X@gE$Z{R1_)n77Tac^ptMKp8Dd-G)o*l*rW0_6--NI&E~>@_S9f`kaL`PrA5SD0g*Va_?&d6*sC z9{v{m8jJ(_euO2&B7jJs$FN60z8$;{+yMT@9Ay?U${DkqDUL4O5H5reLUaH!&pwmE zY-TnxMZrhGK5#F<%N_=o2g!qOGj1|`fbkcG2tb+>_NCHN<*Ge@_3%dc%4G{SR7z$U|_$ zcwoM4KlT;IRmN-fOSS{d8Fn9W2Qdq*L1&f&>p#W|h6l%;^AYwACWJVG@PK$gcv)Pm zUB&^!2jl`m!oz`9%iv%j-o=$^%e=_E&U6FT#%Fi~{2V+H9t_0H=6MtG3()|s2iGvZFrpZ-3^*79 zev3###3I5F_dt(8oAfpMb;fnZbMQ;>Afg{p39o`*=3M2B&b9pV+@KKudPj$_NYM88P4X4)~wAtMk&E>o^nSQAVK zXzL>VJl%q2#X1K)4}FgK5AiQRYXmEdl|#>^W7ueR4lEB=ho}SQ&K<%7$b-cI-?+lL z!Lf#$!_^S#2*6bo+`(vJh%zJ@CqSy8LHH<~2Z2CDgJMC8^aXk(Ba$Hj76bDjco0T# z6L=-3oFmUrWFVL@=D*-u;4MHmZUAV}P$_hG+Tnr0Mo%VC=D784g;67s#%|y@0f57 z561~&3rrsmv>Vg~;%D=)9|CLf9p?=PSV|BxhzW!V#Gqxe(pY3*e~oiSIKRO=Uqcd0K33j)=SnY_E~lfs1k_x;)bY!kAW?LIdx&X zu=xPKO#o2<7|;Xk1VoZOWFA$qKHoU /tmp/ytdl.list + + +## Accents and different languages needed to create encodings. on 8, 16, 32, 64 bits ... +# it is a big mess/// so we remove accent until someone take care of making it better. TODO??? +# +function replace_accents (){ +INPUT="$1" +declare -a acc +declare -a noa +acc=('$' 'è' 'ê' 'é' 'À' 'Á' 'Â' 'Ã' 'Ä' 'Å' 'Æ' 'Ç' 'È' 'É' 'Ê' 'Ë' 'Ì' 'Í' 'Î' 'Ï' 'Ð' 'Ñ' 'Ò' 'Ó' 'Ô' 'Õ' 'Ö' 'Ø' 'Ù' 'Ú' 'Û' 'Ü' 'Ý' 'ß' 'à' 'á' 'â' 'ã' 'ä' 'å' 'æ' 'ç' 'è' 'é' 'ê' 'ë' 'ì' 'í' 'î' 'ï' 'ñ' 'ò' 'ó' 'ô' 'õ' 'ö' 'ø' 'ù' 'ú' 'û' 'ü' 'ý' 'ÿ' 'Ā' 'ā' 'Ă' 'ă' 'Ą' 'ą' 'Ć' 'ć' 'Ĉ' 'ĉ' 'Ċ' 'ċ' 'Č' 'č' 'Ď' 'ď' 'Đ' 'đ' 'Ē' 'ē' 'Ĕ' 'ĕ' 'Ė' 'ė' 'Ę' 'ę' 'Ě' 'ě' 'Ĝ' 'ĝ' 'Ğ' 'ğ' 'Ġ' 'ġ' 'Ģ' 'ģ' 'Ĥ' 'ĥ' 'Ħ' 'ħ' 'Ĩ' 'ĩ' 'Ī' 'ī' 'Ĭ' 'ĭ' 'Į' 'į' 'İ' 'ı' 'IJ' 'ij' 'Ĵ' 'ĵ' 'Ķ' 'ķ' 'Ĺ' 'ĺ' 'Ļ' 'ļ' 'Ľ' 'ľ' 'Ŀ' 'ŀ' 'Ł' 'ł' 'Ń' 'ń' 'Ņ' 'ņ' 'Ň' 'ň' 'ʼn' 'Ō' 'ō' 'Ŏ' 'ŏ' 'Ő' 'ő' 'Œ' 'œ' 'Ŕ' 'ŕ' 'Ŗ' 'ŗ' 'Ř' 'ř' 'Ś' 'ś' 'Ŝ' 'ŝ' 'Ş' 'ş' 'Š' 'š' 'Ţ' 'ţ' 'Ť' 'ť' 'Ŧ' 'ŧ' 'Ũ' 'ũ' 'Ū' 'ū' 'Ŭ' 'ŭ' 'Ů' 'ů' 'Ű' 'ű' 'Ų' 'ų' 'Ŵ' 'ŵ' 'Ŷ' 'ŷ' 'Ÿ' 'Ź' 'ź' 'Ż' 'ż' 'Ž' 'ž' 'ſ' 'ƒ' 'Ơ' 'ơ' 'Ư' 'ư' 'Ǎ' 'ǎ' 'Ǐ' 'ǐ' 'Ǒ' 'ǒ' 'Ǔ' 'ǔ' 'Ǖ' 'ǖ' 'Ǘ' 'ǘ' 'Ǚ' 'ǚ' 'Ǜ' 'ǜ' 'Ǻ' 'ǻ' 'Ǽ' 'ǽ' 'Ǿ' 'ǿ'); +noa=('S' 'e' 'e' 'e' 'A' 'A' 'A' 'A' 'A' 'A' 'AE' 'C' 'E' 'E' 'E' 'E' 'I' 'I' 'I' 'I' 'D' 'N' 'O' 'O' 'O' 'O' 'O' 'O' 'U' 'U' 'U' 'U' 'Y' 's' 'a' 'a' 'a' 'a' 'a' 'a' 'ae' 'c' 'e' 'e' 'e' 'e' 'i' 'i' 'i' 'i' 'n' 'o' 'o' 'o' 'o' 'o' 'o' 'u' 'u' 'u' 'u' 'y' 'y' 'A' 'a' 'A' 'a' 'A' 'a' 'C' 'c' 'C' 'c' 'C' 'c' 'C' 'c' 'D' 'd' 'D' 'd' 'E' 'e' 'E' 'e' 'E' 'e' 'E' 'e' 'E' 'e' 'G' 'g' 'G' 'g' 'G' 'g' 'G' 'g' 'H' 'h' 'H' 'h' 'I' 'i' 'I' 'i' 'I' 'i' 'I' 'i' 'I' 'i' 'IJ' 'ij' 'J' 'j' 'K' 'k' 'L' 'l' 'L' 'l' 'L' 'l' 'L' 'l' 'l' 'l' 'N' 'n' 'N' 'n' 'N' 'n' 'n' 'O' 'o' 'O' 'o' 'O' 'o' 'OE' 'oe' 'R' 'r' 'R' 'r' 'R' 'r' 'S' 's' 'S' 's' 'S' 's' 'S' 's' 'T' 't' 'T' 't' 'T' 't' 'U' 'u' 'U' 'u' 'U' 'u' 'U' 'u' 'U' 'u' 'U' 'u' 'W' 'w' 'Y' 'y' 'Y' 'Z' 'z' 'Z' 'z' 'Z' 'z' 's' 'f' 'O' 'o' 'U' 'u' 'A' 'a' 'I' 'i' 'O' 'o' 'U' 'u' 'U' 'u' 'U' 'u' 'U' 'u' 'U' 'u' 'A' 'a' 'AE' 'ae' 'O' 'o'); + +OUTPUT="" +i=0 +length=${#INPUT} +while [[ $i -lt $length ]]; do./zen/_CopyLaRadio/copy.sh: + char=${INPUT:$i:1}; + #echo $i:$char + j=0 + for letter in "${acc[@]}" + do + if [[ "$letter" == "$char" ]]; then + char="${noa[$j]}" + fi + ((j++)) + done + ((i++)) + OUTPUT=$OUTPUT$char +done +echo $OUTPUT +} + +# BASH CAN MAKE INFINTE LOOP LOOKING FOR A NEW LINE APPEERING IN A FILE. +# this technique can transmit FIFO command between process +# This code is from www.copylaradio.com and RUN youtube-dl search and copy from the use of a button. +# +tail -fn 1 /tmp/ytdl.list | while read -r line +do +################################################# + radio=$(echo $line | cut -d "|" -f 1) + artist=$(echo $line | cut -d "|" -f 2) + song=$(echo $line | cut -d "|" -f 3) + echo "######## $radio ########" >> /tmp/youtube-dl.log 2>&1 + echo $(date) >> /tmp/youtube-dl.log 2>&1 + echo ${line} >> /tmp/youtube-dl.log 2>&1 + +################################################# +# YOUTUBE-DL SEARCH & COPY : "radio|artist|song" +if [[ "$artist" != "" && "$song" != "" && "$radio" != "" && "$radio" != "$song" && "$radio" != "undefined" && "$artist" != "$song" ]]; then + mkdir -p "/home/pi/.zen/music/${artist}/${song}" + $MY_PATH/parle.sh "Démarrage Enregistrement $radio." + $MY_PATH/parle.sh "$artist" "en-US" + $MY_PATH/parle.sh "$song" "en-US" + echo "Copy youtube-dl: $artist | $song ($radio)" >> /tmp/youtube-dl.log 2>&1 + # Clean search string + mysearch=$(replace_accents "$artist $song") + if [[ "$mysearch" == "" ]]; then ~/parle.sh "Aucune recherche reçue!"; continue; fi + # Search & Download bestaudio from 1st video result (ogg / opus / m4a): MEDIUM CPU + # OPTION: --embed-thumbnail --metadata-from-title "%(artist)s - %(title)s" --add-metadata + youtube-dl --default-search ytsearch1: --download-archive /home/pi/.ytdl.list --continue --no-overwrites --metadata-from-title "$artist - %(title)s" --add-metadata --embed-thumbnail --ignore-errors -f m4a --extract-audio -o "/home/pi/music/${artist}/${song}/%(id)s.%(title)s.%(uploader_id)s.%(ext)s" "$mysearch" >> /tmp/youtube-dl.log 2>&1 + # TODO: CHOOSE --metadata-from-title "$artist - %(title)s" or --metadata-from-title %(title)s" + # Update mpd playlist + curl -b "currenthost=Default;player_backend=mpd" http://localhost/albums.php?rebuild=yes > /dev/null + $MY_PATH/parle.sh "Enregistrement $radio terminé!" +###################################################### +#### COPY LINK : "CopyLaRadio||https://link2media.url" +elif [[ "$radio" != "" && "$artist" == "" && "$song" != "" ]]; then + # LINK COPY + $MY_PATH/parle.sh "Copie du lien!" + echo "Copy LINK: $song" >> /tmp/youtube-dl.log 2>&1 + mkdir -p /home/pi/download/ + youtube-dl --download-archive /home/pi/.ytdl.list --continue --no-overwrites --embed-thumbnail --metadata-from-title "%(artist)s - %(title)s" --add-metadata -o "/home/pi/download/%(title)s.%(ext)s" "$song" >> /tmp/youtube-dl.log 2>&1 + $MY_PATH/parle.sh "Enregistrement du lien terminé!" +###################################################### +#### COPY LINK : "radio||" +elif [[ "$radio" != "" && "$artist" == "" && "$song" == "" ]]; then + # EXTERNAL PARSER: ADD SCRAPERS IN ./libradio + $MY_PATH/parle.sh "Recherche RADIO ${radio}" + echo "External search: ${radio}" >> /tmp/youtube-dl.log 2>&1 + if [[ -f $MY_PATH/libradio/${radio}.php ]]; then + $MY_PATH/parle.sh "Module existant" + php "$MY_PATH/libradio/${radio}.php" + else + $MY_PATH/parle.sh "Aucun module de décodage pour cette radio." + fi +#### NOTHING GOOD +else + $MY_PATH/parle.sh "Rien à copier" +fi +done + diff --git a/zen/_CopyLaRadio/install_osb-studio.sh b/zen/_CopyLaRadio/install_osb-studio.sh new file mode 100755 index 0000000..90f155d --- /dev/null +++ b/zen/_CopyLaRadio/install_osb-studio.sh @@ -0,0 +1,10 @@ +#!/bin/bash +# May run on ElementaryOS try it and tell us @Attilax! +sudo add-apt-repository ppa:obsproject/obs-studio +sudo apt update +sudo apt install obs-studio -y +sudo apt install simplescreenrecorder mixxx geany -y + +sudo add-apt-repository ppa:peek-developers/stable +sudo apt update +sudo apt install peek diff --git a/zen/_CopyLaRadio/libradio/FIP autour de llectro.php b/zen/_CopyLaRadio/libradio/FIP autour de llectro.php new file mode 100644 index 0000000..b4d883b --- /dev/null +++ b/zen/_CopyLaRadio/libradio/FIP autour de llectro.php @@ -0,0 +1,75 @@ + array( + 'header'=>array("Referer: ".$referer.PHP_EOL), + 'timeout' => 5 + ) + ) +); +/////////////////////////// +// LOAD RADIO PAGE INTO PARSER +$ontheair = file_get_contents($radiourl); // JSON CONTENT +$ontheair = utf8_encode($ontheair); +$obj = json_decode($ontheair, true); + + +// GET TRACK INFO: ADAPT WITH DATA STRUCTURE +// ADPAPT HERE +$current = $obj['data']['now']['playing_item']; +// GET TRACK INFO +if ( $current ) { + // ADPAPT HERE + $artist = ucwords(strtolower($current['title'])); + $title = ucwords(strtolower($current['subtitle'])); + + if ( $debug != 0 ) $ERR .= "\nTITRE = ".print_r($title, true); + if ( $debug != 0 ) $ERR .= "\nARTISTE = ".print_r($artist, true); + +} +/////////////////////////// +// PREPARE COPY COMMAND +$cmd = $RADIO.'|'.$artist.'|'.$title; + +/////////////////////////// +// DEBUG OR PROD +if($debug == 1) { + print_r($obj); + print_r($cmd); +} else { + if( $artist != "" && $title != "" ) { + // TODO Clean strings?! + if (! exec('grep '.escapeshellarg($cmd).' /tmp/ytdl.list')) { + file_put_contents("/tmp/youtube-dl.log", "ARTIST: ".$artist.". SONG: ".$title, FILE_APPEND); + file_put_contents("/tmp/ytdl.list","$cmd\n", FILE_APPEND); + } else { + file_put_contents("/tmp/youtube-dl.log", "ALREADY THERE!", FILE_APPEND); + file_put_contents("/tmp/ytdl.list","||".PHP_EOL, FILE_APPEND); + } + } else { + file_put_contents("/tmp/youtube-dl.log", "NO TRACK. TRY PODCAST!", FILE_APPEND); + file_put_contents("/tmp/ytdl.list","||".PHP_EOL, FILE_APPEND); + } +} +?> diff --git a/zen/_CopyLaRadio/libradio/Nova zz.php b/zen/_CopyLaRadio/libradio/Nova zz.php new file mode 120000 index 0000000..67488fe --- /dev/null +++ b/zen/_CopyLaRadio/libradio/Nova zz.php @@ -0,0 +1 @@ +radionova.php \ No newline at end of file diff --git a/zen/_CopyLaRadio/libradio/fipelectro-midfi.mp3.php b/zen/_CopyLaRadio/libradio/fipelectro-midfi.mp3.php new file mode 120000 index 0000000..62b4fe5 --- /dev/null +++ b/zen/_CopyLaRadio/libradio/fipelectro-midfi.mp3.php @@ -0,0 +1 @@ +FIP autour de llectro.php \ No newline at end of file diff --git a/zen/_CopyLaRadio/libradio/radionova.php b/zen/_CopyLaRadio/libradio/radionova.php new file mode 100644 index 0000000..fef1c4c --- /dev/null +++ b/zen/_CopyLaRadio/libradio/radionova.php @@ -0,0 +1,74 @@ + array( + 'header'=>array("Referer: ".$referer.PHP_EOL), + 'timeout' => 5 + ) + ) +); +/////////////////////////// +// LOAD RADIO PAGE INTO PARSER +$ontheair = file_get_contents($radiourl); // JSON CONTENT +$ontheair = utf8_encode($ontheair); +$obj = json_decode($ontheair, true); + + +// GET TRACK INFO: ADAPT WITH DATA STRUCTURE +// ADPAPT HERE +if ( $obj['currentTrack'] ) { + + // ADPAPT HERE + $title = ucwords(strtolower($obj['currentTrack']['title'])); + $artist = ucwords(strtolower($obj['currentTrack']['artist'])); + + if ( $debug != 0 ) $ERR .= "\nTITRE = ".print_r($title, true); + if ( $debug != 0 ) $ERR .= "\nARTISTE = ".print_r($artist, true); + +} +/////////////////////////// +// PREPARE COPY COMMAND +$cmd = $RADIO.'|'.$artist.'|'.$title; + +/////////////////////////// +// DEBUG OR PROD +if($debug == 1) { + print_r($obj); + print_r($cmd); +} else { + if( $artist != "" && $title != "" ) { + // TODO Clean strings?! + if (! exec('grep '.escapeshellarg($cmd).' /tmp/ytdl.list')) { + file_put_contents("/tmp/youtube-dl.log", "ARTIST: ".$artist.". SONG: ".$title, FILE_APPEND); + file_put_contents("/tmp/ytdl.list","$cmd\n", FILE_APPEND); + } else { + file_put_contents("/tmp/youtube-dl.log", "ALREADY THERE!", FILE_APPEND); + file_put_contents("/tmp/ytdl.list","||".PHP_EOL, FILE_APPEND); + } + } else { + file_put_contents("/tmp/youtube-dl.log", "NO TRACK. TRY PODCAST!", FILE_APPEND); + file_put_contents("/tmp/ytdl.list","||".PHP_EOL, FILE_APPEND); + } +} +?> diff --git a/zen/_CopyLaRadio/libradio/simple_html_dom.php b/zen/_CopyLaRadio/libradio/simple_html_dom.php new file mode 100644 index 0000000..c0001e3 --- /dev/null +++ b/zen/_CopyLaRadio/libradio/simple_html_dom.php @@ -0,0 +1,2808 @@ +size is the "real" + * number of bytes the dom was created from. But for most purposes, it's a + * really good estimation. + * + * Paperg - Added the forceTagsClosed to the dom constructor. Forcing tags + * closed is great for malformed html, but it CAN lead to parsing errors. + * + * Allow the user to tell us how much they trust the html. + * + * Paperg add the text and plaintext to the selectors for the find syntax. + * plaintext implies text in the innertext of a node. text implies that the + * tag is a text node. This allows for us to find tags based on the text they + * contain. + * + * Create find_ancestor_tag to see if a tag is - at any level - inside of + * another specific tag. + * + * Paperg: added parse_charset so that we know about the character set of + * the source document. NOTE: If the user's system has a routine called + * get_last_retrieve_url_contents_content_type availalbe, we will assume it's + * returning the content-type header from the last transfer or curl_exec, and + * we will parse that and use it in preference to any other method of charset + * detection. + * + * Found infinite loop in the case of broken html in restore_noise. Rewrote to + * protect from that. + * + * PaperG (John Schlick) Added get_display_size for "IMG" tags. + * + * Licensed under The MIT License + * Redistributions of files must retain the above copyright notice. + * + * @author S.C. Chen + * @author John Schlick + * @author Rus Carroll + * @version Rev. 1.8.1 (247) + * @package PlaceLocalInclude + * @subpackage simple_html_dom + */ + +/** + * All of the Defines for the classes below. + * @author S.C. Chen + */ +define('HDOM_TYPE_ELEMENT', 1); +define('HDOM_TYPE_COMMENT', 2); +define('HDOM_TYPE_TEXT', 3); +define('HDOM_TYPE_ENDTAG', 4); +define('HDOM_TYPE_ROOT', 5); +define('HDOM_TYPE_UNKNOWN', 6); +define('HDOM_QUOTE_DOUBLE', 0); +define('HDOM_QUOTE_SINGLE', 1); +define('HDOM_QUOTE_NO', 3); +define('HDOM_INFO_BEGIN', 0); +define('HDOM_INFO_END', 1); +define('HDOM_INFO_QUOTE', 2); +define('HDOM_INFO_SPACE', 3); +define('HDOM_INFO_TEXT', 4); +define('HDOM_INFO_INNER', 5); +define('HDOM_INFO_OUTER', 6); +define('HDOM_INFO_ENDSPACE', 7); + +/** The default target charset */ +defined('DEFAULT_TARGET_CHARSET') || define('DEFAULT_TARGET_CHARSET', 'UTF-8'); + +/** The default
text used instead of
tags when returning text */ +defined('DEFAULT_BR_TEXT') || define('DEFAULT_BR_TEXT', "\r\n"); + +/** The default text used instead of tags when returning text */ +defined('DEFAULT_SPAN_TEXT') || define('DEFAULT_SPAN_TEXT', ' '); + +/** The maximum file size the parser should load */ +defined('MAX_FILE_SIZE') || define('MAX_FILE_SIZE', 600000); + +/** Contents between curly braces "{" and "}" are interpreted as text */ +define('HDOM_SMARTY_AS_TEXT', 1); + +// helper functions +// ----------------------------------------------------------------------------- +// get html dom from file +// $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1. +function file_get_html( + $url, + $use_include_path = false, + $context = null, + $offset = 0, + $maxLen = -1, + $lowercase = true, + $forceTagsClosed = true, + $target_charset = DEFAULT_TARGET_CHARSET, + $stripRN = true, + $defaultBRText = DEFAULT_BR_TEXT, + $defaultSpanText = DEFAULT_SPAN_TEXT) +{ + // Ensure maximum length is greater than zero + if($maxLen <= 0) { $maxLen = MAX_FILE_SIZE; } + + // We DO force the tags to be terminated. + $dom = new simple_html_dom( + null, + $lowercase, + $forceTagsClosed, + $target_charset, + $stripRN, + $defaultBRText, + $defaultSpanText); + + /** + * For sourceforge users: uncomment the next line and comment the + * retrieve_url_contents line 2 lines down if it is not already done. + */ + $contents = file_get_contents( + $url, + $use_include_path, + $context, + $offset, + $maxLen); + + // Paperg - use our own mechanism for getting the contents as we want to + // control the timeout. + // $contents = retrieve_url_contents($url); + if (empty($contents) || strlen($contents) > $maxLen) { return false; } + + // The second parameter can force the selectors to all be lowercase. + $dom->load($contents, $lowercase, $stripRN); + return $dom; +} + +// get html dom from string +function str_get_html( + $str, + $lowercase = true, + $forceTagsClosed = true, + $target_charset = DEFAULT_TARGET_CHARSET, + $stripRN = true, + $defaultBRText = DEFAULT_BR_TEXT, + $defaultSpanText = DEFAULT_SPAN_TEXT) +{ + $dom = new simple_html_dom( + null, + $lowercase, + $forceTagsClosed, + $target_charset, + $stripRN, + $defaultBRText, + $defaultSpanText); + + if (empty($str) || strlen($str) > MAX_FILE_SIZE) { + $dom->clear(); + return false; + } + + $dom->load($str, $lowercase, $stripRN); + return $dom; +} + +// dump html dom tree +function dump_html_tree($node, $show_attr = true, $deep = 0) +{ + $node->dump($node); +} + +/** + * simple html dom node + * PaperG - added ability for "find" routine to lowercase the value of the + * selector. + * + * PaperG - added $tag_start to track the start position of the tag in the total + * byte index + * + * @package PlaceLocalInclude + */ +class simple_html_dom_node +{ + /** + * Node type + * + * Default is {@see HDOM_TYPE_TEXT} + * + * @var int + */ + public $nodetype = HDOM_TYPE_TEXT; + + /** + * Tag name + * + * Default is 'text' + * + * @var string + */ + public $tag = 'text'; + + /** + * List of attributes + * + * @var array + */ + public $attr = array(); + + /** + * List of child node objects + * + * @var array + */ + public $children = array(); + public $nodes = array(); + + /** + * The parent node object + * + * @var object|null + */ + public $parent = null; + + // The "info" array - see HDOM_INFO_... for what each element contains. + public $_ = array(); + + /** + * Start position of the tag in the document + * + * @var int + */ + public $tag_start = 0; + + /** + * The DOM object + * + * @var object|null + */ + private $dom = null; + + /** + * Construct new node object + * + * Adds itself to the list of DOM Nodes {@see simple_html_dom::$nodes} + */ + function __construct($dom) + { + $this->dom = $dom; + $dom->nodes[] = $this; + } + + function __destruct() + { + $this->clear(); + } + + function __toString() + { + return $this->outertext(); + } + + // clean up memory due to php5 circular references memory leak... + function clear() + { + $this->dom = null; + $this->nodes = null; + $this->parent = null; + $this->children = null; + } + + // dump node's tree + function dump($show_attr = true, $deep = 0) + { + $lead = str_repeat(' ', $deep); + + echo $lead . $this->tag; + + if ($show_attr && count($this->attr) > 0) { + echo '('; + foreach ($this->attr as $k => $v) { + echo "[$k]=>\"" . $this->$k . '", '; + } + echo ')'; + } + + echo "\n"; + + if ($this->nodes) { + foreach ($this->nodes as $c) { + $c->dump($show_attr, $deep + 1); + } + } + } + + + // Debugging function to dump a single dom node with a bunch of information about it. + function dump_node($echo = true) + { + $string = $this->tag; + + if (count($this->attr) > 0) { + $string .= '('; + foreach ($this->attr as $k => $v) { + $string .= "[$k]=>\"" . $this->$k . '", '; + } + $string .= ')'; + } + + if (count($this->_) > 0) { + $string .= ' $_ ('; + foreach ($this->_ as $k => $v) { + if (is_array($v)) { + $string .= "[$k]=>("; + foreach ($v as $k2 => $v2) { + $string .= "[$k2]=>\"" . $v2 . '", '; + } + $string .= ')'; + } else { + $string .= "[$k]=>\"" . $v . '", '; + } + } + $string .= ')'; + } + + if (isset($this->text)) { + $string .= ' text: (' . $this->text . ')'; + } + + $string .= " HDOM_INNER_INFO: '"; + + if (isset($node->_[HDOM_INFO_INNER])) { + $string .= $node->_[HDOM_INFO_INNER] . "'"; + } else { + $string .= ' NULL '; + } + + $string .= ' children: ' . count($this->children); + $string .= ' nodes: ' . count($this->nodes); + $string .= ' tag_start: ' . $this->tag_start; + $string .= "\n"; + + if ($echo) { + echo $string; + return; + } else { + return $string; + } + } + + /** + * Return or set parent node + * + * @param object|null $parent (optional) The parent node, `null` to return + * the current parent node. + * @return object|null The parent node + */ + function parent($parent = null) + { + // I am SURE that this doesn't work properly. + // It fails to unset the current node from it's current parents nodes or + // children list first. + if ($parent !== null) { + $this->parent = $parent; + $this->parent->nodes[] = $this; + $this->parent->children[] = $this; + } + + return $this->parent; + } + + /** + * @return bool True if the node has at least one child node + */ + function has_child() + { + return !empty($this->children); + } + + /** + * Get child node at specified index + * + * @param int $idx The index of the child node to return, `-1` to return all + * child nodes. + * @return object|array|null The child node at the specified index, all child + * nodes or null if the index is invalid. + */ + function children($idx = -1) + { + if ($idx === -1) { + return $this->children; + } + + if (isset($this->children[$idx])) { + return $this->children[$idx]; + } + + return null; + } + + /** + * Get first child node + * + * @return object|null The first child node or null if the current node has + * no child nodes. + * + * @todo Use `empty()` instead of `count()` to improve performance on large + * arrays. + */ + function first_child() + { + if (count($this->children) > 0) { + return $this->children[0]; + } + return null; + } + + /** + * Get last child node + * + * @return object|null The last child node or null if the current node has + * no child nodes. + * + * @todo Use `end()` to slightly improve performance on large arrays. + */ + function last_child() + { + if (($count = count($this->children)) > 0) { + return $this->children[$count - 1]; + } + return null; + } + + /** + * Get next sibling node + * + * @return object|null The sibling node or null if the current node has no + * sibling nodes. + */ + function next_sibling() + { + if ($this->parent === null) { + return null; + } + + $idx = 0; + $count = count($this->parent->children); + + while ($idx < $count && $this !== $this->parent->children[$idx]) { + ++$idx; + } + + if (++$idx >= $count) { + return null; + } + + return $this->parent->children[$idx]; + } + + /** + * Get previous sibling node + * + * @return object|null The sibling node or null if the current node has no + * sibling nodes. + */ + function prev_sibling() + { + if ($this->parent === null) { return null; } + + $idx = 0; + $count = count($this->parent->children); + + while ($idx < $count && $this !== $this->parent->children[$idx]) { + ++$idx; + } + + if (--$idx < 0) { return null; } + + return $this->parent->children[$idx]; + } + + /** + * Traverse ancestors to the first matching tag. + * + * @param string $tag Tag to find + * @return object|null First matching node in the DOM tree or null if no + * match was found. + * + * @todo Null is returned implicitly by calling ->parent on the root node. + * This behaviour could change at any time, rendering this function invalid. + */ + function find_ancestor_tag($tag) + { + global $debug_object; + if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } + + // Start by including ourselves in the comparison. + $returnDom = $this; + + while (!is_null($returnDom)) { + if (is_object($debug_object)) { + $debug_object->debug_log(2, 'Current tag is: ' . $returnDom->tag); + } + + if ($returnDom->tag == $tag) { + break; + } + + $returnDom = $returnDom->parent; + } + + return $returnDom; + } + + /** + * Get node's inner text (everything inside the opening and closing tags) + * + * @return string + */ + function innertext() + { + if (isset($this->_[HDOM_INFO_INNER])) { + return $this->_[HDOM_INFO_INNER]; + } + + if (isset($this->_[HDOM_INFO_TEXT])) { + return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + } + + $ret = ''; + + foreach ($this->nodes as $n) { + $ret .= $n->outertext(); + } + + return $ret; + } + + /** + * Get node's outer text (everything including the opening and closing tags) + * + * @return string + */ + function outertext() + { + global $debug_object; + + if (is_object($debug_object)) { + $text = ''; + + if ($this->tag === 'text') { + if (!empty($this->text)) { + $text = ' with text: ' . $this->text; + } + } + + $debug_object->debug_log(1, 'Innertext of tag: ' . $this->tag . $text); + } + + if ($this->tag === 'root') return $this->innertext(); + + // trigger callback + if ($this->dom && $this->dom->callback !== null) { + call_user_func_array($this->dom->callback, array($this)); + } + + if (isset($this->_[HDOM_INFO_OUTER])) { + return $this->_[HDOM_INFO_OUTER]; + } + + if (isset($this->_[HDOM_INFO_TEXT])) { + return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + } + + // render begin tag + if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]) { + $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); + } else { + $ret = ''; + } + + // render inner text + if (isset($this->_[HDOM_INFO_INNER])) { + // If it's a br tag... don't return the HDOM_INNER_INFO that we + // may or may not have added. + if ($this->tag !== 'br') { + $ret .= $this->_[HDOM_INFO_INNER]; + } + } else { + if ($this->nodes) { + foreach ($this->nodes as $n) { + $ret .= $this->convert_text($n->outertext()); + } + } + } + + // render end tag + if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END] != 0) { + $ret .= 'tag . '>'; + } + + return $ret; + } + + /** + * Get node's plain text (everything excluding all tags) + * + * @return string + */ + function text() + { + if (isset($this->_[HDOM_INFO_INNER])) { + return $this->_[HDOM_INFO_INNER]; + } + + switch ($this->nodetype) { + case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + case HDOM_TYPE_COMMENT: return ''; + case HDOM_TYPE_UNKNOWN: return ''; + } + + if (strcasecmp($this->tag, 'script') === 0) { return ''; } + if (strcasecmp($this->tag, 'style') === 0) { return ''; } + + $ret = ''; + + // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed + // for some span tags, and some p tags) $this->nodes is set to NULL. + // NOTE: This indicates that there is a problem where it's set to NULL + // without a clear happening. + // WHY is this happening? + if (!is_null($this->nodes)) { + foreach ($this->nodes as $n) { + // Start paragraph after a blank line + if ($n->tag === 'p') { + $ret .= "\n\n"; + } + + $ret .= $this->convert_text($n->text()); + + // If this node is a span... add a space at the end of it so + // multiple spans don't run into each other. This is plaintext + // after all. + if ($n->tag === 'span') { + $ret .= $this->dom->default_span_text; + } + } + } + return trim($ret); + } + + /** + * Get node's xml text (inner text as a CDATA section) + * + * @return string + */ + function xmltext() + { + $ret = $this->innertext(); + $ret = str_ireplace('', '', $ret); + return $ret; + } + + // build node's text with tag + function makeup() + { + // text, comment, unknown + if (isset($this->_[HDOM_INFO_TEXT])) { + return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); + } + + $ret = '<' . $this->tag; + $i = -1; + + foreach ($this->attr as $key => $val) { + ++$i; + + // skip removed attribute + if ($val === null || $val === false) { continue; } + + $ret .= $this->_[HDOM_INFO_SPACE][$i][0]; + + //no value attr: nowrap, checked selected... + if ($val === true) { + $ret .= $key; + } else { + switch ($this->_[HDOM_INFO_QUOTE][$i]) + { + case HDOM_QUOTE_DOUBLE: $quote = '"'; break; + case HDOM_QUOTE_SINGLE: $quote = '\''; break; + default: $quote = ''; + } + + $ret .= $key + . $this->_[HDOM_INFO_SPACE][$i][1] + . '=' + . $this->_[HDOM_INFO_SPACE][$i][2] + . $quote + . $val + . $quote; + } + } + + $ret = $this->dom->restore_noise($ret); + return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>'; + } + + /** + * Find elements by CSS selector + * + * @param string $selector The CSS selector + * @param int|null $idx Index of element to return form the list of matching + * elements (default: `null` = disabled). + * @param bool $lowercase Matches tag names case insensitive (lowercase) if + * enabled (default: `false`) + * @return array|object|null A list of elements matching the specified CSS + * selector or a single element if $idx is specified or null if no element + * was found. + */ + function find($selector, $idx = null, $lowercase = false) + { + $selectors = $this->parse_selector($selector); + if (($count = count($selectors)) === 0) { return array(); } + $found_keys = array(); + + // find each selector + for ($c = 0; $c < $count; ++$c) { + // The change on the below line was documented on the sourceforge + // code tracker id 2788009 + // used to be: if (($levle=count($selectors[0]))===0) return array(); + if (($levle = count($selectors[$c])) === 0) { return array(); } + if (!isset($this->_[HDOM_INFO_BEGIN])) { return array(); } + + $head = array($this->_[HDOM_INFO_BEGIN] => 1); + $cmd = ' '; // Combinator + + // handle descendant selectors, no recursive! + for ($l = 0; $l < $levle; ++$l) { + $ret = array(); + + foreach ($head as $k => $v) { + $n = ($k === -1) ? $this->dom->root : $this->dom->nodes[$k]; + //PaperG - Pass this optional parameter on to the seek function. + $n->seek($selectors[$c][$l], $ret, $cmd, $lowercase); + } + + $head = $ret; + $cmd = $selectors[$c][$l][4]; // Next Combinator + } + + foreach ($head as $k => $v) { + if (!isset($found_keys[$k])) { + $found_keys[$k] = 1; + } + } + } + + // sort keys + ksort($found_keys); + + $found = array(); + foreach ($found_keys as $k => $v) { + $found[] = $this->dom->nodes[$k]; + } + + // return nth-element or array + if (is_null($idx)) { return $found; } + elseif ($idx < 0) { $idx = count($found) + $idx; } + return (isset($found[$idx])) ? $found[$idx] : null; + } + + /** + * Seek DOM elements by selector + * + * **Note** + * The selector element must be compatible to a selector from + * {@see simple_html_dom_node::parse_selector()} + * + * @param array $selector A selector element + * @param array $ret An array of matches + * @param bool $lowercase Matches tag names case insensitive (lowercase) if + * enabled (default: `false`) + * @return void + */ + protected function seek($selector, &$ret, $parent_cmd, $lowercase = false) + { + global $debug_object; + if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } + + list($tag, $id, $class, $attributes, $cmb) = $selector; + $nodes = array(); + + if ($parent_cmd === ' ') { // Descendant Combinator + // Find parent closing tag if the current element doesn't have a closing + // tag (i.e. void element) + $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0; + if ($end == 0) { + $parent = $this->parent; + while (!isset($parent->_[HDOM_INFO_END]) && $parent !== null) { + $end -= 1; + $parent = $parent->parent; + } + $end += $parent->_[HDOM_INFO_END]; + } + + // Get list of target nodes + $nodes_start = $this->_[HDOM_INFO_BEGIN] + 1; + $nodes_count = $end - $nodes_start; + $nodes = array_slice($this->dom->nodes, $nodes_start, $nodes_count, true); + } elseif ($parent_cmd === '>') { // Child Combinator + $nodes = $this->children; + } elseif ($parent_cmd === '+' + && $this->parent + && in_array($this, $this->parent->children)) { // Next-Sibling Combinator + $index = array_search($this, $this->parent->children, true) + 1; + $nodes[] = $this->parent->children[$index]; + } elseif ($parent_cmd === '~' + && $this->parent + && in_array($this, $this->parent->children)) { // Subsequent Sibling Combinator + $index = array_search($this, $this->parent->children, true); + $nodes = array_slice($this->parent->children, $index); + } + + // Go throgh each element starting at this element until the end tag + // Note: If this element is a void tag, any previous void element is + // skipped. + foreach($nodes as $node) { + $pass = true; + + // Skip root nodes + if(!$node->parent) { + $pass = false; + } + + // Skip if node isn't a child node (i.e. text nodes) + if($pass && !in_array($node, $node->parent->children, true)) { + $pass = false; + } + + // Skip if tag doesn't match + if ($pass && $tag !== '' && $tag !== $node->tag && $tag !== '*') { + $pass = false; + } + + // Skip if ID doesn't exist + if ($pass && $id !== '' && !isset($node->attr['id'])) { + $pass = false; + } + + // Check if ID matches + if ($pass && $id !== '' && isset($node->attr['id'])) { + // Note: Only consider the first ID (as browsers do) + $node_id = explode(' ', trim($node->attr['id']))[0]; + + if($id !== $node_id) { $pass = false; } + } + + // Check if all class(es) exist + if ($pass && $class !== '' && is_array($class) && !empty($class)) { + if (isset($node->attr['class'])) { + $node_classes = explode(' ', $node->attr['class']); + + if ($lowercase) { + $node_classes = array_map('strtolower', $node_classes); + } + + foreach($class as $c) { + if(!in_array($c, $node_classes)) { + $pass = false; + break; + } + } + } else { + $pass = false; + } + } + + // Check attributes + if ($pass + && $attributes !== '' + && is_array($attributes) + && !empty($attributes)) { + foreach($attributes as $a) { + list ( + $att_name, + $att_expr, + $att_val, + $att_inv, + $att_case_sensitivity + ) = $a; + + // Handle indexing attributes (i.e. "[2]") + /** + * Note: This is not supported by the CSS Standard but adds + * the ability to select items compatible to XPath (i.e. + * the 3rd element within it's parent). + * + * Note: This doesn't conflict with the CSS Standard which + * doesn't work on numeric attributes anyway. + */ + if (is_numeric($att_name) + && $att_expr === '' + && $att_val === '') { + $count = 0; + + // Find index of current element in parent + foreach ($node->parent->children as $c) { + if ($c->tag === $node->tag) ++$count; + if ($c === $node) break; + } + + // If this is the correct node, continue with next + // attribute + if ($count === (int)$att_name) continue; + } + + // Check attribute availability + if ($att_inv) { // Attribute should NOT be set + if (isset($node->attr[$att_name])) { + $pass = false; + break; + } + } else { // Attribute should be set + // todo: "plaintext" is not a valid CSS selector! + if ($att_name !== 'plaintext' + && !isset($node->attr[$att_name])) { + $pass = false; + break; + } + } + + // Continue with next attribute if expression isn't defined + if ($att_expr === '') continue; + + // If they have told us that this is a "plaintext" + // search then we want the plaintext of the node - right? + // todo "plaintext" is not a valid CSS selector! + if ($att_name === 'plaintext') { + $nodeKeyValue = $node->text(); + } else { + $nodeKeyValue = $node->attr[$att_name]; + } + + if (is_object($debug_object)) { + $debug_object->debug_log(2, + 'testing node: ' + . $node->tag + . ' for attribute: ' + . $att_name + . $att_expr + . $att_val + . ' where nodes value is: ' + . $nodeKeyValue + ); + } + + // If lowercase is set, do a case insensitive test of + // the value of the selector. + if ($lowercase) { + $check = $this->match( + $att_expr, + strtolower($att_val), + strtolower($nodeKeyValue), + $att_case_sensitivity + ); + } else { + $check = $this->match( + $att_expr, + $att_val, + $nodeKeyValue, + $att_case_sensitivity + ); + } + + if (is_object($debug_object)) { + $debug_object->debug_log(2, + 'after match: ' + . ($check ? 'true' : 'false') + ); + } + + if (!$check) { + $pass = false; + break; + } + } + } + + // Found a match. Add to list and clear node + if ($pass) $ret[$node->_[HDOM_INFO_BEGIN]] = 1; + unset($node); + } + // It's passed by reference so this is actually what this function returns. + if (is_object($debug_object)) { + $debug_object->debug_log(1, 'EXIT - ret: ', $ret); + } + } + + /** + * Match value and pattern for a given CSS expression + * + * **Supported Expressions** + * + * | Expression | Description + * | ---------- | ----------- + * | `=` | $value and $pattern must be equal + * | `!=` | $value and $pattern must not be equal + * | `^=` | $value must start with $pattern + * | `$=` | $value must end with $pattern + * | `*=` | $value must contain $pattern + * + * @param string $exp The expression. + * @param string $pattern The pattern + * @param string $value The value + * @value bool True if $value matches $pattern + */ + protected function match($exp, $pattern, $value, $case_sensitivity) + { + global $debug_object; + if (is_object($debug_object)) {$debug_object->debug_log_entry(1);} + + if ($case_sensitivity === 'i') { + $pattern = strtolower($pattern); + $value = strtolower($value); + } + + switch ($exp) { + case '=': + return ($value === $pattern); + case '!=': + return ($value !== $pattern); + case '^=': + return preg_match('/^' . preg_quote($pattern, '/') . '/', $value); + case '$=': + return preg_match('/' . preg_quote($pattern, '/') . '$/', $value); + case '*=': + return preg_match('/' . preg_quote($pattern, '/') . '/', $value); + case '|=': + /** + * [att|=val] + * + * Represents an element with the att attribute, its value + * either being exactly "val" or beginning with "val" + * immediately followed by "-" (U+002D). + */ + return strpos($value, $pattern) === 0; + case '~=': + /** + * [att~=val] + * + * Represents an element with the att attribute whose value is a + * whitespace-separated list of words, one of which is exactly + * "val". If "val" contains whitespace, it will never represent + * anything (since the words are separated by spaces). Also if + * "val" is the empty string, it will never represent anything. + */ + return in_array($pattern, explode(' ', trim($value)), true); + } + return false; + } + + /** + * Parse CSS selector + * + * @param string $selector_string CSS selector string + * @return array List of CSS selectors. The format depends on the type of + * selector: + * + * ```php + * + * array( // list of selectors (each separated by a comma), i.e. 'img, p, div' + * array( // list of combinator selectors, i.e. 'img > p > div' + * array( // selector element + * [0], // (string) The element tag + * [1], // (string) The element id + * [2], // (array) The element classes + * [3], // (array>) The list of attributes, each + * // with four elements: name, expression, value, inverted + * [4] // (string) The selector combinator (' ' | '>' | '+' | '~') + * ) + * ) + * ) + * ``` + * + * @link https://www.w3.org/TR/selectors/#compound Compound selector + */ + protected function parse_selector($selector_string) + { + global $debug_object; + if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } + + /** + * Pattern of CSS selectors, modified from mootools (https://mootools.net/) + * + * Paperg: Add the colon to the attribute, so that it properly finds + * like google does. + * + * Note: if you try to look at this attribute, you MUST use getAttribute + * since $dom->x:y will fail the php syntax check. + * + * Notice the \[ starting the attribute? and the @? following? This + * implies that an attribute can begin with an @ sign that is not + * captured. This implies that an html attribute specifier may start + * with an @ sign that is NOT captured by the expression. Farther study + * is required to determine of this should be documented or removed. + * + * Matches selectors in this order: + * + * [0] - full match + * + * [1] - tag name + * ([\w:\*-]*) + * Matches the tag name consisting of zero or more words, colons, + * asterisks and hyphens. + * + * [2] - id name + * (?:\#([\w-]+)) + * Optionally matches a id name, consisting of an "#" followed by + * the id name (one or more words and hyphens). + * + * [3] - class names (including dots) + * (?:\.([\w\.-]+))? + * Optionally matches a list of classs, consisting of an "." + * followed by the class name (one or more words and hyphens) + * where multiple classes can be chained (i.e. ".foo.bar.baz") + * + * [4] - attributes + * ((?:\[@?(?:!?[\w:-]+)(?:(?:[!*^$|~]?=)[\"']?(?:.*?)[\"']?)?(?:\s*?(?:[iIsS])?)?\])+)? + * Optionally matches the attributes list + * + * [5] - separator + * ([\/, >+~]+) + * Matches the selector list separator + */ + // phpcs:ignore Generic.Files.LineLength + $pattern = "/([\w:\*-]*)(?:\#([\w-]+))?(?:|\.([\w\.-]+))?((?:\[@?(?:!?[\w:-]+)(?:(?:[!*^$|~]?=)[\"']?(?:.*?)[\"']?)?(?:\s*?(?:[iIsS])?)?\])+)?([\/, >+~]+)/is"; + + preg_match_all( + $pattern, + trim($selector_string) . ' ', // Add final ' ' as pseudo separator + $matches, + PREG_SET_ORDER + ); + + if (is_object($debug_object)) { + $debug_object->debug_log(2, 'Matches Array: ', $matches); + } + + $selectors = array(); + $result = array(); + + foreach ($matches as $m) { + $m[0] = trim($m[0]); + + // Skip NoOps + if ($m[0] === '' || $m[0] === '/' || $m[0] === '//') { continue; } + + // Convert to lowercase + if ($this->dom->lowercase) { + $m[1] = strtolower($m[1]); + } + + // Extract classes + if ($m[3] !== '') { $m[3] = explode('.', $m[3]); } + + /* Extract attributes (pattern based on the pattern above!) + + * [0] - full match + * [1] - attribute name + * [2] - attribute expression + * [3] - attribute value + * [4] - case sensitivity + * + * Note: Attributes can be negated with a "!" prefix to their name + */ + if($m[4] !== '') { + preg_match_all( + "/\[@?(!?[\w:-]+)(?:([!*^$|~]?=)[\"']?(.*?)[\"']?)?(?:\s*?([iIsS])?)?\]/is", + trim($m[4]), + $attributes, + PREG_SET_ORDER + ); + + // Replace element by array + $m[4] = array(); + + foreach($attributes as $att) { + // Skip empty matches + if(trim($att[0]) === '') { continue; } + + $inverted = (isset($att[1][0]) && $att[1][0] === '!'); + $m[4][] = array( + $inverted ? substr($att[1], 1) : $att[1], // Name + (isset($att[2])) ? $att[2] : '', // Expression + (isset($att[3])) ? $att[3] : '', // Value + $inverted, // Inverted Flag + (isset($att[4])) ? strtolower($att[4]) : '', // Case-Sensitivity + ); + } + } + + // Sanitize Separator + if ($m[5] !== '' && trim($m[5]) === '') { // Descendant Separator + $m[5] = ' '; + } else { // Other Separator + $m[5] = trim($m[5]); + } + + // Clear Separator if it's a Selector List + if ($is_list = ($m[5] === ',')) { $m[5] = ''; } + + // Remove full match before adding to results + array_shift($m); + $result[] = $m; + + if ($is_list) { // Selector List + $selectors[] = $result; + $result = array(); + } + } + + if (count($result) > 0) { $selectors[] = $result; } + return $selectors; + } + + function __get($name) + { + if (isset($this->attr[$name])) { + return $this->convert_text($this->attr[$name]); + } + switch ($name) { + case 'outertext': return $this->outertext(); + case 'innertext': return $this->innertext(); + case 'plaintext': return $this->text(); + case 'xmltext': return $this->xmltext(); + default: return array_key_exists($name, $this->attr); + } + } + + function __set($name, $value) + { + global $debug_object; + if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } + + switch ($name) { + case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value; + case 'innertext': + if (isset($this->_[HDOM_INFO_TEXT])) { + return $this->_[HDOM_INFO_TEXT] = $value; + } + return $this->_[HDOM_INFO_INNER] = $value; + } + + if (!isset($this->attr[$name])) { + $this->_[HDOM_INFO_SPACE][] = array(' ', '', ''); + $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; + } + + $this->attr[$name] = $value; + } + + function __isset($name) + { + switch ($name) { + case 'outertext': return true; + case 'innertext': return true; + case 'plaintext': return true; + } + //no value attr: nowrap, checked selected... + return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]); + } + + function __unset($name) + { + if (isset($this->attr[$name])) { unset($this->attr[$name]); } + } + + // PaperG - Function to convert the text from one character set to another + // if the two sets are not the same. + function convert_text($text) + { + global $debug_object; + if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } + + $converted_text = $text; + + $sourceCharset = ''; + $targetCharset = ''; + + if ($this->dom) { + $sourceCharset = strtoupper($this->dom->_charset); + $targetCharset = strtoupper($this->dom->_target_charset); + } + + if (is_object($debug_object)) { + $debug_object->debug_log(3, + 'source charset: ' + . $sourceCharset + . ' target charaset: ' + . $targetCharset + ); + } + + if (!empty($sourceCharset) + && !empty($targetCharset) + && (strcasecmp($sourceCharset, $targetCharset) != 0)) { + // Check if the reported encoding could have been incorrect and the text is actually already UTF-8 + if ((strcasecmp($targetCharset, 'UTF-8') == 0) + && ($this->is_utf8($text))) { + $converted_text = $text; + } else { + $converted_text = iconv($sourceCharset, $targetCharset, $text); + } + } + + // Lets make sure that we don't have that silly BOM issue with any of the utf-8 text we output. + if ($targetCharset === 'UTF-8') { + if (substr($converted_text, 0, 3) === "\xef\xbb\xbf") { + $converted_text = substr($converted_text, 3); + } + + if (substr($converted_text, -3) === "\xef\xbb\xbf") { + $converted_text = substr($converted_text, 0, -3); + } + } + + return $converted_text; + } + + /** + * Returns true if $string is valid UTF-8 and false otherwise. + * + * @param mixed $str String to be tested + * @return boolean + */ + static function is_utf8($str) + { + $c = 0; $b = 0; + $bits = 0; + $len = strlen($str); + for($i = 0; $i < $len; $i++) { + $c = ord($str[$i]); + if($c > 128) { + if(($c >= 254)) { return false; } + elseif($c >= 252) { $bits = 6; } + elseif($c >= 248) { $bits = 5; } + elseif($c >= 240) { $bits = 4; } + elseif($c >= 224) { $bits = 3; } + elseif($c >= 192) { $bits = 2; } + else { return false; } + if(($i + $bits) > $len) { return false; } + while($bits > 1) { + $i++; + $b = ord($str[$i]); + if($b < 128 || $b > 191) { return false; } + $bits--; + } + } + } + return true; + } + + /** + * Function to try a few tricks to determine the displayed size of an img on + * the page. NOTE: This will ONLY work on an IMG tag. Returns FALSE on all + * other tag types. + * + * @author John Schlick + * @version April 19 2012 + * @return array an array containing the 'height' and 'width' of the image + * on the page or -1 if we can't figure it out. + */ + function get_display_size() + { + global $debug_object; + + $width = -1; + $height = -1; + + if ($this->tag !== 'img') { + return false; + } + + // See if there is aheight or width attribute in the tag itself. + if (isset($this->attr['width'])) { + $width = $this->attr['width']; + } + + if (isset($this->attr['height'])) { + $height = $this->attr['height']; + } + + // Now look for an inline style. + if (isset($this->attr['style'])) { + // Thanks to user gnarf from stackoverflow for this regular expression. + $attributes = array(); + + preg_match_all( + '/([\w-]+)\s*:\s*([^;]+)\s*;?/', + $this->attr['style'], + $matches, + PREG_SET_ORDER + ); + + foreach ($matches as $match) { + $attributes[$match[1]] = $match[2]; + } + + // If there is a width in the style attributes: + if (isset($attributes['width']) && $width == -1) { + // check that the last two characters are px (pixels) + if (strtolower(substr($attributes['width'], -2)) === 'px') { + $proposed_width = substr($attributes['width'], 0, -2); + // Now make sure that it's an integer and not something stupid. + if (filter_var($proposed_width, FILTER_VALIDATE_INT)) { + $width = $proposed_width; + } + } + } + + // If there is a width in the style attributes: + if (isset($attributes['height']) && $height == -1) { + // check that the last two characters are px (pixels) + if (strtolower(substr($attributes['height'], -2)) == 'px') { + $proposed_height = substr($attributes['height'], 0, -2); + // Now make sure that it's an integer and not something stupid. + if (filter_var($proposed_height, FILTER_VALIDATE_INT)) { + $height = $proposed_height; + } + } + } + + } + + // Future enhancement: + // Look in the tag to see if there is a class or id specified that has + // a height or width attribute to it. + + // Far future enhancement + // Look at all the parent tags of this image to see if they specify a + // class or id that has an img selector that specifies a height or width + // Note that in this case, the class or id will have the img subselector + // for it to apply to the image. + + // ridiculously far future development + // If the class or id is specified in a SEPARATE css file thats not on + // the page, go get it and do what we were just doing for the ones on + // the page. + + $result = array( + 'height' => $height, + 'width' => $width + ); + + return $result; + } + + // camel naming conventions + function getAllAttributes() + { + return $this->attr; + } + + function getAttribute($name) + { + return $this->__get($name); + } + + function setAttribute($name, $value) + { + $this->__set($name, $value); + } + + function hasAttribute($name) + { + return $this->__isset($name); + } + + function removeAttribute($name) + { + $this->__set($name, null); + } + + function getElementById($id) + { + return $this->find("#$id", 0); + } + + function getElementsById($id, $idx = null) + { + return $this->find("#$id", $idx); + } + + function getElementByTagName($name) + { + return $this->find($name, 0); + } + + function getElementsByTagName($name, $idx = null) + { + return $this->find($name, $idx); + } + + function parentNode() + { + return $this->parent(); + } + + function childNodes($idx = -1) + { + return $this->children($idx); + } + + function firstChild() + { + return $this->first_child(); + } + + function lastChild() + { + return $this->last_child(); + } + + function nextSibling() + { + return $this->next_sibling(); + } + + function previousSibling() + { + return $this->prev_sibling(); + } + + function hasChildNodes() + { + return $this->has_child(); + } + + function nodeName() + { + return $this->tag; + } + + function appendChild($node) + { + $node->parent($this); + return $node; + } + +} + +/** + * simple html dom parser + * + * Paperg - in the find routine: allow us to specify that we want case + * insensitive testing of the value of the selector. + * + * Paperg - change $size from protected to public so we can easily access it + * + * Paperg - added ForceTagsClosed in the constructor which tells us whether we + * trust the html or not. Default is to NOT trust it. + * + * @package PlaceLocalInclude + */ +class simple_html_dom +{ + /** + * The root node of the document + * + * @var object + */ + public $root = null; + + /** + * List of nodes in the current DOM + * + * @var array + */ + public $nodes = array(); + + /** + * Callback function to run for each element in the DOM. + * + * @var callable|null + */ + public $callback = null; + + /** + * Indicates how tags and attributes are matched + * + * @var bool When set to **true** tags and attributes will be converted to + * lowercase before matching. + */ + public $lowercase = false; + + /** + * Original document size + * + * Holds the original document size. + * + * @var int + */ + public $original_size; + + /** + * Current document size + * + * Holds the current document size. The document size is determined by the + * string length of ({@see simple_html_dom::$doc}). + * + * _Note_: Using this variable is more efficient than calling `strlen($doc)` + * + * @var int + * */ + public $size; + + /** + * Current position in the document + * + * @var int + */ + protected $pos; + + /** + * The document + * + * @var string + */ + protected $doc; + + /** + * Current character + * + * Holds the current character at position {@see simple_html_dom::$pos} in + * the document {@see simple_html_dom::$doc} + * + * _Note_: Using this variable is more efficient than calling + * `substr($doc, $pos, 1)` + * + * @var string + */ + protected $char; + + protected $cursor; + + /** + * Parent node of the next node detected by the parser + * + * @var object + */ + protected $parent; + protected $noise = array(); + + /** + * Tokens considered blank in HTML + * + * @var string + */ + protected $token_blank = " \t\r\n"; + + /** + * Tokens to identify the equal sign for attributes, stopping either at the + * closing tag ("/" i.e. "") or the end of an opening tag (">" i.e. + * "") + * + * @var string + */ + protected $token_equal = ' =/>'; + + /** + * Tokens to identify the end of a tag name. A tag name either ends on the + * ending slash ("/" i.e. "") or whitespace ("\s\r\n\t") + * + * @var string + */ + protected $token_slash = " />\r\n\t"; + + /** + * Tokens to identify the end of an attribute + * + * @var string + */ + protected $token_attr = ' >'; + + // Note that this is referenced by a child node, and so it needs to be + // public for that node to see this information. + public $_charset = ''; + public $_target_charset = ''; + + /** + * Innertext for
elements + * + * @var string + */ + protected $default_br_text = ''; + + /** + * Suffix for elements + * + * @var string + */ + public $default_span_text = ''; + + /** + * Defines a list of self-closing tags (Void elements) according to the HTML + * Specification + * + * _Remarks_: + * - Use `isset()` instead of `in_array()` on array elements to boost + * performance about 30% + * - Sort elements by name for better readability! + * + * @link https://www.w3.org/TR/html HTML Specification + * @link https://www.w3.org/TR/html/syntax.html#void-elements Void elements + */ + protected $self_closing_tags = array( + 'area' => 1, + 'base' => 1, + 'br' => 1, + 'col' => 1, + 'embed' => 1, + 'hr' => 1, + 'img' => 1, + 'input' => 1, + 'link' => 1, + 'meta' => 1, + 'param' => 1, + 'source' => 1, + 'track' => 1, + 'wbr' => 1 + ); + + /** + * Defines a list of tags which - if closed - close all optional closing + * elements within if they haven't been closed yet. (So, an element where + * neither opening nor closing tag is omissible consistently closes every + * optional closing element within) + * + * _Remarks_: + * - Use `isset()` instead of `in_array()` on array elements to boost + * performance about 30% + * - Sort elements by name for better readability! + */ + protected $block_tags = array( + 'body' => 1, + 'div' => 1, + 'form' => 1, + 'root' => 1, + 'span' => 1, + 'table' => 1 + ); + + /** + * Defines elements whose end tag is omissible. + * + * * key = Name of an element whose end tag is omissible. + * * value = Names of elements whose end tag is omissible, that are closed + * by the current element. + * + * _Remarks_: + * - Use `isset()` instead of `in_array()` on array elements to boost + * performance about 30% + * - Sort elements by name for better readability! + * + * **Example** + * + * An `li` element’s end tag may be omitted if the `li` element is immediately + * followed by another `li` element. To do that, add following element to the + * array: + * + * ```php + * 'li' => array('li'), + * ``` + * + * With this, the following two examples are considered equal. Note that the + * second example is missing the closing tags on `li` elements. + * + * ```html + *
  • First Item
  • Second Item
+ * ``` + * + *
  • First Item
  • Second Item
+ * + * ```html + *
  • First Item
  • Second Item
+ * ``` + * + *
  • First Item
  • Second Item
+ * + * @var array A two-dimensional array where the key is the name of an + * element whose end tag is omissible and the value is an array of elements + * whose end tag is omissible, that are closed by the current element. + * + * @link https://www.w3.org/TR/html/syntax.html#optional-tags Optional tags + * + * @todo The implementation of optional closing tags doesn't work in all cases + * because it only consideres elements who close other optional closing + * tags, not taking into account that some (non-blocking) tags should close + * these optional closing tags. For example, the end tag for "p" is omissible + * and can be closed by an "address" element, whose end tag is NOT omissible. + * Currently a "p" element without closing tag stops at the next "p" element + * or blocking tag, even if it contains other elements. + * + * @todo Known sourceforge issue #2977341 + * B tags that are not closed cause us to return everything to the end of + * the document. + */ + protected $optional_closing_tags = array( + // Not optional, see + // https://www.w3.org/TR/html/textlevel-semantics.html#the-b-element + 'b' => array('b' => 1), + 'dd' => array('dd' => 1, 'dt' => 1), + // Not optional, see + // https://www.w3.org/TR/html/grouping-content.html#the-dl-element + 'dl' => array('dd' => 1, 'dt' => 1), + 'dt' => array('dd' => 1, 'dt' => 1), + 'li' => array('li' => 1), + 'optgroup' => array('optgroup' => 1, 'option' => 1), + 'option' => array('optgroup' => 1, 'option' => 1), + 'p' => array('p' => 1), + 'rp' => array('rp' => 1, 'rt' => 1), + 'rt' => array('rp' => 1, 'rt' => 1), + 'td' => array('td' => 1, 'th' => 1), + 'th' => array('td' => 1, 'th' => 1), + 'tr' => array('td' => 1, 'th' => 1, 'tr' => 1), + ); + + function __construct( + $str = null, + $lowercase = true, + $forceTagsClosed = true, + $target_charset = DEFAULT_TARGET_CHARSET, + $stripRN = true, + $defaultBRText = DEFAULT_BR_TEXT, + $defaultSpanText = DEFAULT_SPAN_TEXT, + $options = 0) + { + if ($str) { + if (preg_match('/^http:\/\//i', $str) || is_file($str)) { + $this->load_file($str); + } else { + $this->load( + $str, + $lowercase, + $stripRN, + $defaultBRText, + $defaultSpanText, + $options + ); + } + } + // Forcing tags to be closed implies that we don't trust the html, but + // it can lead to parsing errors if we SHOULD trust the html. + if (!$forceTagsClosed) { + $this->optional_closing_array = array(); + } + + $this->_target_charset = $target_charset; + } + + function __destruct() + { + $this->clear(); + } + + // load html from string + function load( + $str, + $lowercase = true, + $stripRN = true, + $defaultBRText = DEFAULT_BR_TEXT, + $defaultSpanText = DEFAULT_SPAN_TEXT, + $options = 0) + { + global $debug_object; + + // prepare + $this->prepare($str, $lowercase, $defaultBRText, $defaultSpanText); + + // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037 + // Script tags removal now preceeds style tag removal. + // strip out