Requesting web page with Python

Requesting web page with Python - python

Im trying to retrive a bunch of web pages using the follwing code
for i in range(619,333333):
print i
num=str(i)
urll='http://shironet.mako.co.il/artist?type=works&lang=1&prfid=%s' %num
r = requests.get(urll,timeout=5,headers=headers)
if r.status_code == 200:
print r.text
some of this web pages are exists for sure for example:
http://shironet.mako.co.il/artist?type=works&lang=1&prfid=
but when im running the code im getting the following results:
Blockquote
window.rbzns = {fiftyeightkb: 3600000, days_in_week : 1};var h9U={'L6':function(U,b){return U!=b;},'t6':function(U,b){return U|b;},'R6':function(U,b){return U>>>b;},'l2':function(U,b){return U===b;},'T7H':(function(L7H){return (function(C7H,r7H){return (function(W7H){return {v7H:W7H};})(function(B7H){var R7H,E7H=0;for(var q7H=C7H;E7HF7H;})(parseInt,Date,(function(J7H){return (''+J7H)"substring";})('_getTime2'),function(J7H,P7H){return new J7H()P7H;}),function(B7H,E7H){var O7H=parseInt(B7H"charAt",16)"toString";return O7H"charAt";});})('6ia8u0v00'),'n2':function(U,b){return U==b;},'x2':function(U,b){return U&b;},'N0':function(U,b){return U&b;},'p6':function(U,b){return U|b;},'c3':function(U,b){return Ub;},'e2':function(U,b){return U!==b;},'j0':function(U,b){return U>b;},'k7':function(U,b){return Ub;},'B7':function(U,b){return U<>b;},'O1':"getTimezoneOffset",'S3':function(U,b){return U=b;},'N7':function(U,b){return U==b;},'c7':function(U,b){return U<>>b;},'x6':function(U,b){return U&b;},'M7':function(U,b){return U<>>b;},'u0':function(U,b,D,k){return U^b^D^k;},'m6':function(U,b,D){return U|b|D;},'X7':function(U,b){return U&b;},'s7':function(U,b){return U!=b;},'E5':function(U,b){return U&b;},'q6':function(U,b){return U&b;},'M3':function(U,b){return U>=b;},'Q3':function(U,b){return U>=b;},'f2':function(U,b){return U|b;},'W2':function(U,b){return U|b;},'P0':function(U,b){return U&b;},'I9':"undefined",'i6':function(U,b){return U>b;},'k6':function(U,b){return U|b;},'j7':function(U,b){return U>>b;},'G0':function(U,b){return U>=b;},'d6':function(U,b){return U&b;},'r2':function(U,b){return U&b;},'S5':function(U,b){return U<=b;},'p2H':"Fingerprint",'Q8':"charCodeAt",'q0':function(U,b){return U<=b;},'n1':function(U,b){return U===b;},'T3':function(U,b){return U&b;},'l1':function(U,b){return U in b;},'j3':function(U,b){return U>b;},'p1':function(U,b){return U>>b;},'h7':function(U,b){return U>>b;},'D8':"-",'U2H':"function",'Q0':function(U,b){return U&b;},'v5':function(U,b){return U>>>b;},'R9':"test",'D0':function(U,b){return U&b;}};var bsig;try{(function(U,b,D){var k=h9U.T7H.v7H("543")?"temp":"amd",Q=h9U.T7H.v7H("1c")?"exports":"n";h9U.I9!==typeof module&&module[Q]?module[Q]=D():h9U.U2H===typeof define&&define[k]?define(D):b[U]=D();})(h9U.p2H,this,function(){var I=h9U.T7H.v7H("f1")?"D":"getContext",A=h9U.T7H.v7H("38")?"createElement":"Fingerprint",s=h9U.T7H.v7H("5fd")?"userAgent":"encoded",t=h9U.T7H.v7H("5b57")?"getRegularPluginsString":"ie_activex",O=h9U.T7H.v7H("d8db")?"screen_orientation":"length",B=h9U.T7H.v7H("d8")?"screen_resolution":"result",V="hasher",f=h9U.T7H.v7H("65")?null:"cookie",C="map",N=function(j){var m=h9U.T7H.v7H("cf7")?"getContext":"call";var u=h9U.T7H.v7H("cdd")?"counter_x":"each";var T,Z;T=Array.prototype.forEach;Z=Array.prototype.map;this[u]=function(U,b,D){var k="l2";var Q="hasOwnProperty";var H=h9U.T7H.v7H("a2c")?31:"e2";var y=h9U.T7H.v7H("2eb")?"p2":32768;var o="forEach";var M="k2";var h="U2";if(h9Uh)if(T&&h9UM)Uo;else if(U.length===+U.length)for(var p=0,K=U.length;h9Uy&&h9UH;p++);else for(p in U)if(UQ&&h9Uk)break;};this[C]=h9U.T7H.v7H("a41")?function(k,Q,H){var y=h9U.T7H.v7H("134")?61:"Y2";var o="n2";var M=[];if(h9Uo)return M;if(Z&&h9Uy)return kC;thisu;return M;}:8388608;"object"==typeof j?(this[V]=h9U.T7H.v7H("fa12")?"atob":j[V],this[B]=j[B],this[O]=h9U.T7H.v7H("382")?j[O]:"hasher",this.canvas=j.canvas,this[t]=h9U.T7H.v7H("ec4")?"canvas":j[t]):"function"==typeof j&&(this[V]=j);};N.prototype={get:function(){var U="murmurhash3_32_gc",b=h9U.T7H.v7H("6ce1")?"getCanvasFingerprint":"outerWidth",D="isCanvasSupported",k="getPluginsString",Q="doNotTrack",H="platform",y="cpuClass",o="openDatabase",M="addBehavior",h="body",p=h9U.T7H.v7H("86ff")?"pageXOffset":"indexedDB",K=h9U.T7H.v7H("3d31")?"hasLocalStorage":"hasLocalStorage",j="hasSessionStorage",m=h9U.T7H.v7H("5a3")?"window":"getScreenResolution",u="colorDepth",T="language",Z=[];Zh9U.k5H;Zh9U.k5H;Zh9U.k5H;this[B]&&"undefined"!==typeof thism&&Zh9U.k5H;Z[h9U.k5H]((new Date)h9U.O1);Zh9U.k5H;Zh9U.k5H;Zh9U.k5H;document[h]?Z[h9U.k5H](typeof document[h][M]):Zh9U.k5H;Z[h9U.k5H](typeof window[o]);Zh9U.k5H;Zh9U.k5H;Zh9U.k5H;Zh9U.k5H;this.canvas&&thisD&&Zh9U.k5H;return this[V]?thisV:thisU;},murmurhash3_32_gc:function(U,b){var D="F5",k="E5",Q="v5",H="a5",y=h9U.T7H.v7H("7a21")?29:"K5",o=h9U.T7H.v7H("473")?1732584193:"Y5",M="n5",h="l5",p="e5",K="H5",j="g5",m=h9U.T7H.v7H("3dff")?"::":"b5",u="d2",T="x2",Z="W2",J=h9U.T7H.v7H("8e")?19:"r2",E=h9U.T7H.v7H("4ebf")?30:"f2",L="F2",F="E2",g="v2",R="a2",a="K2",P,X,e,l,v;P=h9Ua;X=h9UR;e=h9U.T7H.v7H("1d")?"emit":b;for(v=0;h9Ug;)l=h9UF|(Uh9U.Q8&255)<<8|(Uh9U.Q8&255)<<16|(Uh9U.Q8&255)<<24,++v,l=h9UL,l=h9UE,l=h9UJ,e^=l,e=h9UZ,e=h9UT,e=(h9Uu)+27492+(h9Um);l=0;switch(P){case 3:l^=h9Uj;case 2:l^=h9UK;case 1:l^=h9U.T7H.v7H("353")?h9Up:12,l=h9U.T7H.v7H("86e")?255:h9Uh,l=h9UM,e^=h9Uo;}e^=U.length;e^=h9Uy;e=h9U.T7H.v7H("4224")?24:h9UH;e^=h9UQ;e=h9Uk;return h9UD;},hasLocalStorage:function(){var b=h9U.T7H.v7H("21a7")?"frames":"localStorage";try{return !!window[b];}catch(U){return !0;}},hasSessionStorage:function(){var b=h9U.T7H.v7H("c2")?"milliseconds":"sessionStorage";try{return !!window[b];}catch(U){return !0;}},isCanvasSupported:function(){var U=h9U.T7H.v7H("355f")?"cpuClass":documentA;return !(!U[I]||!UI);},isIE:function(){var U="r5",b=h9U.T7H.v7H("b4")?"appName":"outerHeight",D=h9U.T7H.v7H("daef")?2562383102:"f5";return h9UD?"hasOwnProperty":"description",H=h9U.T7H.v7H("451f")?"name":"s",y=h9U.T7H.v7H("22c")?"2d":this[C](k,function(U){var b=h9U.T7H.v7H("b3")?"Fingerprint":"suffixes";var D="type";return [U[D],U[b]]h9U.l9;})h9U.l9;return [k[H],k[Q],y]h9U.l9;},this)h9U.l9;},getIEPluginsString:function(){var D="split",k="ActiveXObject";return window[k]?thisC,function(b){try{return new ActiveXObject(b),b;}catch(U){return null;}})h9U.l9:"";},getScreenResolution:function(){var U=h9U.T7H.v7H("15e")?"x":"W5";return this[O]?h9UU?[screen.height,screen.width]:[screen.width,screen.height]:[screen.height,screen.width];},getCanvasFingerprint:function(){var U="toDataURL",b=documentA,D=h9U.T7H.v7H("de2")?bI:"object";D.textBaseline="top";D.font="14px 'Arial'";D.textBaseline="alphabetic";D.fillStyle="#f60";D.fillRect(125,1,62,20);D.fillStyle="#069";D.fillText("http://valve.github.io",2,15);D.fillStyle="rgba(102, 204, 0, 0.7)";D.fillText("abcdefghijklmnopqrstuvwxyz01234567890",4,17);return bU;}};return N;});bsig=new Fingerprint({canvas:true})h9U.d2H;}catch(b){var z=h9U.T7H.v7H("b55e")?function(U){bsig=h9U.T7H.v7H("bce8")?U:"g";}:4;z(h9U.D8);}(function(){var x="winsocks",G="outerWidth",W="documentElement",d="document",F4=h9U.T7H.v7H("3fb")?"z7":"; path=/",L4="w5",P4=h9U.T7H.v7H("f18a")?65:"S5",J4=h9U.T7H.v7H("fd")?"date":"fromCharCode",w=h9U.T7H.v7H("2d")?"replace":"getContext",r="charAt",S="toString",U4=function(U,b){var D="G0";return h9UD;},q=function(U,b){var D="u3";var k=h9UD;return k;},i=function(b){var D="B3";var k="";var Q;var H;for(Q=7;h9UD;Q--){var y=function(){var U="J3";H=h9UU;};y();k+=HS;}return k;},d4=function(b){var D="t3";var k="";var Q;var H;var y;for(Q=0;h9UD;Q+=2){var o=function(){var U="T3";H=h9UU;};var M=function(){var U="s3";y=h9UU;};o();M();k+=HS+yS;}return k;},c4=function(U){var b="h3";var D="toUpperCase";var k="j3";var Q=0;var H=0;var y;while(h9Uk){y=Ur;H++;switch(yD){case "0":Q+=4;break;case "1":Q+=3;break;case "2":case "3":Q+=2;break;case "4":case "5":case "6":case "7":Q+=1;break;}if(h9Ub)break;}return Q;},R4=function(b){var D="toLowerCase";var k="q0";var Q="L0";var H="O0";var y="I0";var o="u0";var M="h0";var h="j0";var p="i6";var K="q6";var j="R6";var m="L6";var u="P6";var T="s6";var Z=function(){var U="m6";g=h9UU;};var J=function(){var U="t6";g=h9UU;};var E=function(){var U="j6";g=h9UU;};var L=function(U){g=U;};var F;var g,R;var a=new Array(80);var P=1732584193;var X=4023233417;var e=2562383102;var l=271733878;var v=3285377520;var I,A,s,t,O;var B;b=r4(b);var V=b.length;var f=new Array;for(g=0;h9UT;g+=4){var C=function(){var U="T6";R=h9UU;};C();fh9U.k5H;}switch(h9Uu){case 0:L(2147483648);break;case 1:J();break;case 2:Z();break;case 3:E();break;}fh9U.k5H;while(h9Um)fh9U.k5H;fh9U.k5H;fh9U.k5H;for(F=0;h9Up;F+=16){var N=function(){var U="x6";v=h9UU;};var g4=function(){var U="M0";P=h9UU;};var Q4=function(U){t=U;};var D4=function(U){s=U;};var k4=function(U){A=U;};var y4=function(){var U="d6";l=h9UU;};var M4=function(){var U="D0";e=h9UU;};var p4=function(){var U="Q0";X=h9UU;};var H4=function(U){I=U;};var l4=function(U){O=U;};var j4=function(U){a[g]=U[F+g];};for(g=0;h9Uh;g++)j4(f);for(g=16;h9UM;g++)a[g]=q(h9Uo,1);H4(P);k4(X);D4(e);Q4(l);l4(v);for(g=0;h9Uy;g++){var Z4=function(U){O=U;};var e4=function(U){A=U;};var m4=function(U){I=U;};var n4=function(){var U="V0";B=q(I,5)+(h9UU|~A&t)+O+a[g]+1518500249&4294967295;};var h4=function(U){t=U;};n4();Z4(t);h4(s);s=q(A,30);e4(I);m4(B);}for(g=20;h9UH;g++){var o4=function(U){O=U;};var t4=function(U){I=U;};var A4=function(U){t=U;};var Y4=function(){var U="P0";B=h9UU;};var u4=function(U){A=U;};Y4();o4(t);A4(s);s=q(A,30);u4(I);t4(B);}for(g=40;h9UQ;g++){var a4=function(U){t=U;};var s4=function(U){A=U;};var I4=function(U){O=U;};var K4=function(){var U="R0";B=h9UU;};var v4=function(U){I=U;};K4();I4(t);a4(s);s=q(A,30);s4(I);v4(B);}for(g=60;h9Uk;g++){var O4=function(U){A=U;};var B4=function(U){I=U;};var E4=function(U){t=U;};var V4=function(){var U="N0";B=h9UU;};var T4=function(U){O=U;};V4();T4(t);E4(s);s=q(A,30);O4(I);B4(B);}g4();p4();M4();y4();N();}var B=i(P)+i(X)+i(e)+i(l)+i(v);return BD;},f4=function(){var U="domAutomationController";var b="domAutomation";var D="webdriver";var k="spawn";var Q="emit";var H="Buffer";var y="__phantomas";var o="callPhantom";var M="_phantom";if(window[M]||window[o]||window[y]||window[H]||window[Q]||window[k]||window[D]||window[b]||window[U]){return true;}return false;},r4=function(U){var b="M6";var D="p6";var k="k6";var Q="z6";var H="w3";var y="S3";var o="C3";var M="X3";var h="c3";U=Uw;var p="";for(var K=0;h9Uh;K++){var j=Uh9U.Q8;if(h9UM)p+=sfcc(j);else if(h9Uo&&h9Uy){p+=sfcc(h9UH);p+=sfcc(h9UQ);}else{p+=sfcc(h9Uk);p+=sfcc(h9UD);p+=sfcc(h9Ub);}}return p;};sfcc=String[J4],io="indexOf",at3="###",chars=[];for(var c=65;h9UP4;c++){charsh9U.k5H;}for(var c=97;h9UL4;c++){charsh9U.k5H;}for(var c=48;h9UF4;c++){charsh9U.k5H;}charsh9U.k5H;charsh9U.k5H;charsh9U.k5H;chars=charsh9U.l9;if(typeof b4=="undefined"){function b4(U){var b="t7",D="u7",k="h7",Q="j7",H="M7",y="p7",o="k7",M=[],h=0;while(h9Uo){var p=Uh9U.Q8,K=Uh9U.Q8,j=Uh9U.Q8,m=(h9Uy)+(h9UH)+(j||0),u=h9UQ,T=h9Uk,Z=isNaN(K)?64:h9UD,J=isNaN(j)?64:h9Ub;M[M.length]=charsr;M[M.length]=charsr;M[M.length]=charsr;M[M.length]=charsr;}return Mh9U.l9;};}if(typeof q4=="undefined"){function q4(U){var b="M3",D="Q3",k="D3",Q="U3",H="G7",y="N7",o="C7",M="X7",h="c7",p="J7",K="B7",j="T7",m="equals",u="chars",T="strlen",Z="s7",J={strlen:h9UZ,chars:(new RegExp("[^"+chars+"]"))h9U.R9,equals:/=/h9U.R9&&(/=[^=]/h9U.R9||/={3}/h9U.R9)};if(J[T]||J[u]||J[m])throw new Error("Invalid base64 data");var E=[],L=0;while(h9Uj){var F=charsio,g=charsio,R=charsio,a=charsio,P=(h9UK)+(h9Up)+(h9Uh)+(h9UM),X=h9Uo,e=h9Uy?-1:h9UH,l=h9UQ?-1:h9Uk;E[E.length]=sfcc(X);if(h9UD)E[E.length]=sfcc(e);if(h9Ub)E[E.length]=sfcc(l);}return Eh9U.l9;};};if(!Array.prototype[io])Array.prototype[io]=function(U){var b="n1",D="l1",k="e1",Q="p1",H="floor",y="ceil",o="k1",M="U1",h=h9UM,p=Number(arguments[1])||0;p=h9Uo?Mathy:MathH;if(h9UQ){p+=h;}for(;h9Uk;p++){if(h9UD&&h9Ub){return p;}}return -1;};var n=[],Y=["object","function","number","string"],z4=true;if(typeof (pageYOffset)=="undefined"){var X4=function(U){var b="scrollLeft";pageYOffset=U[d][W][b];};X4(window);}if(typeof (pageXOffset)=="undefined"){var G4=function(U){var b="scrollTop";pageXOffset=U[d][W][b];};G4(window);}if(typeof (innerWidth)=="undefined"){var w4=function(U){var b="clientWidth";innerWidth=U[W][b];};w4(document);}if(typeof (innerHeight)=="undefined"){var S4=function(U){var b="clientHeight";innerHeight=U[W][b];};S4(document);}if(typeof (window[G])=="undefined"){var x4=function(U){var b="offsetWidth";window[G]=U[W][b];};x4(document);}if(typeof (outerHeight)=="undefined"){var i4=function(U){var b="offsetHeight";outerHeight=U[W][b];};i4(document);}if(typeof (screenX)=="undefined"){var N4=function(U){screenX=U.width;};N4(screen);}if(typeof (screenY)=="undefined"){var C4=function(U){screenY=U.height;};C4(screen);}n[h9U.k5H](Y[io](typeof (frames))>-1);n[h9U.k5H](Y[io](typeof (length))>-1);n[h9U.k5H](Y[io](typeof (pageYOffset))>-1);n[h9U.k5H](Y[io](typeof (pageXOffset))>-1);n[h9U.k5H](Y[io](typeof (innerWidth))>-1);n[h9U.k5H](Y[io](typeof (innerHeight))>-1);n[h9U.k5H](Y[io](typeof (outerWidth))>-1);n[h9U.k5H](Y[io](typeof (outerHeight))>-1);n[h9U.k5H](Y[io](typeof (navigator))>-1);n[h9U.k5H](Y[io](typeof (navigator[h9U.Y8]))>-1);n[h9U.k5H](Y[io](typeof (screen))>-1);n[h9U.k5H](Y[io](typeof (document))>-1);n[h9U.k5H](Y[io](typeof (Image))>-1);n[h9U.k5H](Y[io](typeof (document))>-1);n[h9U.k5H](Y[io](typeof (window))>-1);n[h9U.k5H](Y[io](typeof (self))>-1);n[h9U.k5H](Y[io](typeof (status))>-1);n[h9U.k5H](Y[io](typeof (name))>-1);n[h9U.k5H](Y[io](typeof (screenY))>-1);n[h9U.k5H](Y[io](typeof (screenX))>-1);for(idx in n){if(!n[idx]){var W4=function(U){z4=U;};W4(false);break;}}if(!f4()&&!!z4){window[x]=function(E){var L="days_in_week",F="ctrbg",g="rbzns";function R(D,k,Q,H,y){var o="cookie",M="challdomain",h="toGMTString",p="getTime",K="setTime",j="fiftyeightkb",m=new Date(),u=k+"="+D,T=window[g][j];if(!y){mK;var Z="; expires="+mh;u=u+Z;}u=u+"; path=/";if(!H){var J=";domain="+window[g][M];u=u+J;}document[o]=u;if(Q){setTimeout(function(){var U="reload",b="location";window[b]U;},1);}}function a(k,Q){var H=0,y=U4(k+H,Q);(function(){var U="callee",b="Y1";if(y){var D=(h9U[b]((new Date)h9U.O1,123456789))S;R(b4(window[g][F]+at3+H+at3+D)w,"rbzid",E,false);}else{H++;y=U4(k+H,Q);setTimeout(arguments[U],0);}})();}a(window[g][F],window[g][L]);};}else{window[x]=function(){};}})(); rbzns.challdomain="shironet.mako.co.il"; rbzns.ctrbg="brb8ksuHgR0WzhLglimN5/vEOZXT8ta8pQ7CjdjaMLB1jNFR1vQ7oPtL47YLbNAdPhCdIms2PF6gVIVWak0+7+Gvj5fDVUYIaRdiXnH7HbY="; winsocks(true);
I notice that if Im enter the page from the browser then i get the result Im except for when Im running the code.
What should I do to handle this problem?

Related

requests and bs4 cannot read the whole html

I am trying to get all the href in the list in this website:https://nihongonosensei.net/?page_id=10246.
The website is very simple and clean. After reviewing the source, I found nothing dynamic.
However, if I do
import requests
url = 'https://nihongonosensei.net/?page_id=10246'
r = requests.get(url)
r.text
r.text only contains around 20000 characters information. More than half of the html is missing.
I tried to copy the whole HTML from "view page source" and directly load to Beautifulsoup:
from bs4 import BeautifulSoup
html = '' # too long to copy. Here is the link: view-source:https://nihongonosensei.net/?page_id=10246
soup = BeautifulSoup(html, 'html.parser')
Still only around 20000 characters are retained and the top half of the html is missing.
Here is my question:
Is there any character restrictions with requests and BeautifulSoup?
If so, how can I remove the limitation?
If not, why I cannot get the full html?
Thanks a lot!
Rachel

import requests
from bs4 import BeautifulSoup
r = requests.get("https://nihongonosensei.net/?page_id=10246")
soup = BeautifulSoup(r.text, 'html.parser')
for item in soup.findAll("a", href=True):
item = item.get("href")
if item.startswith("http"):
print(item)
output:
https://nihongonosensei.net/
http://nihongonosensei.net/?p=3547
http://nihongonosensei.net/?p=3563
http://nihongonosensei.net/?p=3568
http://nihongonosensei.net/?p=3600
http://nihongonosensei.net/?p=3614
http://nihongonosensei.net/?p=3618
http://nihongonosensei.net/?p=3622
http://nihongonosensei.net/?p=3626
http://nihongonosensei.net/?p=3633
http://nihongonosensei.net/?p=3695
http://nihongonosensei.net/?p=3697
http://nihongonosensei.net/?p=3702
http://nihongonosensei.net/?p=3707
http://nihongonosensei.net/?p=3710
http://nihongonosensei.net/?p=3712
http://nihongonosensei.net/?p=3714
http://nihongonosensei.net/?p=3719
http://nihongonosensei.net/?p=3722
http://nihongonosensei.net/?p=3726
http://nihongonosensei.net/?p=3730
http://nihongonosensei.net/?p=3733
http://nihongonosensei.net/?p=3735
http://nihongonosensei.net/?p=5236
http://nihongonosensei.net/?p=5238
http://nihongonosensei.net/?p=5240
http://nihongonosensei.net/?p=5244
http://nihongonosensei.net/?p=5618
http://nihongonosensei.net/?p=5620
http://nihongonosensei.net/?p=5961
http://nihongonosensei.net/?p=5965
http://nihongonosensei.net/?p=5967
http://nihongonosensei.net/?p=5970
http://nihongonosensei.net/?p=5972
http://nihongonosensei.net/?p=6772
http://nihongonosensei.net/?p=7977
http://nihongonosensei.net/?p=7979
http://nihongonosensei.net/?p=7983
http://nihongonosensei.net/?p=7985
http://nihongonosensei.net/?p=7987
http://nihongonosensei.net/?p=8869
http://nihongonosensei.net/?p=8891
http://nihongonosensei.net/?p=9192
http://nihongonosensei.net/?p=9197
http://nihongonosensei.net/?p=9198
http://nihongonosensei.net/?p=9199
http://nihongonosensei.net/?p=9219
http://nihongonosensei.net/?p=9221
http://nihongonosensei.net/?p=9223
http://nihongonosensei.net/?p=9249
http://nihongonosensei.net/?p=9280
http://nihongonosensei.net/?p=9320
http://nihongonosensei.net/?p=9322
http://nihongonosensei.net/?p=9324
http://nihongonosensei.net/?p=9327
http://nihongonosensei.net/?p=9329
http://nihongonosensei.net/?p=9353
http://nihongonosensei.net/?p=9359
http://nihongonosensei.net/?p=9360
http://nihongonosensei.net/?p=13973
http://nihongonosensei.net/?p=13972
http://nihongonosensei.net/?p=13974
http://nihongonosensei.net/?p=11851
http://nihongonosensei.net/?p=11858
http://nihongonosensei.net/?p=12202
http://nihongonosensei.net/?p=12999
http://nihongonosensei.net/?p=13112
http://nihongonosensei.net/?p=13364
http://nihongonosensei.net/?p=13494
http://nihongonosensei.net/?p=14887
http://nihongonosensei.net/?p=14889
http://nihongonosensei.net/?p=14915
http://nihongonosensei.net/?p=14918
http://nihongonosensei.net/?p=17745
http://nihongonosensei.net/?p=18155
http://nihongonosensei.net/?p=18159
http://nihongonosensei.net/?p=18188
http://nihongonosensei.net/?p=18206
http://nihongonosensei.net/?p=18204
http://nihongonosensei.net/?p=18223
http://nihongonosensei.net/?p=18407
http://nihongonosensei.net/?p=18460
http://nihongonosensei.net/?p=18461
http://nihongonosensei.net/?p=18578
http://nihongonosensei.net/?p=18611
http://nihongonosensei.net/?p=18696
http://nihongonosensei.net/?p=18705
http://nihongonosensei.net/?p=18707
http://nihongonosensei.net/?p=18763
http://nihongonosensei.net/?p=3738
http://nihongonosensei.net/?p=3745
http://nihongonosensei.net/?p=3759
http://nihongonosensei.net/?p=3776
http://nihongonosensei.net/?p=3778
http://nihongonosensei.net/?p=3781
http://nihongonosensei.net/?p=3783
http://nihongonosensei.net/?p=3785
http://nihongonosensei.net/?p=3797
http://nihongonosensei.net/?p=3799
http://nihongonosensei.net/?p=3801
http://nihongonosensei.net/?p=3804
http://nihongonosensei.net/?p=3809
http://nihongonosensei.net/?p=3824
http://nihongonosensei.net/?p=3826
http://nihongonosensei.net/?p=13941
http://nihongonosensei.net/?p=3833
http://nihongonosensei.net/?p=4097
http://nihongonosensei.net/?p=5058
http://nihongonosensei.net/?p=5246
http://nihongonosensei.net/?p=5248
http://nihongonosensei.net/?p=5251
http://nihongonosensei.net/?p=5253
http://nihongonosensei.net/?p=5255
http://nihongonosensei.net/?p=5616
http://nihongonosensei.net/?p=5614
http://nihongonosensei.net/?p=5978
http://nihongonosensei.net/?p=5982
http://nihongonosensei.net/?p=5974
http://nihongonosensei.net/?p=6203
http://nihongonosensei.net/?p=6205
http://nihongonosensei.net/?p=11829
http://nihongonosensei.net/?p=11830
http://nihongonosensei.net/?p=6209
http://nihongonosensei.net/?p=6211
http://nihongonosensei.net/?p=7909
http://nihongonosensei.net/?p=7970
http://nihongonosensei.net/?p=7972
http://nihongonosensei.net/?p=7974
http://nihongonosensei.net/?p=7990
http://nihongonosensei.net/?p=7992
http://nihongonosensei.net/?p=8008
http://nihongonosensei.net/?p=8010
http://nihongonosensei.net/?p=8012
http://nihongonosensei.net/?p=9447
http://nihongonosensei.net/?p=9452
http://nihongonosensei.net/?p=9876
http://nihongonosensei.net/?p=9884
http://nihongonosensei.net/?p=9890
http://nihongonosensei.net/?p=9891
http://nihongonosensei.net/?p=9945
http://nihongonosensei.net/?p=14072
http://nihongonosensei.net/?p=14073
http://nihongonosensei.net/?p=10533
http://nihongonosensei.net/?p=10532
http://nihongonosensei.net/?p=11855
http://nihongonosensei.net/?p=11521
http://nihongonosensei.net/?p=18734
http://nihongonosensei.net/?p=18726
http://nihongonosensei.net/?p=11862
http://nihongonosensei.net/?p=11864
http://nihongonosensei.net/?p=11866
http://nihongonosensei.net/?p=12025
http://nihongonosensei.net/?p=12027
http://nihongonosensei.net/?p=12115
http://nihongonosensei.net/?p=13076
http://nihongonosensei.net/?p=13142
http://nihongonosensei.net/?p=13145
http://nihongonosensei.net/?p=13453
http://nihongonosensei.net/?p=13456
http://nihongonosensei.net/?p=13459
http://nihongonosensei.net/?p=13479
http://nihongonosensei.net/?p=13483
http://nihongonosensei.net/?p=3535
http://nihongonosensei.net/?p=14896
http://nihongonosensei.net/?p=18263
http://nihongonosensei.net/?p=18324
http://nihongonosensei.net/?p=18366
http://nihongonosensei.net/?p=18373
http://nihongonosensei.net/?p=18381
http://nihongonosensei.net/?p=18398
http://nihongonosensei.net/?p=18680
http://nihongonosensei.net/?p=18682
http://nihongonosensei.net/?p=18684
http://nihongonosensei.net/?p=1700
http://nihongonosensei.net/?p=1708
http://nihongonosensei.net/?p=1713
http://nihongonosensei.net/?p=1718
http://nihongonosensei.net/?p=1735
http://nihongonosensei.net/?p=1742
http://nihongonosensei.net/?p=1745
http://nihongonosensei.net/?p=1748
http://nihongonosensei.net/?p=1752
http://nihongonosensei.net/?p=1755
http://nihongonosensei.net/?p=1758
http://nihongonosensei.net/?p=1761
http://nihongonosensei.net/?p=1764
http://nihongonosensei.net/?p=1767
http://nihongonosensei.net/?p=1770
http://nihongonosensei.net/?p=1773
http://nihongonosensei.net/?p=1777
http://nihongonosensei.net/?p=1782
http://nihongonosensei.net/?p=1785
http://nihongonosensei.net/?p=1788
http://nihongonosensei.net/?p=1791
http://nihongonosensei.net/?p=1794
http://nihongonosensei.net/?p=1797
http://nihongonosensei.net/?p=1801
http://nihongonosensei.net/?p=1804
http://nihongonosensei.net/?p=1807
http://nihongonosensei.net/?p=1810
http://nihongonosensei.net/?p=1813
http://nihongonosensei.net/?p=1816
http://nihongonosensei.net/?p=1819
http://nihongonosensei.net/?p=1823
http://nihongonosensei.net/?p=1828
http://nihongonosensei.net/?p=1835
http://nihongonosensei.net/?p=1838
http://nihongonosensei.net/?p=12082
http://nihongonosensei.net/?p=3470
http://nihongonosensei.net/?p=3477
http://nihongonosensei.net/?p=3484
http://nihongonosensei.net/?p=3492
http://nihongonosensei.net/?p=3553
http://nihongonosensei.net/?p=3559
http://nihongonosensei.net/?p=13970
http://nihongonosensei.net/?p=6331
http://nihongonosensei.net/?p=6335
http://nihongonosensei.net/?p=6339
http://nihongonosensei.net/?p=6341
http://nihongonosensei.net/?p=6769
http://nihongonosensei.net/?p=8506
http://nihongonosensei.net/?p=8857
http://nihongonosensei.net/?p=9283
http://nihongonosensei.net/?p=9306
http://nihongonosensei.net/?p=9308
http://nihongonosensei.net/?p=9312
http://nihongonosensei.net/?p=9314
http://nihongonosensei.net/?p=9422
http://nihongonosensei.net/?p=9462
http://nihongonosensei.net/?p=9860
http://nihongonosensei.net/?p=11635
http://nihongonosensei.net/?p=12073
http://nihongonosensei.net/?p=12784
http://nihongonosensei.net/?p=12795
http://nihongonosensei.net/?p=12821
http://nihongonosensei.net/?p=12824
http://nihongonosensei.net/?p=12830
http://nihongonosensei.net/?p=12832
http://nihongonosensei.net/?p=12834
http://nihongonosensei.net/?p=12987
http://nihongonosensei.net/?p=12995
http://nihongonosensei.net/?p=13018
http://nihongonosensei.net/?p=3761
http://nihongonosensei.net/?p=13326
http://nihongonosensei.net/?p=13327
http://nihongonosensei.net/?p=13340
http://nihongonosensei.net/?p=13344
http://nihongonosensei.net/?p=17748
http://nihongonosensei.net/?p=17758
http://nihongonosensei.net/?p=17767
http://nihongonosensei.net/?p=17771
http://nihongonosensei.net/?p=18162
http://nihongonosensei.net/?p=18165
http://nihongonosensei.net/?p=18171
http://nihongonosensei.net/?p=18202
http://nihongonosensei.net/?p=18199
http://nihongonosensei.net/?p=18314
http://nihongonosensei.net/?p=18312
http://nihongonosensei.net/?p=18399
http://nihongonosensei.net/?p=18400
http://nihongonosensei.net/?p=18585
http://nihongonosensei.net/?p=18589
http://nihongonosensei.net/?p=18591
http://nihongonosensei.net/?p=18301
http://nihongonosensei.net/?p=18701
http://nihongonosensei.net/?p=18773
http://nihongonosensei.net/?p=18775
http://nihongonosensei.net/?p=18788
http://nihongonosensei.net/?p=18790
http://nihongonosensei.net/?p=18792
http://nihongonosensei.net/?p=18821
http://nihongonosensei.net/?p=3571
http://nihongonosensei.net/?p=9936
http://nihongonosensei.net/?p=3578
http://nihongonosensei.net/?p=5980
http://nihongonosensei.net/?p=3609
http://nihongonosensei.net/?p=3680
http://nihongonosensei.net/?p=3828
http://nihongonosensei.net/?p=6345
http://nihongonosensei.net/?p=6347
http://nihongonosensei.net/?p=6351
http://nihongonosensei.net/?p=7905
http://nihongonosensei.net/?p=7907
http://nihongonosensei.net/?p=8063
http://nihongonosensei.net/?p=18470
http://nihongonosensei.net/?p=18471
http://nihongonosensei.net/?p=9425
http://nihongonosensei.net/?p=9426
http://nihongonosensei.net/?p=9465
http://nihongonosensei.net/?p=9466
http://nihongonosensei.net/?p=9872
http://nihongonosensei.net/?p=10058
http://nihongonosensei.net/?p=11304
http://nihongonosensei.net/?p=11948
http://nihongonosensei.net/?p=18497
http://nihongonosensei.net/?p=18499
http://nihongonosensei.net/?p=18501
http://nihongonosensei.net/?p=12143
http://nihongonosensei.net/?p=12789
http://nihongonosensei.net/?p=12882
http://nihongonosensei.net/?p=12885
http://nihongonosensei.net/?p=12886
http://nihongonosensei.net/?p=13074
http://nihongonosensei.net/?p=13087
http://nihongonosensei.net/?p=13092
http://nihongonosensei.net/?p=13136
http://nihongonosensei.net/?p=13151
http://nihongonosensei.net/?p=13371
http://nihongonosensei.net/?p=18157
http://nihongonosensei.net/?p=18219
http://nihongonosensei.net/?p=18221
http://nihongonosensei.net/?p=18266
http://nihongonosensei.net/?p=18292
http://nihongonosensei.net/?p=18293
http://nihongonosensei.net/?p=18392
http://nihongonosensei.net/?p=18488
http://nihongonosensei.net/?p=18489
http://nihongonosensei.net/?p=18593
http://nihongonosensei.net/?p=18595
http://nihongonosensei.net/?p=18612
http://nihongonosensei.net/?p=18613
http://nihongonosensei.net/?p=18657
http://nihongonosensei.net/?p=18659
http://nihongonosensei.net/?p=18662
http://nihongonosensei.net/?p=18664
http://nihongonosensei.net/?p=12827
http://nihongonosensei.net/?p=4094
http://nihongonosensei.net/?p=18732
http://nihongonosensei.net/?p=18728
http://nihongonosensei.net/?p=18720
http://nihongonosensei.net/?p=18722
http://nihongonosensei.net/?p=18730
http://nihongonosensei.net/?p=18724
http://nihongonosensei.net/?p=4094
http://nihongonosensei.net/?p=3500
http://nihongonosensei.net/?p=3526
http://nihongonosensei.net/?p=3529
http://nihongonosensei.net/?p=3474
http://nihongonosensei.net/?p=3585
http://nihongonosensei.net/?p=3606
http://nihongonosensei.net/?p=3643
http://nihongonosensei.net/?p=3650
http://nihongonosensei.net/?p=3656
http://nihongonosensei.net/?p=5062
http://nihongonosensei.net/?p=5941
http://nihongonosensei.net/?p=5943
http://nihongonosensei.net/?p=5945
http://nihongonosensei.net/?p=5947
http://nihongonosensei.net/?p=5949
http://nihongonosensei.net/?p=5984
http://nihongonosensei.net/?p=7024
http://nihongonosensei.net/?p=7026
http://nihongonosensei.net/?p=7096
http://nihongonosensei.net/?p=7098
http://nihongonosensei.net/?p=7100
http://nihongonosensei.net/?p=7102
http://nihongonosensei.net/?p=7104
http://nihongonosensei.net/?p=7152
http://nihongonosensei.net/?p=10116
http://nihongonosensei.net/?p=3550
http://nihongonosensei.net/?p=8048
http://nihongonosensei.net/?p=6349
http://nihongonosensei.net/?p=8051
http://nihongonosensei.net/?p=8058
http://nihongonosensei.net/?p=8061
http://nihongonosensei.net/?p=8070
http://nihongonosensei.net/?p=8080
http://nihongonosensei.net/?p=8082
http://nihongonosensei.net/?p=4085
http://nihongonosensei.net/?p=4088
http://nihongonosensei.net/?p=8540
http://nihongonosensei.net/?p=8542
http://nihongonosensei.net/?p=8558
http://nihongonosensei.net/?p=8564
http://nihongonosensei.net/?p=8665
http://nihongonosensei.net/?p=8669
http://nihongonosensei.net/?p=8672
http://nihongonosensei.net/?p=8675
http://nihongonosensei.net/?p=8710
http://nihongonosensei.net/?p=8705
http://nihongonosensei.net/?p=7981
http://nihongonosensei.net/?p=8724
http://nihongonosensei.net/?p=8730
http://nihongonosensei.net/?p=8733
http://nihongonosensei.net/?p=8856
http://nihongonosensei.net/?p=9310
http://nihongonosensei.net/?p=9352
http://nihongonosensei.net/?p=5242
http://nihongonosensei.net/?p=9385
http://nihongonosensei.net/?p=9386
http://nihongonosensei.net/?p=9488
http://nihongonosensei.net/?p=9487
http://nihongonosensei.net/?p=12075
http://nihongonosensei.net/?p=18193
http://nihongonosensei.net/?p=18350
http://nihongonosensei.net/?p=18351
http://nihongonosensei.net/?p=18406
http://nihongonosensei.net/?p=18428
http://nihongonosensei.net/?p=18447
http://nihongonosensei.net/?p=18587
http://nihongonosensei.net/?p=18698
http://nihongonosensei.net/?p=18695
http://nihongonosensei.net/?p=18703
http://nihongonosensei.net/?p=3659
http://nihongonosensei.net/?p=3673
http://nihongonosensei.net/?p=3676
http://nihongonosensei.net/?p=3683
http://nihongonosensei.net/?p=3686
http://nihongonosensei.net/?p=18190
http://nihongonosensei.net/?p=3747
http://nihongonosensei.net/?p=3749
http://nihongonosensei.net/?p=3753
http://nihongonosensei.net/?p=5951
http://nihongonosensei.net/?p=5953
http://nihongonosensei.net/?p=5955
http://nihongonosensei.net/?p=5957
http://nihongonosensei.net/?p=7068
http://nihongonosensei.net/?p=7071
http://nihongonosensei.net/?p=7075
http://nihongonosensei.net/?p=7121
http://nihongonosensei.net/?p=3541
http://nihongonosensei.net/?p=8004
http://nihongonosensei.net/?p=6343
http://nihongonosensei.net/?p=8144
http://nihongonosensei.net/?p=8143
http://nihongonosensei.net/?p=8150
http://nihongonosensei.net/?p=8152
http://nihongonosensei.net/?p=8161
http://nihongonosensei.net/?p=8164
http://nihongonosensei.net/?p=8257
http://nihongonosensei.net/?p=9482
http://nihongonosensei.net/?p=8261
http://nihongonosensei.net/?p=8159
http://nihongonosensei.net/?p=8272
http://nihongonosensei.net/?p=8274
http://nihongonosensei.net/?p=8277
http://nihongonosensei.net/?p=8279
http://nihongonosensei.net/?p=9215
http://nihongonosensei.net/?p=9217
http://nihongonosensei.net/?p=9859
http://nihongonosensei.net/?p=10102
http://nihongonosensei.net/?p=18631
http://nihongonosensei.net/?p=18632
http://nihongonosensei.net/?p=11303
http://nihongonosensei.net/?p=12781
http://nihongonosensei.net/?p=12812
http://nihongonosensei.net/?p=12799
http://nihongonosensei.net/?p=12802
http://nihongonosensei.net/?p=12809
http://nihongonosensei.net/?p=13150
http://nihongonosensei.net/?p=11946
http://nihongonosensei.net/?p=13152
http://nihongonosensei.net/?p=18503
http://nihongonosensei.net/?p=3582
http://nihongonosensei.net/?p=17664
http://nihongonosensei.net/?p=17751
http://nihongonosensei.net/?p=18264
http://nihongonosensei.net/?p=18267
http://nihongonosensei.net/?p=18265
http://nihongonosensei.net/?p=18303
http://nihongonosensei.net/?p=18393
http://nihongonosensei.net/?p=8281
http://nihongonosensei.net/?p=18614
http://nihongonosensei.net/?p=18676
http://nihongonosensei.net/?p=18678
http://nihongonosensei.net/?p=18816
http://nihongonosensei.net/?p=18818
http://nihongonosensei.net/?p=18812
http://nihongonosensei.net/?p=18809
http://nihongonosensei.net/?p=18807
http://nihongonosensei.net/?p=18805
http://nihongonosensei.net/?p=18803
http://nihongonosensei.net/?p=18330
http://nihongonosensei.net/?p=3446
http://nihongonosensei.net/?p=3662
http://nihongonosensei.net/?p=5182
http://nihongonosensei.net/?p=9262
http://nihongonosensei.net/?p=9264
http://nihongonosensei.net/?p=3647
http://nihongonosensei.net/?p=8567
http://nihongonosensei.net/?p=9343
http://nihongonosensei.net/?p=8045
http://nihongonosensei.net/?p=18305
http://nihongonosensei.net/?p=18307
http://nihongonosensei.net/?p=18427
http://nihongonosensei.net/?p=18615
http://nihongonosensei.net/?p=18713
http://nihongonosensei.net/?p=18715
http://nihongonosensei.net/?p=18717
http://nihongonosensei.net/?p=18736
http://nihongonosensei.net/?p=3668
http://nihongonosensei.net/?p=5180
http://nihongonosensei.net/?p=4090
http://nihongonosensei.net/?p=11943
http://nihongonosensei.net/?p=11950
http://nihongonosensei.net/?p=11941
http://nihongonosensei.net/?p=12816
http://nihongonosensei.net/?p=18323
http://nihongonosensei.net/?p=18349
http://nihongonosensei.net/?p=18784
http://nihongonosensei.net/?p=18786
http://nihongonosensei.net/?p=18814
http://nihongonosensei.net/?p=18405
http://nihongonosensei.net/?p=5233
http://nihongonosensei.net/?p=7154
http://nihongonosensei.net/?p=7938
http://nihongonosensei.net/?p=7943
http://nihongonosensei.net/?p=8509
http://nihongonosensei.net/?p=8541
http://nihongonosensei.net/?p=8886
http://nihongonosensei.net/?p=8889
http://nihongonosensei.net/?p=9440
http://nihongonosensei.net/?p=9441
http://nihongonosensei.net/?p=3639
http://nihongonosensei.net/?p=3575
http://nihongonosensei.net/?p=3603
http://nihongonosensei.net/?p=11627
http://nihongonosensei.net/?p=11953
http://nihongonosensei.net/?p=11955
http://nihongonosensei.net/?p=17914
http://nihongonosensei.net/?p=18195
http://nihongonosensei.net/?p=18217
http://nihongonosensei.net/?p=18348
http://nihongonosensei.net/?p=18371
http://nihongonosensei.net/?p=18375
http://nihongonosensei.net/?p=18377
http://nihongonosensei.net/?p=18379
http://nihongonosensei.net/?p=18653
http://nihongonosensei.net/?p=18655
http://nihongonosensei.net/?p=13346
http://nihongonosensei.net/?p=13347
http://nihongonosensei.net/?p=13348
http://nihongonosensei.net/?p=13358
http://nihongonosensei.net/?p=13362
http://nihongonosensei.net/?p=13373
http://nihongonosensei.net/?p=13369
http://nihongonosensei.net/?p=13379
http://nihongonosensei.net/?p=13385
http://nihongonosensei.net/?p=13462
http://nihongonosensei.net/?p=13466
http://nihongonosensei.net/?p=14905
http://nihongonosensei.net/?p=17576
http://nihongonosensei.net/?p=17593
http://nihongonosensei.net/?p=17597
http://nihongonosensei.net/?p=17600
http://nihongonosensei.net/?p=17917
http://nihongonosensei.net/?p=18268
http://nihongonosensei.net/?p=18363
http://nihongonosensei.net/?p=19118
http://nihongonosensei.net/
http://nihongonosensei.net/?cat=7
http://nihongonosensei.net/?cat=3
http://nihongonosensei.net/?page_id=10246
http://nihongonosensei.net/?page_id=10246#linkn1
http://nihongonosensei.net/?page_id=10246#linkn2
http://nihongonosensei.net/?page_id=10246#linkn3
http://nihongonosensei.net/?page_id=10246#linkn4n5
http://nihongonosensei.net/?page_id=10246#linkn0
http://nihongonosensei.net/?page_id=13879
http://nihongonosensei.net/?page_id=8874
http://nihongonosensei.net/?p=17729
http://nihongonosensei.net/?page_id=8874#link2019
http://nihongonosensei.net/?page_id=8874#link30
http://nihongonosensei.net/?page_id=8874#link29
http://nihongonosensei.net/?page_id=8874#link28
http://nihongonosensei.net/?page_id=8874#link27
http://nihongonosensei.net/?page_id=8874#link26
http://nihongonosensei.net/?page_id=8874#link25
http://nihongonosensei.net/?page_id=8874#link24
http://nihongonosensei.net/?page_id=8874#link23
http://nihongonosensei.net/?page_id=4945
http://nihongonosensei.net/?page_id=5094
http://nihongonosensei.net/?page_id=13794
http://nihongonosensei.net/?page_id=13794#link1
http://nihongonosensei.net/?page_id=13794#link2
http://nihongonosensei.net/?page_id=13825
http://nihongonosensei.net/?page_id=13827
http://nihongonosensei.net/?page_id=1904
https://thk.kanzae.net/

Trying to grab just the first href in each table row

I'm trying to grab just the first href in each row in an HTML table. Using find_all on the soup object doesn't work because there are multiple tables so I used soup.select() to isolate just that table and work from there but it doesn't seem to be working.
Tried using find_all on the soup object alone, tried looping through the table rows with find() but it said that it returns 'NoneType'.
I Would like to be able to store a list that starts [/players/a/abrinal01.html, "/players/a/acyqu01.html, etc]
url = 'https://www.basketball-reference.com/leagues/NBA_2019_per_game.html'
res = requests.get(url)
res.raise_for_status()
soup = bs4.BeautifulSoup(res.text, 'html.parser')
table = soup.find("table", { "id" : "per_game_stats" })

You can access the desired data by anchoring the parsing from the outer div wrapper with the id of all_per_game_stats:
import requests
from bs4 import BeautifulSoup as soup
d = soup(requests.get('https://www.basketball-reference.com/leagues/NBA_2019_per_game.html').text, 'html.parser')
data = [b.td.a['href'] for b in d.find('div', {'id':'all_per_game_stats'}).table.find_all('tr') if b.td]
Output:
['/players/a/abrinal01.html', '/players/a/acyqu01.html', '/players/a/adamsja01.html', '/players/a/adamsst01.html', '/players/a/adebaba01.html', '/players/a/adelde01.html', '/players/a/akoonde01.html', '/players/a/aldrila01.html', '/players/a/alkinra01.html', '/players/a/allengr01.html', '/players/a/allenja01.html', '/players/a/allenka01.html', '/players/a/aminual01.html', '/players/a/anderju01.html', '/players/a/anderky01.html', '/players/a/anderry01.html', '/players/a/anderry01.html', '/players/a/anderry01.html', '/players/a/anigbik01.html', '/players/a/antetgi01.html', '/players/a/antetko01.html', '/players/a/anthoca01.html', '/players/a/anunoog01.html', '/players/a/arcidry01.html', '/players/a/arizatr01.html', '/players/a/arizatr01.html', '/players/a/arizatr01.html', '/players/a/augusdj01.html', '/players/a/aytonde01.html', '/players/b/bacondw01.html', '/players/b/baglema01.html', '/players/b/bakerro01.html', '/players/b/bakerro01.html', '/players/b/bakerro01.html', '/players/b/baldwwa01.html', '/players/b/balllo01.html', '/players/b/bambamo01.html', '/players/b/bareajo01.html', '/players/b/barneha02.html', '/players/b/barneha02.html', '/players/b/barneha02.html', '/players/b/bartowi01.html', '/players/b/bateske01.html', '/players/b/batumni01.html', '/players/b/bayleje01.html', '/players/b/baynear01.html', '/players/b/bazemke01.html', '/players/b/bealbr01.html', '/players/b/beaslma01.html', '/players/b/beaslmi01.html', '/players/b/belinma01.html', '/players/b/belljo01.html', '/players/b/bembrde01.html', '/players/b/bendedr01.html', '/players/b/bertada02.html', '/players/b/bertada01.html', '/players/b/beverpa01.html', '/players/b/birchkh01.html', '/players/b/biyombi01.html', '/players/b/bjeline01.html', '/players/b/blakean01.html', '/players/b/bledser01.html', '/players/b/blossja01.html', '/players/b/bogdabo01.html', '/players/b/bogdabo02.html', '/players/b/bogutan01.html', '/players/b/boldejo01.html', '/players/b/bongais01.html', '/players/b/bookede01.html', '/players/b/bouchch01.html', '/players/b/bradlav01.html', '/players/b/bradlav01.html', '/players/b/bradlav01.html', '/players/b/bradlto01.html', '/players/b/breweco01.html', '/players/b/breweco01.html', '/players/b/breweco01.html', '/players/b/bridgmi01.html', '/players/b/bridgmi02.html', '/players/b/briscis01.html', '/players/b/broekry01.html', '/players/b/brogdma01.html', '/players/b/brookdi01.html', '/players/b/brookma01.html', '/players/b/brownbr01.html', '/players/b/brownja02.html', '/players/b/brownlo01.html', '/players/b/brownst02.html', '/players/b/browntr01.html', '/players/b/brunsja01.html', '/players/b/bryanth01.html', '/players/b/bullore01.html', '/players/b/bullore01.html', '/players/b/bullore01.html', '/players/b/burketr01.html', '/players/b/burketr01.html', '/players/b/burketr01.html', '/players/b/burksal01.html', '/players/b/burksal01.html', '/players/b/burksal01.html', '/players/b/burksal01.html', '/players/b/burtode02.html', '/players/b/butleji01.html', '/players/b/butleji01.html', '/players/b/butleji01.html', '/players/c/cabocbr01.html', '/players/c/caldejo01.html', '/players/c/caldwke01.html', '/players/c/canaais01.html', '/players/c/canaais01.html', '/players/c/canaais01.html', '/players/c/canaais01.html', '/players/c/capelca01.html', '/players/c/carrode01.html', '/players/c/carteje01.html', '/players/c/cartevi01.html', '/players/c/cartewe01.html', '/players/c/cartemi01.html', '/players/c/cartemi01.html', '/players/c/cartemi01.html', '/players/c/carusal01.html', '/players/c/casspom01.html', '/players/c/caulewi01.html', '/players/c/caupatr01.html', '/players/c/cavanty01.html', '/players/c/chandty01.html', '/players/c/chandty01.html', '/players/c/chandty01.html', '/players/c/chandwi01.html', '/players/c/chandwi01.html', '/players/c/chandwi01.html', '/players/c/chealjo01.html', '/players/c/chiozch01.html', '/players/c/chrisma01.html', '/players/c/chrisma01.html', '/players/c/chrisma01.html', '/players/c/clarkga01.html', '/players/c/clarkia01.html', '/players/c/clarkjo01.html', '/players/c/collijo01.html', '/players/c/colliza01.html', '/players/c/collida01.html', '/players/c/colsobo01.html', '/players/c/conlemi01.html', '/players/c/connapa01.html', '/players/c/cookqu01.html', '/players/c/couside01.html', '/players/c/covinro01.html', '/players/c/covinro01.html', '/players/c/covinro01.html', '/players/c/crabbal01.html', '/players/c/craigto01.html', '/players/c/crawfja01.html', '/players/c/creekmi01.html', '/players/c/creekmi01.html', '/players/c/creekmi01.html', '/players/c/crowdja01.html', '/players/c/cunnida01.html', '/players/c/curryse01.html', '/players/c/curryst01.html', '/players/d/danietr01.html', '/players/d/davisan02.html', '/players/d/davisde01.html', '/players/d/davised01.html', '/players/d/davisty01.html', '/players/d/dedmode01.html', '/players/d/dekkesa01.html', '/players/d/dekkesa01.html', '/players/d/dekkesa01.html', '/players/d/delgaan01.html', '/players/d/dellama01.html', '/players/d/dellama01.html', '/players/d/dellama01.html', '/players/d/denglu01.html', '/players/d/derozde01.html', '/players/d/derrima01.html', '/players/d/diallch01.html', '/players/d/diallha01.html', '/players/d/dienggo01.html', '/players/d/dinwisp01.html', '/players/d/divindo01.html', '/players/d/doncilu01.html', '/players/d/dorsety01.html', '/players/d/dorsety01.html', '/players/d/dorsety01.html', '/players/d/dotsoda01.html', '/players/d/doziepj01.html', '/players/d/dragigo01.html', '/players/d/drumman01.html', '/players/d/dudleja01.html', '/players/d/dunnkr01.html', '/players/d/duranke01.html', '/players/d/duvaltr01.html', '/players/e/edwarvi01.html', '/players/e/ellenhe01.html', '/players/e/ellenhe01.html', '/players/e/ellenhe01.html', '/players/e/ellinwa01.html', '/players/e/ellinwa01.html', '/players/e/ellinwa01.html', '/players/e/embiijo01.html', '/players/e/ennisja01.html', '/players/e/ennisja01.html', '/players/e/ennisja01.html', '/players/e/eubandr01.html', '/players/e/evansja02.html', '/players/e/evansja01.html', '/players/e/evansja01.html', '/players/e/evansja01.html', '/players/e/evansty01.html', '/players/e/exumda01.html', '/players/f/farieke01.html', '/players/f/farieke01.html', '/players/f/farieke01.html', '/players/f/favorde01.html', '/players/f/feliccr01.html', '/players/f/feltora01.html', '/players/f/fergute01.html', '/players/f/ferreyo01.html', '/players/f/finnedo01.html', '/players/f/forbebr01.html', '/players/f/fournev01.html', '/players/f/foxde01.html', '/players/f/frazime01.html', '/players/f/fraziti01.html', '/players/f/fraziti01.html', '/players/f/fraziti01.html', '/players/f/fredeji01.html', '/players/f/fryech01.html', '/players/f/fultzma01.html', '/players/g/gallida01.html', '/players/g/gallola01.html', '/players/g/garrebi01.html', '/players/g/gasolma01.html', '/players/g/gasolma01.html', '/players/g/gasolma01.html', '/players/g/gasolpa01.html', '/players/g/gasolpa01.html', '/players/g/gasolpa01.html', '/players/g/gayru01.html', '/players/g/georgpa01.html', '/players/g/gibsota01.html', '/players/g/gilesha01.html', '/players/g/gilgesh01.html', '/players/g/goberru01.html', '/players/g/goodwbr01.html', '/players/g/gordoaa01.html', '/players/g/gordoer01.html', '/players/g/gortama01.html', '/players/g/grahade01.html', '/players/g/grahatr01.html', '/players/g/grantje01.html', '/players/g/grantje02.html', '/players/g/grantdo01.html', '/players/g/greenda02.html', '/players/g/greendr01.html', '/players/g/greenge01.html', '/players/g/greenja01.html', '/players/g/greenja01.html', '/players/g/greenja01.html', '/players/g/greenje02.html', '/players/g/griffbl01.html', '/players/h/hamilda02.html', '/players/h/hannadu01.html', '/players/h/hardati02.html', '/players/h/hardati02.html', '/players/h/hardati02.html', '/players/h/hardeja01.html', '/players/h/harklma01.html', '/players/h/harremo01.html', '/players/h/harride01.html', '/players/h/harriga01.html', '/players/h/harrijo01.html', '/players/h/harrito02.html', '/players/h/harrito02.html', '/players/h/harrito02.html', '/players/h/harrian01.html', '/players/h/harrian01.html', '/players/h/harrian01.html', '/players/h/harrian01.html', '/players/h/harrish01.html', '/players/h/hartjo01.html', '/players/h/harteis01.html', '/players/h/hasleud01.html', '/players/h/haywago01.html', '/players/h/hensojo01.html', '/players/h/hernaju01.html', '/players/h/hernawi01.html', '/players/h/hezonma01.html', '/players/h/hicksis01.html', '/players/h/hieldbu01.html', '/players/h/highsha01.html', '/players/h/hilarne01.html', '/players/h/hillge01.html', '/players/h/hillge01.html', '/players/h/hillge01.html', '/players/h/hillso01.html', '/players/h/holidaa01.html', '/players/h/holidjr01.html', '/players/h/holidju01.html', '/players/h/holidju01.html', '/players/h/holidju01.html', '/players/h/hollajo02.html', '/players/h/holliro01.html', '/players/h/holmeri01.html', '/players/h/hoodro01.html', '/players/h/hoodro01.html', '/players/h/hoodro01.html', '/players/h/horfoal01.html', '/players/h/houseda01.html', '/players/h/howardw01.html', '/players/h/huertke01.html', '/players/h/humphis01.html', '/players/h/hunterj01.html', '/players/h/hutchch01.html', '/players/i/ibakase01.html', '/players/i/iguodan01.html', '/players/i/ilyaser01.html', '/players/i/inglejo01.html', '/players/i/ingraan01.html', '/players/i/ingrabr01.html', '/players/i/irvinky01.html', '/players/i/isaacjo01.html', '/players/i/iwundwe01.html', '/players/j/jacksde01.html', '/players/j/jacksfr01.html', '/players/j/jacksja02.html', '/players/j/jacksjo02.html', '/players/j/jacksju01.html', '/players/j/jacksju01.html', '/players/j/jacksju01.html', '/players/j/jacksre01.html', '/players/j/jamesle01.html', '/players/j/jeffeam01.html', '/players/j/jenkijo01.html', '/players/j/jenkijo01.html', '/players/j/jenkijo01.html', '/players/j/jerebjo01.html', '/players/j/johnsal02.html', '/players/j/johnsam01.html', '/players/j/johnsbj01.html', '/players/j/johnsbj01.html', '/players/j/johnsbj01.html', '/players/j/johnsja01.html', '/players/j/johnsst04.html', '/players/j/johnsst04.html', '/players/j/johnsst04.html', '/players/j/johnsty01.html', '/players/j/johnsty01.html', '/players/j/johnsty01.html', '/players/j/johnswe01.html', '/players/j/johnswe01.html', '/players/j/johnswe01.html', '/players/j/jokicni01.html', '/players/j/jonesda03.html', '/players/j/jonesde02.html', '/players/j/jonesja04.html', '/players/j/jonesje01.html', '/players/j/joneste01.html', '/players/j/jonesty01.html', '/players/j/jordade01.html', '/players/j/jordade01.html', '/players/j/jordade01.html', '/players/j/josepco01.html', '/players/k/kaminfr01.html', '/players/k/kanteen01.html', '/players/k/kanteen01.html', '/players/k/kanteen01.html', '/players/k/kennalu01.html', '/players/k/kiddgmi01.html', '/players/k/kingge03.html', '/players/k/klebima01.html', '/players/k/knighbr03.html', '/players/k/knighbr03.html', '/players/k/knighbr03.html', '/players/k/knoxke01.html', '/players/k/korkmfu01.html', '/players/k/kornelu01.html', '/players/k/korveky01.html', '/players/k/korveky01.html', '/players/k/korveky01.html', '/players/k/koufoko01.html', '/players/k/kurucro01.html', '/players/k/kuzmaky01.html', '/players/l/labissk01.html', '/players/l/labissk01.html', '/players/l/labissk01.html', '/players/l/lambje01.html', '/players/l/lavinza01.html', '/players/l/laymaja01.html', '/players/l/leaftj01.html', '/players/l/leeco01.html', '/players/l/leeco01.html', '/players/l/leeco01.html', '/players/l/leeda03.html', '/players/l/lemonwa01.html', '/players/l/lenal01.html', '/players/l/leonaka01.html', '/players/l/leoname01.html', '/players/l/leuerjo01.html', '/players/l/leverca01.html', '/players/l/lillada01.html', '/players/l/linje01.html', '/players/l/linje01.html', '/players/l/linje01.html', '/players/l/livinsh01.html', '/players/l/loftoza01.html', '/players/l/looneke01.html', '/players/l/lopezbr01.html', '/players/l/lopezro01.html', '/players/l/loveke01.html', '/players/l/lowryky01.html', '/players/l/loydjo01.html', '/players/l/lucaska01.html', '/players/l/luwawti01.html', '/players/l/luwawti01.html', '/players/l/luwawti01.html', '/players/l/lydonty01.html', '/players/l/lylestr01.html', '/players/m/machasc01.html', '/players/m/macksh01.html', '/players/m/macksh01.html', '/players/m/macksh01.html', '/players/m/maconda01.html', '/players/m/macurjp01.html', '/players/m/mahinia01.html', '/players/m/makerth01.html', '/players/m/makerth01.html', '/players/m/makerth01.html', '/players/m/marjabo01.html', '/players/m/marjabo01.html', '/players/m/marjabo01.html', '/players/m/markkla01.html', '/players/m/martija01.html', '/players/m/masonfr01.html', '/players/m/matenya01.html', '/players/m/matthwe02.html', '/players/m/matthwe02.html', '/players/m/matthwe02.html', '/players/m/matthwe02.html', '/players/m/mbahalu01.html', '/players/m/mccalta01.html', '/players/m/mccawpa01.html', '/players/m/mccawpa01.html', '/players/m/mccawpa01.html', '/players/m/mccolcj01.html', '/players/m/mccontj01.html', '/players/m/mcderdo01.html', '/players/m/mcgeeja01.html', '/players/m/mcgruro01.html', '/players/m/mckinal01.html', '/players/m/mclembe01.html', '/players/m/mcraejo01.html', '/players/m/meeksjo01.html', '/players/m/mejrisa01.html', '/players/m/meltode01.html', '/players/m/metuch01.html', '/players/m/middlkh01.html', '/players/m/milescj01.html', '/players/m/milescj01.html', '/players/m/milescj01.html', '/players/m/milleda01.html', '/players/m/millema01.html', '/players/m/millspa02.html', '/players/m/millspa01.html', '/players/m/miltosh01.html', '/players/m/mirotni01.html', '/players/m/mirotni01.html', '/players/m/mirotni01.html', '/players/m/mitchdo01.html', '/players/m/mitrona01.html', '/players/m/monkma01.html', '/players/m/monrogr01.html', '/players/m/monrogr01.html', '/players/m/monrogr01.html', '/players/m/monrogr01.html', '/players/m/mooreet01.html', '/players/m/moreler01.html', '/players/m/moreler01.html', '/players/m/moreler01.html', '/players/m/morrija01.html', '/players/m/morrima03.html', '/players/m/morrima02.html', '/players/m/morrima02.html', '/players/m/morrima02.html', '/players/m/morrimo01.html', '/players/m/motiedo01.html', '/players/m/motlejo01.html', '/players/m/mudiaem01.html', '/players/m/murraja01.html', '/players/m/musadz01.html', '/players/m/muscami01.html', '/players/m/muscami01.html', '/players/m/muscami01.html', '/players/m/mykhasv01.html', '/players/m/mykhasv01.html', '/players/m/mykhasv01.html', '/players/n/naderab01.html', '/players/n/nancela02.html', '/players/n/napiesh01.html', '/players/n/netora01.html', '/players/n/niangge01.html', '/players/n/noahjo01.html', '/players/n/noelne01.html', '/players/n/nowitdi01.html', '/players/n/ntilila01.html', '/players/n/nunnaja01.html', '/players/n/nunnaja01.html', '/players/n/nunnaja01.html', '/players/n/nurkiju01.html', '/players/n/nwabada01.html', '/players/o/onealro01.html', '/players/o/oquinky01.html', '/players/o/ojelese01.html', '/players/o/okafoja01.html', '/players/o/okoboel01.html', '/players/o/okogijo01.html', '/players/o/oladivi01.html', '/players/o/olynyke01.html', '/players/o/osmande01.html', '/players/o/oubreke01.html', '/players/o/oubreke01.html', '/players/o/oubreke01.html', '/players/p/pachuza01.html', '/players/p/parkeja01.html', '/players/p/parkeja01.html', '/players/p/parkeja01.html', '/players/p/parketo01.html', '/players/p/parsoch01.html', '/players/p/pattepa01.html', '/players/p/pattoju01.html', '/players/p/paulch01.html', '/players/p/payneca01.html', '/players/p/payneca01.html', '/players/p/payneca01.html', '/players/p/paytoel01.html', '/players/p/paytoga02.html', '/players/p/pinsoth01.html', '/players/p/plumlma01.html', '/players/p/plumlmi01.html', '/players/p/poeltja01.html', '/players/p/pondequ01.html', '/players/p/porteot01.html', '/players/p/porteot01.html', '/players/p/porteot01.html', '/players/p/portibo01.html', '/players/p/portibo01.html', '/players/p/portibo01.html', '/players/p/poweldw01.html', '/players/p/powelno01.html', '/players/p/poythal01.html', '/players/q/qizh01.html', '/players/r/rabbiv01.html', '/players/r/randlch01.html', '/players/r/randlju01.html', '/players/r/redicjj01.html', '/players/r/reedda01.html', '/players/r/reynoca01.html', '/players/r/richajo01.html', '/players/r/richama01.html', '/players/r/riverau01.html', '/players/r/riverau01.html', '/players/r/riverau01.html', '/players/r/robinde01.html', '/players/r/robindu01.html', '/players/r/robingl02.html', '/players/r/robinje01.html', '/players/r/robinmi01.html', '/players/r/rondora01.html', '/players/r/rosede01.html', '/players/r/rosste01.html', '/players/r/roziete01.html', '/players/r/rubiori01.html', '/players/r/russeda01.html', '/players/s/sabondo01.html', '/players/s/sampsbr01.html', '/players/s/sampsja02.html', '/players/s/saricda01.html', '/players/s/saricda01.html', '/players/s/saricda01.html', '/players/s/satorto01.html', '/players/s/schrode01.html', '/players/s/scottmi01.html', '/players/s/scottmi01.html', '/players/s/scottmi01.html', '/players/s/sefolth01.html', '/players/s/seldewa01.html', '/players/s/seldewa01.html', '/players/s/seldewa01.html', '/players/s/sextoco01.html', '/players/s/shamela01.html', '/players/s/shamela01.html', '/players/s/shamela01.html', '/players/s/shumpim01.html', '/players/s/shumpim01.html', '/players/s/shumpim01.html', '/players/s/siakapa01.html', '/players/s/siberjo01.html', '/players/s/simmobe01.html', '/players/s/simmojo02.html', '/players/s/simmojo02.html', '/players/s/simmojo02.html', '/players/s/simmoko01.html', '/players/s/simonan01.html', '/players/s/smartma01.html', '/players/s/smithde03.html', '/players/s/smithde03.html', '/players/s/smithde03.html', '/players/s/smithis01.html', '/players/s/smithjr01.html', '/players/s/smithja02.html', '/players/s/smithja02.html', '/players/s/smithja02.html', '/players/s/smithja02.html', '/players/s/smithzh01.html', '/players/s/snellto01.html', '/players/s/spaldra01.html', '/players/s/spaldra01.html', '/players/s/spaldra01.html', '/players/s/spellom01.html', '/players/s/stausni01.html', '/players/s/stausni01.html', '/players/s/stausni01.html', '/players/s/stephdj01.html', '/players/s/stephla01.html', '/players/s/sumneed01.html', '/players/s/swanica01.html', '/players/s/swanica01.html', '/players/s/swanica01.html', '/players/t/tatumja01.html', '/players/t/teaguje01.html', '/players/t/templga01.html', '/players/t/templga01.html', '/players/t/templga01.html', '/players/t/teodomi01.html', '/players/t/terreja01.html', '/players/t/terryem01.html', '/players/t/terryem01.html', '/players/t/terryem01.html', '/players/t/theisda01.html', '/players/t/thomais02.html', '/players/t/thomakh01.html', '/players/t/thomala01.html', '/players/t/thompkl01.html', '/players/t/thomptr01.html', '/players/t/thornsi01.html', '/players/t/tollian01.html', '/players/t/townska01.html', '/players/t/trentga02.html', '/players/t/trieral01.html', '/players/t/tuckepj01.html', '/players/t/turneev01.html', '/players/t/turnemy01.html', '/players/u/udohek01.html', '/players/u/ulisty01.html', '/players/v/valanjo01.html', '/players/v/valanjo01.html', '/players/v/valanjo01.html', '/players/v/vandeja01.html', '/players/v/vanvlfr01.html', '/players/v/vonleno01.html', '/players/v/vucevni01.html', '/players/w/wadedw01.html', '/players/w/wagnemo01.html', '/players/w/waitedi01.html', '/players/w/walkeke02.html', '/players/w/walkelo01.html', '/players/w/walljo01.html', '/players/w/wallaty01.html', '/players/p/princta02.html', '/players/w/wanambr01.html', '/players/w/warretj01.html', '/players/w/washbju01.html', '/players/w/watanyu01.html', '/players/w/welshth01.html', '/players/w/westbru01.html', '/players/w/whitede01.html', '/players/w/whiteok01.html', '/players/w/whiteha01.html', '/players/w/wiggian01.html', '/players/w/willial03.html', '/players/w/willicj01.html', '/players/w/willijo04.html', '/players/w/willike04.html', '/players/w/willilo02.html', '/players/w/willima02.html', '/players/w/williro04.html', '/players/w/willitr02.html', '/players/w/wilsodj01.html', '/players/w/winslju01.html', '/players/w/woodch01.html', '/players/w/woodch01.html', '/players/w/woodch01.html', '/players/w/wrighde01.html', '/players/w/wrighde01.html', '/players/w/wrighde01.html', '/players/y/yabusgu01.html', '/players/y/youngni01.html', '/players/y/youngth01.html', '/players/y/youngtr01.html', '/players/z/zelleco01.html', '/players/z/zellety01.html', '/players/z/zellety01.html', '/players/z/zellety01.html', '/players/z/zizican01.html', '/players/z/zubaciv01.html', '/players/z/zubaciv01.html', '/players/z/zubaciv01.html']

I would use a set comprehension to remove duplicates and also I think nth-of-type to select the appropriate column reads more cleanly. Using bs4 4.7.1
import requests
from bs4 import BeautifulSoup as bs
soup = bs(requests.get('https://www.basketball-reference.com/leagues/NBA_2019_per_game.html').text, 'html.parser')
links = {i['href'] for i in soup.select('#per_game_stats td:nth-of-type(1) a')}
print(links)
You could also use the following css selector:
[csk] > a

Python - How to count specific section in a list

I'm brand new to python and I'm struggling how to add certain sections of a cvs file in python. I'm not allowed to use "import cvs"
I'm importing the TipJoke CVS file from https://vincentarelbundock.github.io/Rdatasets/datasets.html
This is the only code I have so far that worked and I'm at a total loss on where to go from here.
if __name__ == '__main__':
from pprint import pprint
from string import punctuation
f = open("TipJoke.csv", "r")
tipList = []
for line in f:
#deletes the quotes
line = line.replace('"', '')
tipList.append(line)
pprint(tipList[])
Output:
[',Card,Tip,Ad,Joke,None\n',
'1,None,1,0,0,1\n',
'2,Joke,1,0,1,0\n',
'3,Ad,0,1,0,0\n',
'4,None,0,0,0,1\n',
'5,None,1,0,0,1\n',
'6,None,0,0,0,1\n',
'7,Ad,0,1,0,0\n',
'8,Ad,0,1,0,0\n',
'9,None,0,0,0,1\n',
'10,None,0,0,0,1\n',
'11,None,1,0,0,1\n',
'12,Ad,0,1,0,0\n',
'13,None,0,0,0,1\n',
'14,Ad,1,1,0,0\n',
'15,Joke,1,0,1,0\n',
'16,Joke,0,0,1,0\n',
'17,Joke,1,0,1,0\n',
'18,None,0,0,0,1\n',
'19,Joke,0,0,1,0\n',
'20,None,0,0,0,1\n',
'21,Ad,1,1,0,0\n',
'22,Ad,1,1,0,0\n',
'23,Ad,0,1,0,0\n',
'24,Joke,0,0,1,0\n',
'25,Joke,1,0,1,0\n',
'26,Joke,0,0,1,0\n',
'27,None,1,0,0,1\n',
'28,Joke,1,0,1,0\n',
'29,Joke,1,0,1,0\n',
'30,None,1,0,0,1\n',
'31,Joke,0,0,1,0\n',
'32,None,1,0,0,1\n',
'33,Joke,1,0,1,0\n',
'34,Ad,0,1,0,0\n',
'35,Joke,0,0,1,0\n',
'36,Ad,1,1,0,0\n',
'37,Joke,0,0,1,0\n',
'38,Ad,0,1,0,0\n',
'39,Joke,0,0,1,0\n',
'40,Joke,0,0,1,0\n',
'41,Joke,1,0,1,0\n',
'42,None,0,0,0,1\n',
'43,None,0,0,0,1\n',
'44,Ad,0,1,0,0\n',
'45,None,0,0,0,1\n',
'46,None,0,0,0,1\n',
'47,Ad,0,1,0,0\n',
'48,Joke,0,0,1,0\n',
'49,Joke,1,0,1,0\n',
'50,None,1,0,0,1\n',
'51,None,0,0,0,1\n',
'52,Joke,1,0,1,0\n',
'53,Joke,1,0,1,0\n',
'54,Joke,0,0,1,0\n',
'55,None,1,0,0,1\n',
'56,Ad,0,1,0,0\n',
'57,Joke,0,0,1,0\n',
'58,None,0,0,0,1\n',
'59,Ad,0,1,0,0\n',
'60,Joke,1,0,1,0\n',
'61,Ad,0,1,0,0\n',
'62,None,1,0,0,1\n',
'63,Joke,0,0,1,0\n',
'64,Ad,0,1,0,0\n',
'65,Joke,0,0,1,0\n',
'66,Ad,0,1,0,0\n',
'67,Ad,0,1,0,0\n',
'68,Ad,0,1,0,0\n',
'69,None,0,0,0,1\n',
'70,Joke,1,0,1,0\n',
'71,None,1,0,0,1\n',
'72,None,0,0,0,1\n',
'73,None,0,0,0,1\n',
'74,Joke,0,0,1,0\n',
'75,Ad,1,1,0,0\n',
'76,Ad,0,1,0,0\n',
'77,Ad,1,1,0,0\n',
'78,Joke,0,0,1,0\n',
'79,Joke,0,0,1,0\n',
'80,Ad,1,1,0,0\n',
'81,Ad,0,1,0,0\n',
'82,None,0,0,0,1\n',
'83,Ad,0,1,0,0\n',
'84,Joke,0,0,1,0\n',
'85,Joke,0,0,1,0\n',
'86,Ad,1,1,0,0\n',
'87,None,1,0,0,1\n',
'88,Joke,1,0,1,0\n',
'89,Ad,0,1,0,0\n',
'90,None,0,0,0,1\n',
'91,None,0,0,0,1\n',
'92,Joke,0,0,1,0\n',
'93,Joke,0,0,1,0\n',
'94,Ad,0,1,0,0\n',
'95,Ad,0,1,0,0\n',
'96,Ad,0,1,0,0\n',
'97,Joke,1,0,1,0\n',
'98,None,0,0,0,1\n',
'99,None,0,0,0,1\n',
'100,None,1,0,0,1\n',
'101,Joke,0,0,1,0\n',
'102,Joke,0,0,1,0\n',
'103,Ad,1,1,0,0\n',
'104,Ad,0,1,0,0\n',
'105,Ad,0,1,0,0\n',
'106,Ad,1,1,0,0\n',
'107,Ad,0,1,0,0\n',
'108,None,0,0,0,1\n',
'109,Ad,0,1,0,0\n',
'110,Joke,1,0,1,0\n',
'111,None,0,0,0,1\n',
'112,Ad,0,1,0,0\n',
'113,Ad,0,1,0,0\n',
'114,None,0,0,0,1\n',
'115,Ad,0,1,0,0\n',
'116,None,0,0,0,1\n',
'117,None,0,0,0,1\n',
'118,Ad,0,1,0,0\n',
'119,None,1,0,0,1\n',
'120,Ad,1,1,0,0\n',
'121,Ad,0,1,0,0\n',
'122,Ad,1,1,0,0\n',
'123,None,0,0,0,1\n',
'124,None,0,0,0,1\n',
'125,Joke,1,0,1,0\n',
'126,Joke,1,0,1,0\n',
'127,Ad,0,1,0,0\n',
'128,Joke,0,0,1,0\n',
'129,Joke,0,0,1,0\n',
'130,Ad,0,1,0,0\n',
'131,None,0,0,0,1\n',
'132,None,0,0,0,1\n',
'133,None,0,0,0,1\n',
'134,Joke,1,0,1,0\n',
'135,Ad,0,1,0,0\n',
'136,None,0,0,0,1\n',
'137,Joke,0,0,1,0\n',
'138,Ad,0,1,0,0\n',
'139,Ad,0,1,0,0\n',
'140,None,0,0,0,1\n',
'141,Joke,0,0,1,0\n',
'142,None,0,0,0,1\n',
'143,Ad,0,1,0,0\n',
'144,None,1,0,0,1\n',
'145,Joke,0,0,1,0\n',
'146,Ad,0,1,0,0\n',
'147,Ad,0,1,0,0\n',
'148,Ad,0,1,0,0\n',
'149,Joke,1,0,1,0\n',
'150,Ad,1,1,0,0\n',
'151,Joke,1,0,1,0\n',
'152,None,0,0,0,1\n',
'153,Ad,0,1,0,0\n',
'154,None,0,0,0,1\n',
'155,None,0,0,0,1\n',
'156,Ad,0,1,0,0\n',
'157,Ad,0,1,0,0\n',
'158,Joke,0,0,1,0\n',
'159,None,0,0,0,1\n',
'160,Joke,1,0,1,0\n',
'161,None,1,0,0,1\n',
'162,Ad,1,1,0,0\n',
'163,Joke,0,0,1,0\n',
'164,Joke,0,0,1,0\n',
'165,Ad,0,1,0,0\n',
'166,Joke,1,0,1,0\n',
'167,Joke,1,0,1,0\n',
'168,Ad,0,1,0,0\n',
'169,Joke,1,0,1,0\n',
'170,Joke,0,0,1,0\n',
'171,Ad,0,1,0,0\n',
'172,Joke,0,0,1,0\n',
'173,Joke,0,0,1,0\n',
'174,Ad,0,1,0,0\n',
'175,None,0,0,0,1\n',
'176,Joke,1,0,1,0\n',
'177,Ad,0,1,0,0\n',
'178,Joke,0,0,1,0\n',
'179,Joke,0,0,1,0\n',
'180,None,0,0,0,1\n',
'181,None,0,0,0,1\n',
'182,Ad,0,1,0,0\n',
'183,None,0,0,0,1\n',
'184,None,0,0,0,1\n',
'185,None,0,0,0,1\n',
'186,None,0,0,0,1\n',
'187,Ad,0,1,0,0\n',
'188,None,1,0,0,1\n',
'189,Ad,0,1,0,0\n',
'190,Ad,0,1,0,0\n',
'191,Ad,0,1,0,0\n',
'192,Joke,1,0,1,0\n',
'193,Joke,0,0,1,0\n',
'194,Ad,0,1,0,0\n',
'195,None,0,0,0,1\n',
'196,Joke,1,0,1,0\n',
'197,Joke,0,0,1,0\n',
'198,Joke,1,0,1,0\n',
'199,Ad,0,1,0,0\n',
'200,None,0,0,0,1\n',
'201,Joke,1,0,1,0\n',
'202,Joke,0,0,1,0\n',
'203,Joke,0,0,1,0\n',
'204,Ad,0,1,0,0\n',
'205,None,0,0,0,1\n',
'206,Ad,0,1,0,0\n',
'207,Ad,0,1,0,0\n',
'208,Joke,0,0,1,0\n',
'209,Ad,0,1,0,0\n',
'210,Joke,0,0,1,0\n',
'211,None,0,0,0,1\n']
I'm currently trying to find the Total number of entries of the specified card type and the Percentage of tips given for the specified card type with two decimal places of precision. The tip column is the 0 or 1 right after the card type (None, Ad, Joke).

if you are allowed with pandas library then
import pandas as pd
df = pd.read_csv("TipJoke.csv")
df is a pandas dataframe object in which you can perform multiple filtering task according to your need.
for example if you want to get data for Joke you can filter like this:
print(df[df["Card"] == "Joke"])
Though, i'm just providing you the direction , not whole logic for your question.

This works
from pprint import pprint
from string import punctuation
counts = {"Joke": 0, "Ad": 0, "None": 0}
with open("TipJoke.csv", "r") as f:
for line in f:
line_clean = line.replace('"', "").replace("\n", "").split(",")
try:
counts[line_clean[1]] += int(line_clean[2])
except:
pass
print(counts)

Using beautiful soup inside a loop to search for urls

I am trying to write a python script that goes onto the website https://www.premierleague.com/players, takes a list of football player names from a spreadsheet I have (400+ footballer names), and inside a loop, iteratively searches for the link to each football player's page. For example : https://www.premierleague.com/players/4040/Benik-Afobe/overview.
The final bit of the script is commented out as I have finalised that yet, but for context of what I'm eventually going to get to: it will take this list of urls that I will have obtained, and iteratively search for each players link to the player image, and append it to a list.
I managed to get it to work for an individual player (Benik Afobe), but since adding the 'players_list' and trying a loop, I get the following error:
Traceback (most recent call last):
File "C:/Users/Liam/Documents/GitHub/Football_Scraping/fantast_pl_images.py", line 33, in <module>
player_link = soup.find('a', href=re.compile('%s'))['href'] %player
TypeError: 'NoneType' object is not subscriptable
Does anyone know what I'm doing wrong and how to get my loop working?
The Repo of my project can be found here: https://github.com/leej11/Football_Scraping
# Import the Libraries that I need
import urllib3
import certifi
from bs4 import BeautifulSoup
import re
import pandas as pd
# Specify the URL
url = 'https://www.premierleague.com/players'
http = urllib3.PoolManager(cert_reqs='CERT_REQUIRED', ca_certs=certifi.where())
response = http.request('GET', url, headers={'User-Agent': 'Mozilla/5.0'})
#Parse the html using beautiful soup and store in variable 'soup'
soup = BeautifulSoup(response.data, "html.parser")
#Importing the list of players I want to scrape the image of
players_list = pd.read_csv('epl_players_anki_clean.csv')
#Test that it's pulling all of the players names correctly
print(players_list.iloc[:,0])
print (type(players_list))
#Convert the pandas dataframe to a list of strings, with each item being the string of a player name
list_of_players = players_list['name'].values.tolist()
print(list_of_players)
#Setup an empty list to append the player links to
player_link_list = []
#Loop over the list of player names, and search for the player url and append it to the player_link_list
for player in players_list:
player_link = soup.find('a', href=re.compile('%s'))['href'] %player
print(player_link)
player_url = 'https://www.premierleague.com' + '%s' %player_link
print(player_url)
player_link_list.append(player_url)
##### The final step
##### To be worked on in a bit, basically take the list of links and loop over it pulling out the player image links and appending them to a list
#####
# url2 = player_url
# http2 = urllib3.PoolManager(cert_reqs='CERT_REQUIRED', ca_certs=certifi.where())
# response2 = http2.request('GET', url2, headers={'User-Agent': 'Mozilla/5.0'})
# soup2 = BeautifulSoup(response2.data, "html.parser")
# player_img = str(soup2.find("img", {'alt':'Benik Afobe'})['data-player'])
# print(player_img)
#
# photo_link = 'http://platform-static-files.s3.amazonaws.com/premierleague/photos/players/250x250/' + '%s' %player_img + '.png'
# print(photo_link)

It appears that the Premier League's player listing is dynamic, meaning that a browser script is loading additional players as the user scrolls down. Thus, using requests or urllib to find all the players will not work. Therefore, you will have to use a browser manipulation tool called selenium:
Install:
pip install selenium:
Then, install the proper binding for the webbrowser you are using:
http://selenium-python.readthedocs.io/installation.html#drivers
import re
import selenium
import time
import csv
driver = selenium.webdriver.Chrome('/path/to/driver')#substitute Chrome with browser you are using
driver.get('https://www.premierleague.com/players')
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
time.sleep(0.5)
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
break
last_height = new_height
time.sleep(10)
players = re.findall('www\.premierleague\.com/players/(.*?)/(.*?)/overview', driver.page_source)
csv_filedata = list(csv.reader(open('epl_players_anki_clean.csv')))
player_dict = {re.sub('-', ' ', b):(a, b) for a, b in players}
new_rows = [[csv_filedata[0]]+['url']]+[a+['https://www.premierleague.com/players/{}/{}/overview'.format(*player_dict[a[0]])] for a in csv_filedata]
with open('players.csv', 'a') as f:
write = csv.writer(f)
write.writerows(new_rows)
player_dict stores the following (truncated data):
Output:
{u'Asmir Begovic': [u'2537', u'Asmir-Begovic'], u'Ragnar Klavan': [u'15608', u'Ragnar-Klavan'], u'Eddie Nketiah': [u'14451', u'Eddie-Nketiah'], u'Mohamed Salah': [u'5178', u'Mohamed-Salah'], u'Jos\xe9 Holebas': [u'5713', u'Jos\xe9-Holebas'], u'Christian Eriksen': [u'4845', u'Christian-Eriksen'], u'Kurt Zouma': [u'5175', u'Kurt-Zouma'], u'Gareth Barry': [u'1308', u'Gareth-Barry'], u'Diego Costa': [u'4941', u'Diego-Costa'], u'Sam McQueen': [u'9649', u'Sam-McQueen'], u'Roque Mesa': [u'22575', u'Roque-Mesa'], u'Siem de Jong': [u'4885', u'Siem-de-Jong'], u'Lazar Markovic': [u'5078', u'Lazar-Markovic'], u'Adam Federici': [u'3182', u'Adam-Federici'], u'Dean Marney': [u'2359', u'Dean-Marney'], u'Nathan Broadhead': [u'14636', u'Nathan-Broadhead'], u'Alex Pritchard': [u'4433', u'Alex-Pritchard'], u'Matthew Pennington': [u'9895', u'Matthew-Pennington'], u'Tomas Kalas': [u'4101', u'Tomas-Kalas'], u'Nathan Ak\xe9': [u'4499', u'Nathan-Ak\xe9'], u'Mathias Normann': [u'23556', u'Mathias-Normann'], u'Grzegorz Krychowiak': [u'12735', u'Grzegorz-Krychowiak'], u'Wojciech Szczesny': [u'3543', u'Wojciech-Szczesny'], u'Charlie Adam': [u'4081', u'Charlie-Adam'], u'Marko Grujic': [u'13985', u'Marko-Grujic'], u'Harry Maguire': [u'9566', u'Harry-Maguire'], u'Isaiah Brown': [u'4674', u'Isaiah-Brown'], u'Matz Sels': [u'16723', u'Matz-Sels'], u'Leighton Baines': [u'3030', u'Leighton-Baines'], u'Marouane Fellaini': [u'3604', u'Marouane-Fellaini'], u'Jairo Riedewald': [u'4878', u'Jairo-Riedewald'], u'Glenn Murray': [u'4772', u'Glenn-Murray'], u'Tom Cadman': [u'14547', u'Tom-Cadman'], u'Ryan Shawcross': [u'3158', u'Ryan-Shawcross'], u"N'Golo Kant\xe9": [u'13492', u"N'Golo-Kant\xe9"], u'Aaron Ramsey': [u'3548', u'Aaron-Ramsey'], u'Stephen Kingsley': [u'10517', u'Stephen-Kingsley'], u'Eliaquim Mangala': [u'5334', u'Eliaquim-Mangala'], u'Josh Tymon': [u'13477', u'Josh-Tymon'], u'Mohamed Diam\xe9': [u'3982', u'Mohamed-Diam\xe9'], u'Sofiane Boufal': [u'12584', u'Sofiane-Boufal'], u'Nya Kirby': [u'15134', u'Nya-Kirby'], u'Max Melbourne': [u'15160', u'Max-Melbourne'], u'Marcin Bulka': [u'23695', u'Marcin-Bulka'], u'Rub\xe9n Sobrino': [u'16608', u'Rub\xe9n-Sobrino'], u'Tareiq Holmes Dennis': [u'8340', u'Tareiq-Holmes-Dennis'], u'Martin Cranie': [u'2559', u'Martin-Cranie'], u'Connor Mahoney': [u'7985', u'Connor-Mahoney'], u'Jamaal Lascelles': [u'9257', u'Jamaal-Lascelles'], u'Phil Foden': [u'14805', u'Phil-Foden'], u'Arijanet Muric': [u'19911', u'Arijanet-Muric'], u'Sadio Man\xe9': [u'6519', u'Sadio-Man\xe9'], u"Aiden O'Neill": [u'20095', u"Aiden-O'Neill"], u'Steve Cook': [u'8045', u'Steve-Cook'], u'Samuel Shashoua': [u'15142', u'Samuel-Shashoua'], u'Kyle Bartley': [u'3312', u'Kyle-Bartley'], u'Bojan': [u'4898', u'Bojan'], u'Jason Puncheon': [u'4084', u'Jason-Puncheon'], u'Damien Delaney': [u'1911', u'Damien-Delaney'], u'Steven Defour': [u'5345', u'Steven-Defour'], u'Christian Walton': [u'8159', u'Christian-Walton'], u'Timothy Fosu Mensah': [u'13561', u'Timothy-Fosu-Mensah'], u'Michael Keane': [u'4333', u'Michael-Keane'], u'Levi Lumeka': [u'14170', u'Levi-Lumeka'], u'Chancel Mbemba': [u'5850', u'Chancel-Mbemba'], u'Brice Dja Dj\xe9dj\xe9': [u'5577', u'Brice-Dja-Dj\xe9dj\xe9'], u'Vurnon Anita': [u'4550', u'Vurnon-Anita'], u'Jefferson Montero': [u'10518', u'Jefferson-Montero'], u'Toby Alderweireld': [u'4916', u'Toby-Alderweireld'], u'Dominic Calvert Lewin': [u'9576', u'Dominic-Calvert-Lewin'], u'Brad Jackson': [u'13246', u'Brad-Jackson'], u'James McArthur': [u'4224', u'James-McArthur'], u'Mat Ryan': [u'12192', u'Mat-Ryan'], u'Bartosz Kapustka': [u'19679', u'Bartosz-Kapustka'], u'Robert Snodgrass': [u'4558', u'Robert-Snodgrass'], u'Jonathan Leko': [u'13866', u'Jonathan-Leko'], u'Harry Arter': [u'8050', u'Harry-Arter'], u'Connor Goldson': [u'9634', u'Connor-Goldson'], u'Shaun Hobson': [u'21691', u'Shaun-Hobson'], u'Ayoze P\xe9rez': [u'10487', u'Ayoze-P\xe9rez'], u'Marc Pugh': [u'8049', u'Marc-Pugh'], u'Luciano Narsingh': [u'7122', u'Luciano-Narsingh'], u'Michael Folivi': [u'14298', u'Michael-Folivi'], u'Adri\xe1n': [u'4852', u'Adri\xe1n'], u'Mason Holgate': [u'10564', u'Mason-Holgate'], u'Joy Mukena': [u'15118', u'Joy-Mukena'], u"Lewis O'Brien": [u'24353', u"Lewis-O'Brien"], u'Javier Manquillo': [u'4918', u'Javier-Manquillo'], u"Dara O'Shea": [u'15154', u"Dara-O'Shea"], u"Clinton N'Jie": [u'6903', u"Clinton-N'Jie"], u'Yoan Gouffran': [u'4554', u'Yoan-Gouffran'], u'Michael Carrick': [u'1634', u'Michael-Carrick'], u'Moha': [u'13778', u'Moha'], u'Michy Batshuayi': [u'7450', u'Michy-Batshuayi'], u'Nathaniel Chalobah': [u'4105', u'Nathaniel-Chalobah'], u'Ryan Inniss': [u'4760', u'Ryan-Inniss'], u'Etienne Capoue': [u'4843', u'Etienne-Capoue'], u'Badou Ndiaye': [u'20538', u'Badou-Ndiaye'], u'Alexandre Lacazette': [u'6899', u'Alexandre-Lacazette'], u'Charlie Rowan': [u'14285', u'Charlie-Rowan'], u'Nathan Ferguson': [u'23976', u'Nathan-Ferguson'], u'Anthony Georgiou': [u'15146', u'Anthony-Georgiou'], u'Dujon Sterling': [u'14572', u'Dujon-Sterling'], u'Axel Tuanzebe': [u'13559', u'Axel-Tuanzebe'], u'Emre Can': [u'5001', u'Emre-Can'], u'Sam Surridge': [u'13195', u'Sam-Surridge'], u'Ryan Kent': [u'13509', u'Ryan-Kent'], u'Marc Albrighton': [u'3564', u'Marc-Albrighton'], u'Joe Williams': [u'10454', u'Joe-Williams'], u'Tom Heaton': [u'2933', u'Tom-Heaton'], u'Danny Rose': [u'3507', u'Danny-Rose'], u'Nathan Redmond': [u'3811', u'Nathan-Redmond'], u'Chicharito': [u'4161', u'Chicharito'], u'Dean Whitehead': [u'2980', u'Dean-Whitehead'], u'M.J. Williams': [u'10464', u'M.J.-Williams'], u'Harry Winks': [u'7488', u'Harry-Winks'], u'Josh Sims': [u'15374', u'Josh-Sims'], u'Charlie Gilmour': [u'14453', u'Charlie-Gilmour'], u'Aaron Wan Bissaka': [u'14164', u'Aaron-Wan-Bissaka'], u'Marc Muniesa': [u'4822', u'Marc-Muniesa'], u'Beni Baningime': [u'14623', u'Beni-Baningime'], u'Demarai Gray': [u'7946', u'Demarai-Gray'], u'Junior Stanislas': [u'3766', u'Junior-Stanislas'], u'Liam Rosenior': [u'2464', u'Liam-Rosenior'], u'Nathaniel Clyne': [u'4604', u'Nathaniel-Clyne'], u'Kamil Grabara': [u'19909', u'Kamil-Grabara'], u'Anthony Martial': [u'11272', u'Anthony-Martial'], u'Ben Foster': [u'2932', u'Ben-Foster'], u'Laurent Depoitre': [u'16747', u'Laurent-Depoitre'], u'Mike van der Hoorn': [u'4877', u'Mike-van-der-Hoorn'], u'Didier Ndong': [u'20708', u'Didier-Ndong'], u'Jordon Mutch': [u'3333', u'Jordon-Mutch'], u'Harry Kane': [u'3960', u'Harry-Kane'], u'Fernandinho': [u'4804', u'Fernandinho'], u'Riyad Mahrez': [u'8983', u'Riyad-Mahrez'], u'Kleton Perntreou': [u'14144', u'Kleton-Perntreou'], u'Dion Henry': [u'10855', u'Dion-Henry'], u'Kelechi Iheanacho': [u'13554', u'Kelechi-Iheanacho'], u'Salom\xf3n Rond\xf3n': [u'6030', u'Salom\xf3n-Rond\xf3n'], u'Ryan Allsop': [u'3732', u'Ryan-Allsop'], u'Erik Pieters': [u'4821', u'Erik-Pieters'], u'Willy Caballero': [u'10466', u'Willy-Caballero'], u'Claudio Yacob': [u'4673', u'Claudio-Yacob'], u'Craig Dawson': [u'4198', u'Craig-Dawson'], u'Jayson Molumby': [u'15293', u'Jayson-Molumby'], u'Lucas Leiva': [u'3137', u'Lucas-Leiva'], u'Martin Dubravka': [u'6451', u'Martin-Dubravka'], u'Bruno': [u'8162', u'Bruno'], u'Sam Johnstone': [u'4331', u'Sam-Johnstone'], u'Jes\xfas G\xe1mez': [u'11070', u'Jes\xfas-G\xe1mez'], u'Tomer Hemed': [u'13234', u'Tomer-Hemed'], u'Victor Moses': [u'3983', u'Victor-Moses'], u'Vincent Janssen': [u'15481', u'Vincent-Janssen'], u'Lo\xefc Remy': [u'4572', u'Lo\xefc-Remy'], u'Craig Cathcart': [u'3160', u'Craig-Cathcart'], u'Leroy Fer': [u'4810', u'Leroy-Fer'], u"Kieran O'Hara": [u'13584', u"Kieran-O'Hara"], u'Ola Aina': [u'10439', u'Ola-Aina'], u'Winston Reid': [u'4209', u'Winston-Reid'], u'Jose Baxter': [u'3608', u'Jose-Baxter'], u'Michael Obafemi': [u'21532', u'Michael-Obafemi'], u'Bruno Martins Indi': [u'11177', u'Bruno-Martins-Indi'], u'Laurent Koscielny': [u'4030', u'Laurent-Koscielny'], u'Borja Bast\xf3n': [u'16622', u'Borja-Bast\xf3n'], u'Daryl Janmaat': [u'10480', u'Daryl-Janmaat'], u'Freddy Woodman': [u'10479', u'Freddy-Woodman'], u'Jordy Hiwula Mayifuila': [u'10949', u'Jordy-Hiwula-Mayifuila'], u'Raphael Spiegel': [u'4679', u'Raphael-Spiegel'], u'Anthony Knockaert': [u'8982', u'Anthony-Knockaert'], u'Harry Lewis': [u'14982', u'Harry-Lewis'], u'Henrikh Mkhitaryan': [u'5102', u'Henrikh-Mkhitaryan'], u'Santiago Cazorla': [u'4477', u'Santiago-Cazorla'], u'Sean Scannell': [u'8887', u'Sean-Scannell'], u'Christian Atsu': [u'4859', u'Christian-Atsu'], u'Pascal Gro\xdf': [u'22542', u'Pascal-Gro\xdf'], u'Charlie Austin': [u'9468', u'Charlie-Austin'], u'Sam Byram': [u'8945', u'Sam-Byram'], u'Daniel Sturridge': [u'3154', u'Daniel-Sturridge'], u'Ga\xebtan Bong': [u'5721', u'Ga\xebtan-Bong'], u'Martin Kelly': [u'3644', u'Martin-Kelly'], u'Jack Payne': [u'9664', u'Jack-Payne'], u'Michel Vorm': [u'4398', u'Michel-Vorm'], u'Oriol Romeu': [u'4286', u'Oriol-Romeu'], u'Philip Billing': [u'8882', u'Philip-Billing'], u'Matthew Lowton': [u'4487', u'Matthew-Lowton'], u'Wayne Hennessey': [u'2569', u'Wayne-Hennessey'], u'Geoff Cameron': [u'4636', u'Geoff-Cameron'], u'Tammy Abraham': [u'13286', u'Tammy-Abraham'], u'Elvis Manu': [u'12374', u'Elvis-Manu'], u'Marvin Zeegelaar': [u'10123', u'Marvin-Zeegelaar'], u'Jordy Clasie': [u'12365', u'Jordy-Clasie'], u'Wayne Routledge': [u'2681', u'Wayne-Routledge'], u'Tom Anderson': [u'8234', u'Tom-Anderson'], u'Stephen Duke McKenna': [u'23738', u'Stephen-Duke-McKenna'], u'Harry Charsley': [u'14632', u'Harry-Charsley'], u'Erik Lamela': [u'4842', u'Erik-Lamela'], u'Elias Kachunga': [u'19611', u'Elias-Kachunga'], u'Molla Wagu\xe9': [u'21730', u'Molla-Wagu\xe9'], u'Ilkay G\xfcndogan': [u'5101', u'Ilkay-G\xfcndogan'], u'Ashley Williams': [u'4403', u'Ashley-Williams'], u'Lewis Grabban': [u'8055', u'Lewis-Grabban'], u'Seamus Coleman': [u'3600', u'Seamus-Coleman'], u'Jason Denayer': [u'11002', u'Jason-Denayer'], u'Jack Wilshere': [u'3547', u'Jack-Wilshere'], u'Calum Chambers': [u'4620', u'Calum-Chambers'], u'Samir Nasri': [u'3546', u'Samir-Nasri'], u'Alexis S\xe1nchez': [u'4973', u'Alexis-S\xe1nchez'], u'Kyle Walker': [u'3955', u'Kyle-Walker'], u'Martin Olsson': [u'2867', u'Martin-Olsson'], u'Modou Barrow': [u'10520', u'Modou-Barrow'], u'Robbie Brady': [u'4158', u'Robbie-Brady'], u'Tom Davies': [u'13389', u'Tom-Davies'], u'Fraser Forster': [u'3170', u'Fraser-Forster'], u'Francis Coquelin': [u'3549', u'Francis-Coquelin'], u'Matt Targett': [u'4815', u'Matt-Targett'], u'Davy Klaassen': [u'4886', u'Davy-Klaassen'], u"Stefan O'Connor": [u'10425', u"Stefan-O'Connor"], u'Fraser Hornby': [u'23744', u'Fraser-Hornby'], u'Tim Krul': [u'3169', u'Tim-Krul'], u'Ryan Hill': [u'21858', u'Ryan-Hill'], u'J\xfcrgen Locadia': [u'7124', u'J\xfcrgen-Locadia'], u'Ki Sung yueng': [u'4656', u'Ki-Sung-yueng'], u'Leon Britton': [u'2152', u'Leon-Britton'], u'Mesut \xd6zil': [u'4714', u'Mesut-\xd6zil'], u'Alex Denny': [u'14643', u'Alex-Denny'], u'Nemanja Matic': [u'3861', u'Nemanja-Matic'], u'Ryan Fraser': [u'8052', u'Ryan-Fraser'], u'Julian Speroni': [u'2664', u'Julian-Speroni'], u'Joel Campbell': [u'4254', u'Joel-Campbell'], u'Robert Elliot': [u'2214', u'Robert-Elliot'], u'Tosin Adarabioyo': [u'13549', u'Tosin-Adarabioyo'], u'Jack Colback': [u'3713', u'Jack-Colback'], u'Soufyan Ahannach': [u'24695', u'Soufyan-Ahannach'], u'Aaron Connolly': [u'21653', u'Aaron-Connolly'], u'Yasin Ben El Mhanni': [u'20879', u'Yasin-Ben-El-Mhanni'], u'Kazenga Lua Lua': [u'3173', u'Kazenga-Lua-Lua'], u'Ben Chilwell': [u'13491', u'Ben-Chilwell'], u'Aaron Ramsdale': [u'13703', u'Aaron-Ramsdale']}

AttributeError when extracting data from a URL in Python

I am using the code below to try an extract the data at the table in this URL. However, I get the following error message:
Error: `AttributeError: 'NoneType' object has no attribute 'find'`in
the line `data = iter(soup.find("table", {"class":
"tablestats"}).find("th", {"class": "header"}).find_all_next("tr"))`
My code is as follows:
from bs4 import BeautifulSoup
import requests
r = requests.get(
"http://www.federalreserve.gov/econresdata/researchdata/feds200628_1.html")
soup = BeautifulSoup(r.content)
data = iter(soup.find("table", {"class": "tablestats"}).find("th", {"class": "header"}).find_all_next("tr"))
headers = (next(data).text, next(data).text)
table_items = [(a.text, b.text) for ele in data for a, b in [ele.find_all("td")]]
for a, b in table_items:
print(u"Date={}, Maturity={}".format(a, b if b.strip() else "null"))
Thank You

from bs4 import BeautifulSoup
import requests
r = requests.get(
"http://www.federalreserve.gov/econresdata/researchdata/feds200628_1.html")
soup = BeautifulSoup(r.content)
# column headers
h = data.find_all("th", scope="col")
# get all the tr tags after the headers
final = [[t.th.text] + [ele.text for ele in t.find_all("td")] for t in h[-1].find_all_next("tr")]
headers = [th.text for th in h]
The final out list is all the rows in individual lists:
[['2015-06-05', '4.82039691', '-4.66420959', '-4.18904598',
'-3.94541434', '1.1477', '2.9361', '3.3588', '0.6943', '1.5881',
'2.3034', '2.7677', '3.0363', '3.1801', '3.2537', '3.2930', '3.3190',
'3.3431', '3.3707', '3.4038', '3.4428', '3.4871', '3.5357', '3.5876',
'3.6419', '3.6975', '3.7538', '3.8100', '3.8656', '3.9202', '3.9734',
'4.0250', '4.0748', '4.1225', '4.1682', '4.2117', '4.2530', '4.2921',
'0.3489', '0.7464', '1.1502', '1.4949', '1.7700', '1.9841', '2.1500',
'2.2800', '2.3837', '2.4685', '2.5396', '2.6006', '2.6544', '2.7027',
'2.7469', '2.7878', '2.8260', '2.8621', '2.8964', '2.9291', '2.9603',
'2.9901', '3.0187', '3.0461', '3.0724', '3.0976', '3.1217', '3.1448',
'3.1669', '3.1881', '0.3487', '0.7469', '1.1536', '1.5039', '1.7862',
'2.0078', '2.1811', '2.3179', '2.4277', '2.5181', '2.5943', '2.6603',
'2.7190', '2.7722', '2.8215', '2.8677', '2.9117', '2.9538', '2.9944',
'3.0338', '3.0721', '3.1094', '3.1458', '3.1814', '3.2161', '3.2501',
'3.2832', '3.3156', '3.3472', '3.3781', '1.40431658', '9.48795888'],
['2015-06-04', '4.64953424', '-4.52780982', '-3.98051369',
......................................
The headers:
['BETA0', 'BETA1', 'BETA2', 'BETA3', 'SVEN1F01', 'SVEN1F04', 'SVEN1F09', 'SVENF01', 'SVENF02', 'SVENF03', 'SVENF04', 'SVENF05', 'SVENF06', 'SVENF07', 'SVENF08', 'SVENF09', 'SVENF10', 'SVENF11', 'SVENF12', 'SVENF13', 'SVENF14', 'SVENF15', 'SVENF16', 'SVENF17', 'SVENF18', 'SVENF19', 'SVENF20', 'SVENF21', 'SVENF22', 'SVENF23', 'SVENF24', 'SVENF25', 'SVENF26', 'SVENF27', 'SVENF28', 'SVENF29', 'SVENF30', 'SVENPY01', 'SVENPY02', 'SVENPY03', 'SVENPY04', 'SVENPY05', 'SVENPY06', 'SVENPY07', 'SVENPY08', 'SVENPY09', 'SVENPY10', 'SVENPY11', 'SVENPY12', 'SVENPY13', 'SVENPY14', 'SVENPY15', 'SVENPY16', 'SVENPY17', 'SVENPY18', 'SVENPY19', 'SVENPY20', 'SVENPY21', 'SVENPY22', 'SVENPY23', 'SVENPY24', 'SVENPY25', 'SVENPY26', 'SVENPY27', 'SVENPY28', 'SVENPY29', 'SVENPY30', 'SVENY01', 'SVENY02', 'SVENY03', 'SVENY04', 'SVENY05', 'SVENY06', 'SVENY07', 'SVENY08', 'SVENY09', 'SVENY10', 'SVENY11', 'SVENY12', 'SVENY13', 'SVENY14', 'SVENY15', 'SVENY16', 'SVENY17', 'SVENY18', 'SVENY19', 'SVENY20', 'SVENY21', 'SVENY22', 'SVENY23', 'SVENY24', 'SVENY25', 'SVENY26', 'SVENY27', 'SVENY28', 'SVENY29', 'SVENY30', 'TAU1', 'TAU2']

There are a lot of issues in your code.
There is no table with class 'tablestats'.
There are no 'th' fields with class 'header'.
Following line-
table_items = [(a.text, b.text) for ele in data for a, b in [ele.find_all("td")]]
doesnt return just 2 values, so cant assign to a, b

We Keep Coding

Python is a programming language that lets you work quickly and integrate systems more effectively.

Requesting web page with Python - python

Related

requests and bs4 cannot read the whole html

Trying to grab just the first href in each table row

Python - How to count specific section in a list

Using beautiful soup inside a loop to search for urls

AttributeError when extracting data from a URL in Python

Categories

Resources