{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "6f2034b5", "metadata": {}, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 2, "id": "7b7e56b0", "metadata": {}, "outputs": [], "source": [ "data=pd.read_csv('Final Dataa.tsv', sep='\\t')\n" ] }, { "cell_type": "code", "execution_count": null, "id": "84868654", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 3, "id": "68b48e83", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Unnamed: 0titleIdtitleaverageRatingnumVotesprimaryTitleisAdultstartYearruntimeMinutesgenres
00tt0111161The Shawshank Redemption9.32405502The Shawshank Redemption01994142Drama
11tt0468569The Dark Knight9.02365212The Dark Knight02008152Action,Crime,Drama
22tt1375666Inception8.82122723Inception02010148Action,Adventure,Sci-Fi
33tt0137523Fight Club8.81899050Fight Club01999139Drama
44tt0110912Pulp Fiction8.91868911Pulp Fiction01994154Crime,Drama
.................................
130713130713tt00622537 uomini e un cervello4.6101Criminal Affair01968106Comedy,Crime
130714130714tt0068885La lunga cavalcata della vendetta4.6101Deadly Trackers0197292Drama,Western
130715130715tt2583192Lucid4.6101Lucid0201387Drama,Horror,Thriller
130716130716tt3899070Gone Tomorrow4.6101Gone Tomorrow0201590Crime,Drama,Mystery
130717130717tt8343748Seven Senses of the Re'Union4.6101Seven Senses of the Re'Union0201824Action,Adventure,Animation
\n", "

130718 rows × 10 columns

\n", "
" ], "text/plain": [ " Unnamed: 0 titleId title \\\n", "0 0 tt0111161 The Shawshank Redemption \n", "1 1 tt0468569 The Dark Knight \n", "2 2 tt1375666 Inception \n", "3 3 tt0137523 Fight Club \n", "4 4 tt0110912 Pulp Fiction \n", "... ... ... ... \n", "130713 130713 tt0062253 7 uomini e un cervello \n", "130714 130714 tt0068885 La lunga cavalcata della vendetta \n", "130715 130715 tt2583192 Lucid \n", "130716 130716 tt3899070 Gone Tomorrow \n", "130717 130717 tt8343748 Seven Senses of the Re'Union \n", "\n", " averageRating numVotes primaryTitle isAdult \\\n", "0 9.3 2405502 The Shawshank Redemption 0 \n", "1 9.0 2365212 The Dark Knight 0 \n", "2 8.8 2122723 Inception 0 \n", "3 8.8 1899050 Fight Club 0 \n", "4 8.9 1868911 Pulp Fiction 0 \n", "... ... ... ... ... \n", "130713 4.6 101 Criminal Affair 0 \n", "130714 4.6 101 Deadly Trackers 0 \n", "130715 4.6 101 Lucid 0 \n", "130716 4.6 101 Gone Tomorrow 0 \n", "130717 4.6 101 Seven Senses of the Re'Union 0 \n", "\n", " startYear runtimeMinutes genres \n", "0 1994 142 Drama \n", "1 2008 152 Action,Crime,Drama \n", "2 2010 148 Action,Adventure,Sci-Fi \n", "3 1999 139 Drama \n", "4 1994 154 Crime,Drama \n", "... ... ... ... \n", "130713 1968 106 Comedy,Crime \n", "130714 1972 92 Drama,Western \n", "130715 2013 87 Drama,Horror,Thriller \n", "130716 2015 90 Crime,Drama,Mystery \n", "130717 2018 24 Action,Adventure,Animation \n", "\n", "[130718 rows x 10 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "data" ] }, { "cell_type": "code", "execution_count": 4, "id": "3437c9b7", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "import requests as req\n", "from bs4 import BeautifulSoup" ] }, { "cell_type": "code", "execution_count": null, "id": "16d08cdf", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 5, "id": "4105e803", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1\n", "2\n", "3\n", "4\n", "5\n", "6\n", "zz7\n", "8\n", "9\n", "10\n", "11\n", "12\n", "13\n", "zz14\n", "15\n", "16\n", "17\n", "18\n", "19\n", "20\n", "21\n", "22\n", "23\n", "24\n", "25\n", "26\n", "27\n", "28\n", "29\n", "30\n", "31\n", "32\n", "33\n", "34\n", "35\n", "36\n", "37\n", "38\n", "39\n", "40\n", "41\n", "42\n", "43\n", "44\n", "45\n", "46\n", "47\n", "48\n", "49\n", "50\n", "51\n", "52\n", "53\n", "54\n", "55\n", "56\n", "57\n", "58\n", "59\n", "60\n", "61\n", "62\n", "63\n", "64\n", "65\n", "66\n", "67\n", "68\n", "69\n", "70\n", "zz71\n", "72\n", "73\n", "zz74\n", "zz75\n", "76\n", "77\n", "78\n", "zz79\n", "80\n", "81\n", "82\n", "83\n", "84\n", "85\n", "86\n", "87\n", "88\n", "89\n", "90\n", "91\n", "92\n", "93\n", "94\n", "95\n", "96\n", "97\n", "98\n", "99\n", "100\n", "101\n", "102\n", "103\n", "104\n", "105\n", "106\n", "107\n", "zz108\n", "109\n", "110\n", "111\n", "112\n", "113\n", "114\n", "115\n", "116\n", "117\n", "118\n", "119\n", "120\n", "121\n", "122\n", "123\n", "124\n", "125\n", "126\n", "127\n", "128\n", "129\n", "130\n", "131\n", "132\n", "133\n", "134\n", "135\n", "136\n", "zz137\n", "138\n", "139\n", "140\n", "141\n", "142\n", "143\n", "144\n", "145\n", "146\n", "147\n", "148\n", "149\n", "150\n", "151\n", "152\n", "153\n", "154\n", "155\n", "156\n", "157\n", "158\n", "159\n", "160\n", "zz161\n", "162\n", "163\n", "164\n", "165\n", "166\n", "167\n", "168\n", "169\n", "170\n", "171\n", "172\n", "173\n", "174\n", "175\n", "176\n", "177\n", "178\n", "179\n", "180\n", "181\n", "182\n", "183\n", "184\n", "185\n", "186\n", "187\n", "188\n", "189\n", "190\n", "191\n", "192\n", "zz193\n", "194\n", "195\n", "196\n", "197\n", "198\n", "199\n", "200\n", "201\n", "202\n", "203\n", "204\n", "205\n", "206\n", "207\n", "208\n", "209\n", "210\n", "211\n", "212\n", "213\n", "214\n", "215\n", "216\n", "217\n", "218\n", "219\n", "220\n", "221\n", "222\n", "223\n", "224\n", "225\n", "226\n", "227\n", "228\n", "229\n", "230\n", "231\n", "232\n", "233\n", "234\n", "235\n", "236\n", "237\n", "zz238\n", "239\n", "240\n", "241\n", "242\n", "243\n", "zz244\n", "245\n", "246\n", "247\n", "248\n", "249\n", "250\n", "251\n", "252\n", "253\n", "254\n", "255\n", "256\n", "257\n", "258\n", "259\n", "260\n", "zz261\n", "262\n", "263\n", "264\n", "265\n", "266\n", "267\n", "268\n", "269\n", "270\n", "zz271\n", "272\n", "273\n", "274\n", "275\n", "276\n", "277\n", "278\n", "279\n", "280\n", "281\n", "zz282\n", "283\n", "284\n", "285\n", "286\n", "287\n", "288\n", "289\n", "290\n", "291\n", "292\n", "293\n", "294\n", "295\n", "296\n", "297\n", "298\n", "zz299\n", "300\n", "301\n", "302\n", "303\n", "304\n", "305\n", "306\n", "307\n", "308\n", "309\n", "310\n", "zz311\n", "312\n", "zz313\n", "314\n", "315\n", "316\n", "317\n", "318\n", "319\n", "320\n", "321\n", "322\n", "323\n", "324\n", "325\n", "326\n", "327\n", "328\n", "329\n", "330\n", "331\n", "332\n", "333\n", "334\n", "335\n", "336\n", "337\n", "338\n", "zz339\n", "340\n", "341\n", "342\n", "343\n", "344\n", "345\n", "346\n", "347\n", "348\n", "349\n", "350\n", "351\n", "352\n", "353\n", "354\n", "zz355\n", "356\n", "357\n", "358\n", "359\n", "360\n", "361\n", "362\n", "363\n", "364\n", "365\n", "366\n", "367\n", "368\n", "zz369\n", "370\n", "371\n", "372\n", "373\n", "374\n", "zz375\n", "376\n", "377\n", "378\n", "379\n", "380\n", "381\n", "382\n", "383\n", "384\n", "385\n", "386\n", "zz387\n", "388\n", "389\n", "390\n", "391\n", "392\n", "393\n", "394\n", "395\n", "396\n", "397\n", "398\n", "399\n", "400\n", "401\n", "402\n", "403\n", "404\n", "405\n", "406\n", "407\n", "408\n", "zz409\n", "410\n", "411\n", "412\n", "413\n", "414\n", "415\n", "416\n", "417\n", "418\n", "419\n", "420\n", "421\n", "422\n", "423\n", "424\n", "zz425\n", "zz426\n", "427\n", "zz428\n", "zz429\n", "430\n", "zz431\n", "432\n", "433\n", "434\n", "435\n", "436\n", "437\n", "438\n", "439\n", "440\n", "441\n", "442\n", "443\n", "444\n", "445\n", "446\n", "447\n", "448\n", "449\n", "450\n", "451\n", "452\n", "453\n", "454\n", "455\n", "456\n", "457\n", "458\n", "459\n", "460\n", "461\n", "462\n", "463\n", "464\n", "465\n", "466\n", "467\n", "468\n", "469\n", "470\n", "471\n", "472\n", "473\n", "474\n", "475\n", "476\n", "477\n", "478\n", "479\n", "zz480\n", "481\n", "482\n", "zz483\n", "484\n", "485\n", "486\n", "487\n", "488\n", "489\n", "490\n", "zz491\n", "zz492\n", "493\n", "494\n", "495\n", "496\n", "497\n", "498\n", "499\n", "500\n", "501\n", "502\n", "503\n", "504\n", "zz505\n", "506\n", "507\n", "508\n", "509\n", "510\n", "511\n", "512\n", "513\n", "514\n", "515\n", "516\n", "zz517\n", "518\n", "519\n", "520\n", "521\n", "522\n", "zz523\n", "zz524\n", "525\n", "526\n", "zz527\n", "528\n", "529\n", "530\n", "531\n", "532\n", "533\n", "534\n", "535\n", "536\n", "537\n", "538\n", "539\n", "540\n", "541\n", "542\n", "543\n", "544\n", "zz545\n", "546\n", "547\n", "zz548\n", "549\n", "550\n", "551\n", "552\n", "553\n", "554\n", "555\n", "zz556\n", "557\n", "558\n", "559\n", "560\n", "561\n", "562\n", "zz563\n", "564\n", "565\n", "566\n", "567\n", "568\n", "569\n", "570\n", "571\n", "572\n", "573\n", "574\n", "zz575\n", "576\n", "577\n", "578\n", "579\n", "580\n", "581\n", "582\n", "583\n", "584\n", "585\n", "586\n", "587\n", "588\n", "589\n", "590\n", "591\n", "592\n", "593\n", "594\n", "595\n", "596\n", "597\n", "zz598\n", "599\n", "600\n", "601\n", "602\n", "603\n", "604\n", "605\n", "606\n", "607\n", "608\n", "609\n", "zz610\n", "611\n", "612\n", "613\n", "614\n", "zz615\n", "616\n", "617\n", "618\n", "619\n", "620\n", "621\n", "622\n", "623\n", "624\n", "625\n", "626\n", "627\n", "628\n", "629\n", "630\n", "631\n" ] }, { "ename": "KeyboardInterrupt", "evalue": "", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[0mcontent\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 7\u001b[0m \u001b[0mr\u001b[0m\u001b[1;33m=\u001b[0m \u001b[0mreq\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'https://www.imdb.com/title/'\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 8\u001b[1;33m \u001b[0msoup\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mBeautifulSoup\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcontent\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'html5lib'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 9\u001b[0m \u001b[0mr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcookies\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclear\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 10\u001b[0m \u001b[0mrows\u001b[0m\u001b[1;33m=\u001b[0m \u001b[0msoup\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind_all\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mclass_\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'ipc-metadata-list-item__list-content-item'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\bs4\\__init__.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, markup, features, builder, parse_only, from_encoding, exclude_encodings, element_classes, **kwargs)\u001b[0m\n\u001b[0;32m 346\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreset\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 347\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 348\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_feed\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 349\u001b[0m \u001b[0msuccess\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 350\u001b[0m \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\bs4\\__init__.py\u001b[0m in \u001b[0;36m_feed\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 432\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbuilder\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreset\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 433\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 434\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbuilder\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfeed\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmarkup\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 435\u001b[0m \u001b[1;31m# Close out any unfinished strings and close all the open tags.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 436\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mendData\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\bs4\\builder\\_html5lib.py\u001b[0m in \u001b[0;36mfeed\u001b[1;34m(self, markup)\u001b[0m\n\u001b[0;32m 85\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 86\u001b[0m \u001b[0mextra_kwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'encoding'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0muser_specified_encoding\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 87\u001b[1;33m \u001b[0mdoc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mparse\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmarkup\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mextra_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 88\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 89\u001b[0m \u001b[1;31m# Set the character encoding detected by the tokenizer.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\html5lib\\html5parser.py\u001b[0m in \u001b[0;36mparse\u001b[1;34m(self, stream, *args, **kwargs)\u001b[0m\n\u001b[0;32m 282\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 283\u001b[0m \"\"\"\n\u001b[1;32m--> 284\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_parse\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstream\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 285\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtree\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetDocument\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 286\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\html5lib\\html5parser.py\u001b[0m in \u001b[0;36m_parse\u001b[1;34m(self, stream, innerHTML, container, scripting, **kwargs)\u001b[0m\n\u001b[0;32m 127\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcontainer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcontainer\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 128\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mscripting\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mscripting\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 129\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtokenizer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_tokenizer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mHTMLTokenizer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstream\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparser\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 130\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreset\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 131\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\html5lib\\_tokenizer.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, stream, parser, **kwargs)\u001b[0m\n\u001b[0;32m 40\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstream\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparser\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 41\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 42\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstream\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mHTMLInputStream\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstream\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 43\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mparser\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 44\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\html5lib\\_inputstream.py\u001b[0m in \u001b[0;36mHTMLInputStream\u001b[1;34m(source, **kwargs)\u001b[0m\n\u001b[0;32m 143\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mHTMLUnicodeInputStream\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msource\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 144\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 145\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mHTMLBinaryInputStream\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msource\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 146\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 147\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\html5lib\\_inputstream.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, source, override_encoding, transport_encoding, same_origin_parent_encoding, likely_encoding, default_encoding, useChardet)\u001b[0m\n\u001b[0;32m 420\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 421\u001b[0m \u001b[1;31m# Determine encoding\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 422\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcharEncoding\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdetermineEncoding\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0museChardet\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 423\u001b[0m \u001b[1;32massert\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcharEncoding\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 424\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\html5lib\\_inputstream.py\u001b[0m in \u001b[0;36mdetermineEncoding\u001b[1;34m(self, chardet)\u001b[0m\n\u001b[0;32m 496\u001b[0m \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 497\u001b[0m \u001b[0mbuffers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbuffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 498\u001b[1;33m \u001b[0mdetector\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfeed\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbuffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 499\u001b[0m \u001b[0mdetector\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 500\u001b[0m \u001b[0mencoding\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlookupEncoding\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdetector\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'encoding'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\chardet\\universaldetector.py\u001b[0m in \u001b[0;36mfeed\u001b[1;34m(self, byte_str)\u001b[0m\n\u001b[0;32m 209\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_charset_probers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mLatin1Prober\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 210\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mprober\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_charset_probers\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 211\u001b[1;33m \u001b[1;32mif\u001b[0m \u001b[0mprober\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfeed\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbyte_str\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mProbingState\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mFOUND_IT\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 212\u001b[0m self.result = {'encoding': prober.charset_name,\n\u001b[0;32m 213\u001b[0m \u001b[1;34m'confidence'\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mprober\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_confidence\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\chardet\\charsetgroupprober.py\u001b[0m in \u001b[0;36mfeed\u001b[1;34m(self, byte_str)\u001b[0m\n\u001b[0;32m 69\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mprober\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mactive\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 70\u001b[0m \u001b[1;32mcontinue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 71\u001b[1;33m \u001b[0mstate\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mprober\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfeed\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbyte_str\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 72\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mstate\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 73\u001b[0m \u001b[1;32mcontinue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\chardet\\sbcharsetprober.py\u001b[0m in \u001b[0;36mfeed\u001b[1;34m(self, byte_str)\u001b[0m\n\u001b[0;32m 90\u001b[0m \u001b[1;31m# TODO: Make filter_international_words keep things in self.alphabet\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 91\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_model\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeep_ascii_letters\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 92\u001b[1;33m \u001b[0mbyte_str\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfilter_international_words\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbyte_str\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 93\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mbyte_str\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 94\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstate\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\chardet\\charsetprober.py\u001b[0m in \u001b[0;36mfilter_international_words\u001b[1;34m(buf)\u001b[0m\n\u001b[0;32m 84\u001b[0m \u001b[1;31m# international character. The word may include one marker character at\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 85\u001b[0m \u001b[1;31m# the end.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 86\u001b[1;33m words = re.findall(b'[a-zA-Z]*[\\x80-\\xFF]+[a-zA-Z]*[^a-zA-Z\\x80-\\xFF]?',\n\u001b[0m\u001b[0;32m 87\u001b[0m buf)\n\u001b[0;32m 88\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\re.py\u001b[0m in \u001b[0;36mfindall\u001b[1;34m(pattern, string, flags)\u001b[0m\n\u001b[0;32m 239\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 240\u001b[0m Empty matches are included in the result.\"\"\"\n\u001b[1;32m--> 241\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0m_compile\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpattern\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfindall\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mstring\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 242\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 243\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mfinditer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpattern\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstring\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;31mKeyboardInterrupt\u001b[0m: " ] } ], "source": [ "directors=[]\n", "writer_actor=[]\n", "earned=[]\n", "j=1\n", "for i in data.titleId:\n", " content=[]\n", " r= req.get('https://www.imdb.com/title/'+i)\n", " soup=BeautifulSoup(r.content, 'html5lib')\n", " r.cookies.clear()\n", " rows= soup.find_all(class_='ipc-metadata-list-item__list-content-item')\n", " if len(rows)>1:\n", " for i in rows:\n", " content.append(i.get_text().strip())\n", " directors.append(content[0].strip())\n", " writer_actor.append(list(set(content[1:10])))\n", " nums=[]\n", " for i in content[-15:]:\n", " \n", " num= i.replace(',','').replace('$','').replace('(estimated)','')\n", " try:\n", " nums.append(int(num))\n", " except:\n", " continue\n", " \n", " if len(nums) > 1:\n", " print(j)\n", " earned.append(max(nums))\n", " else:\n", " print('zz'+str(j))\n", " earned.append('NaN')\n", " \n", " else:\n", " print('z'+str(j))\n", " directors.append(np.nan)\n", " writer_actor.append(np.nan)\n", " j+=1" ] }, { "cell_type": "code", "execution_count": null, "id": "8d8a9d77", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "10d5adb7", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 6, "id": "2cfa1e5d", "metadata": {}, "outputs": [], "source": [ "directors=pd.DataFrame(directors)\n", "writer_actor= pd.DataFrame(writer_actor)" ] }, { "cell_type": "code", "execution_count": 7, "id": "836f83c9", "metadata": {}, "outputs": [], "source": [ "directors.to_csv('directors.tsv', sep='\\t')\n", "writer_actor.to_csv('writer_actor.tsv', sep= '\\t')" ] }, { "cell_type": "code", "execution_count": null, "id": "5a5fdd45", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" } }, "nbformat": 4, "nbformat_minor": 5 }