{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "d035e38d", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import requests as req\n", "from bs4 import BeautifulSoup" ] }, { "cell_type": "code", "execution_count": 2, "id": "1169b79b", "metadata": {}, "outputs": [], "source": [ "movies = pd.read_csv('Final Dataa.tsv', sep='\\t')" ] }, { "cell_type": "code", "execution_count": 3, "id": "900ba1f2", "metadata": {}, "outputs": [], "source": [ "movies=movies[['titleId','title','genres']]" ] }, { "cell_type": "code", "execution_count": 4, "id": "fc9f7101", "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", "
titleIdtitlegenres
0tt0111161The Shawshank RedemptionDrama
1tt0468569The Dark KnightAction,Crime,Drama
2tt1375666InceptionAction,Adventure,Sci-Fi
3tt0137523Fight ClubDrama
4tt0110912Pulp FictionCrime,Drama
............
130713tt00622537 uomini e un cervelloComedy,Crime
130714tt0068885La lunga cavalcata della vendettaDrama,Western
130715tt2583192LucidDrama,Horror,Thriller
130716tt3899070Gone TomorrowCrime,Drama,Mystery
130717tt8343748Seven Senses of the Re'UnionAction,Adventure,Animation
\n", "

130718 rows × 3 columns

\n", "
" ], "text/plain": [ " titleId title \\\n", "0 tt0111161 The Shawshank Redemption \n", "1 tt0468569 The Dark Knight \n", "2 tt1375666 Inception \n", "3 tt0137523 Fight Club \n", "4 tt0110912 Pulp Fiction \n", "... ... ... \n", "130713 tt0062253 7 uomini e un cervello \n", "130714 tt0068885 La lunga cavalcata della vendetta \n", "130715 tt2583192 Lucid \n", "130716 tt3899070 Gone Tomorrow \n", "130717 tt8343748 Seven Senses of the Re'Union \n", "\n", " genres \n", "0 Drama \n", "1 Action,Crime,Drama \n", "2 Action,Adventure,Sci-Fi \n", "3 Drama \n", "4 Crime,Drama \n", "... ... \n", "130713 Comedy,Crime \n", "130714 Drama,Western \n", "130715 Drama,Horror,Thriller \n", "130716 Crime,Drama,Mystery \n", "130717 Action,Adventure,Animation \n", "\n", "[130718 rows x 3 columns]" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "movies" ] }, { "cell_type": "code", "execution_count": 30, "id": "3f4c1736", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "12096\n", "12097\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 5\u001b[0m \u001b[0mp\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 6\u001b[0m \u001b[0mre\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[1;32m----> 7\u001b[1;33m \u001b[0mre\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;33m(\u001b[0m\u001b[1;34m'https://www.imdb.com/title/'\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mmovie\u001b[0m\u001b[1;33m+\u001b[0m\u001b[1;34m'/keywords'\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 8\u001b[0m \u001b[0msoup\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mBeautifulSoup\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mre\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[0;32m 9\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\requests\\api.py\u001b[0m in \u001b[0;36mget\u001b[1;34m(url, params, **kwargs)\u001b[0m\n\u001b[0;32m 74\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 75\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msetdefault\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'allow_redirects'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 76\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mrequest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'get'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mparams\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 77\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 78\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\requests\\api.py\u001b[0m in \u001b[0;36mrequest\u001b[1;34m(method, url, **kwargs)\u001b[0m\n\u001b[0;32m 59\u001b[0m \u001b[1;31m# cases, and look like a memory leak in others.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 60\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0msessions\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSession\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0murl\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 62\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 63\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\requests\\sessions.py\u001b[0m in \u001b[0;36mrequest\u001b[1;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[0;32m 540\u001b[0m }\n\u001b[0;32m 541\u001b[0m \u001b[0msend_kwargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msettings\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 542\u001b[1;33m \u001b[0mresp\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mprep\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0msend_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 543\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 544\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresp\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\requests\\sessions.py\u001b[0m in \u001b[0;36msend\u001b[1;34m(self, request, **kwargs)\u001b[0m\n\u001b[0;32m 695\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 696\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mstream\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 697\u001b[1;33m \u001b[0mr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcontent\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 698\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 699\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mr\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\requests\\models.py\u001b[0m in \u001b[0;36mcontent\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 829\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_content\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 830\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--> 831\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_content\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34mb''\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0miter_content\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mCONTENT_CHUNK_SIZE\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mor\u001b[0m \u001b[1;34mb''\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 832\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 833\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_content_consumed\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[1;32m~\\anaconda3\\lib\\site-packages\\requests\\models.py\u001b[0m in \u001b[0;36mgenerate\u001b[1;34m()\u001b[0m\n\u001b[0;32m 751\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mraw\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'stream'\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 752\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--> 753\u001b[1;33m \u001b[1;32mfor\u001b[0m \u001b[0mchunk\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mraw\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstream\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mchunk_size\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdecode_content\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\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 754\u001b[0m \u001b[1;32myield\u001b[0m \u001b[0mchunk\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 755\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mProtocolError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\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\\urllib3\\response.py\u001b[0m in \u001b[0;36mstream\u001b[1;34m(self, amt, decode_content)\u001b[0m\n\u001b[0;32m 570\u001b[0m \"\"\"\n\u001b[0;32m 571\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mchunked\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msupports_chunked_reads\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--> 572\u001b[1;33m \u001b[1;32mfor\u001b[0m \u001b[0mline\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread_chunked\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mamt\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdecode_content\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdecode_content\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 573\u001b[0m \u001b[1;32myield\u001b[0m \u001b[0mline\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 574\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~\\anaconda3\\lib\\site-packages\\urllib3\\response.py\u001b[0m in \u001b[0;36mread_chunked\u001b[1;34m(self, amt, decode_content)\u001b[0m\n\u001b[0;32m 762\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 763\u001b[0m \u001b[1;32mwhile\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 764\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_update_chunk_length\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 765\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mchunk_left\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[0m\n\u001b[0;32m 766\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\\urllib3\\response.py\u001b[0m in \u001b[0;36m_update_chunk_length\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 692\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mchunk_left\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[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 693\u001b[0m \u001b[1;32mreturn\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 694\u001b[1;33m \u001b[0mline\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_fp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreadline\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 695\u001b[0m \u001b[0mline\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mline\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mb\";\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\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[0m\n\u001b[0;32m 696\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~\\anaconda3\\lib\\socket.py\u001b[0m in \u001b[0;36mreadinto\u001b[1;34m(self, b)\u001b[0m\n\u001b[0;32m 667\u001b[0m \u001b[1;32mwhile\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 668\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--> 669\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sock\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mb\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 670\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 671\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_timeout_occurred\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[1;32m~\\anaconda3\\lib\\ssl.py\u001b[0m in \u001b[0;36mrecv_into\u001b[1;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[0;32m 1239\u001b[0m \u001b[1;34m\"non-zero flags not allowed in calls to recv_into() on %s\"\u001b[0m \u001b[1;33m%\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1240\u001b[0m self.__class__)\n\u001b[1;32m-> 1241\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnbytes\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 1242\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 1243\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbuffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnbytes\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mflags\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\\ssl.py\u001b[0m in \u001b[0;36mread\u001b[1;34m(self, len, buffer)\u001b[0m\n\u001b[0;32m 1097\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[0;32m 1098\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mbuffer\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[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1099\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\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 1100\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 1101\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\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": [ "\n", "\n", "plots=[]\n", "plots_tags=[]\n", "i=12096\n", "for movie in movies.titleId[12096:15000]:\n", " p=[]\n", " re.cookies.clear()\n", " re= req.get(('https://www.imdb.com/title/'+movie+'/keywords'))\n", " soup=BeautifulSoup(re.content, 'html5lib')\n", " \n", " rows= soup.find_all(class_='sodatext')\n", " if len(rows)> 1:\n", " l=min(len(rows),60)\n", " #print(l)\n", " for row in rows[:l]:\n", " p.append(row.get_text().strip())\n", " plots_tags.append(p)\n", " plots.append(' '.join(p))\n", " print(i)\n", " else:\n", " print('zz'+str(i))\n", " plots_tags.append('NaN')\n", " plots.append('NaN')\n", " i+=1\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "55cd6853", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "22c17552", "metadata": {}, "outputs": [], "source": [ "Tags=pd.DataFrame(plots_tags)\n", "tagTexts= pd.DataFrame(plots)" ] }, { "cell_type": "code", "execution_count": null, "id": "1f29929c", "metadata": {}, "outputs": [], "source": [ "tagTexts.to_csv('tagsText.tsv', sep= '\\t', index=False)\n", "Tags.to_csv('plot_tags7.tsv', sep='\\t', index=False)" ] }, { "cell_type": "code", "execution_count": null, "id": "f5f05c69", "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": null, "id": "cc2ddb40", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.8" } }, "nbformat": 4, "nbformat_minor": 5 }