Format: application/octet-stream
1 {
2 "cells": [
3 {
4 "cell_type": "code",
5 "execution_count": 1,
6 "id": "d035e38d",
7 "metadata": {},
8 "outputs": [],
9 "source": [
10 "import pandas as pd\n",
11 "import requests as req\n",
12 "from bs4 import BeautifulSoup"
13 ]
14 },
15 {
16 "cell_type": "code",
17 "execution_count": 2,
18 "id": "1169b79b",
19 "metadata": {},
20 "outputs": [],
21 "source": [
22 "movies = pd.read_csv('Final Dataa.tsv', sep='\\t')"
23 ]
24 },
25 {
26 "cell_type": "code",
27 "execution_count": 3,
28 "id": "900ba1f2",
29 "metadata": {},
30 "outputs": [],
31 "source": [
32 "movies=movies[['titleId','title','genres']]"
33 ]
34 },
35 {
36 "cell_type": "code",
37 "execution_count": 4,
38 "id": "fc9f7101",
39 "metadata": {},
40 "outputs": [
41 {
42 "data": {
43 "text/html": [
44 "<div>\n",
45 "<style scoped>\n",
46 " .dataframe tbody tr th:only-of-type {\n",
47 " vertical-align: middle;\n",
48 " }\n",
49 "\n",
50 " .dataframe tbody tr th {\n",
51 " vertical-align: top;\n",
52 " }\n",
53 "\n",
54 " .dataframe thead th {\n",
55 " text-align: right;\n",
56 " }\n",
57 "</style>\n",
58 "<table border=\"1\" class=\"dataframe\">\n",
59 " <thead>\n",
60 " <tr style=\"text-align: right;\">\n",
61 " <th></th>\n",
62 " <th>titleId</th>\n",
63 " <th>title</th>\n",
64 " <th>genres</th>\n",
65 " </tr>\n",
66 " </thead>\n",
67 " <tbody>\n",
68 " <tr>\n",
69 " <th>0</th>\n",
70 " <td>tt0111161</td>\n",
71 " <td>The Shawshank Redemption</td>\n",
72 " <td>Drama</td>\n",
73 " </tr>\n",
74 " <tr>\n",
75 " <th>1</th>\n",
76 " <td>tt0468569</td>\n",
77 " <td>The Dark Knight</td>\n",
78 " <td>Action,Crime,Drama</td>\n",
79 " </tr>\n",
80 " <tr>\n",
81 " <th>2</th>\n",
82 " <td>tt1375666</td>\n",
83 " <td>Inception</td>\n",
84 " <td>Action,Adventure,Sci-Fi</td>\n",
85 " </tr>\n",
86 " <tr>\n",
87 " <th>3</th>\n",
88 " <td>tt0137523</td>\n",
89 " <td>Fight Club</td>\n",
90 " <td>Drama</td>\n",
91 " </tr>\n",
92 " <tr>\n",
93 " <th>4</th>\n",
94 " <td>tt0110912</td>\n",
95 " <td>Pulp Fiction</td>\n",
96 " <td>Crime,Drama</td>\n",
97 " </tr>\n",
98 " <tr>\n",
99 " <th>...</th>\n",
100 " <td>...</td>\n",
101 " <td>...</td>\n",
102 " <td>...</td>\n",
103 " </tr>\n",
104 " <tr>\n",
105 " <th>130713</th>\n",
106 " <td>tt0062253</td>\n",
107 " <td>7 uomini e un cervello</td>\n",
108 " <td>Comedy,Crime</td>\n",
109 " </tr>\n",
110 " <tr>\n",
111 " <th>130714</th>\n",
112 " <td>tt0068885</td>\n",
113 " <td>La lunga cavalcata della vendetta</td>\n",
114 " <td>Drama,Western</td>\n",
115 " </tr>\n",
116 " <tr>\n",
117 " <th>130715</th>\n",
118 " <td>tt2583192</td>\n",
119 " <td>Lucid</td>\n",
120 " <td>Drama,Horror,Thriller</td>\n",
121 " </tr>\n",
122 " <tr>\n",
123 " <th>130716</th>\n",
124 " <td>tt3899070</td>\n",
125 " <td>Gone Tomorrow</td>\n",
126 " <td>Crime,Drama,Mystery</td>\n",
127 " </tr>\n",
128 " <tr>\n",
129 " <th>130717</th>\n",
130 " <td>tt8343748</td>\n",
131 " <td>Seven Senses of the Re'Union</td>\n",
132 " <td>Action,Adventure,Animation</td>\n",
133 " </tr>\n",
134 " </tbody>\n",
135 "</table>\n",
136 "<p>130718 rows × 3 columns</p>\n",
137 "</div>"
138 ],
139 "text/plain": [
140 " titleId title \\\n",
141 "0 tt0111161 The Shawshank Redemption \n",
142 "1 tt0468569 The Dark Knight \n",
143 "2 tt1375666 Inception \n",
144 "3 tt0137523 Fight Club \n",
145 "4 tt0110912 Pulp Fiction \n",
146 "... ... ... \n",
147 "130713 tt0062253 7 uomini e un cervello \n",
148 "130714 tt0068885 La lunga cavalcata della vendetta \n",
149 "130715 tt2583192 Lucid \n",
150 "130716 tt3899070 Gone Tomorrow \n",
151 "130717 tt8343748 Seven Senses of the Re'Union \n",
152 "\n",
153 " genres \n",
154 "0 Drama \n",
155 "1 Action,Crime,Drama \n",
156 "2 Action,Adventure,Sci-Fi \n",
157 "3 Drama \n",
158 "4 Crime,Drama \n",
159 "... ... \n",
160 "130713 Comedy,Crime \n",
161 "130714 Drama,Western \n",
162 "130715 Drama,Horror,Thriller \n",
163 "130716 Crime,Drama,Mystery \n",
164 "130717 Action,Adventure,Animation \n",
165 "\n",
166 "[130718 rows x 3 columns]"
167 ]
168 },
169 "execution_count": 4,
170 "metadata": {},
171 "output_type": "execute_result"
172 }
173 ],
174 "source": [
175 "movies"
176 ]
177 },
178 {
179 "cell_type": "code",
180 "execution_count": 30,
181 "id": "3f4c1736",
182 "metadata": {},
183 "outputs": [
184 {
185 "name": "stdout",
186 "output_type": "stream",
187 "text": [
188 "12096\n",
189 "12097\n"
190 ]
191 },
192 {
193 "ename": "KeyboardInterrupt",
194 "evalue": "",
195 "output_type": "error",
196 "traceback": [
197 "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
198 "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
199 "\u001b[1;32m<ipython-input-30-ade7f124c19f>\u001b[0m in \u001b[0;36m<module>\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",
200 "\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",
201 "\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",
202 "\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",
203 "\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",
204 "\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",
205 "\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",
206 "\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",
207 "\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",
208 "\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",
209 "\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",
210 "\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",
211 "\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",
212 "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
213 ]
214 }
215 ],
216 "source": [
217 "\n",
218 "\n",
219 "plots=[]\n",
220 "plots_tags=[]\n",
221 "i=12096\n",
222 "for movie in movies.titleId[12096:15000]:\n",
223 " p=[]\n",
224 " re.cookies.clear()\n",
225 " re= req.get(('https://www.imdb.com/title/'+movie+'/keywords'))\n",
226 " soup=BeautifulSoup(re.content, 'html5lib')\n",
227 " \n",
228 " rows= soup.find_all(class_='sodatext')\n",
229 " if len(rows)> 1:\n",
230 " l=min(len(rows),60)\n",
231 " #print(l)\n",
232 " for row in rows[:l]:\n",
233 " p.append(row.get_text().strip())\n",
234 " plots_tags.append(p)\n",
235 " plots.append(' '.join(p))\n",
236 " print(i)\n",
237 " else:\n",
238 " print('zz'+str(i))\n",
239 " plots_tags.append('NaN')\n",
240 " plots.append('NaN')\n",
241 " i+=1\n",
242 "\n"
243 ]
244 },
245 {
246 "cell_type": "code",
247 "execution_count": null,
248 "id": "55cd6853",
249 "metadata": {},
250 "outputs": [],
251 "source": []
252 },
253 {
254 "cell_type": "code",
255 "execution_count": null,
256 "id": "22c17552",
257 "metadata": {},
258 "outputs": [],
259 "source": [
260 "Tags=pd.DataFrame(plots_tags)\n",
261 "tagTexts= pd.DataFrame(plots)"
262 ]
263 },
264 {
265 "cell_type": "code",
266 "execution_count": null,
267 "id": "1f29929c",
268 "metadata": {},
269 "outputs": [],
270 "source": [
271 "tagTexts.to_csv('tagsText.tsv', sep= '\\t', index=False)\n",
272 "Tags.to_csv('plot_tags7.tsv', sep='\\t', index=False)"
273 ]
274 },
275 {
276 "cell_type": "code",
277 "execution_count": null,
278 "id": "f5f05c69",
279 "metadata": {},
280 "outputs": [],
281 "source": []
282 },
283 {
284 "cell_type": "code",
285 "execution_count": null,
286 "id": "cc2ddb40",
287 "metadata": {},
288 "outputs": [],
289 "source": []
290 }
291 ],
292 "metadata": {
293 "kernelspec": {
294 "display_name": "Python 3",
295 "language": "python",
296 "name": "python3"
297 },
298 "language_info": {
299 "codemirror_mode": {
300 "name": "ipython",
301 "version": 3
302 },
303 "file_extension": ".py",
304 "mimetype": "text/x-python",
305 "name": "python",
306 "nbconvert_exporter": "python",
307 "pygments_lexer": "ipython3",
308 "version": "3.8.8"
309 }
310 },
311 "nbformat": 4,
312 "nbformat_minor": 5
313 }
314