Format: application/octet-stream
1 {
2 "cells": [
3 {
4 "cell_type": "code",
5 "execution_count": 1,
6 "id": "6f2034b5",
7 "metadata": {},
8 "outputs": [],
9 "source": [
10 "import pandas as pd"
11 ]
12 },
13 {
14 "cell_type": "code",
15 "execution_count": 2,
16 "id": "7b7e56b0",
17 "metadata": {},
18 "outputs": [],
19 "source": [
20 "data=pd.read_csv('Final Dataa.tsv', sep='\\t')\n"
21 ]
22 },
23 {
24 "cell_type": "code",
25 "execution_count": null,
26 "id": "84868654",
27 "metadata": {},
28 "outputs": [],
29 "source": []
30 },
31 {
32 "cell_type": "code",
33 "execution_count": 3,
34 "id": "68b48e83",
35 "metadata": {},
36 "outputs": [
37 {
38 "data": {
39 "text/html": [
40 "<div>\n",
41 "<style scoped>\n",
42 " .dataframe tbody tr th:only-of-type {\n",
43 " vertical-align: middle;\n",
44 " }\n",
45 "\n",
46 " .dataframe tbody tr th {\n",
47 " vertical-align: top;\n",
48 " }\n",
49 "\n",
50 " .dataframe thead th {\n",
51 " text-align: right;\n",
52 " }\n",
53 "</style>\n",
54 "<table border=\"1\" class=\"dataframe\">\n",
55 " <thead>\n",
56 " <tr style=\"text-align: right;\">\n",
57 " <th></th>\n",
58 " <th>Unnamed: 0</th>\n",
59 " <th>titleId</th>\n",
60 " <th>title</th>\n",
61 " <th>averageRating</th>\n",
62 " <th>numVotes</th>\n",
63 " <th>primaryTitle</th>\n",
64 " <th>isAdult</th>\n",
65 " <th>startYear</th>\n",
66 " <th>runtimeMinutes</th>\n",
67 " <th>genres</th>\n",
68 " </tr>\n",
69 " </thead>\n",
70 " <tbody>\n",
71 " <tr>\n",
72 " <th>0</th>\n",
73 " <td>0</td>\n",
74 " <td>tt0111161</td>\n",
75 " <td>The Shawshank Redemption</td>\n",
76 " <td>9.3</td>\n",
77 " <td>2405502</td>\n",
78 " <td>The Shawshank Redemption</td>\n",
79 " <td>0</td>\n",
80 " <td>1994</td>\n",
81 " <td>142</td>\n",
82 " <td>Drama</td>\n",
83 " </tr>\n",
84 " <tr>\n",
85 " <th>1</th>\n",
86 " <td>1</td>\n",
87 " <td>tt0468569</td>\n",
88 " <td>The Dark Knight</td>\n",
89 " <td>9.0</td>\n",
90 " <td>2365212</td>\n",
91 " <td>The Dark Knight</td>\n",
92 " <td>0</td>\n",
93 " <td>2008</td>\n",
94 " <td>152</td>\n",
95 " <td>Action,Crime,Drama</td>\n",
96 " </tr>\n",
97 " <tr>\n",
98 " <th>2</th>\n",
99 " <td>2</td>\n",
100 " <td>tt1375666</td>\n",
101 " <td>Inception</td>\n",
102 " <td>8.8</td>\n",
103 " <td>2122723</td>\n",
104 " <td>Inception</td>\n",
105 " <td>0</td>\n",
106 " <td>2010</td>\n",
107 " <td>148</td>\n",
108 " <td>Action,Adventure,Sci-Fi</td>\n",
109 " </tr>\n",
110 " <tr>\n",
111 " <th>3</th>\n",
112 " <td>3</td>\n",
113 " <td>tt0137523</td>\n",
114 " <td>Fight Club</td>\n",
115 " <td>8.8</td>\n",
116 " <td>1899050</td>\n",
117 " <td>Fight Club</td>\n",
118 " <td>0</td>\n",
119 " <td>1999</td>\n",
120 " <td>139</td>\n",
121 " <td>Drama</td>\n",
122 " </tr>\n",
123 " <tr>\n",
124 " <th>4</th>\n",
125 " <td>4</td>\n",
126 " <td>tt0110912</td>\n",
127 " <td>Pulp Fiction</td>\n",
128 " <td>8.9</td>\n",
129 " <td>1868911</td>\n",
130 " <td>Pulp Fiction</td>\n",
131 " <td>0</td>\n",
132 " <td>1994</td>\n",
133 " <td>154</td>\n",
134 " <td>Crime,Drama</td>\n",
135 " </tr>\n",
136 " <tr>\n",
137 " <th>...</th>\n",
138 " <td>...</td>\n",
139 " <td>...</td>\n",
140 " <td>...</td>\n",
141 " <td>...</td>\n",
142 " <td>...</td>\n",
143 " <td>...</td>\n",
144 " <td>...</td>\n",
145 " <td>...</td>\n",
146 " <td>...</td>\n",
147 " <td>...</td>\n",
148 " </tr>\n",
149 " <tr>\n",
150 " <th>130713</th>\n",
151 " <td>130713</td>\n",
152 " <td>tt0062253</td>\n",
153 " <td>7 uomini e un cervello</td>\n",
154 " <td>4.6</td>\n",
155 " <td>101</td>\n",
156 " <td>Criminal Affair</td>\n",
157 " <td>0</td>\n",
158 " <td>1968</td>\n",
159 " <td>106</td>\n",
160 " <td>Comedy,Crime</td>\n",
161 " </tr>\n",
162 " <tr>\n",
163 " <th>130714</th>\n",
164 " <td>130714</td>\n",
165 " <td>tt0068885</td>\n",
166 " <td>La lunga cavalcata della vendetta</td>\n",
167 " <td>4.6</td>\n",
168 " <td>101</td>\n",
169 " <td>Deadly Trackers</td>\n",
170 " <td>0</td>\n",
171 " <td>1972</td>\n",
172 " <td>92</td>\n",
173 " <td>Drama,Western</td>\n",
174 " </tr>\n",
175 " <tr>\n",
176 " <th>130715</th>\n",
177 " <td>130715</td>\n",
178 " <td>tt2583192</td>\n",
179 " <td>Lucid</td>\n",
180 " <td>4.6</td>\n",
181 " <td>101</td>\n",
182 " <td>Lucid</td>\n",
183 " <td>0</td>\n",
184 " <td>2013</td>\n",
185 " <td>87</td>\n",
186 " <td>Drama,Horror,Thriller</td>\n",
187 " </tr>\n",
188 " <tr>\n",
189 " <th>130716</th>\n",
190 " <td>130716</td>\n",
191 " <td>tt3899070</td>\n",
192 " <td>Gone Tomorrow</td>\n",
193 " <td>4.6</td>\n",
194 " <td>101</td>\n",
195 " <td>Gone Tomorrow</td>\n",
196 " <td>0</td>\n",
197 " <td>2015</td>\n",
198 " <td>90</td>\n",
199 " <td>Crime,Drama,Mystery</td>\n",
200 " </tr>\n",
201 " <tr>\n",
202 " <th>130717</th>\n",
203 " <td>130717</td>\n",
204 " <td>tt8343748</td>\n",
205 " <td>Seven Senses of the Re'Union</td>\n",
206 " <td>4.6</td>\n",
207 " <td>101</td>\n",
208 " <td>Seven Senses of the Re'Union</td>\n",
209 " <td>0</td>\n",
210 " <td>2018</td>\n",
211 " <td>24</td>\n",
212 " <td>Action,Adventure,Animation</td>\n",
213 " </tr>\n",
214 " </tbody>\n",
215 "</table>\n",
216 "<p>130718 rows × 10 columns</p>\n",
217 "</div>"
218 ],
219 "text/plain": [
220 " Unnamed: 0 titleId title \\\n",
221 "0 0 tt0111161 The Shawshank Redemption \n",
222 "1 1 tt0468569 The Dark Knight \n",
223 "2 2 tt1375666 Inception \n",
224 "3 3 tt0137523 Fight Club \n",
225 "4 4 tt0110912 Pulp Fiction \n",
226 "... ... ... ... \n",
227 "130713 130713 tt0062253 7 uomini e un cervello \n",
228 "130714 130714 tt0068885 La lunga cavalcata della vendetta \n",
229 "130715 130715 tt2583192 Lucid \n",
230 "130716 130716 tt3899070 Gone Tomorrow \n",
231 "130717 130717 tt8343748 Seven Senses of the Re'Union \n",
232 "\n",
233 " averageRating numVotes primaryTitle isAdult \\\n",
234 "0 9.3 2405502 The Shawshank Redemption 0 \n",
235 "1 9.0 2365212 The Dark Knight 0 \n",
236 "2 8.8 2122723 Inception 0 \n",
237 "3 8.8 1899050 Fight Club 0 \n",
238 "4 8.9 1868911 Pulp Fiction 0 \n",
239 "... ... ... ... ... \n",
240 "130713 4.6 101 Criminal Affair 0 \n",
241 "130714 4.6 101 Deadly Trackers 0 \n",
242 "130715 4.6 101 Lucid 0 \n",
243 "130716 4.6 101 Gone Tomorrow 0 \n",
244 "130717 4.6 101 Seven Senses of the Re'Union 0 \n",
245 "\n",
246 " startYear runtimeMinutes genres \n",
247 "0 1994 142 Drama \n",
248 "1 2008 152 Action,Crime,Drama \n",
249 "2 2010 148 Action,Adventure,Sci-Fi \n",
250 "3 1999 139 Drama \n",
251 "4 1994 154 Crime,Drama \n",
252 "... ... ... ... \n",
253 "130713 1968 106 Comedy,Crime \n",
254 "130714 1972 92 Drama,Western \n",
255 "130715 2013 87 Drama,Horror,Thriller \n",
256 "130716 2015 90 Crime,Drama,Mystery \n",
257 "130717 2018 24 Action,Adventure,Animation \n",
258 "\n",
259 "[130718 rows x 10 columns]"
260 ]
261 },
262 "execution_count": 3,
263 "metadata": {},
264 "output_type": "execute_result"
265 }
266 ],
267 "source": [
268 "data"
269 ]
270 },
271 {
272 "cell_type": "code",
273 "execution_count": 4,
274 "id": "3437c9b7",
275 "metadata": {},
276 "outputs": [],
277 "source": [
278 "import numpy as np\n",
279 "import requests as req\n",
280 "from bs4 import BeautifulSoup"
281 ]
282 },
283 {
284 "cell_type": "code",
285 "execution_count": null,
286 "id": "16d08cdf",
287 "metadata": {},
288 "outputs": [],
289 "source": []
290 },
291 {
292 "cell_type": "code",
293 "execution_count": 5,
294 "id": "4105e803",
295 "metadata": {},
296 "outputs": [
297 {
298 "name": "stdout",
299 "output_type": "stream",
300 "text": [
301 "1\n",
302 "2\n",
303 "3\n",
304 "4\n",
305 "5\n",
306 "6\n",
307 "zz7\n",
308 "8\n",
309 "9\n",
310 "10\n",
311 "11\n",
312 "12\n",
313 "13\n",
314 "zz14\n",
315 "15\n",
316 "16\n",
317 "17\n",
318 "18\n",
319 "19\n",
320 "20\n",
321 "21\n",
322 "22\n",
323 "23\n",
324 "24\n",
325 "25\n",
326 "26\n",
327 "27\n",
328 "28\n",
329 "29\n",
330 "30\n",
331 "31\n",
332 "32\n",
333 "33\n",
334 "34\n",
335 "35\n",
336 "36\n",
337 "37\n",
338 "38\n",
339 "39\n",
340 "40\n",
341 "41\n",
342 "42\n",
343 "43\n",
344 "44\n",
345 "45\n",
346 "46\n",
347 "47\n",
348 "48\n",
349 "49\n",
350 "50\n",
351 "51\n",
352 "52\n",
353 "53\n",
354 "54\n",
355 "55\n",
356 "56\n",
357 "57\n",
358 "58\n",
359 "59\n",
360 "60\n",
361 "61\n",
362 "62\n",
363 "63\n",
364 "64\n",
365 "65\n",
366 "66\n",
367 "67\n",
368 "68\n",
369 "69\n",
370 "70\n",
371 "zz71\n",
372 "72\n",
373 "73\n",
374 "zz74\n",
375 "zz75\n",
376 "76\n",
377 "77\n",
378 "78\n",
379 "zz79\n",
380 "80\n",
381 "81\n",
382 "82\n",
383 "83\n",
384 "84\n",
385 "85\n",
386 "86\n",
387 "87\n",
388 "88\n",
389 "89\n",
390 "90\n",
391 "91\n",
392 "92\n",
393 "93\n",
394 "94\n",
395 "95\n",
396 "96\n",
397 "97\n",
398 "98\n",
399 "99\n",
400 "100\n",
401 "101\n",
402 "102\n",
403 "103\n",
404 "104\n",
405 "105\n",
406 "106\n",
407 "107\n",
408 "zz108\n",
409 "109\n",
410 "110\n",
411 "111\n",
412 "112\n",
413 "113\n",
414 "114\n",
415 "115\n",
416 "116\n",
417 "117\n",
418 "118\n",
419 "119\n",
420 "120\n",
421 "121\n",
422 "122\n",
423 "123\n",
424 "124\n",
425 "125\n",
426 "126\n",
427 "127\n",
428 "128\n",
429 "129\n",
430 "130\n",
431 "131\n",
432 "132\n",
433 "133\n",
434 "134\n",
435 "135\n",
436 "136\n",
437 "zz137\n",
438 "138\n",
439 "139\n",
440 "140\n",
441 "141\n",
442 "142\n",
443 "143\n",
444 "144\n",
445 "145\n",
446 "146\n",
447 "147\n",
448 "148\n",
449 "149\n",
450 "150\n",
451 "151\n",
452 "152\n",
453 "153\n",
454 "154\n",
455 "155\n",
456 "156\n",
457 "157\n",
458 "158\n",
459 "159\n",
460 "160\n",
461 "zz161\n",
462 "162\n",
463 "163\n",
464 "164\n",
465 "165\n",
466 "166\n",
467 "167\n",
468 "168\n",
469 "169\n",
470 "170\n",
471 "171\n",
472 "172\n",
473 "173\n",
474 "174\n",
475 "175\n",
476 "176\n",
477 "177\n",
478 "178\n",
479 "179\n",
480 "180\n",
481 "181\n",
482 "182\n",
483 "183\n",
484 "184\n",
485 "185\n",
486 "186\n",
487 "187\n",
488 "188\n",
489 "189\n",
490 "190\n",
491 "191\n",
492 "192\n",
493 "zz193\n",
494 "194\n",
495 "195\n",
496 "196\n",
497 "197\n",
498 "198\n",
499 "199\n",
500 "200\n",
501 "201\n",
502 "202\n",
503 "203\n",
504 "204\n",
505 "205\n",
506 "206\n",
507 "207\n",
508 "208\n",
509 "209\n",
510 "210\n",
511 "211\n",
512 "212\n",
513 "213\n",
514 "214\n",
515 "215\n",
516 "216\n",
517 "217\n",
518 "218\n",
519 "219\n",
520 "220\n",
521 "221\n",
522 "222\n",
523 "223\n",
524 "224\n",
525 "225\n",
526 "226\n",
527 "227\n",
528 "228\n",
529 "229\n",
530 "230\n",
531 "231\n",
532 "232\n",
533 "233\n",
534 "234\n",
535 "235\n",
536 "236\n",
537 "237\n",
538 "zz238\n",
539 "239\n",
540 "240\n",
541 "241\n",
542 "242\n",
543 "243\n",
544 "zz244\n",
545 "245\n",
546 "246\n",
547 "247\n",
548 "248\n",
549 "249\n",
550 "250\n",
551 "251\n",
552 "252\n",
553 "253\n",
554 "254\n",
555 "255\n",
556 "256\n",
557 "257\n",
558 "258\n",
559 "259\n",
560 "260\n",
561 "zz261\n",
562 "262\n",
563 "263\n",
564 "264\n",
565 "265\n",
566 "266\n",
567 "267\n",
568 "268\n",
569 "269\n",
570 "270\n",
571 "zz271\n",
572 "272\n",
573 "273\n",
574 "274\n",
575 "275\n",
576 "276\n",
577 "277\n",
578 "278\n",
579 "279\n",
580 "280\n",
581 "281\n",
582 "zz282\n",
583 "283\n",
584 "284\n",
585 "285\n",
586 "286\n",
587 "287\n",
588 "288\n",
589 "289\n",
590 "290\n",
591 "291\n",
592 "292\n",
593 "293\n",
594 "294\n",
595 "295\n",
596 "296\n",
597 "297\n",
598 "298\n",
599 "zz299\n",
600 "300\n",
601 "301\n",
602 "302\n",
603 "303\n",
604 "304\n",
605 "305\n",
606 "306\n",
607 "307\n",
608 "308\n",
609 "309\n",
610 "310\n",
611 "zz311\n",
612 "312\n",
613 "zz313\n",
614 "314\n",
615 "315\n",
616 "316\n",
617 "317\n",
618 "318\n",
619 "319\n",
620 "320\n",
621 "321\n",
622 "322\n",
623 "323\n",
624 "324\n",
625 "325\n",
626 "326\n",
627 "327\n",
628 "328\n",
629 "329\n",
630 "330\n",
631 "331\n",
632 "332\n",
633 "333\n",
634 "334\n",
635 "335\n",
636 "336\n",
637 "337\n",
638 "338\n",
639 "zz339\n",
640 "340\n",
641 "341\n",
642 "342\n",
643 "343\n",
644 "344\n",
645 "345\n",
646 "346\n",
647 "347\n",
648 "348\n",
649 "349\n",
650 "350\n",
651 "351\n",
652 "352\n",
653 "353\n",
654 "354\n",
655 "zz355\n",
656 "356\n",
657 "357\n",
658 "358\n",
659 "359\n",
660 "360\n",
661 "361\n",
662 "362\n",
663 "363\n",
664 "364\n",
665 "365\n",
666 "366\n",
667 "367\n",
668 "368\n",
669 "zz369\n",
670 "370\n",
671 "371\n",
672 "372\n",
673 "373\n",
674 "374\n",
675 "zz375\n",
676 "376\n",
677 "377\n",
678 "378\n",
679 "379\n",
680 "380\n",
681 "381\n",
682 "382\n",
683 "383\n",
684 "384\n",
685 "385\n",
686 "386\n",
687 "zz387\n",
688 "388\n",
689 "389\n",
690 "390\n",
691 "391\n",
692 "392\n",
693 "393\n",
694 "394\n",
695 "395\n",
696 "396\n",
697 "397\n",
698 "398\n",
699 "399\n",
700 "400\n",
701 "401\n",
702 "402\n",
703 "403\n",
704 "404\n",
705 "405\n",
706 "406\n",
707 "407\n",
708 "408\n",
709 "zz409\n",
710 "410\n",
711 "411\n",
712 "412\n",
713 "413\n",
714 "414\n",
715 "415\n",
716 "416\n",
717 "417\n",
718 "418\n",
719 "419\n",
720 "420\n",
721 "421\n",
722 "422\n",
723 "423\n",
724 "424\n",
725 "zz425\n",
726 "zz426\n",
727 "427\n",
728 "zz428\n",
729 "zz429\n",
730 "430\n",
731 "zz431\n",
732 "432\n",
733 "433\n",
734 "434\n",
735 "435\n",
736 "436\n",
737 "437\n",
738 "438\n",
739 "439\n",
740 "440\n",
741 "441\n",
742 "442\n",
743 "443\n",
744 "444\n",
745 "445\n",
746 "446\n",
747 "447\n",
748 "448\n",
749 "449\n",
750 "450\n",
751 "451\n",
752 "452\n",
753 "453\n",
754 "454\n",
755 "455\n",
756 "456\n",
757 "457\n",
758 "458\n",
759 "459\n",
760 "460\n",
761 "461\n",
762 "462\n",
763 "463\n",
764 "464\n",
765 "465\n",
766 "466\n",
767 "467\n",
768 "468\n",
769 "469\n",
770 "470\n",
771 "471\n",
772 "472\n",
773 "473\n",
774 "474\n",
775 "475\n",
776 "476\n",
777 "477\n",
778 "478\n",
779 "479\n",
780 "zz480\n",
781 "481\n",
782 "482\n",
783 "zz483\n",
784 "484\n",
785 "485\n",
786 "486\n",
787 "487\n",
788 "488\n",
789 "489\n",
790 "490\n",
791 "zz491\n",
792 "zz492\n",
793 "493\n",
794 "494\n",
795 "495\n",
796 "496\n",
797 "497\n",
798 "498\n",
799 "499\n",
800 "500\n",
801 "501\n",
802 "502\n",
803 "503\n",
804 "504\n",
805 "zz505\n",
806 "506\n",
807 "507\n",
808 "508\n",
809 "509\n",
810 "510\n",
811 "511\n",
812 "512\n",
813 "513\n",
814 "514\n",
815 "515\n",
816 "516\n",
817 "zz517\n",
818 "518\n",
819 "519\n",
820 "520\n",
821 "521\n",
822 "522\n",
823 "zz523\n",
824 "zz524\n",
825 "525\n",
826 "526\n",
827 "zz527\n",
828 "528\n",
829 "529\n",
830 "530\n",
831 "531\n",
832 "532\n",
833 "533\n",
834 "534\n",
835 "535\n",
836 "536\n",
837 "537\n",
838 "538\n",
839 "539\n",
840 "540\n",
841 "541\n",
842 "542\n",
843 "543\n",
844 "544\n",
845 "zz545\n",
846 "546\n",
847 "547\n",
848 "zz548\n",
849 "549\n",
850 "550\n",
851 "551\n",
852 "552\n",
853 "553\n",
854 "554\n",
855 "555\n",
856 "zz556\n",
857 "557\n",
858 "558\n",
859 "559\n",
860 "560\n",
861 "561\n",
862 "562\n",
863 "zz563\n",
864 "564\n",
865 "565\n",
866 "566\n",
867 "567\n",
868 "568\n",
869 "569\n",
870 "570\n",
871 "571\n",
872 "572\n",
873 "573\n",
874 "574\n",
875 "zz575\n",
876 "576\n",
877 "577\n",
878 "578\n",
879 "579\n",
880 "580\n",
881 "581\n",
882 "582\n",
883 "583\n",
884 "584\n",
885 "585\n",
886 "586\n",
887 "587\n",
888 "588\n",
889 "589\n",
890 "590\n",
891 "591\n",
892 "592\n",
893 "593\n",
894 "594\n",
895 "595\n",
896 "596\n",
897 "597\n",
898 "zz598\n",
899 "599\n",
900 "600\n",
901 "601\n",
902 "602\n",
903 "603\n",
904 "604\n",
905 "605\n",
906 "606\n",
907 "607\n",
908 "608\n",
909 "609\n",
910 "zz610\n",
911 "611\n",
912 "612\n",
913 "613\n",
914 "614\n",
915 "zz615\n",
916 "616\n",
917 "617\n",
918 "618\n",
919 "619\n",
920 "620\n",
921 "621\n",
922 "622\n",
923 "623\n",
924 "624\n",
925 "625\n",
926 "626\n",
927 "627\n",
928 "628\n",
929 "629\n",
930 "630\n",
931 "631\n"
932 ]
933 },
934 {
935 "ename": "KeyboardInterrupt",
936 "evalue": "",
937 "output_type": "error",
938 "traceback": [
939 "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
940 "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
941 "\u001b[1;32m<ipython-input-5-768a82e690ef>\u001b[0m in \u001b[0;36m<module>\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",
942 "\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",
943 "\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",
944 "\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",
945 "\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",
946 "\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",
947 "\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",
948 "\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",
949 "\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",
950 "\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",
951 "\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",
952 "\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",
953 "\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",
954 "\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",
955 "\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",
956 "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
957 ]
958 }
959 ],
960 "source": [
961 "directors=[]\n",
962 "writer_actor=[]\n",
963 "earned=[]\n",
964 "j=1\n",
965 "for i in data.titleId:\n",
966 " content=[]\n",
967 " r= req.get('https://www.imdb.com/title/'+i)\n",
968 " soup=BeautifulSoup(r.content, 'html5lib')\n",
969 " r.cookies.clear()\n",
970 " rows= soup.find_all(class_='ipc-metadata-list-item__list-content-item')\n",
971 " if len(rows)>1:\n",
972 " for i in rows:\n",
973 " content.append(i.get_text().strip())\n",
974 " directors.append(content[0].strip())\n",
975 " writer_actor.append(list(set(content[1:10])))\n",
976 " nums=[]\n",
977 " for i in content[-15:]:\n",
978 " \n",
979 " num= i.replace(',','').replace('$','').replace('(estimated)','')\n",
980 " try:\n",
981 " nums.append(int(num))\n",
982 " except:\n",
983 " continue\n",
984 " \n",
985 " if len(nums) > 1:\n",
986 " print(j)\n",
987 " earned.append(max(nums))\n",
988 " else:\n",
989 " print('zz'+str(j))\n",
990 " earned.append('NaN')\n",
991 " \n",
992 " else:\n",
993 " print('z'+str(j))\n",
994 " directors.append(np.nan)\n",
995 " writer_actor.append(np.nan)\n",
996 " j+=1"
997 ]
998 },
999 {
1000 "cell_type": "code",
1001 "execution_count": null,
1002 "id": "8d8a9d77",
1003 "metadata": {},
1004 "outputs": [],
1005 "source": []
1006 },
1007 {
1008 "cell_type": "code",
1009 "execution_count": null,
1010 "id": "10d5adb7",
1011 "metadata": {},
1012 "outputs": [],
1013 "source": []
1014 },
1015 {
1016 "cell_type": "code",
1017 "execution_count": 6,
1018 "id": "2cfa1e5d",
1019 "metadata": {},
1020 "outputs": [],
1021 "source": [
1022 "directors=pd.DataFrame(directors)\n",
1023 "writer_actor= pd.DataFrame(writer_actor)"
1024 ]
1025 },
1026 {
1027 "cell_type": "code",
1028 "execution_count": 7,
1029 "id": "836f83c9",
1030 "metadata": {},
1031 "outputs": [],
1032 "source": [
1033 "directors.to_csv('directors.tsv', sep='\\t')\n",
1034 "writer_actor.to_csv('writer_actor.tsv', sep= '\\t')"
1035 ]
1036 },
1037 {
1038 "cell_type": "code",
1039 "execution_count": null,
1040 "id": "5a5fdd45",
1041 "metadata": {},
1042 "outputs": [],
1043 "source": []
1044 }
1045 ],
1046 "metadata": {
1047 "kernelspec": {
1048 "display_name": "Python 3",
1049 "language": "python",
1050 "name": "python3"
1051 }
1052 },
1053 "nbformat": 4,
1054 "nbformat_minor": 5
1055 }
1056