project-data-extraction[Agustin-Sanchez]

Project2-WebScraping.ipynb

@@ -0,0 +1,167 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 232,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "import sys\n",
+    "import requests\n",
+    "from pathlib import Path\n",
+    "\n",
+    "from bs4 import BeautifulSoup\n",
+    "\n",
+    "from selenium import webdriver\n",
+    "from selenium.webdriver.common.keys import Keys\n",
+    "from selenium.webdriver.common.action_chains import ActionChains\n",
+    "from selenium.common.exceptions import NoSuchElementException"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 233,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "driver = webdriver.Firefox(executable_path=r'C:\\Program Files\\geckodriver-v0.29.1-win64\\geckodriver.exe')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 241,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_movies(name: str):\n",
+    "    \n",
+    "    driver = webdriver.Firefox(executable_path=r'C:\\Program Files\\geckodriver-v0.29.1-win64\\geckodriver.exe')\n",
+    "    driver.get(\"https://www.imdb.com/\")\n",
+    "    \n",
+    "    time.sleep(1)\n",
+    "    elem = driver.find_element_by_name(\"q\")\n",
+    "    elem.clear()\n",
+    "    elem.send_keys(name)\n",
+    "    elem.send_keys(Keys.RETURN)\n",
+    "    \n",
+    "    time.sleep(1)\n",
+    "    try:\n",
+    "        element = driver.find_element_by_partial_link_text(name)\n",
+    "        element.click()\n",
+    "    except NoSuchElementException: \n",
+    "        driver.close()\n",
+    "        return 'Could not find actor/actress'\n",
+    "        \n",
+    "    time.sleep(1)\n",
+    "    page_source = driver.page_source\n",
+    "    \n",
+    "    time.sleep(1)\n",
+    "    driver.close()\n",
+    "    \n",
+    "    world_selection = BeautifulSoup(page_source, 'lxml')\n",
+    "    movie_source = world_selection.find('div', class_='filmo-category-section')\n",
+    "    movie_list = re.findall(r'>(.*?)<', str(movie_source))\n",
+    "    movies = [i for i in movie_list if i != '']\n",
+    "    \n",
+    "    return movies\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 243,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Big Bug Man',\n",
+       " 'completed',\n",
+       " 'Superman II: The Richard Donner Cut',\n",
+       " 'The Godfather',\n",
+       " 'Michael Jackson: You Rock My World',\n",
+       " 'The Score',\n",
+       " 'Free Money',\n",
+       " 'The Brave',\n",
+       " 'The Island of Dr. Moreau',\n",
+       " 'Divine Rapture',\n",
+       " 'Don Juan DeMarco',\n",
+       " 'Christopher Columbus: The Discovery',\n",
+       " 'The Freshman',\n",
+       " 'A Dry White Season',\n",
+       " 'The Formula',\n",
+       " 'Apocalypse Now',\n",
+       " 'Roots: The Next Generations',\n",
+       " 'Part VII (1960-1967)',\n",
+       " 'Superman',\n",
+       " 'The Godfather Saga',\n",
+       " 'Episode #1.4',\n",
+       " 'Episode #1.3',\n",
+       " 'Episode #1.2',\n",
+       " 'Episode #1.1',\n",
+       " 'The Missouri Breaks',\n",
+       " 'Last Tango in Paris',\n",
+       " 'The Godfather',\n",
+       " 'The Nightcomers',\n",
+       " 'Burn!',\n",
+       " 'The Night of the Following Day',\n",
+       " 'Candy',\n",
+       " 'Reflections in a Golden Eye',\n",
+       " 'A Countess from Hong Kong',\n",
+       " 'The Appaloosa',\n",
+       " 'The Chase',\n",
+       " 'Morituri',\n",
+       " 'Bedtime Story',\n",
+       " 'The Ugly American',\n",
+       " 'Mutiny on the Bounty',\n",
+       " 'One-Eyed Jacks',\n",
+       " 'The Fugitive Kind',\n",
+       " 'The Young Lions',\n",
+       " 'Sayonara',\n",
+       " 'The Teahouse of the August Moon',\n",
+       " 'Guys and Dolls',\n",
+       " 'Omnibus',\n",
+       " 'Advice to Bathers',\n",
+       " 'Désirée',\n",
+       " 'On the Waterfront',\n",
+       " 'The Wild One',\n",
+       " 'Julius Caesar',\n",
+       " 'Viva Zapata!',\n",
+       " 'A Streetcar Named Desire',\n",
+       " 'The Men',\n",
+       " \"Actor's Studio\",\n",
+       " \"I'm No Hero\"]"
+      ]
+     },
+     "execution_count": 243,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "get_movies('Marlon Brando')"
+   ]
+  }
+ ],
+ "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": "3.8.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}