sending files

web-scraping-single-page.ipynb

@@ -0,0 +1,218 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<Response [200]>"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "from bs4 import BeautifulSoup\n",
+    "\n",
+    "import requests\n",
+    "\n",
+    "url = 'https://www.billboard.com/charts/hot-100/'\n",
+    "\n",
+    "response = requests.get(url)\n",
+    "response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "soup = BeautifulSoup(response.content, 'html.parser')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "100"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "artist_tags = soup.find_all('span', class_ = 'lrv-u-font-size-14@mobile-max')\n",
+    "\n",
+    "artists = []\n",
+    "for artist in artist_tags:\n",
+    "    artists.append(artist.getText().strip())\n",
+    "    \n",
+    "len(artists)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.DataFrame({\n",
+    "    'song': songs,\n",
+    "    'artist': artists\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>song</th>\n",
+       "      <th>artist</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Additional Awards</td>\n",
+       "      <td>Shaboozey</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>Post Malone Featuring Morgan Wallen</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>Kendrick Lamar</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>Sabrina Carpenter</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>Tommy Richman</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>David Guetta &amp; OneRepublic</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>96</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>Taylor Swift</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>97</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>Billie Eilish</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>98</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>Charli XCX With Lorde</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>99</th>\n",
+       "      <td>Imprint/Promotion Label:</td>\n",
+       "      <td>The Red Clay Strays</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>100 rows × 2 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                        song                               artist\n",
+       "0          Additional Awards                            Shaboozey\n",
+       "1   Imprint/Promotion Label:  Post Malone Featuring Morgan Wallen\n",
+       "2   Imprint/Promotion Label:                       Kendrick Lamar\n",
+       "3   Imprint/Promotion Label:                    Sabrina Carpenter\n",
+       "4   Imprint/Promotion Label:                        Tommy Richman\n",
+       "..                       ...                                  ...\n",
+       "95  Imprint/Promotion Label:           David Guetta & OneRepublic\n",
+       "96  Imprint/Promotion Label:                         Taylor Swift\n",
+       "97  Imprint/Promotion Label:                        Billie Eilish\n",
+       "98  Imprint/Promotion Label:                Charli XCX With Lorde\n",
+       "99  Imprint/Promotion Label:                  The Red Clay Strays\n",
+       "\n",
+       "[100 rows x 2 columns]"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "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": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}