Skip to content

[lab-web-scraping-single-page] João #17

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
joaomatoslopes wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[lab-web-scraping-single-page] João #17

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
297 changes: 297 additions & 0 deletions .ipynb_checkpoints/Lab-Web-Scraping-Single-Page-checkpoint.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,297 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "5da87cb9",
"metadata": {},
"outputs": [],
"source": [
"# Importing library\n",
"import pandas as pd\n",
"import requests\n",
"from bs4 import BeautifulSoup"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "479ead92",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Response [200]>"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# URL\n",
"url = \"https://www.billboard.com/charts/hot-100/\"\n",
"\n",
"# Get the response\n",
"response = requests.get(url)\n",
"response"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b6d709c6",
"metadata": {},
"outputs": [],
"source": [
"# Getting the soup\n",
"soup = BeautifulSoup(response.content, \"html.parser\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "ed4a8144",
"metadata": {},
"outputs": [],
"source": [
"# Finding all by tag and class\n",
"songs = soup.find_all(name = \"h3\", class_ = \"c-title\")\n",
"authors = soup.find_all(name = \"span\", class_ = \"c-label\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "847d3484",
"metadata": {},
"outputs": [],
"source": [
"# Songs\n",
"list_songs = []\n",
"for _ in range(0,100):\n",
" list_songs.append(songs[6+_*4].text.strip())"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "85196d0b",
"metadata": {},
"outputs": [],
"source": [
"# Authors\n",
"list_authors_1 = []\n",
"for _ in range(0,14):\n",
" list_authors_1.append(authors[4+_*8].text.strip())\n",
" \n",
"list_authors_2 = []\n",
"for _ in range(0,43):\n",
" list_authors_2.append(authors[118+_*8].text.strip())\n",
" \n",
"list_authors_3 = []\n",
"for _ in range(0,12):\n",
" list_authors_3.append(authors[464+_*8].text.strip())\n",
" \n",
"list_authors_4 = []\n",
"for _ in range(0,24):\n",
" list_authors_4.append(authors[562+_*8].text.strip())\n",
" \n",
"list_authors_5 = []\n",
"for _ in range(0,5):\n",
" list_authors_5.append(authors[756+_*10].text.strip())\n",
" \n",
"list_authors_6 = []\n",
"for _ in range(0,2):\n",
" list_authors_6.append(authors[804+_*8].text.strip())\n",
" \n",
"list_authors = list_authors_1 + list_authors_2 + list_authors_3 + list_authors_4 + list_authors_5 + list_authors_6"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "8f29ae88",
"metadata": {},
"outputs": [],
"source": [
"# Ranking\n",
"song_rank = []\n",
"for _ in range(1,101):\n",
" song_rank.append(_)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "293cb875",
"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>rank</th>\n",
" <th>song_name</th>\n",
" <th>author_name</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Lovin On Me</td>\n",
" <td>Jack Harlow</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>Cruel Summer</td>\n",
" <td>Taylor Swift</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>Greedy</td>\n",
" <td>Tate McRae</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>Lose Control</td>\n",
" <td>Teddy Swims</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>I Remember Everything</td>\n",
" <td>Zach Bryan Featuring Kacey Musgraves</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>95</th>\n",
" <td>96</td>\n",
" <td>Sensational</td>\n",
" <td>Chris Brown Featuring Davido &amp; Lojay</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>97</td>\n",
" <td>When It Comes To You</td>\n",
" <td>Fridayy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>97</th>\n",
" <td>98</td>\n",
" <td>IDGAF</td>\n",
" <td>Tee Grizzley, Mariah The Scientist &amp; Chris Brown</td>\n",
" </tr>\n",
" <tr>\n",
" <th>98</th>\n",
" <td>99</td>\n",
" <td>Save Me The Trouble</td>\n",
" <td>Dan + Shay</td>\n",
" </tr>\n",
" <tr>\n",
" <th>99</th>\n",
" <td>100</td>\n",
" <td>Red Sky</td>\n",
" <td>21 Savage, Tommy Newport &amp; Mikky Ekko</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>100 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" rank song_name \\\n",
"0 1 Lovin On Me \n",
"1 2 Cruel Summer \n",
"2 3 Greedy \n",
"3 4 Lose Control \n",
"4 5 I Remember Everything \n",
".. ... ... \n",
"95 96 Sensational \n",
"96 97 When It Comes To You \n",
"97 98 IDGAF \n",
"98 99 Save Me The Trouble \n",
"99 100 Red Sky \n",
"\n",
" author_name \n",
"0 Jack Harlow \n",
"1 Taylor Swift \n",
"2 Tate McRae \n",
"3 Teddy Swims \n",
"4 Zach Bryan Featuring Kacey Musgraves \n",
".. ... \n",
"95 Chris Brown Featuring Davido & Lojay \n",
"96 Fridayy \n",
"97 Tee Grizzley, Mariah The Scientist & Chris Brown \n",
"98 Dan + Shay \n",
"99 21 Savage, Tommy Newport & Mikky Ekko \n",
"\n",
"[100 rows x 3 columns]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Dataframe\n",
"df = pd.DataFrame({\n",
" \"rank\" : song_rank,\n",
" \"song_name\" : list_songs,\n",
" \"author_name\" : list_authors\n",
"})\n",
"df"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Loading