From d43d40b25d96cb7f7c6d286d7789e9029100b5c1 Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Thu, 13 Apr 2023 22:41:10 -0500 Subject: [PATCH 1/9] venv --- instructions.md | 6 ++++++ 1 file changed, 6 insertions(+) create mode 100644 instructions.md diff --git a/instructions.md b/instructions.md new file mode 100644 index 0000000..32191e7 --- /dev/null +++ b/instructions.md @@ -0,0 +1,6 @@ +# Instructions + +- Activate venv with ```source venv/bin/activate``` on macOS +- ```venv\Scripts\activate``` on Windows. + + From d5f32d429af94f1c25b2ecb5bc71481461e0237d Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Thu, 13 Apr 2023 22:46:25 -0500 Subject: [PATCH 2/9] scaffold --- src/__init__.py | 0 src/scraper.py | 0 2 files changed, 0 insertions(+), 0 deletions(-) create mode 100644 src/__init__.py create mode 100644 src/scraper.py diff --git a/src/__init__.py b/src/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/src/scraper.py b/src/scraper.py new file mode 100644 index 0000000..e69de29 From c6e2c559295b2dd185dac78abddcbae712e1ec51 Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Thu, 13 Apr 2023 22:47:56 -0500 Subject: [PATCH 3/9] updated ignore --- .gitignore | 19 +++++++++++++++++++ requirements.txt | 2 ++ 2 files changed, 21 insertions(+) create mode 100644 .gitignore create mode 100644 requirements.txt diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..cbe96eb --- /dev/null +++ b/.gitignore @@ -0,0 +1,19 @@ +# Virtual environment +venv/ + +# Python cache files +__pycache__/ +*.pyc +*.pyo +*.pyd +*.pyc + +# Jupyter Notebook files +.ipynb_checkpoints/ + +# Collected data files (optional, if you don't want to track data files in Git) +data/ + +# OS generated files +.DS_Store +Thumbs.db diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..1f3e778 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,2 @@ +beautifulsoup4 +requests From f783af6f2d75bda08a1eb4ec53a267bae70b782c Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Thu, 13 Apr 2023 22:52:18 -0500 Subject: [PATCH 4/9] nba facts --- NBAfacts.md | 9 +++++++++ 1 file changed, 9 insertions(+) create mode 100644 NBAfacts.md diff --git a/NBAfacts.md b/NBAfacts.md new file mode 100644 index 0000000..b474675 --- /dev/null +++ b/NBAfacts.md @@ -0,0 +1,9 @@ +# NBA Fun Facts to explore. + +## 2017-2018 Rockets + +- Record 65-17. 1st in NBA conference. +- NBA 2018 Playoffs: + - Won NBA Western Conference First Round (4-1) versus Minnesota Timberwolves (Series Stats) + - Won NBA Western Conference Semifinals (4-1) versus Utah Jazz (Series Stats) + - Lost NBA Western Conference Finals (3-4) versus Golden State Warriors (Series Stats) From 6ecf1ddddbdee1edd7be68aecc4dd293021241eb Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Thu, 13 Apr 2023 23:09:52 -0500 Subject: [PATCH 5/9] bball scrape rows complete --- src/scraper.py | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/src/scraper.py b/src/scraper.py index e69de29..ef47cc2 100644 --- a/src/scraper.py +++ b/src/scraper.py @@ -0,0 +1,13 @@ +import requests +from bs4 import BeautifulSoup + +url = 'https://www.basketball-reference.com/teams/HOU/2018.html' +response = requests.get(url) + +soup = BeautifulSoup(response.text, "html.parser") + +table = soup.find("table", {"id": "per_game"}) +rows = table.find_all("tr") + + +# print(rows) \ No newline at end of file From d51458136625f8dc48763cb8a07baa311a584e77 Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Thu, 13 Apr 2023 23:36:41 -0500 Subject: [PATCH 6/9] scrapping success :D --- src/scraper.py | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/src/scraper.py b/src/scraper.py index ef47cc2..e717ce5 100644 --- a/src/scraper.py +++ b/src/scraper.py @@ -1,5 +1,7 @@ import requests from bs4 import BeautifulSoup +import csv +import os url = 'https://www.basketball-reference.com/teams/HOU/2018.html' response = requests.get(url) @@ -7,7 +9,27 @@ response = requests.get(url) soup = BeautifulSoup(response.text, "html.parser") table = soup.find("table", {"id": "per_game"}) -rows = table.find_all("tr") +# rows = table.find_all("tr") +header_row = table.find("thead").find("tr") +rows = table.find("tbody").find_all("tr") +# Extract coloumn headers +headers = [col.text.strip() for col in header_row.find_all("th")][1:] -# print(rows) \ No newline at end of file +# add coloumn headers to the data list +data = [headers] + +# extract rows of data into proper column with headers. + +for row in rows: + cols = row.find_all("td") + cols = [col.text.strip() for col in cols] + data.append(cols) + + +script_dir = os.path.dirname(os.path.abspath(__file__)) +output_path = os.path.join(script_dir, '..', 'data', 'output.csv') + +with open(output_path, "w", newline="") as csvfile: + writer = csv.writer(csvfile) + writer.writerows(data) \ No newline at end of file From 9d899226972936a6ee87149d18088d91f6a4e954 Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Thu, 13 Apr 2023 23:54:10 -0500 Subject: [PATCH 7/9] JSON scraper works --- src/scraper.py | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-) diff --git a/src/scraper.py b/src/scraper.py index e717ce5..c9edaef 100644 --- a/src/scraper.py +++ b/src/scraper.py @@ -1,6 +1,7 @@ import requests from bs4 import BeautifulSoup import csv +import json import os url = 'https://www.basketball-reference.com/teams/HOU/2018.html' @@ -16,20 +17,30 @@ rows = table.find("tbody").find_all("tr") # Extract coloumn headers headers = [col.text.strip() for col in header_row.find_all("th")][1:] -# add coloumn headers to the data list -data = [headers] - -# extract rows of data into proper column with headers. +# extract rows as dictionaries +data = [] for row in rows: cols = row.find_all("td") cols = [col.text.strip() for col in cols] - data.append(cols) - + row_dict = dict(zip(headers, cols)) + data.append(row_dict) +## locate current directory script_dir = os.path.dirname(os.path.abspath(__file__)) -output_path = os.path.join(script_dir, '..', 'data', 'output.csv') -with open(output_path, "w", newline="") as csvfile: - writer = csv.writer(csvfile) - writer.writerows(data) \ No newline at end of file +## CSV file + +csv_output_path = os.path.join(script_dir, '..', 'data', 'output.csv') + +with open(csv_output_path, "w", newline="") as csvfile: + writer = csv.DictWriter(csvfile, fieldnames =headers) + writer.writeheader() + for row in data: + writer.writerow(row) + +# Save as JSON + +json_output_path = os.path.join(script_dir, '..', 'data', 'output.json') +with open(json_output_path, 'w') as jsonfile: + json.dump(data, jsonfile) \ No newline at end of file From 5651909552f92f9f91db9a92368bf075c558a3ba Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Fri, 14 Apr 2023 00:08:34 -0500 Subject: [PATCH 8/9] django init --- manage.py | 22 ++++++++ nba_stats/__init__.py | 0 nba_stats/asgi.py | 16 ++++++ nba_stats/settings.py | 123 ++++++++++++++++++++++++++++++++++++++++++ nba_stats/urls.py | 22 ++++++++ nba_stats/wsgi.py | 16 ++++++ src/scraper.py | 2 + 7 files changed, 201 insertions(+) create mode 100755 manage.py create mode 100644 nba_stats/__init__.py create mode 100644 nba_stats/asgi.py create mode 100644 nba_stats/settings.py create mode 100644 nba_stats/urls.py create mode 100644 nba_stats/wsgi.py diff --git a/manage.py b/manage.py new file mode 100755 index 0000000..2bdc83c --- /dev/null +++ b/manage.py @@ -0,0 +1,22 @@ +#!/usr/bin/env python +"""Django's command-line utility for administrative tasks.""" +import os +import sys + + +def main(): + """Run administrative tasks.""" + os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'nba_stats.settings') + try: + from django.core.management import execute_from_command_line + except ImportError as exc: + raise ImportError( + "Couldn't import Django. Are you sure it's installed and " + "available on your PYTHONPATH environment variable? Did you " + "forget to activate a virtual environment?" + ) from exc + execute_from_command_line(sys.argv) + + +if __name__ == '__main__': + main() diff --git a/nba_stats/__init__.py b/nba_stats/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/nba_stats/asgi.py b/nba_stats/asgi.py new file mode 100644 index 0000000..c7e9578 --- /dev/null +++ b/nba_stats/asgi.py @@ -0,0 +1,16 @@ +""" +ASGI config for nba_stats project. + +It exposes the ASGI callable as a module-level variable named ``application``. + +For more information on this file, see +https://docs.djangoproject.com/en/4.2/howto/deployment/asgi/ +""" + +import os + +from django.core.asgi import get_asgi_application + +os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'nba_stats.settings') + +application = get_asgi_application() diff --git a/nba_stats/settings.py b/nba_stats/settings.py new file mode 100644 index 0000000..5320c25 --- /dev/null +++ b/nba_stats/settings.py @@ -0,0 +1,123 @@ +""" +Django settings for nba_stats project. + +Generated by 'django-admin startproject' using Django 4.2. + +For more information on this file, see +https://docs.djangoproject.com/en/4.2/topics/settings/ + +For the full list of settings and their values, see +https://docs.djangoproject.com/en/4.2/ref/settings/ +""" + +from pathlib import Path + +# Build paths inside the project like this: BASE_DIR / 'subdir'. +BASE_DIR = Path(__file__).resolve().parent.parent + + +# Quick-start development settings - unsuitable for production +# See https://docs.djangoproject.com/en/4.2/howto/deployment/checklist/ + +# SECURITY WARNING: keep the secret key used in production secret! +SECRET_KEY = 'django-insecure-sww_z^4ek6_2vly0_hcwvapk4j(-5&v#$8dh*2_2m%=6@izeqj' + +# SECURITY WARNING: don't run with debug turned on in production! +DEBUG = True + +ALLOWED_HOSTS = [] + + +# Application definition + +INSTALLED_APPS = [ + 'django.contrib.admin', + 'django.contrib.auth', + 'django.contrib.contenttypes', + 'django.contrib.sessions', + 'django.contrib.messages', + 'django.contrib.staticfiles', +] + +MIDDLEWARE = [ + 'django.middleware.security.SecurityMiddleware', + 'django.contrib.sessions.middleware.SessionMiddleware', + 'django.middleware.common.CommonMiddleware', + 'django.middleware.csrf.CsrfViewMiddleware', + 'django.contrib.auth.middleware.AuthenticationMiddleware', + 'django.contrib.messages.middleware.MessageMiddleware', + 'django.middleware.clickjacking.XFrameOptionsMiddleware', +] + +ROOT_URLCONF = 'nba_stats.urls' + +TEMPLATES = [ + { + 'BACKEND': 'django.template.backends.django.DjangoTemplates', + 'DIRS': [], + 'APP_DIRS': True, + 'OPTIONS': { + 'context_processors': [ + 'django.template.context_processors.debug', + 'django.template.context_processors.request', + 'django.contrib.auth.context_processors.auth', + 'django.contrib.messages.context_processors.messages', + ], + }, + }, +] + +WSGI_APPLICATION = 'nba_stats.wsgi.application' + + +# Database +# https://docs.djangoproject.com/en/4.2/ref/settings/#databases + +DATABASES = { + 'default': { + 'ENGINE': 'django.db.backends.sqlite3', + 'NAME': BASE_DIR / 'db.sqlite3', + } +} + + +# Password validation +# https://docs.djangoproject.com/en/4.2/ref/settings/#auth-password-validators + +AUTH_PASSWORD_VALIDATORS = [ + { + 'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator', + }, + { + 'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator', + }, + { + 'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator', + }, + { + 'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator', + }, +] + + +# Internationalization +# https://docs.djangoproject.com/en/4.2/topics/i18n/ + +LANGUAGE_CODE = 'en-us' + +TIME_ZONE = 'UTC' + +USE_I18N = True + +USE_TZ = True + + +# Static files (CSS, JavaScript, Images) +# https://docs.djangoproject.com/en/4.2/howto/static-files/ + +STATIC_URL = 'static/' + +# Default primary key field type +# https://docs.djangoproject.com/en/4.2/ref/settings/#default-auto-field + +DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField' diff --git a/nba_stats/urls.py b/nba_stats/urls.py new file mode 100644 index 0000000..505bd88 --- /dev/null +++ b/nba_stats/urls.py @@ -0,0 +1,22 @@ +""" +URL configuration for nba_stats project. + +The `urlpatterns` list routes URLs to views. For more information please see: + https://docs.djangoproject.com/en/4.2/topics/http/urls/ +Examples: +Function views + 1. Add an import: from my_app import views + 2. Add a URL to urlpatterns: path('', views.home, name='home') +Class-based views + 1. Add an import: from other_app.views import Home + 2. Add a URL to urlpatterns: path('', Home.as_view(), name='home') +Including another URLconf + 1. Import the include() function: from django.urls import include, path + 2. Add a URL to urlpatterns: path('blog/', include('blog.urls')) +""" +from django.contrib import admin +from django.urls import path + +urlpatterns = [ + path('admin/', admin.site.urls), +] diff --git a/nba_stats/wsgi.py b/nba_stats/wsgi.py new file mode 100644 index 0000000..e23d4eb --- /dev/null +++ b/nba_stats/wsgi.py @@ -0,0 +1,16 @@ +""" +WSGI config for nba_stats project. + +It exposes the WSGI callable as a module-level variable named ``application``. + +For more information on this file, see +https://docs.djangoproject.com/en/4.2/howto/deployment/wsgi/ +""" + +import os + +from django.core.wsgi import get_wsgi_application + +os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'nba_stats.settings') + +application = get_wsgi_application() diff --git a/src/scraper.py b/src/scraper.py index c9edaef..f34d1f5 100644 --- a/src/scraper.py +++ b/src/scraper.py @@ -5,6 +5,8 @@ import json import os url = 'https://www.basketball-reference.com/teams/HOU/2018.html' +lakers = 'https://www.basketball-reference.com/teams/LAL/2020.html' + response = requests.get(url) soup = BeautifulSoup(response.text, "html.parser") From 0f754caac334c2c06330e7eb0ae6a893403aad9c Mon Sep 17 00:00:00 2001 From: nprasad2077 <114438461+nprasad2077@users.noreply.github.com> Date: Fri, 14 Apr 2023 00:13:58 -0500 Subject: [PATCH 9/9] django app install --- nba_data/__init__.py | 0 nba_data/admin.py | 3 +++ nba_data/apps.py | 6 ++++++ nba_data/migrations/__init__.py | 0 nba_data/models.py | 3 +++ {src => nba_data}/scraper.py | 0 nba_data/tests.py | 3 +++ nba_data/views.py | 3 +++ nba_stats/settings.py | 2 +- 9 files changed, 19 insertions(+), 1 deletion(-) create mode 100644 nba_data/__init__.py create mode 100644 nba_data/admin.py create mode 100644 nba_data/apps.py create mode 100644 nba_data/migrations/__init__.py create mode 100644 nba_data/models.py rename {src => nba_data}/scraper.py (100%) create mode 100644 nba_data/tests.py create mode 100644 nba_data/views.py diff --git a/nba_data/__init__.py b/nba_data/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/nba_data/admin.py b/nba_data/admin.py new file mode 100644 index 0000000..8c38f3f --- /dev/null +++ b/nba_data/admin.py @@ -0,0 +1,3 @@ +from django.contrib import admin + +# Register your models here. diff --git a/nba_data/apps.py b/nba_data/apps.py new file mode 100644 index 0000000..0ac65f1 --- /dev/null +++ b/nba_data/apps.py @@ -0,0 +1,6 @@ +from django.apps import AppConfig + + +class NbaDataConfig(AppConfig): + default_auto_field = 'django.db.models.BigAutoField' + name = 'nba_data' diff --git a/nba_data/migrations/__init__.py b/nba_data/migrations/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/nba_data/models.py b/nba_data/models.py new file mode 100644 index 0000000..71a8362 --- /dev/null +++ b/nba_data/models.py @@ -0,0 +1,3 @@ +from django.db import models + +# Create your models here. diff --git a/src/scraper.py b/nba_data/scraper.py similarity index 100% rename from src/scraper.py rename to nba_data/scraper.py diff --git a/nba_data/tests.py b/nba_data/tests.py new file mode 100644 index 0000000..7ce503c --- /dev/null +++ b/nba_data/tests.py @@ -0,0 +1,3 @@ +from django.test import TestCase + +# Create your tests here. diff --git a/nba_data/views.py b/nba_data/views.py new file mode 100644 index 0000000..91ea44a --- /dev/null +++ b/nba_data/views.py @@ -0,0 +1,3 @@ +from django.shortcuts import render + +# Create your views here. diff --git a/nba_stats/settings.py b/nba_stats/settings.py index 5320c25..6c29440 100644 --- a/nba_stats/settings.py +++ b/nba_stats/settings.py @@ -20,7 +20,7 @@ BASE_DIR = Path(__file__).resolve().parent.parent # See https://docs.djangoproject.com/en/4.2/howto/deployment/checklist/ # SECURITY WARNING: keep the secret key used in production secret! -SECRET_KEY = 'django-insecure-sww_z^4ek6_2vly0_hcwvapk4j(-5&v#$8dh*2_2m%=6@izeqj' +SECRET_KEY = 'django-insecure-f*v4mu4cc=d6razef+!wlw0zs!z(wh)c5z!vqc)=xh0yfz47zg' # SECURITY WARNING: don't run with debug turned on in production! DEBUG = True