First scraper to download match summary

.gitignore

@@ -164,3 +164,4 @@ cython_debug/
 
 # Added by Bhargav.
 _proc/
+data/

README.md

@@ -1,19 +1,20 @@
-# isl-2024
+# Indian Super League, 2024
 
 
 <!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
 
-This file will become your README and also the index of your
-documentation.
+## Installation
 
-## Developer Guide
+Install latest from the GitHub
+[repository](https://github.com/bkowshik/isl-2024):
 
-If you are new to using `nbdev` here are some useful pointers to get you
-started.
+``` bash
+$ pip install git+https://github.com/bkowshik/isl-2024.git
+```
 
-### Install isl_2024 in Development mode
+## Development
 
-``` sh
+``` bash
 # make sure isl_2024 package is installed in development mode
 $ pip install -e .
 
@@ -24,44 +25,6 @@ $ pip install -e .
 $ nbdev_prepare
 ```
 
-## Usage
-
-### Installation
-
-Install latest from the GitHub
-[repository](https://github.com/bkowshik/isl-2024):
-
-``` sh
-$ pip install git+https://github.com/bkowshik/isl-2024.git
-```
-
-or from [conda](https://anaconda.org/bkowshik/isl-2024)
-
-``` sh
-$ conda install -c bkowshik isl_2024
-```
-
-or from [pypi](https://pypi.org/project/isl-2024/)
-
-``` sh
-$ pip install isl_2024
-```
-
-### Documentation
-
-Documentation can be found hosted on this GitHub
-[repository](https://github.com/bkowshik/isl-2024)’s
-[pages](https://bkowshik.github.io/isl-2024/). Additionally you can find
-package manager specific guidelines on
-[conda](https://anaconda.org/bkowshik/isl-2024) and
-[pypi](https://pypi.org/project/isl-2024/) respectively.
-
-## How to use
-
-Fill me in please! Don’t forget code examples:
-
-``` python
-1+1
-```
+## Scrapers
 
-    2
+1.  Scrape matches.

isl_2024/_modidx.py

@@ -5,4 +5,4 @@
                 'doc_host': 'https://bkowshik.github.io',
                 'git_url': 'https://github.com/bkowshik/isl-2024',
                 'lib_path': 'isl_2024'},
-  'syms': {'isl_2024.core': {'isl_2024.core.foo': ('core.html#foo', 'isl_2024/core.py')}}}
+  'syms': {'isl_2024.core': {'isl_2024.core.foo': ('core.html#foo', 'isl_2024/core.py')}, 'isl_2024.scrape_matches': {}}}

isl_2024/scrape_matches.py

@@ -0,0 +1,52 @@
+"""Script data about matches."""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/01_scrape_matches.ipynb.
+
+# %% auto 0
+__all__ = ['parent_dir', 'log_dir', 'data_dir', 'url', 'headers', 'response']
+
+# %% ../nbs/01_scrape_matches.ipynb 2
+import warnings
+warnings.filterwarnings('ignore')
+
+import json
+import logging
+import os
+import requests
+
+# %% ../nbs/01_scrape_matches.ipynb 4
+try:
+    # This will work when running as a script
+    script_dir = os.path.dirname(os.path.abspath(__file__))
+except NameError:
+    # This will work when running in a Jupyter notebook
+    script_dir = os.getcwd()
+
+parent_dir = os.path.abspath(os.path.join(script_dir, os.pardir))
+log_dir = os.path.join(parent_dir, 'logs')
+data_dir = os.path.join(parent_dir, 'data')
+
+if not os.path.exists(log_dir):
+    os.makedirs(log_dir)
+
+if not os.path.exists(data_dir):
+    os.makedirs(data_dir)
+
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', filename=os.path.join(log_dir, 'scrape_matches.log'), filemode='a')
+
+# %% ../nbs/01_scrape_matches.ipynb 5
+url = 'https://www.indiansuperleague.com/default.aspx?methodtype=3&client=3747164737&sport=2&league=india_sl_stats&timezone=0530&language=&tournament=india_sl_stats_2024'
+headers = {
+    'accept': '*/*',
+    'referer': 'https://www.indiansuperleague.com/',
+    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36'
+}
+response = requests.get(url, headers=headers)
+
+# %% ../nbs/01_scrape_matches.ipynb 6
+if response.status_code == 200:
+    logging.info('API request successful. Content length: {}'.format(len(response.content)))
+    with open(os.path.join(data_dir, 'scrape_matches.txt'), 'a') as f:
+        f.write(response.text + "\n")
+else:
+    logging.error('API request failed. Status code: {}'.format(response.status_code))

nbs/01_scrape_matches.ipynb

@@ -0,0 +1,134 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "#| default_exp scrape_matches"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Scrape matches\n",
+    "\n",
+    "> Script data about matches."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "\n",
+    "import json\n",
+    "import logging\n",
+    "import os\n",
+    "import requests"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "from nbdev.showdoc import *"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "try:\n",
+    "    # This will work when running as a script\n",
+    "    script_dir = os.path.dirname(os.path.abspath(__file__))\n",
+    "except NameError:\n",
+    "    # This will work when running in a Jupyter notebook\n",
+    "    script_dir = os.getcwd()\n",
+    "\n",
+    "parent_dir = os.path.abspath(os.path.join(script_dir, os.pardir))\n",
+    "log_dir = os.path.join(parent_dir, 'logs')\n",
+    "data_dir = os.path.join(parent_dir, 'data')\n",
+    "    \n",
+    "if not os.path.exists(log_dir):\n",
+    "    os.makedirs(log_dir)\n",
+    "\n",
+    "if not os.path.exists(data_dir):\n",
+    "    os.makedirs(data_dir)\n",
+    "\n",
+    "logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s', filename=os.path.join(log_dir, 'scrape_matches.log'), filemode='a')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "url = 'https://www.indiansuperleague.com/default.aspx?methodtype=3&client=3747164737&sport=2&league=india_sl_stats&timezone=0530&language=&tournament=india_sl_stats_2024'\n",
+    "headers = {\n",
+    "    'accept': '*/*',\n",
+    "    'referer': 'https://www.indiansuperleague.com/',\n",
+    "    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36'\n",
+    "}\n",
+    "response = requests.get(url, headers=headers)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| export\n",
+    "if response.status_code == 200:\n",
+    "    logging.info('API request successful. Content length: {}'.format(len(response.content)))\n",
+    "    with open(os.path.join(data_dir, 'scrape_matches.txt'), 'a') as f:\n",
+    "        f.write(response.text + \"\\n\")\n",
+    "else:\n",
+    "    logging.error('API request failed. Status code: {}'.format(response.status_code))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#| hide\n",
+    "import nbdev; nbdev.nbdev_export()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "python3",
+   "language": "python",
+   "name": "python3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}