From 4f1af1d12967eb2128ecadeb26b69b4380ab6865 Mon Sep 17 00:00:00 2001
From: Sean Kim <33474168+seankim658@users.noreply.github.com>
Date: Fri, 25 Oct 2024 12:12:09 -0400
Subject: [PATCH 1/6] Add cloudscraper and remove mechanicalsoup

---
 requirements.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index 229629c..739348d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-mechanicalsoup
 pandas
 bs4
-sphinx>2.2.0
\ No newline at end of file
+sphinx>2.2.0
+cloudscraper

From e99e9951499ff82cb1b9971074091e7a2fdfc877 Mon Sep 17 00:00:00 2001
From: Sean Kim <33474168+seankim658@users.noreply.github.com>
Date: Fri, 25 Oct 2024 12:12:41 -0400
Subject: [PATCH 2/6] Refactor login function for cloudscraper and add get_html
 function

---
 kenpompy/utils.py | 66 +++++++++++++++++++++++++++--------------------
 1 file changed, 38 insertions(+), 28 deletions(-)

diff --git a/kenpompy/utils.py b/kenpompy/utils.py
index 9e81b02..c40f32c 100644
--- a/kenpompy/utils.py
+++ b/kenpompy/utils.py
@@ -2,11 +2,10 @@
 The utils module provides utility functions, such as logging in.
 """
 
-import mechanicalsoup
-from requests import Session
-from ._DESAdapter import DESAdapter, environment_requires_DES_adapter
+import cloudscraper
+from cloudscraper import CloudScraper
 
-def login(email, password):
+def login(email: str, password: str):
 	"""
 	Logs in to kenpom.com using user credentials.
 
@@ -18,33 +17,44 @@ def login(email, password):
 		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com.
 	"""
 
-	# Fix for Cloudflare SSL profiling (https://github.com/j-andrews7/kenpompy/issues/33) provided by Nick Ostendorf (@nickostendorf)
-	session = Session()
-	if environment_requires_DES_adapter():
-		session.mount('https://kenpom.com/', DESAdapter())
+	browser = cloudscraper.create_scraper()
+	browser.get('https://kenpom.com/index.php')
 
-	browser = mechanicalsoup.StatefulBrowser(session)
-	browser.set_user_agent('Mozilla/5.0')
-	browser.open('https://kenpom.com/index.php')
-
-	if 'Cloudflare' in browser.page.title.string:
-		raise Exception(
-			'Opening kenpom.com failed - request was intercepted by Cloudflare protection')
+	form_data = {
+		'email': email,
+		'password': password,
+		'submit': 'Login!',
+	}
 
 	# Response page actually throws an error but further navigation works and will show you as logged in.
-	browser.get_current_page()
-	browser.select_form('form[action="handlers/login_handler.php"]')
-	browser['email'] = email
-	browser['password'] = password
-
-	response = browser.submit_selected()
+	browser.post(
+		'https://kenpom.com/handlers/login_handler.php',
+		data=form_data, 
+		allow_redirects=True
+	)
 
-	if response.status_code != 200 or 'PHPSESSID=' not in response.headers['set-cookie']:
-		raise Exception(
-			'Logging in to kenpom.com failed - check that the site is available and your credentials are correct.')
-	
-	if 'subscription expired' in str(browser.get('https://kenpom.com/index.php').content):
-		raise Exception(
-			'Logging in to kenpom.com failed - account subscription is expired')
+	home_page = browser.get('https://kenpom.com/')
+	if 'Logout' not in home_page.text:
+		raise Exception('Logging in failed - check your credentials')
 
 	return browser
+
+def get_html(browser: CloudScraper, url: str):
+	"""
+	Performs a get request on the specified url.
+
+	Args:
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
+            by the `login` function.
+		url (str): The url to perform the get request on.
+	
+	Returns:
+		html (Bytes | Any): The return content.
+	
+	Raises:
+		Exception if get request gets a non-200 response code.
+	"""	
+	response = browser.get(url)
+	if response.status_code != 200:
+		raise Exception(f'Failed to retrieve {url} (status code: {response.status_code})')
+	return response.content
\ No newline at end of file

From 8e9fcd7999eac2a3d33b239da550f4c62a452f71 Mon Sep 17 00:00:00 2001
From: Sean Kim <33474168+seankim658@users.noreply.github.com>
Date: Fri, 25 Oct 2024 12:13:02 -0400
Subject: [PATCH 3/6] Refactor for cloudscraper and beautifulsoup

---
 kenpompy/FanMatch.py   | 11 +++++---
 kenpompy/conference.py | 42 +++++++++++++--------------
 kenpompy/misc.py       | 64 ++++++++++++++++++++----------------------
 kenpompy/summary.py    | 53 +++++++++++++++++-----------------
 kenpompy/team.py       | 27 +++++++++---------
 5 files changed, 96 insertions(+), 101 deletions(-)

diff --git a/kenpompy/FanMatch.py b/kenpompy/FanMatch.py
index 58a86f9..37f10c1 100644
--- a/kenpompy/FanMatch.py
+++ b/kenpompy/FanMatch.py
@@ -4,6 +4,10 @@
 
 import pandas as pd
 from io import StringIO
+from cloudscraper import CloudScraper
+from bs4 import BeautifulSoup
+from typing import Optional
+from .utils import get_html
 
 class FanMatch:
     """Object to hold FanMatch page scraping results.
@@ -11,7 +15,7 @@ class FanMatch:
     This class scrapes the kenpom FanMatch page when a new instance is created. 
 
     Args:
-        browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+        browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
             by the `login` function.
         date (str): Date to scrape, in format "YYYY-MM-DD", such as "2020-01-29".
 
@@ -31,7 +35,7 @@ class FanMatch:
         fm_df (pandas dataframe): Pandas dataframe containing parsed FanMatch table.
     """
 
-    def __init__(self, browser, date = None):
+    def __init__(self, browser: CloudScraper, date: Optional[str]=None):
         self.url = 'https://kenpom.com/fanmatch.php'
         self.date = date
         self.lines_o_night = None
@@ -48,8 +52,7 @@ def __init__(self, browser, date = None):
         if self.date is not None:
             self.url = self.url + "?d=" + self.date
 
-        browser.open(self.url)
-        fm = browser.get_current_page()
+        fm = BeautifulSoup(get_html(browser, self.url), "html.parser")
         table = fm.find_all("table")[0]
         fm_df = pd.read_html(StringIO(str(table)))
         fm_df = fm_df[0]
diff --git a/kenpompy/conference.py b/kenpompy/conference.py
index f5a41d7..a17d47a 100644
--- a/kenpompy/conference.py
+++ b/kenpompy/conference.py
@@ -5,13 +5,17 @@
 
 import pandas as pd
 from io import StringIO
+from cloudscraper import CloudScraper
+from bs4 import BeautifulSoup
+from typing import Optional
+from .utils import get_html
 
-def get_valid_conferences(browser, season=None):
+def get_valid_conferences(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the conferences (https://kenpom.com/conf.php) into a list.
 
 	Args:
-		browser (mechanicalsoul StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
 
@@ -23,8 +27,7 @@ def get_valid_conferences(browser, season=None):
 	url = url + '?c=B10'
 	if(season):
 		url = url + '&y=' + str(season)
-	browser.open(url)
-	confs = browser.get_current_page()
+	confs = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = confs.find_all('table')[-1]
 	links = table.find_all('a')
 	conf_list = []
@@ -34,12 +37,12 @@ def get_valid_conferences(browser, season=None):
 	return conf_list
 
 
-def get_aggregate_stats(browser, conf=None, season=None):
+def get_aggregate_stats(browser: CloudScraper, conf: Optional[str]=None, season: Optional[str]=None):
 	"""
 	Scrapes a given conference's stats (https://kenpom.com/conf.php or https://kenpom.com/confstats.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoul StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
 		conf (str: optional): conference abbreviation (ie B10, P12). If None, it will grab the table from https://kenpom.com/confstats.php instead of https://kenpom.com/conf.php
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
@@ -52,8 +55,7 @@ def get_aggregate_stats(browser, conf=None, season=None):
 		url = url + f'?c={conf}'
 		if(season):
 			url = url + '&y=' + str(season)
-		browser.open(url)
-		confs = browser.get_current_page()
+		confs = BeautifulSoup(get_html(browser, url), "html.parser")
 		#get first table
 		table = confs.find_all('table')[-3]
 		conf_df = pd.read_html(StringIO(str(table)))[0]
@@ -72,8 +74,7 @@ def get_aggregate_stats(browser, conf=None, season=None):
 		url = "https://kenpom.com/confstats.php"
 		if(season):
 			url = url + '?y=' + str(season)
-		browser.open(url)
-		confs = browser.get_current_page()
+		confs = BeautifulSoup(get_html(browser, url), "html.parser")
 		#get table
 		table = confs.find_all('table')[0]
 		conf_df = pd.read_html(StringIO(str(table)))[0]
@@ -82,12 +83,12 @@ def get_aggregate_stats(browser, conf=None, season=None):
 		conf_df.columns = [stat[:-1] + 'Rank' if '.1' in stat else stat for stat in conf_df.columns]
 		return conf_df
 
-def get_standings(browser, conf, season=None):
+def get_standings(browser: CloudScraper, conf: str, season: Optional[str]=None):
 	"""
 	Scrapes a given conference's standing stats (https://kenpom.com/conf.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoul StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
 		conf (str): conference abbreviation (ie B10, P12)
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
@@ -100,8 +101,7 @@ def get_standings(browser, conf, season=None):
 	url = url + f'?c={conf}'
 	if(season):
 		url = url + '&y=' + str(season)
-	browser.open(url)
-	confs = browser.get_current_page()
+	confs = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = confs.find_all('table')[0]
 	conf_df = pd.read_html(StringIO(str(table)))[0]
 	# Parse out seed
@@ -114,12 +114,12 @@ def get_standings(browser, conf, season=None):
 	return conf_df
 
 
-def get_offense(browser, conf, season=None):
+def get_offense(browser: CloudScraper, conf: str, season: Optional[str]=None):
 	"""
 	Scrapes a given conference's offense only stats (https://kenpom.com/conf.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoul StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
 		conf (str): conference abbreviation (ie B10, P12)
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
@@ -132,8 +132,7 @@ def get_offense(browser, conf, season=None):
 	url = url + f'?c={conf}'
 	if(season):
 		url = url + '&y=' + str(season)
-	browser.open(url)
-	confs = browser.get_current_page()
+	confs = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = confs.find_all('table')[1]
 	conf_df = pd.read_html(StringIO(str(table)))[0]
 
@@ -143,12 +142,12 @@ def get_offense(browser, conf, season=None):
 	return conf_df
 
 
-def get_defense(browser, conf, season=None):
+def get_defense(browser: CloudScraper, conf: str, season: Optional[str]=None):
 	"""
 	Scrapes a given conference's defense only stats (https://kenpom.com) into a dataframe.
 
 	Args:
-		browser (mechanicalsoul StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
 		conf (str): conference abbreviation (ie B10, P12)
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
@@ -161,8 +160,7 @@ def get_defense(browser, conf, season=None):
 	url = url + f'?c={conf}'
 	if(season):
 		url = url + '&y=' + str(season)
-	browser.open(url)
-	confs = browser.get_current_page()
+	confs = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = confs.find_all('table')[2]
 	conf_df = pd.read_html(StringIO(str(table)))[0]
 
diff --git a/kenpompy/misc.py b/kenpompy/misc.py
index f460221..7aef1f9 100644
--- a/kenpompy/misc.py
+++ b/kenpompy/misc.py
@@ -6,30 +6,34 @@
 import pandas as pd
 from io import StringIO
 import re
-import mechanicalsoup
+from cloudscraper import CloudScraper
+from bs4 import BeautifulSoup
+from typing import Optional
+from .utils import get_html
 
-def get_current_season(browser: mechanicalsoup.StatefulBrowser):
+def get_current_season(browser: CloudScraper):
 	"""
 	Scrapes the KenPom homepage to get the latest season year that has data published
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
             by the `login` function.
 
 	Returns:
 		current_season (int): Number corresponding to the last season year that has data published
 	"""
-	browser.open('https://kenpom.com/index.php')
-	page_title = browser.page.select_one('#content-header h2').text
+	url = 'https://kenpom.com/index.php'
+	content = BeautifulSoup(get_html(browser, url), "html.parser")
+	page_title = content.select_one('#content-header h2').text
 	YEAR_PATTERN = r'^(\d{4})'
 	return int(re.match(YEAR_PATTERN, page_title).group(0))
 
-def get_pomeroy_ratings(browser, season=None):
+def get_pomeroy_ratings(browser: CloudScraper, season: Optional[str]=None):
     """
     Scrapes the Pomeroy College Basketball Ratings table (https://kenpom.com/index.php) into a dataframe.
 
     Args:
-        browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+        browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
             by the `login` function.
         season (str, optional): Used to define different seasons. 2002 is the earliest available season.
             Most recent season is the default.
@@ -42,8 +46,7 @@ def get_pomeroy_ratings(browser, season=None):
     if season and int(season) < 2002:
         raise ValueError("season cannot be less than 2002")
     url += '?y={}'.format(season)
-    browser.open(url)
-    page = browser.get_current_page()
+    page = BeautifulSoup(get_html(browser, url), "html.parser")
     table = page.find_all('table')[0]
     ratings_df = pd.read_html(StringIO(str(table)))
     # Dataframe tidying.
@@ -66,12 +69,12 @@ def get_pomeroy_ratings(browser, season=None):
     return ratings_df
 
 
-def get_trends(browser):
+def get_trends(browser: CloudScraper):
 	"""
 	Scrapes the statistical trends table (https://kenpom.com/trends.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 
 	Returns:
@@ -80,8 +83,7 @@ def get_trends(browser):
 
 	url = 'https://kenpom.com/trends.php'
 
-	browser.open(url)
-	trends = browser.get_current_page()
+	trends = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = trends.find_all('table')[0]
 	trends_df = pd.read_html(StringIO(str(table)))
 
@@ -92,12 +94,12 @@ def get_trends(browser):
 	return trends_df
 
 
-def get_refs(browser, season=None):
+def get_refs(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the officials rankings table (https://kenpom.com/officials.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2016 is the earliest available season.
 			Most recent season is the default.
@@ -117,8 +119,7 @@ def get_refs(browser, season=None):
 				'season cannot be less than 2016, as data only goes back that far.')
 		url = url + '?y=' + str(season)
 
-	browser.open(url)
-	refs = browser.get_current_page()
+	refs = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = refs.find_all('table')[0]
 	refs_df = pd.read_html(StringIO(str(table)))
 
@@ -131,14 +132,13 @@ def get_refs(browser, season=None):
 	return refs_df
 
 
-def get_hca(browser):
+def get_hca(browser: CloudScraper):
 	"""
 	Scrapes the home court advantage table (https://kenpom.com/hca.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
-		season (str, optional): Used to define different seasons. 2010 is the earliest available season.
 
 	Returns:
 		hca_df (pandas dataframe): Pandas dataframe containing the home court advantage table from kenpom.com.
@@ -146,8 +146,7 @@ def get_hca(browser):
 
 	url = 'https://kenpom.com/hca.php'
 
-	browser.open(url)
-	hca = browser.get_current_page()
+	hca = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = hca.find_all('table')[0]
 	hca_df = pd.read_html(StringIO(str(table)))
 
@@ -160,12 +159,12 @@ def get_hca(browser):
 	return hca_df
 
 
-def get_arenas(browser, season=None):
+def get_arenas(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the arenas table (https://kenpom.com/arenas.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2010 is the earliest available season.
 			Most recent season is the default.
@@ -185,8 +184,7 @@ def get_arenas(browser, season=None):
 				'season cannot be less than 2010, as data only goes back that far.')
 		url = url + '?y=' + str(season)
 
-	browser.open(url)
-	arenas = browser.get_current_page()
+	arenas = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = arenas.find_all('table')[0]
 	arenas_df = pd.read_html(StringIO(str(table)))
 
@@ -201,12 +199,12 @@ def get_arenas(browser, season=None):
 	return arenas_df
 
 
-def get_gameattribs(browser, season=None, metric='Excitement'):
+def get_gameattribs(browser: CloudScraper, season: Optional[str]=None, metric: str='Excitement'):
 	"""
 	Scrapes the Game Attributes tables (https://kenpom.com/game_attrs.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2010 is the earliest available season.
 			Most recent season is the default.
@@ -247,8 +245,7 @@ def get_gameattribs(browser, season=None, metric='Excitement'):
 			)
 		url = url + '&y=' + str(season)
 
-	browser.open(url)
-	playerstats = browser.get_current_page()
+	playerstats = BeautifulSoup(get_html(browser, url), "html.parser")
 
 	table = playerstats.find_all('table')[0]
 	ga_df = pd.read_html(StringIO(str(table)))
@@ -263,12 +260,12 @@ def get_gameattribs(browser, season=None, metric='Excitement'):
 	return ga_df
 
 
-def get_program_ratings(browser):
+def get_program_ratings(browser: CloudScraper):
 	"""
 	Scrapes the program ratings table (https://kenpom.com/programs.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 
 	Returns:
@@ -277,8 +274,7 @@ def get_program_ratings(browser):
 
 	url = 'https://kenpom.com/programs.php'
 
-	browser.open(url)
-	programs = browser.get_current_page()
+	programs = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = programs.find_all('table')[0]
 	programs_df = pd.read_html(StringIO(str(table)))
 	programs_df = programs_df[0]
diff --git a/kenpompy/summary.py b/kenpompy/summary.py
index 21c5721..d7c4cf1 100644
--- a/kenpompy/summary.py
+++ b/kenpompy/summary.py
@@ -6,13 +6,17 @@
 import pandas as pd
 import re
 from io import StringIO
+from cloudscraper import CloudScraper
+from bs4 import BeautifulSoup
+from typing import Optional
+from .utils import get_html
 
-def get_efficiency(browser, season=None):
+def get_efficiency(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the Efficiency stats table (https://kenpom.com/summary.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season but 
 			possession length data wasn't available until 2010. Most recent season is the default.
@@ -32,8 +36,7 @@ def get_efficiency(browser, season=None):
 				'season cannot be less than 2002, as data only goes back that far.')
 		url = url + '?y=' + str(season)
 
-	browser.open(url)
-	eff = browser.get_current_page()
+	eff = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = eff.find_all('table')[0]
 	eff_df = pd.read_html(StringIO(str(table)))
 
@@ -65,12 +68,12 @@ def get_efficiency(browser, season=None):
 	return eff_df
 
 
-def get_fourfactors(browser, season=None):
+def get_fourfactors(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the Four Factors table (https://kenpom.com/stats.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
 			Most recent season is the default.
@@ -90,8 +93,7 @@ def get_fourfactors(browser, season=None):
 				'season cannot be less than 2002, as data only goes back that far.')
 		url = url + '?y=' + str(season)
 
-	browser.open(url)
-	ff = browser.get_current_page()
+	ff = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = ff.find_all('table')[0]
 	ff_df = pd.read_html(StringIO(str(table)))
 
@@ -113,12 +115,12 @@ def get_fourfactors(browser, season=None):
 	return ff_df
 
 
-def get_teamstats(browser, defense=False, season=None):
+def get_teamstats(browser: CloudScraper, defense: Optional[bool]=False, season: Optional[str]=None):
 	"""
 	Scrapes the Miscellaneous Team Stats table (https://kenpom.com/teamstats.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		defense (bool, optional): Used to flag whether the defensive teamstats table is wanted or not. False by 
 			default.
@@ -148,8 +150,7 @@ def get_teamstats(browser, defense=False, season=None):
 		url = url + '?od=d'
 		last_cols = ['AdjDE', 'AdjDE.Rank']
 
-	browser.open(url)
-	ts = browser.get_current_page()
+	ts = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = ts.find_all('table')[0]
 	ts_df = pd.read_html(StringIO(str(table)))
 
@@ -170,12 +171,12 @@ def get_teamstats(browser, defense=False, season=None):
 	return ts_df
 
 
-def get_pointdist(browser, season=None):
+def get_pointdist(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the Team Points Distribution table (https://kenpom.com/pointdist.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
 			Most recent season is the default.
@@ -196,8 +197,7 @@ def get_pointdist(browser, season=None):
 				'season cannot be less than 2002, as data only goes back that far.')
 		url = url + '?y=' + str(season)
 
-	browser.open(url)
-	dist = browser.get_current_page()
+	dist = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = dist.find_all('table')[0]
 	dist_df = pd.read_html(StringIO(str(table)))
 
@@ -217,12 +217,12 @@ def get_pointdist(browser, season=None):
 	return dist_df
 
 
-def get_height(browser, season=None):
+def get_height(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the Height/Experience table (https://kenpom.com/height.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2007 is the earliest available season but 
 			continuity data wasn't available until 2008. Most recent season is the default.
@@ -242,8 +242,7 @@ def get_height(browser, season=None):
 				'Season cannot be less than 2007, as data only goes back that far.')
 		url = url + '?y=' + str(season)
 
-	browser.open(url)
-	height = browser.get_current_page()
+	height = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = height.find_all('table')[0]
 	h_df = pd.read_html(StringIO(str(table)))
 
@@ -274,12 +273,12 @@ def get_height(browser, season=None):
 	return h_df
 
 
-def get_playerstats(browser, season=None, metric='EFG', conf=None, conf_only=False):
+def get_playerstats(browser: CloudScraper, season: Optional[str]=None, metric: str='EFG', conf: Optional[str]=None, conf_only: bool=False):
 	"""
 	Scrapes the Player Leaders tables (https://kenpom.com/playerstats.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2004 is the earliest available season. 
 			Most recent season is the default.
@@ -338,8 +337,7 @@ def get_playerstats(browser, season=None, metric='EFG', conf=None, conf_only=Fal
 	if conf:
 		url = url + '&f=' + conf
 
-	browser.open(url)
-	playerstats = browser.get_current_page()
+	playerstats = BeautifulSoup(get_html(browser, url), "html.parser")
 	if metric == 'ORTG':
 		ps_dfs = []
 		tables = playerstats.find_all('table')
@@ -380,12 +378,12 @@ def get_playerstats(browser, season=None, metric='EFG', conf=None, conf_only=Fal
 	return ps_df
 
 
-def get_kpoy(browser, season=None):
+def get_kpoy(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the kenpom Player of the Year tables (https://kenpom.com/kpoy.php) into dataframes.
 
 	Args:
-		browser (mechanicalsoup StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function.
 		season (str, optional): Used to define different seasons. 2011 is the earliest available season.
 			Most recent season is the default.
@@ -410,8 +408,7 @@ def get_kpoy(browser, season=None):
 	else:
 		season = 2013
 
-	browser.open(url)
-	kpoy = browser.get_current_page()
+	kpoy = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = kpoy.find_all('table')[0]
 	df = pd.read_html(StringIO(str(table)))
 
diff --git a/kenpompy/team.py b/kenpompy/team.py
index 651e1d6..2a32f9f 100644
--- a/kenpompy/team.py
+++ b/kenpompy/team.py
@@ -7,15 +7,18 @@
 from io import StringIO
 from .misc import get_current_season
 import re
+from cloudscraper import CloudScraper
 from bs4 import BeautifulSoup
 from codecs import encode, decode
+from typing import Optional
+from .utils import get_html
 
-def get_valid_teams(browser, season=None):
+def get_valid_teams(browser: CloudScraper, season: Optional[str]=None):
 	"""
 	Scrapes the teams (https://kenpom.com) into a list.
 
 	Args:
-		browser (mechanicalsoup.StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
 
@@ -26,8 +29,7 @@ def get_valid_teams(browser, season=None):
 	url = "https://kenpom.com"
 	url = url + '?y=' + str(season)
 
-	browser.open(url)
-	teams = browser.get_current_page()
+	teams = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = teams.find_all('table')[0]
 	team_df = pd.read_html(StringIO(str(table)))
 	# Get only the team column.
@@ -42,14 +44,14 @@ def get_valid_teams(browser, season=None):
 
 	return team_list
 
-def get_schedule(browser, team=None, season=None):
+def get_schedule(browser: CloudScraper, team: str, season: Optional[str]=None):
 	"""
 	Scrapes a team's schedule from (https://kenpom.com/team.php) into a dataframe.
 
 	Args:
-		browser (mechanicalsoup.StatefulBrowser): Authenticated browser with full access to kenpom.com generated
+		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
-		team: Used to determine which team to scrape for schedule.
+		team (str): Used to determine which team to scrape for schedule.
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
 
 	Returns:
@@ -84,8 +86,7 @@ def get_schedule(browser, team=None, season=None):
 	url = url + "?team=" + str(team)
 	url = url + "&y=" + str(season)
 
-	browser.open(url)
-	schedule = browser.get_current_page()
+	schedule = BeautifulSoup(get_html(browser, url), "html.parser")
 	table = schedule.find_all('table')[1]
 	schedule_df = pd.read_html(StringIO(str(table)))
 
@@ -119,12 +120,12 @@ def get_schedule(browser, team=None, season=None):
 
 	return schedule_df.reset_index(drop=True)
 
-def get_scouting_report(browser, team=None, season=None, conference_only=False):
+def get_scouting_report(browser: CloudScraper, team: str, season: Optional[int]=None, conference_only: bool=False):
 	"""
     Retrieves and parses team scouting report data from (https://kenpom.com/team.php) into a dictionary.
 
     Args:
-    	browser (mechanicalsoup.StatefulBrowser): The mechanize browser object for web scraping.
+    	browser (CloudScraper): The mechanize browser object for web scraping.
     	team (str): team: Used to determine which team to scrape for schedule.
     	season (int, optional): Used to define different seasons. 2002 is the earliest available season.
     	conference_only (bool, optional): When True, only conference-related stats are retrieved; otherwise, all stats are fetched.
@@ -161,8 +162,8 @@ def get_scouting_report(browser, team=None, season=None, conference_only=False):
 	url = url + "?team=" + str(team)
 	url = url + "&y=" + str(season)
 
-	browser.open(url)
-	scouting_report_scripts = browser.page.find("script", { "type": "text/javascript", "src": ""} )
+	report = BeautifulSoup(get_html(browser, url), "html.parser")
+	scouting_report_scripts = report.find("script", { "type": "text/javascript", "src": ""} )
 
 	extraction_pattern = re.compile(r"\$\(\"td#(?P<token>[A-Za-z0-9]+)\"\)\.html\(\"(.+)\"\);")
 	if conference_only:

From 67319af73e1ada0912327309f2fbe83a8220a529 Mon Sep 17 00:00:00 2001
From: Sean Kim <33474168+seankim658@users.noreply.github.com>
Date: Fri, 25 Oct 2024 12:36:28 -0400
Subject: [PATCH 4/6] Update AdjO to ORtg

---
 tests/test_conference.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tests/test_conference.py b/tests/test_conference.py
index dab4992..b3c2e33 100644
--- a/tests/test_conference.py
+++ b/tests/test_conference.py
@@ -67,8 +67,8 @@ def test_get_standings(browser):
 	
 	confs_2021 = kpconf.get_standings(browser, 'B10', season = '2021')
 	assert confs_2021.iloc[0, :]['Team'] == expectedTeam1
-	assert confs_2021.iloc[0, :]['AdjO'] == expectedTeam1AdjO
-	assert confs_2021.iloc[0, :]['AdjO.Rank'] == expectedTeam1AdjORank
+	assert confs_2021.iloc[0, :]['ORtg'] == expectedTeam1AdjO
+	assert confs_2021.iloc[0, :]['ORtg.Rank'] == expectedTeam1AdjORank
 
 	expectedTeam1 = 'Wisconsin'
 	expectedTeam1AdjO = 114.4
@@ -76,8 +76,8 @@ def test_get_standings(browser):
 
 	confs_2003 = kpconf.get_standings(browser, 'B10', season = '2003')
 	assert confs_2003.iloc[0, :]['Team'] == expectedTeam1
-	assert confs_2003.iloc[0, :]['AdjO'] == expectedTeam1AdjO
-	assert confs_2003.iloc[0, :]['AdjO.Rank'] == expectedTeam1AdjORank
+	assert confs_2003.iloc[0, :]['ORtg'] == expectedTeam1AdjO
+	assert confs_2003.iloc[0, :]['ORtg.Rank'] == expectedTeam1AdjORank
 
 
 def test_get_offense(browser):

From 4fe156a69406a8fc23e7057edc0d3a7423084294 Mon Sep 17 00:00:00 2001
From: Sean Kim <33474168+seankim658@users.noreply.github.com>
Date: Fri, 25 Oct 2024 12:45:10 -0400
Subject: [PATCH 5/6] Restore default None for team arg

---
 kenpompy/team.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kenpompy/team.py b/kenpompy/team.py
index 2a32f9f..005197d 100644
--- a/kenpompy/team.py
+++ b/kenpompy/team.py
@@ -44,14 +44,14 @@ def get_valid_teams(browser: CloudScraper, season: Optional[str]=None):
 
 	return team_list
 
-def get_schedule(browser: CloudScraper, team: str, season: Optional[str]=None):
+def get_schedule(browser: CloudScraper, team: Optional[str]=None, season: Optional[str]=None):
 	"""
 	Scrapes a team's schedule from (https://kenpom.com/team.php) into a dataframe.
 
 	Args:
 		browser (CloudScraper): Authenticated browser with full access to kenpom.com generated
 			by the `login` function
-		team (str): Used to determine which team to scrape for schedule.
+		team (str, optional): Used to determine which team to scrape for schedule.
 		season (str, optional): Used to define different seasons. 2002 is the earliest available season.
 
 	Returns:

From e01aa17d4ebd5a34902ddc07711949e79cbb5874 Mon Sep 17 00:00:00 2001
From: Sean Kim <33474168+seankim658@users.noreply.github.com>
Date: Fri, 25 Oct 2024 12:46:18 -0400
Subject: [PATCH 6/6] Fix expected for cloudscraper instead of stateful browser

---
 tests/test_misc.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_misc.py b/tests/test_misc.py
index 4fe91f9..196beed 100644
--- a/tests/test_misc.py
+++ b/tests/test_misc.py
@@ -89,5 +89,5 @@ def test_get_gameattribs(browser):
 
 def test_get_program_ratings(browser):
 	df = kpmisc.get_program_ratings(browser)
-	expected = (len(browser.page.select("tr:not(:has(th))")), 17)
+	expected = (362, 17)
 	assert df.shape == expected
\ No newline at end of file