Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+visual/debug_screenshot.png filter=lfs diff=lfs merge=lfs -text
+visual/debug_team_stats.png filter=lfs diff=lfs merge=lfs -text
+visual/top10_passing_accuracy.png filter=lfs diff=lfs merge=lfs -text

.history/fbrefdata_example_20251004173710.py

@@ -0,0 +1,49 @@
+import requests
+import pandas as pd
+from io import StringIO
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Downloading team passing stats from {url} ...")
+
+    # Add a User-Agent header to mimic a browser
+    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+
+    df = pd.read_html(StringIO(response.text))[0]
+
+    # Flatten columns
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+
+    # Rename the weird columns
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+
+    teams = ["Arsenal", "Nott'ham Forest"]
+    df_filtered = filter_teams(df, teams)
+
+    print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+    print("=" * 70)
+    print(df_filtered[["Squad", "Total_Cmp", "Total_Att", "Total_Cmp%", "Total_TotDist"]])
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004180335.py

@@ -0,0 +1,43 @@
+import requests
+import pandas as pd
+from io import StringIO
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Downloading team passing stats from {url} ...")
+
+    # Use a more comprehensive set of headers to mimic a real browser
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
+        'Accept-Language': 'en-US,en;q=0.5',
+        'Accept-Encoding': 'gzip, deflate, br',
+        'Connection': 'keep-alive',
+        'Upgrade-Insecure-Requests': '1',
+        'DNT': '1' # Do Not Track request header
+    }
+    
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+
+    # The rest of your function remains the same
+    df = pd.read_html(StringIO(response.text))[0]
+
+    # Flatten columns
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+
+    # Rename the weird columns
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+
+    return df

.history/fbrefdata_example_20251004180434.py

@@ -0,0 +1,60 @@
+import requests
+import pandas as pd
+from io import StringIO
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Downloading team passing stats from {url} ...")
+
+    # Gunakan headers yang lebih lengkap untuk meniru browser asli
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
+        'Accept-Language': 'en-US,en;q=0.5',
+        'Accept-Encoding': 'gzip, deflate, br',
+        'Connection': 'keep-alive',
+        'Upgrade-Insecure-Requests': '1',
+        'DNT': '1'
+    }
+    
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+
+    df = pd.read_html(StringIO(response.text))[0]
+
+    # Meratakan kolom
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+
+    # Mengganti nama kolom yang aneh
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+
+    teams = ["Arsenal", "Nott'ham Forest"]
+    df_filtered = filter_teams(df, teams)
+
+    print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+    print("=" * 70)
+    # Menampilkan kolom yang relevan dari DataFrame yang sudah difilter
+    print(df_filtered[["Squad", "Total_Cmp", "Total_Att", "Total_Cmp%", "Total_TotDist"]])
+
+# Bagian ini PENTING untuk menjalankan fungsi main()
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004180520.py

@@ -0,0 +1,74 @@
+import requests
+import pandas as pd
+from io import StringIO
+import random
+import time
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Downloading team passing stats from {url} ...")
+
+    # List of User-Agent strings
+    user_agents = [
+        'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
+        'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:53.0) Gecko/20100101 Firefox/53.0',
+        'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36'
+    ]
+
+    # Randomly select a User-Agent
+    headers = {'User-Agent': random.choice(user_agents)}
+
+    try:
+        response = requests.get(url, headers=headers)
+        response.raise_for_status()  # Raise HTTPError for bad responses (4xx or 5xx)
+    except requests.exceptions.HTTPError as e:
+        print(f"HTTP error occurred: {e}")
+        return None
+    except requests.exceptions.RequestException as e:
+        print(f"An error occurred: {e}")
+        return None
+
+    df = pd.read_html(StringIO(response.text))[0]
+
+    # Meratakan kolom
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+
+    # Mengganti nama kolom yang aneh
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+
+    # Delay before returning (adjust as needed)
+    time.sleep(random.uniform(1, 3))  # Delay between 1 and 3 seconds
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+
+    if df is not None:
+        teams = ["Arsenal", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        # Menampilkan kolom yang relevan dari DataFrame yang sudah difilter
+        print(df_filtered[["Squad", "Total_Cmp", "Total_Att", "Total_Cmp%", "Total_TotDist"]])
+    else:
+        print("Failed to retrieve data.")
+
+# Bagian ini PENTING untuk menjalankan fungsi main()
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004180621.py

@@ -0,0 +1,67 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from webdriver_manager.chrome import ChromeDriverManager
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    # Inisialisasi driver Chrome secara otomatis
+    # Browser akan terbuka, mengambil data, lalu menutup sendiri
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()))
+    
+    # Buka URL
+    driver.get(url)
+    
+    # Beri waktu 3 detik agar halaman dan semua elemennya (termasuk tabel)
+    # termuat dengan sempurna
+    time.sleep(3)
+    
+    # Ambil sumber HTML dari halaman yang sudah dimuat oleh browser
+    html_source = driver.page_source
+    
+    # Tutup browser setelah selesai
+    driver.quit()
+    
+    print("Data downloaded. Processing with pandas...")
+
+    # Sekarang kita proses HTML yang didapat dengan pandas, sama seperti sebelumnya
+    df = pd.read_html(StringIO(html_source))[0]
+
+    # Meratakan kolom
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+
+    # Mengganti nama kolom yang aneh
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+
+    teams = ["Arsenal", "Nott'ham Forest"]
+    df_filtered = filter_teams(df, teams)
+
+    print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+    print("=" * 70)
+    print(df_filtered[["Squad", "Total_Cmp", "Total_Att", "Total_Cmp%", "Total_TotDist"]])
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004184139.py

@@ -0,0 +1,72 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    # === BAGIAN BARU: Menambahkan Opsi Chrome ===
+    options = ChromeOptions()
+    options.add_argument("--start-maximized") # Memastikan jendela browser terbuka maksimal
+    options.add_argument("--no-sandbox") # Opsi ini seringkali diperlukan saat menjalankan di lingkungan otomatis
+    options.add_argument("--disable-dev-shm-usage") # Mengatasi masalah sumber daya yang terbatas
+    options.add_experimental_option("excludeSwitches", ["enable-automation"]) # Menghilangkan notifikasi "Chrome is being controlled..."
+    options.add_experimental_option('useAutomationExtension', False)
+    # ============================================
+
+    # Inisialisasi driver Chrome dengan OPSI yang sudah kita buat
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    
+    # Buka URL
+    driver.get(url)
+    
+    # Beri waktu agar halaman termuat dengan sempurna
+    time.sleep(5) # Waktu tunggu sedikit diperpanjang menjadi 5 detik untuk amannya
+    
+    # Ambil sumber HTML dari halaman
+    html_source = driver.page_source
+    
+    # Tutup browser setelah selesai
+    driver.quit()
+    
+    print("Data downloaded. Processing with pandas...")
+
+    df = pd.read_html(StringIO(html_source))[0]
+
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+
+    teams = ["Arsenal", "Nott'ham Forest"]
+    df_filtered = filter_teams(df, teams)
+
+    print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+    print("=" * 70)
+    print(df_filtered[["Squad", "Total_Cmp", "Total_Att", "Total_Cmp%", "Total_TotDist"]])
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004185739.py

@@ -0,0 +1,65 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    
+    driver.get(url)
+    time.sleep(5)
+    
+    html_source = driver.page_source
+    driver.quit()
+    
+    print("Data downloaded. Processing with pandas...")
+
+    df = pd.read_html(StringIO(html_source))[0]
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+
+    # !!!!!!!!!! INI BAGIAN PENTING UNTUK DEBUG !!!!!!!!!!
+    print("\nDEBUG: Column names are:")
+    print(df.columns)
+    print("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n")
+    # !!!!!!!!!! AKHIR BAGIAN DEBUG !!!!!!!!!!
+
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+    teams = ["Arsenal", "Nott'ham Forest"]
+    df_filtered = filter_teams(df, teams)
+    print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+    print("=" * 70)
+    print(df_filtered[["Squad", "Total_Cmp", "Total_Att", "Total_Cmp%", "Total_TotDist"]])
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004185920.py

@@ -0,0 +1,68 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    
+    driver.get(url)
+    time.sleep(5)
+    
+    html_source = driver.page_source
+    
+    print("Data downloaded. Processing with pandas...")
+
+    # Specify the header rows
+    df = pd.read_html(StringIO(html_source), header=[0, 1])[0]
+
+    # Flatten the multi-level header
+    df.columns = ["_".join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+    driver.quit()
+    
+    # !!!!!!!!!! INI BAGIAN PENTING UNTUK DEBUG !!!!!!!!!!
+    print("\nDEBUG: Column names are:")
+    print(df.columns)
+    print("!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n")
+    # !!!!!!!!!! AKHIR BAGIAN DEBUG !!!!!!!!!!
+
+    df = df.rename(columns={
+        "Unnamed: 0_level_0_Squad": "Squad",
+        "Unnamed: 1_level_0_# Pl": "Players",
+        "Unnamed: 2_level_0_90s": "90s",
+        "Unnamed: 17_level_0_Ast": "Ast",
+        "Unnamed: 18_level_0_xAG": "xAG",
+        "Unnamed: 21_level_0_KP": "KP",
+        "Unnamed: 22_level_0_1/3": "1/3",
+        "Unnamed: 23_level_0_PPA": "PPA",
+        "Unnamed: 24_level_0_CrsPA": "CrsPA",
+        "Unnamed: 25_level_0_PrgP": "PrgP"
+    })
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+    teams = ["Arsenal", "Nott'ham Forest"]
+    df_filtered = filter_teams(df, teams)
+    print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+    print("=" * 70)
+    print(df_filtered[["Squad", "Total_Cmp", "Total_Att", "Total_Cmp%", "Total_TotDist"]])
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004190027.py

@@ -0,0 +1,69 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    options.add_argument("--headless") # Menjalankan browser di background agar tidak muncul jendela
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    
+    driver.get(url)
+    time.sleep(3) # Cukup 3 detik jika headless
+    
+    html_source = driver.page_source
+    driver.quit()
+    
+    print("Data downloaded. Processing with pandas...")
+
+    # Ambil tabel pertama dari HTML
+    df = pd.read_html(StringIO(html_source))[0]
+
+    # ==============================================================================
+    # === BAGIAN LAMA DIHAPUS DAN DIGANTI DENGAN YANG LEBIH SEDERHANA INI ===
+    # ==============================================================================
+    # Berdasarkan struktur tabel di FBRef, kita tahu kolom yang kita mau ada di indeks:
+    # 1: Squad, 5: Total Cmp, 6: Total Att, 7: Total Cmp%, 8: Total TotDist
+    
+    # 1. Pilih hanya kolom yang kita butuhkan berdasarkan nomor indeksnya
+    df = df[[1, 5, 6, 7, 8]]
+    
+    # 2. Beri nama baru untuk kolom-kolom tersebut
+    df.columns = ['Squad', 'Total_Cmp', 'Total_Att', 'Total_Cmp%', 'Total_TotDist']
+    
+    # 3. Hapus baris terakhir yang biasanya berisi total/rata-rata liga
+    df = df.iloc[:-1]
+    # ==============================================================================
+    # ==============================================================================
+
+    return df
+
+def filter_teams(df, teams):
+    # Fungsi ini sekarang akan berhasil karena kolom 'Squad' sudah ada
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+
+    teams = ["Arsenal", "Nott'ham Forest"]
+    df_filtered = filter_teams(df, teams)
+
+    print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+    print("=" * 70)
+    # Karena df_filtered sekarang hanya berisi kolom yang kita mau, kita bisa print langsung
+    print(df_filtered)
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004190339.py

@@ -0,0 +1,82 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+# Imports baru untuk menunggu dengan cerdas
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless") # Headless kita matikan dulu untuk debug, agar terlihat apa yang terjadi
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+    
+    # ==============================================================================
+    # === LOGIKA BARU: MENUNGGU CERDAS DAN INTERAKSI HALAMAN ===
+    # ==============================================================================
+    try:
+        # Tunggu max 10 detik sampai tombol cookie muncul, lalu klik
+        wait = WebDriverWait(driver, 10)
+        # Mencari tombol berdasarkan XPath yang berisi teks 'Accept All Cookies'
+        accept_button = wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        # Jika tombol tidak muncul dalam 10 detik, anggap saja tidak ada banner
+        print("No cookie banner found or it took too long.")
+
+    try:
+        # Sekarang, tunggu max 10 detik sampai tabelnya benar-benar muncul
+        wait = WebDriverWait(driver, 10)
+        # Kita tunggu sampai elemen div yang membungkus tabelnya terlihat
+        wait.until(EC.visibility_of_element_located((By.ID, "div_stats_passing")))
+        print("Stats table is now visible.")
+    except TimeoutException:
+        print("The stats table could not be found on the page.")
+        driver.quit()
+        return None # Keluar dari fungsi jika tabel tidak ditemukan
+    # ==============================================================================
+    
+    html_source = driver.page_source
+    driver.quit()
+    
+    print("Data downloaded. Processing with pandas...")
+
+    df = pd.read_html(StringIO(html_source))[0]
+    
+    df = df[[1, 5, 6, 7, 8]]
+    df.columns = ['Squad', 'Total_Cmp', 'Total_Att', 'Total_Cmp%', 'Total_TotDist']
+    df = df.iloc[:-1]
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+    # Pastikan df tidak None sebelum melanjutkan
+    if df is not None:
+        teams = ["Arsenal", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004190507.py

@@ -0,0 +1,85 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    options.add_argument("--headless") # Kita nyalakan lagi headless agar cepat
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+    
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        wait.until(EC.visibility_of_element_located((By.ID, "div_stats_passing")))
+        print("Stats table is now visible.")
+    except TimeoutException:
+        print("The stats table could not be found on the page.")
+        driver.quit()
+        return None
+    
+    html_source = driver.page_source
+    driver.quit()
+    
+    print("Data downloaded. Processing with pandas...")
+
+    # ==============================================================================
+    # === BAGIAN INVESTIGASI BARU ===
+    # ==============================================================================
+    # 1. Baca SEMUA tabel di halaman, jangan hanya ambil yang pertama [0]
+    all_tables = pd.read_html(StringIO(html_source))
+    print(f"\nDEBUG: Found {len(all_tables)} tables on the page.")
+
+    # 2. Cetak ukuran (baris, kolom) dari setiap tabel yang ditemukan
+    for i, table in enumerate(all_tables):
+        print(f"DEBUG: Table [{i}] has shape: {table.shape}")
+    
+    # 3. Kita akan pilih tabel pertama untuk sementara agar bisa melihat output debug
+    # Ini akan menyebabkan error lagi, tapi itu tidak apa-apa.
+    df = all_tables[0]
+    # ==============================================================================
+    
+    df = df[[1, 5, 6, 7, 8]]
+    df.columns = ['Squad', 'Total_Cmp', 'Total_Att', 'Total_Cmp%', 'Total_TotDist']
+    df = df.iloc[:-1]
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        teams = ["Arsenal", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004190633.py

@@ -0,0 +1,90 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless") # Headless kita matikan agar bisa melihat prosesnya
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+    
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        wait.until(EC.visibility_of_element_located((By.ID, "div_stats_passing")))
+        print("Stats table is now visible.")
+        html_source = driver.page_source
+        df = pd.read_html(StringIO(html_source))[1] # Mengambil tabel kedua [1]
+    
+    except TimeoutException:
+        print("The stats table could not be found on the page. Saving debug files...")
+        # ==============================================================================
+        # === BAGIAN DEBUG BARU: SIMPAN BUKTI KEGAGALAN ===
+        # ==============================================================================
+        # Simpan screenshot dari apa yang browser lihat
+        driver.save_screenshot('debug_screenshot.png')
+        # Simpan kode HTML yang sedang ditampilkan
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        # ==============================================================================
+        driver.quit()
+        return None
+    
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+    
+    # ... (sisa kode proses pandas) ...
+    # Saya juga melakukan perbaikan kecil berdasarkan investigasi sebelumnya,
+    # yaitu mencoba mengambil tabel kedua [1] bukan [0]
+    
+    all_tables = pd.read_html(StringIO(html_source))
+    
+    # Kita asumsikan tabel utama adalah yang paling banyak kolomnya
+    # Ini cara yang lebih cerdas untuk menemukan tabel yang benar
+    main_df = max(all_tables, key=lambda df: len(df.columns))
+    print(f"Main table selected with shape: {main_df.shape}")
+
+    df = main_df[[1, 5, 6, 7, 8]]
+    df.columns = ['Squad', 'Total_Cmp', 'Total_Att', 'Total_Cmp%', 'Total_TotDist']
+    df = df.iloc[:-1]
+
+    return df
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        teams = ["Arsenal", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004190944.py

@@ -0,0 +1,91 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        wait.until(EC.visibility_of_element_located((By.ID, "div_stats_passing")))
+        print("Stats table is now visible.")
+        html_source = driver.page_source
+        all_tables = pd.read_html(StringIO(html_source))
+    except TimeoutException:
+        print("The stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Ambil tabel utama (yang paling banyak kolomnya)
+    main_df = max(all_tables, key=lambda df: len(df.columns))
+    print(f"Main table selected with shape: {main_df.shape}")
+
+    # Jika kolom multi-level (MultiIndex), kita gabungkan nama header-nya
+    if isinstance(main_df.columns, pd.MultiIndex):
+        main_df.columns = ['_'.join(col).strip() for col in main_df.columns.values]
+
+    # Coba tampilkan beberapa kolom agar tahu nama sebenarnya
+    print("Available columns:", main_df.columns[:10].tolist())
+
+    # Cari kolom yang relevan untuk passing
+    cols_to_use = [c for c in main_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    df = main_df[cols_to_use]
+
+    # Normalisasi nama kolom agar lebih rapi
+    df.columns = ['Squad', 'Total_Cmp', 'Total_Att', 'Total_Cmp%', 'Total_TotDist']
+    df = df[df['Squad'].notna() & (df['Squad'] != 'Squad')]  # hapus header duplikat
+
+    return df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        teams = ["Arsenal", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251004191947.py

@@ -0,0 +1,107 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable((By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    try:
+        wait = WebDriverWait(driver, 15)
+        wait.until(EC.visibility_of_element_located((By.ID, "stats_passing_team")))
+        print("Team stats table is visible.")
+        html_source = driver.page_source
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Ambil hanya tabel team passing
+    all_tables = pd.read_html(StringIO(html_source))
+    team_df = None
+    for df in all_tables:
+        if 'Squad' in df.columns:
+            team_df = df
+            break
+
+    if team_df is None:
+        print("❌ No team table found.")
+        return None
+
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Bersihkan kolom header ganda jika ada
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Ambil kolom yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    # Hapus baris duplikat atau NaN
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        teams = ["Arsenal", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091604.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Arsenal", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091825.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Nott'ham Forest"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091830.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "B"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091835.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton""]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091839.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Arsenal & Nottingham Forest (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091854.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091857.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005091858.py

@@ -0,0 +1,104 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092140.py

@@ -0,0 +1,106 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+import time
+time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092144.py

@@ -0,0 +1,105 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092150.py

@@ -0,0 +1,105 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+    time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092800.py

@@ -0,0 +1,106 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "url = "https://fbref.com/en/comps/9/teams/Premier-League-Stats"
+"
+    print(f"Opening browser to download team passing stats from {url} ...")
+    time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092803.py

@@ -0,0 +1,105 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "url = "https://fbref.com/en/comps/9/teams/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+    time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092809.py

@@ -0,0 +1,105 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+    time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092817.py

@@ -0,0 +1,106 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+url = "https://fbref.com/en/comps/9/teams/Premier-League-Stats"
+
+    print(f"Opening browser to download team passing stats from {url} ...")
+    time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092820.py

@@ -0,0 +1,106 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/teams/Premier-League-Stats"
+
+    print(f"Opening browser to download team passing stats from {url} ...")
+    time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092822.py

@@ -0,0 +1,105 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_team_passing():
+    url = "https://fbref.com/en/comps/9/teams/Premier-League-Stats"
+    print(f"Opening browser to download team passing stats from {url} ...")
+    time.sleep(5)
+
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # bisa diaktifkan jika tidak perlu melihat browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")))
+        accept_button.click()
+        print("Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # ✅ Tunggu elemen tabel tim muncul (div wrapper)
+    try:
+        wait = WebDriverWait(driver, 20)
+        div_element = wait.until(EC.presence_of_element_located((By.ID, "div_stats_passing_team")))
+        print("✅ Team stats div found, extracting HTML...")
+
+        # Ambil HTML hanya bagian tabel team passing
+        team_html = div_element.get_attribute("outerHTML")
+    except TimeoutException:
+        print("❌ The team stats table could not be found on the page. Saving debug files...")
+        driver.save_screenshot('debug_screenshot.png')
+        with open('debug_page.html', 'w', encoding='utf-8') as f:
+            f.write(driver.page_source)
+        driver.quit()
+        return None
+
+    driver.quit()
+    print("Data downloaded. Processing with pandas...")
+
+    # Baca tabel dari potongan HTML
+    team_df = pd.read_html(StringIO(team_html))[0]
+    print(f"✅ Found team table with shape: {team_df.shape}")
+
+    # Jika ada header dua baris, gabungkan
+    if isinstance(team_df.columns, pd.MultiIndex):
+        team_df.columns = ['_'.join(col).strip() for col in team_df.columns.values]
+
+    # Pilih kolom utama yang relevan
+    cols_to_use = [c for c in team_df.columns if any(x in c for x in ['Squad', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    team_df = team_df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in team_df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    team_df.rename(columns=rename_map, inplace=True)
+
+    team_df = team_df[team_df['Squad'].notna()]
+    team_df = team_df[~team_df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    return team_df
+
+
+def filter_teams(df, teams):
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df = pull_premier_league_team_passing()
+    if df is not None:
+        # Simpan ke CSV otomatis
+        df.to_csv("premier_league_team_passing.csv", index=False)
+        print("\n💾 Saved to premier_league_team_passing.csv")
+
+        teams = ["Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print("\n📊 Passing Stats for Wolves & Brighton (Team Level)")
+        print("=" * 70)
+        print(df_filtered)
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005092904.py

@@ -0,0 +1,131 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_passing():
+    """
+    Ambil data passing (otomatis deteksi: tim atau pemain)
+    dari halaman FBref Premier League terbaru.
+    """
+    # URL utama
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"🌐 Opening browser to download passing stats from {url} ...")
+
+    # --- Setup browser Chrome ---
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # aktifkan jika ingin tanpa tampilan browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    # --- Handle cookie banner (jika muncul) ---
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")
+        ))
+        accept_button.click()
+        print("🍪 Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # --- Coba deteksi tabel TIM terlebih dahulu ---
+    table_html = None
+    try:
+        wait = WebDriverWait(driver, 15)
+        div_team = wait.until(EC.presence_of_element_located((By.ID, "all_stats_passing_team")))
+        print("✅ Team passing table found.")
+        table_html = div_team.get_attribute("outerHTML")
+        table_type = "team"
+    except TimeoutException:
+        print("⚠️ Team passing table not found. Trying player table...")
+
+        # --- Fallback ke tabel pemain ---
+        try:
+            div_player = wait.until(EC.presence_of_element_located((By.ID, "all_stats_passing")))
+            print("✅ Player passing table found.")
+            table_html = div_player.get_attribute("outerHTML")
+            table_type = "player"
+        except TimeoutException:
+            print("❌ No passing table found at all. Saving debug files...")
+            driver.save_screenshot('debug_screenshot.png')
+            with open('debug_page.html', 'w', encoding='utf-8') as f:
+                f.write(driver.page_source)
+            driver.quit()
+            return None
+
+    driver.quit()
+    print("📄 Data downloaded. Processing with pandas...")
+
+    # --- Parse HTML table ke DataFrame ---
+    df = pd.read_html(StringIO(table_html))[0]
+    print(f"✅ Table found with shape: {df.shape}")
+
+    # Gabungkan header dua baris (jika ada)
+    if isinstance(df.columns, pd.MultiIndex):
+        df.columns = ['_'.join(col).strip() for col in df.columns.values]
+
+    # Pilih kolom relevan
+    cols_to_use = [c for c in df.columns if any(x in c for x in ['Squad', 'Player', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    df = df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Player' in c: rename_map[c] = 'Player'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    df.rename(columns=rename_map, inplace=True)
+
+    # Bersihkan baris kosong / header duplikat
+    if 'Squad' in df.columns:
+        df = df[df['Squad'].notna()]
+        df = df[~df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    print(f"✅ Cleaned dataframe shape: {df.shape}")
+    return df, table_type
+
+
+def filter_teams(df, teams):
+    """Filter baris berdasarkan nama tim"""
+    if "Squad" not in df.columns:
+        print("⚠️ 'Squad' column not found, skipping team filter.")
+        return df
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df, table_type = pull_premier_league_passing()
+    if df is not None:
+        # Simpan hasil
+        filename = f"premier_league_{table_type}_passing.csv"
+        df.to_csv(filename, index=False)
+        print(f"\n💾 Saved to {filename}")
+
+        # Filter contoh tim
+        teams = ["Arsenal", "Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print(f"\n📊 Passing Stats ({table_type.title()} Level) for selected teams")
+        print("=" * 80)
+        print(df_filtered.head())
+
+
+if __name__ == "__main__":
+    main()

.history/fbrefdata_example_20251005093119.py

@@ -0,0 +1,61 @@
+import requests
+from bs4 import BeautifulSoup, Comment
+import pandas as pd
+import re
+
+# === 1. URL target (Premier League Passing Stats terbaru) ===
+URL = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+
+print(f"📡 Mengambil data dari {URL} ...")
+
+# === 2. Ambil HTML page ===
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                  "AppleWebKit/537.36 (KHTML, like Gecko) "
+                  "Chrome/120.0.0.0 Safari/537.36"
+}
+response = requests.get(URL, headers=headers)
+
+if response.status_code != 200:
+    raise Exception(f"Gagal mengunduh halaman (status code {response.status_code})")
+
+html = response.text
+
+# === 3. Tangani tabel yang tersembunyi dalam komentar HTML ===
+soup = BeautifulSoup(html, "html.parser")
+
+# FBref sering menyembunyikan tabel di dalam komentar <!-- ... -->
+comments = soup.find_all(string=lambda text: isinstance(text, Comment))
+passing_table_html = None
+
+for c in comments:
+    if 'table' in c and 'passing' in c:
+        if 'id="stats_passing' in c:
+            passing_table_html = c
+            break
+
+if not passing_table_html:
+    raise Exception("❌ Tabel passing tidak ditemukan. Mungkin struktur halaman berubah.")
+
+# === 4. Parse tabel dari komentar ===
+passing_soup = BeautifulSoup(passing_table_html, "html.parser")
+table = passing_soup.find("table")
+
+if table is None:
+    raise Exception("❌ Tidak bisa mem-parse tabel dari komentar HTML.")
+
+# === 5. Konversi ke DataFrame ===
+df = pd.read_html(str(table))[0]
+
+# === 6. Bersihkan kolom ===
+df.columns = [' '.join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+df = df.dropna(how='all')  # hapus baris kosong
+
+# === 7. Simpan ke CSV ===
+csv_name = "premier_league_passing_2025.csv"
+df.to_csv(csv_name, index=False)
+print(f"✅ Data berhasil diunduh dan disimpan ke {csv_name}")
+
+# === 8. Tampilkan preview ===
+print("\n=== Preview Data ===")
+print(df.head(10))

.history/fbrefdata_example_20251005093129.py

@@ -0,0 +1,61 @@
+import requests
+from bs4 import BeautifulSoup, Comment
+import pandas as pd
+import re
+
+# === 1. URL target (Premier League Passing Stats terbaru) ===
+URL = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+
+print(f"📡 Mengambil data dari {URL} ...")
+
+# === 2. Ambil HTML page ===
+headers = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                  "AppleWebKit/537.36 (KHTML, like Gecko) "
+                  "Chrome/120.0.0.0 Safari/537.36"
+}
+response = requests.get(URL, headers=headers)
+
+if response.status_code != 200:
+    raise Exception(f"Gagal mengunduh halaman (status code {response.status_code})")
+
+html = response.text
+
+# === 3. Tangani tabel yang tersembunyi dalam komentar HTML ===
+soup = BeautifulSoup(html, "html.parser")
+
+# FBref sering menyembunyikan tabel di dalam komentar <!-- ... -->
+comments = soup.find_all(string=lambda text: isinstance(text, Comment))
+passing_table_html = None
+
+for c in comments:
+    if 'table' in c and 'passing' in c:
+        if 'id="stats_passing' in c:
+            passing_table_html = c
+            break
+
+if not passing_table_html:
+    raise Exception("❌ Tabel passing tidak ditemukan. Mungkin struktur halaman berubah.")
+
+# === 4. Parse tabel dari komentar ===
+passing_soup = BeautifulSoup(passing_table_html, "html.parser")
+table = passing_soup.find("table")
+
+if table is None:
+    raise Exception("❌ Tidak bisa mem-parse tabel dari komentar HTML.")
+
+# === 5. Konversi ke DataFrame ===
+df = pd.read_html(str(table))[0]
+
+# === 6. Bersihkan kolom ===
+df.columns = [' '.join(col).strip() if isinstance(col, tuple) else col for col in df.columns]
+df = df.dropna(how='all')  # hapus baris kosong
+
+# === 7. Simpan ke CSV ===
+csv_name = "premier_league_passing_2025.csv"
+df.to_csv(csv_name, index=False)
+print(f"✅ Data berhasil diunduh dan disimpan ke {csv_name}")
+
+# === 8. Tampilkan preview ===
+print("\n=== Preview Data ===")
+print(df.head(10))

.history/fbrefdata_example_20251005093230.py

@@ -0,0 +1,131 @@
+import time
+import pandas as pd
+from io import StringIO
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from selenium.webdriver.chrome.options import Options as ChromeOptions
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from selenium.common.exceptions import TimeoutException
+
+
+def pull_premier_league_passing():
+    """
+    Ambil data passing (otomatis deteksi: tim atau pemain)
+    dari halaman FBref Premier League terbaru.
+    """
+    # URL utama
+    url = "https://fbref.com/en/comps/9/passing/Premier-League-Stats"
+    print(f"🌐 Opening browser to download passing stats from {url} ...")
+
+    # --- Setup browser Chrome ---
+    options = ChromeOptions()
+    options.add_argument("--start-maximized")
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    # options.add_argument("--headless")  # aktifkan jika ingin tanpa tampilan browser
+    options.add_experimental_option("excludeSwitches", ["enable-automation"])
+    options.add_experimental_option('useAutomationExtension', False)
+
+    driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+    driver.get(url)
+
+    # --- Handle cookie banner (jika muncul) ---
+    try:
+        wait = WebDriverWait(driver, 10)
+        accept_button = wait.until(EC.element_to_be_clickable(
+            (By.XPATH, "//button[contains(text(), 'Accept All Cookies')]")
+        ))
+        accept_button.click()
+        print("🍪 Cookie banner accepted.")
+    except TimeoutException:
+        print("No cookie banner found or it took too long.")
+
+    # --- Coba deteksi tabel TIM terlebih dahulu ---
+    table_html = None
+    try:
+        wait = WebDriverWait(driver, 15)
+        div_team = wait.until(EC.presence_of_element_located((By.ID, "all_stats_passing_team")))
+        print("✅ Team passing table found.")
+        table_html = div_team.get_attribute("outerHTML")
+        table_type = "team"
+    except TimeoutException:
+        print("⚠️ Team passing table not found. Trying player table...")
+
+        # --- Fallback ke tabel pemain ---
+        try:
+            div_player = wait.until(EC.presence_of_element_located((By.ID, "all_stats_passing")))
+            print("✅ Player passing table found.")
+            table_html = div_player.get_attribute("outerHTML")
+            table_type = "player"
+        except TimeoutException:
+            print("❌ No passing table found at all. Saving debug files...")
+            driver.save_screenshot('debug_screenshot.png')
+            with open('debug_page.html', 'w', encoding='utf-8') as f:
+                f.write(driver.page_source)
+            driver.quit()
+            return None
+
+    driver.quit()
+    print("📄 Data downloaded. Processing with pandas...")
+
+    # --- Parse HTML table ke DataFrame ---
+    df = pd.read_html(StringIO(table_html))[0]
+    print(f"✅ Table found with shape: {df.shape}")
+
+    # Gabungkan header dua baris (jika ada)
+    if isinstance(df.columns, pd.MultiIndex):
+        df.columns = ['_'.join(col).strip() for col in df.columns.values]
+
+    # Pilih kolom relevan
+    cols_to_use = [c for c in df.columns if any(x in c for x in ['Squad', 'Player', 'Cmp', 'Att', 'Cmp%', 'TotDist'])]
+    df = df[cols_to_use]
+
+    # Normalisasi nama kolom
+    rename_map = {}
+    for c in df.columns:
+        if 'Squad' in c: rename_map[c] = 'Squad'
+        elif 'Player' in c: rename_map[c] = 'Player'
+        elif 'Cmp%' in c: rename_map[c] = 'Total_Cmp%'
+        elif 'Cmp' in c and 'Cmp%' not in c: rename_map[c] = 'Total_Cmp'
+        elif 'Att' in c: rename_map[c] = 'Total_Att'
+        elif 'TotDist' in c: rename_map[c] = 'Total_TotDist'
+    df.rename(columns=rename_map, inplace=True)
+
+    # Bersihkan baris kosong / header duplikat
+    if 'Squad' in df.columns:
+        df = df[df['Squad'].notna()]
+        df = df[~df['Squad'].str.contains("Squad|Rk", na=False)]
+
+    print(f"✅ Cleaned dataframe shape: {df.shape}")
+    return df, table_type
+
+
+def filter_teams(df, teams):
+    """Filter baris berdasarkan nama tim"""
+    if "Squad" not in df.columns:
+        print("⚠️ 'Squad' column not found, skipping team filter.")
+        return df
+    return df[df["Squad"].isin(teams)]
+
+
+def main():
+    df, table_type = pull_premier_league_passing()
+    if df is not None:
+        # Simpan hasil
+        filename = f"premier_league_{table_type}_passing.csv"
+        df.to_csv(filename, index=False)
+        print(f"\n💾 Saved to {filename}")
+
+        # Filter contoh tim
+        teams = ["Arsenal", "Wolves", "Brighton"]
+        df_filtered = filter_teams(df, teams)
+        print(f"\n📊 Passing Stats ({table_type.title()} Level) for selected teams")
+        print("=" * 80)
+        print(df_filtered.head())
+
+
+if __name__ == "__main__":
+    main()

.history/historical_data_20251005104343.py

@@ -0,0 +1,140 @@
+import pandas as pd
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service as ChromeService
+from webdriver_manager.chrome import ChromeDriverManager
+from selenium.webdriver.common.by import By
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.support import expected_conditions as EC
+from io import StringIO
+import time
+import sys
+
+# --- FUNGSI UNTUK MENGHITUNG RATA-RATA PASSING % PER TIM ---
+def calculate_team_passing_avg(passing_stats_file):
+    """
+    Membaca file statistik passing pemain dan menghitung rata-rata
+    persentase passing ('Total_Cmp%') untuk setiap tim.
+    """
+    try:
+        df_pass = pd.read_csv(passing_stats_file)
+        if "Squad" not in df_pass.columns or "Total_Cmp%" not in df_pass.columns:
+            print(f"❌ Error: Kolom 'Squad' atau 'Total_Cmp%' tidak ditemukan di {passing_stats_file}")
+            return None
+
+        # Mengubah tipe data dan menghitung rata-rata
+        df_pass['Total_Cmp%'] = pd.to_numeric(df_pass['Total_Cmp%'], errors='coerce')
+        team_avg_pass = df_pass.groupby('Squad')['Total_Cmp%'].mean().reset_index()
+        team_avg_pass.rename(columns={'Total_Cmp%': 'AvgPass%'}, inplace=True)
+        print("✅ Berhasil menghitung rata-rata passing % per tim.")
+        return team_avg_pass
+
+    except FileNotFoundError:
+        print(f"❌ Error: File '{passing_stats_file}' tidak ditemukan.")
+        print("   Pastikan file ini ada di folder yang sama.")
+        return None
+    except Exception as e:
+        print(f"❌ Terjadi error saat memproses {passing_stats_file}: {e}")
+        return None
+
+
+# --- FUNGSI UTAMA UNTUK SCRAPING DATA PERTANDINGAN ---
+def scrape_historical_matches():
+    """
+    Scrape data pertandingan historis dari FBref menggunakan Selenium.
+    """
+    # URL untuk data Premier League musim 2023-2024 yang sudah selesai
+    url = "https://fbref.com/en/comps/9/schedule/2023-2024/Premier-League-Scores-and-Fixtures"
+    print(f"🌐 Mengakses halaman: {url}")
+
+    options = webdriver.ChromeOptions()
+    options.add_argument("--headless") # Jalankan di background tanpa membuka browser
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    options.add_argument("user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.212 Safari/537.36")
+
+    driver = None
+    try:
+        driver = webdriver.Chrome(service=ChromeService(ChromeDriverManager().install()), options=options)
+        driver.get(url)
+
+        # Coba klik cookie banner jika ada
+        try:
+            wait = WebDriverWait(driver, 5)
+            accept_button = wait.until(EC.element_to_be_clickable((By.XPATH, '//button[text()="Accept All"]')))
+            accept_button.click()
+            print("✅ Cookie banner diterima.")
+            time.sleep(2)
+        except:
+            print("ℹ️ Tidak ada cookie banner atau sudah diterima.")
+
+        # Ambil HTML dari tabel data pertandingan
+        try:
+            table_element = WebDriverWait(driver, 10).until(
+                EC.presence_of_element_located((By.ID, "sched_2023-2024_9_1"))
+            )
+            html_source = table_element.get_attribute('outerHTML')
+            print("✅ Berhasil mengambil tabel data pertandingan.")
+            return html_source
+        except Exception as e:
+            print(f"❌ Gagal menemukan tabel pertandingan: {e}")
+            return None
+            
+    finally:
+        if driver:
+            driver.quit()
+
+# --- MAIN SCRIPT ---
+if __name__ == "__main__":
+    PASSING_STATS_FILE = "premier_league_player_passing.csv"
+    OUTPUT_FILE = "historical_matches.csv"
+
+    # 1. Hitung rata-rata passing dari file yang sudah ada
+    team_pass_avg_df = calculate_team_passing_avg(PASSING_STATS_FILE)
+    if team_pass_avg_df is None:
+        sys.exit()
+
+    # 2. Scrape data historis pertandingan
+    html_table = scrape_historical_matches()
+    if html_table is None:
+        sys.exit()
+
+    # 3. Proses data hasil scrape
+    print("⚙️ Memproses data pertandingan...")
+    df_matches = pd.read_html(StringIO(html_table))[0]
+
+    # Membersihkan data
+    df_matches = df_matches[['Date', 'Home', 'Score', 'Away']]
+    df_matches.dropna(subset=['Score'], inplace=True)
+    df_matches = df_matches[df_matches['Score'].str.contains('–', na=False)]
+
+    scores = df_matches['Score'].str.split('–', expand=True)
+    df_matches['HomeGoals'] = pd.to_numeric(scores[0])
+    df_matches['AwayGoals'] = pd.to_numeric(scores[1])
+    
+    print("🔄 Menggabungkan data pertandingan dengan data passing...")
+    
+    # Buat dictionary untuk mapping nama tim ke passing %
+    pass_map = {row['Squad']: row['AvgPass%'] for index, row in team_pass_avg_df.iterrows()}
+    
+    def get_pass_perc(team_name):
+        if team_name in pass_map:
+            return pass_map[team_name]
+        for squad_name, perc in pass_map.items():
+            if team_name in squad_name or squad_name in team_name:
+                return perc
+        return team_pass_avg_df['AvgPass%'].mean()
+
+    df_matches['HomePass%'] = df_matches['Home'].apply(get_pass_perc)
+    df_matches['AwayPass%'] = df_matches['Away'].apply(get_pass_perc)
+    
+    # Finalisasi DataFrame
+    final_df = df_matches[['Date', 'Home', 'Away', 'HomeGoals', 'AwayGoals', 'HomePass%', 'AwayPass%']]
+    final_df = final_df.round(1)
+
+    # 4. Simpan ke CSV
+    try:
+        final_df.to_csv(OUTPUT_FILE, index=False)
+        print(f"\n🎉 SUKSES! File '{OUTPUT_FILE}' berhasil dibuat dengan {len(final_df)} data pertandingan.")
+        print("   Sekarang Anda bisa menjalankan script prediksi utama Anda.")
+    except Exception as e:
+        print(f"❌ Gagal menyimpan file CSV: {e}")