Spaces:
Sleeping
Sleeping
File size: 4,439 Bytes
abcb943 7f1dc32 abcb943 8c94d1f 7f1dc32 8c94d1f 132b34b 7f1dc32 8c94d1f abcb943 7f1dc32 abcb943 19e44c2 abcb943 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
import os
import pandas as pd
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.chrome.options import Options
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 webdriver_manager.core.os_manager import ChromeType
from helper import convert_percentage_to_decimal
def setup_driver():
"""Setup and return a configured Chrome WebDriver with optimized settings"""
chrome_options = Options()
chrome_options.add_argument("--headless")
chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage")
chrome_options.add_argument("--disable-gpu")
chrome_options.add_argument("--disable-extensions")
chrome_options.add_argument("--disable-logging")
chrome_options.add_argument("--log-level=3")
chrome_options.add_argument("--silent")
chrome_options.page_load_strategy = 'eager'
chrome_options.add_argument(
"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
)
# Check if we're running in Hugging Face Spaces or locally
if 'HF_SPACE' in os.environ:
# Hugging Face Space is detected, handle accordingly (example for versioning)
print("Running on Hugging Face Space.")
chromedriver_path = ChromeDriverManager().install()
else:
# Local environment setup
print("Running chrome webdriver.")
chromedriver_path = ChromeDriverManager(chrome_type=ChromeType.CHROMIUM).install()
# Create the Service object using the installed chromedriver
service = Service(executable_path=chromedriver_path)
# Return the configured WebDriver instance
driver = webdriver.Chrome(service=service, options=chrome_options)
return driver
def get_weekly_meta():
print("======================== IN get_weekly_meta() ===============================\n")
BASE_URL = "https://www.op.gg/statistics/champions?tier=challenger&period=week&mode=ranked"
driver = setup_driver()
try:
driver.get(BASE_URL)
table = WebDriverWait(driver, 20).until(
EC.presence_of_element_located((By.CSS_SELECTOR, "#content-container > div:nth-child(2) > table"))
)
# Extract table rows
rows = table.find_elements(By.TAG_NAME, "tr")
# Define the column order
columns = ["rank", "champion", "games", "KDA", "WR", "pick", "ban", "cs", "gold"]
data = []
for row in rows[1:]: # Skip the header row
cells = row.find_elements(By.TAG_NAME, "td")
row_data = [cell.text for cell in cells]
if len(row_data) >= len(columns):
# Remove ":1" from KDA format
row_data[3] = row_data[3].replace(":1", "")
# Convert WR, pick, and ban percentages to decimals
row_data[4] = convert_percentage_to_decimal(row_data[4])
row_data[5] = convert_percentage_to_decimal(row_data[5])
row_data[6] = convert_percentage_to_decimal(row_data[6])
# Remove commas from the gold values
row_data[8] = int(row_data[8].replace(",", ""))
data.append(row_data[:len(columns)])
# Create a DataFrame with the extracted data
df = pd.DataFrame(data, columns=columns)
# Ensure the directory exists
os.makedirs('./util/data', exist_ok=True)
# Define the save path
save_path = "./util/data/weekly_meta_stats.csv"
# Automatically save the DataFrame to a CSV file in the specified directory
df.to_csv(save_path, index=False)
# Print confirmation message
print(f"Saved weekly meta to {save_path}")
print("======================== Exiting: IN get_weekly_meta() ===============================")
return df
except Exception as e:
print(f"Error: {e}")
return None
finally:
driver.quit()
# if __name__ == "__main__":
# weekly_meta_data = get_weekly_meta()
# if weekly_meta_data is not None:
# print(weekly_meta_data) |