import asyncio
import requests
import sys
import time

from bs4 import BeautifulSoup
import pandas as pd
import pybaseball as pb



def pull_stats(start_date_string: str, end_date_string: str):
    print(f"Pulling stats from {start_date_string} to {end_date_string}")
    data = pb.batting_stats_range(start_date_string, end_date_string)
    print("Got it!")
    return data


def batting_game_log_table(bbref_id: str, season: int = 1998):
    page_url = f"https://www.baseball-reference.com/players/gl.fcgi?id={bbref_id}&t=b&year={season}"
    soup = BeautifulSoup(requests.get(page_url).text, "html.parser")
    time.sleep(3)
    table = soup.find("table", {"id": "batting_gamelogs"})
    tbody = table.find("tbody")
    headers = []
    data = []
    indeces = []

    for row in tbody.find_all("tr"):
        row_data = []
        col_names = []
        for cell in row.find_all("td"):
            row_data.append(cell.text)
            if len(headers) == 0:
                col_names.append(cell["data-stat"])

        if len(row_data) > 0:
            data.append(row_data)
            indeces.append(row_data[0])
            if len(headers) == 0:
                headers.extend(col_names)

    player_frame = pd.DataFrame(data, index=indeces, columns=headers)
    return player_frame


def batting_splits_table(bbref_id: str, season: int = 1998):
    page_url = f"https://www.baseball-reference.com/players/split.fcgi?id={bbref_id}&year={season}&t=b"
    soup = BeautifulSoup(requests.get(page_url).text, "lxml")
    time.sleep(3)
    table = soup.find("table", {"id": "plato"})
    tbody = table.find("tbody")
    headers = []
    data = []
    indeces = []

    for row in tbody.findAll("tr"):
        row_data = []
        col_names = []
        for cell in row.find_all("td"):
            row_data.append(cell.text)
            if len(headers) == 0:
                col_names.append(cell["data-stat"])

        if len(row_data) > 0:
            data.append(row_data)
            indeces.append(row_data[0])
            if len(headers) == 0:
                headers.extend(col_names)

    bsplit_frame = pd.DataFrame(data, index=indeces, columns=headers)
    return bsplit_frame


async def main(args):
    # print('Fetching peripherals')
    # peripherals = get_pitching_peripherals(2021)
    # print('Got them!')
    # print(f'There are {len(peripherals)} records')

    # month_1 = pull_stats('1997-03-01', '1997-04-30')
    # print(f'Received {len(month_1)} records.')

    # print(f'Grabbing game logs...')
    # player_frame = batting_game_log_table('jeterde01')
    # print(f'Received {len(player_frame)} records')

    print("Grabbing game logs...")
    player_frame = batting_splits_table("jeterde01")
    print(f"Received {len(player_frame)} records")

    pass


if __name__ == "__main__":
    asyncio.run(main(sys.argv[1:]))