import pandas as pd
from selenium import webdriver
from datetime import datetime
from bs4 import BeautifulSoup as bs
from math import nan
from tabulate import tabulate
import os

pd.set_option('display.max_rows', 30000)
pd.set_option('display.max_columns', 500)
pd.set_option('display.width', 1000)

start = datetime.now()

os.chdir(r"C:\Users\harsh\Google Drive\Oddsportal\Webdriver")
cwd = os.getcwd()
print("Path for webdriver : ")
print(cwd)
browser = webdriver.Chrome()


class GameData:
    def __init__(self):
        self.score = []
        self.country = []
        self.league = []
        self.game = []

    def append(self, score):
        pass


def get_urls(browser, landing_page):
    browser.get(landing_page)
    urls = [i.get_attribute('href') for i in
            browser.find_elements_by_css_selector(
                '.next-games-date > a:nth-child(1), .next-games-date > a:nth-child(n+3)')]

    return urls


def parse_data(html):
    global league
    df = pd.read_html(html, header=0)[0]
    # print(len(df.index))
    # print(df.columns)
    html = browser.page_source
    soup = bs(html, "lxml")
    # print(len(soup.select('#table-matches tr')))
    scores = [i.select_one('.table-score').text if i.select_one('.table-score') is not None else nan for i in
              soup.select('#table-matches tr:nth-of-type(n+2)')]
    cont = soup.find('div', {'id': 'wrap'})
    content = cont.find('div', {'id': 'col-content'})
    content = content.find('table', {'class': 'table-main'}, {'id': 'table-matches'})
    main = content.find('th', {'class': 'first2 tl'})

    if main is None:
        return None

    count = main.findAll('a')
    country = count[0].text
    game_data = GameData()
    leagues = [i.text for i in soup.select('.first2 > a:last-child')]

    n = 0

    for number, row in enumerate(df.itertuples()):
        if n == 0 or '»' in row[1]:
            league = leagues[n]
            n += 1
        if not isinstance(row[1], str):
            continue
        elif ':' not in row[1]:
            country = row[1].split('»')[0]
            continue
        game_time = row[1]
        print(len(scores[number]))
        print(scores[number])

        game_data.country.append(country)
        game_data.league.append(league)
        game_data.game.append(row[2])
        game_data.score.append(scores[number])

    return game_data


if __name__ == '__main__':

    start_url = "https://www.oddsportal.com/matches/soccer/"
    urls = []
    browser = webdriver.Chrome()
    results = None
    urls = get_urls(browser, start_url)
    urls.insert(0, start_url)

    for number, url in enumerate(urls):
        if number > 0:
            browser.get(url)
        html = browser.page_source
        game_data = parse_data(html)

        if game_data is None:
            continue

        result = pd.DataFrame(game_data.__dict__)

        if results is None:
            results = result
        else:
            results = results.append(result, ignore_index=True)
#
print(tabulate(results, headers='keys', tablefmt='github'))
#
# results.to_csv(r"C:\Users\harsh\Google Drive\Oddsportal\Files\Oddsportal "
#                r"Data\Pre-processed\oddsportal_upcoming_matches.csv")