如何使用selenium循环浏览页面？

Question

我试图从Oddsportal中获取数据，但我有一个不完整的代码

如何循环浏览比赛和赛季的页面

我刚刚开始使用硒，我对它很陌生

我目前的代码是：

browser = webdriver.Chrome()
browser.get("https://www.oddsportal.com/soccer/england/premier-league/results/")

df = pd.read_html(browser.page_source, header=0)[0]

dateList = []
gameList = []
scoreList = []
home_odds = []
draw_odds = []
away_odds = []

for row in df.itertuples():
    if not isinstance(row[1], str):
        continue
    elif ':' not in row[1]:
        date = row[1].split('-')[0]
        continue
    time = row[1]
    dateList.append(date)
    gameList.append(row[2])
    scoreList.append(row[3])
    home_odds.append(row[4])
    draw_odds.append(row[5])
    away_odds.append(row[6])

result = pd.DataFrame({'date': dateList,
                       'game': gameList,
                       'score': scoreList,
                       'Home': home_odds,
                       'Draw': draw_odds,
                       'Away': away_odds})

Answer 1

您必须首先创建for循环

class GameData:

    def __init__(self):
        self.date = []
        self.time = []
        self.game = []
        self.score = []
        self.home_odds = []
        self.draw_odds = []
        self.away_odds = []
        self.country = []
        self.league = []


def parse_data(url):
    browser.get(url)
    df = pd.read_html(browser.page_source, header=0)[0]
    html = browser.page_source
    soup = bs(html, "lxml")
    cont = soup.find('div', {'id': 'wrap'})
    content = cont.find('div', {'id': 'col-content'})
    content = content.find('table', {'class': 'table-main'}, {'id': 'tournamentTable'})
    main = content.find('th', {'class': 'first2 tl'})
    if main is None:
        return None
    count = main.findAll('a')
    country = count[1].text
    league = count[2].text
    game_data = GameData()
    game_date = None
    for row in df.itertuples():
        if not isinstance(row[1], str):
            continue
        elif ':' not in row[1]:
            game_date = row[1].split('-')[0]
            continue
        game_data.date.append(game_date)
        game_data.time.append(row[1])
        game_data.game.append(row[2])
        game_data.score.append(row[3])
        game_data.home_odds.append(row[4])
        game_data.draw_odds.append(row[5])
        game_data.away_odds.append(row[6])
        game_data.country.append(country)
        game_data.league.append(league)
    return game_data

# input URLs here
urls = {}

if __name__ == '__main__':

    results = None

    for url in urls:
        game_data = parse_data(url)
        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)