python - 提取游戏数据：不正确的值

Question

我对 BeautifulSoup 很陌生

我正在努力从类似的代码中获取游戏数据，但我不理解语法和放置。

此代码适用于一页：

browser = webdriver.Chrome()
    
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


urls = {
"https://www.oddsportal.com/soccer/australia/a-league/results/#/page/1/",

}
if __name__ == '__main__':

    results = None

    for url in urls:
        try:
            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)
        except ValueError:
            game_data = parse_data(url)
            if game_data is None:
                continue
            result = pd.DataFrame(game_data.__dict__)
            if results is None:
                results = result
        except AttributeError:
            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)

print(tabulate(results.head(), headers='keys', tablefmt="github"))

结果：

|    | date              | time   | game                                     | score   |   home_odds |   draw_odds |   away_odds | country   | league   |
|----|-------------------|--------|------------------------------------------|---------|-------------|-------------|-------------|-----------|----------|
|  0 | Yesterday, 03 Apr | 09:05  | Brisbane Roar - WS Wanderers             | 1:1     |        2.38 |        3.65 |        2.79 | Australia | A-League |
|  1 | 02 Apr 2021       | 08:05  | Macarthur FC - Perth Glory               | 2:0     |        2.01 |        3.66 |        3.57 | Australia | A-League |
|  2 | 01 Apr 2021       | 09:40  | Central Coast Mariners - Adelaide United | 2:1     |        2.1  |        3.8  |        3.17 | Australia | A-League |
|  3 | 01 Apr 2021       | 07:35  | Western United - Melbourne City          | 2:1     |        5.95 |        4.61 |        1.49 | Australia | A-League |
|  4 | 28 Mar 2021       | 08:10  | Adelaide United - Sydney FC              | 1:0     |        2.97 |        3.72 |        2.24 | Australia | A-League |

我修改了另一个页面的代码：

    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': 'table-matches'})
        main = content.find('th', {'class': 'first2 tl'})
        if main is None:
            return None
        count = main.findAll('a')
# The competition and the country was earlier for the same for the entire page. Now its different for every match. Hos can I capture that data?
        country = count[0].text
        league = count[1].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
    
    
    urls = {
    "https://www.oddsportal.com/matches/soccer/20210405/",
    
    }

……

我得到了同一个国家和所有人的竞争，而它却不一样。

|    | date                        | time   | game                           | score                          |   home_odds |   draw_odds |   away_odds | country   | league                      |
|----|-----------------------------|--------|--------------------------------|--------------------------------|-------------|-------------|-------------|-----------|-----------------------------|
|  0 |                             | 00:00  | Racing Club - Godoy Cruz       | Racing Club - Godoy Cruz       |        1.74 |        3.63 |        4.56 | Argentina | Copa de la Liga Profesional |
|  1 | Costa Rica»Primera Division | 00:00  | Sporting San Jose - San Carlos | Sporting San Jose - San Carlos |        2.65 |        2.85 |        2.81 | Argentina | Copa de la Liga Profesional |
|  2 | Guatemala»Liga Nacional     | 00:00  | Comunicaciones - Iztapa        | Comunicaciones - Iztapa        |        1.49 |        3.83 |        5.83 | Argentina | Copa de la Liga Profesional |
|  3 | Mexico»Liga MX              | 00:00  | Queretaro - U.A.N.L.- Tigres   | Queretaro - U.A.N.L.- Tigres   |        3.34 |        3.29 |        2.18 | Argentina | Copa de la Liga Profesional |
|  4 | Colombia»Primera A          | 01:00  | Junior - Aguilas               | Junior - Aguilas               |        1.66 |        3.3  |        5.99 | Argentina | Copa de la Liga Profesional 

|

如何编辑代码？

我了解页面的 Xpath 与工作的不同，即

//*[@id="table-matches"]/table/tbody/tr[2]/td[2]/a[2]

标签： pythonweb-scrapingbeautifulsoup