如何使用美丽汤从网站获取特定的子类？

Question

我想从这个链接中获取表格： 足球运动员市场价值 我设法这样做了，用这个代码：def few(urls, file):f = open(file, 'a', newline='', encoding="utf-8")writer = csv.writer(f)url = urlspage = requests.get(url, headers={'User-Agent': 'Mozilla/5.0'})soup = BeautifulSoup(page.content, 'lxml')tbody = soup('table', {"class": "items"})[0].find_all('tr')for row in tbody:    cols = row.findChildren(recursive=False)[1:]    exclude = [0, 3, 4, 6, 7, 8]    cols = [ele.text.strip() for ele in cols[:] if ele not in exclude]    writer.writerow(cols)我的问题是，从第一列开始，我只想得到名字（例如：“Ram Strauss”），而不是它包含的所有数据。你能帮忙吗？谢谢！

Answer 1

import requests , csv

def SaveAsCsv(list_of_rows,file_name):

    try:

        print('\nSaving CSV Result')

        with open(file_name, 'a',  newline='', encoding='utf-8') as outfile:

            writer = csv.writer(outfile)

            writer.writerow(list_of_rows)

            print("rsults saved successully")

    except PermissionError:

        print(f"Please make sure {file_name} is closed \n")

def fetch_data(url,file_name='test.csv'):

        page = requests.get(url, headers={'User-Agent': 'Mozilla/5.0'})

        if page.status_code == 200 :

                soup = BeautifulSoup(page.content, 'lxml')

                header = [col_name.text.strip() for col_name in soup.select('table.items thead th')[1:]]

                SaveAsCsv(header,file_name)

                rows = soup.select('table.items tbody tr')

                for row in rows:                        

                        name_tag = row.select('img.bilderrahmen-fixed')

                        if name_tag:

                                name = name_tag[0].get('title')

                                tds  = row.select('td')[5:]

                                cols = [ele.text.strip() for ele in tds]

                                if cols :

                                        cols.insert(0,name) 

                                        SaveAsCsv(cols,file_name)

fetch_data('https://www.transfermarkt.com/hapoel-acre/kader/verein/6025/saison_id/2017/plus/1')