Question

我是新手，正在学习BeautifulSoup。有人可以看看下面的代码吗？我想要网站上的剪贴数据，但没有成功。我想创建一个数据框，其中包含每年玩家到来的总数和一列玩家平均年龄。

我的代码：

import pandas as pd
import requests
from bs4 import BeautifulSoup


anos_list = list(range(2005, 2018))

anos_lista = []
valor_contratos_lista = []
idade_média_lista = []

    for ano_lista in anos_list:
        url = 'https://www.transfermarkt.com/flamengo-rio-de-janeiro/transfers/verein/614/saison_id/'+ str(anos_list) + ''
        page = requests.get(url, headers={'User-Agent': 'Custom5'})
        soup = BeautifulSoup(page.text, 'html.parser')

    tag_list = soup.tfoot.find_all('td')
    valor = (tag_list[0].string)
    idade = (tag_list[1].string)
    ano = ano_lista 

    valor_contratos_lista.append(valor)
    idade_media_lista.append(idade)
    anos_lista.append(ano)


flamengo_df = pd.DataFrame({'Ano': ano_lista,
         'Despesa com contratações':valor_contratos_lista,
                        'Média de idade': idade_média_lista
                       })
flamengo_df.to_csv('flamengo.csv', encoding = 'utf-8')`

Answer 1

这是我的方法：

使用Beautiful Soup + Regex：

import requests
from bs4 import BeautifulSoup
import re
import numpy as np

# Set min and max years as variables
min_year = 2005
max_year = 2019
year_range = list(range(min_year, 2019+1))
base_url = 'https://www.transfermarkt.com/flamengo-rio-de-janeiro/transfers/verein/614/saison_id/'

# Begin iterating
records = []
for year in year_range:

    url = base_url+str(year)

    # get the page
    page = requests.get(url, headers={'User-Agent': 'Custom5'})
    soup = BeautifulSoup(page.text, 'html.parser')

    # I used the class of "responsive table"
    tables = soup.find_all('div',{'class':'responsive-table'})
    rows = tables[0].find_all('tr')
    cells = [row.find_all('td', {'class':'zentriert'}) for row in rows]

    # get variable names:
    variables = [x.text for x in rows[0].find_all('th')]
    variables_values = {x:[] for x in variables}
    # get values
    for row in rows:
        values = [' '.join(x.text.split()) for x in row.find_all('td')]
        values = [x for x in values if x!='']

        if len(variables)< len(values):
            values.pop(4)
            values.pop(2)  
        for k,v in zip(variables_values.keys(), values):
            variables_values[k].append(v)

    num_pattern = re.compile('[0-9,]+')
    to_float = lambda x: float(x) if x!='' else np.NAN
    get_nums = lambda x: to_float(''.join(num_pattern.findall(x)).replace(',','.'))

    # Add values to an individual record
    rec = {
        'Url':url,
        'Year':year,
        'Total Transfers':len(variables_values['Player']),
        'Avg Age': np.mean([int(x) for x in variables_values['Age']]),
        'Avg Cost': np.nanmean([get_nums(x) for x in variables_values['Fee'] if ('loan' not in x)]),
        'Total Cost': np.nansum([get_nums(x) for x in variables_values['Fee'] if ('loan' not in x)]),
    }

    # Store record
    records.append(rec)

此后，初始化数据框： 值得注意的是，其中一些数字代表数百万，需要对其进行调整。

import pandas as pd

# Drop the URL
df = pd.DataFrame(records, columns=['Year','Total Transfers','Avg Age','Avg Cost','Total Cost'])

    Year  Total Transfers    Avg Age    Avg Cost  Total Cost
0   2005               26  22.038462    2.000000        2.00
1   2006               32  23.906250  240.660000     1203.30
2   2007               37  22.837838  462.750000     1851.00
3   2008               41  22.926829  217.750000      871.00
4   2009               31  23.419355  175.000000      350.00
5   2010               46  23.239130  225.763333     1354.58
6   2011               47  23.042553  340.600000     1703.00
7   2012               45  24.133333  345.820000     1037.46
8   2013               36  24.166667  207.166667      621.50
9   2014               37  24.189189  111.700000      335.10
10  2015               49  23.530612  413.312000     2066.56
11  2016               41  23.341463  241.500000      966.00
12  2017               31  24.000000  101.433333      304.30
13  2018               18  25.388889  123.055000      738.33
14  2019               10  25.300000         NaN        0.00

我的年份列表不适用于BeautifulSoup。为什么？

1 个答案: