我无法在 dataframe 中添加两列

Question

我正在尝试在 dataframe 中添加两列。 我无法检查他们的属性。 我怎样才能了解它？

import re
import textwrap
import pandas as pd
import numpy as np
import requests
from bs4 import BeautifulSoup
from pandas import DataFrame

URL = "https://www.soccerbase.com/teams/team.sd?team_id=536&comp_id=1&teamTabs=results"
# URL = "http://worldpopulationreview.com/countries/countries-by-gdp/"
r = requests.get(URL)

# soup = BeautifulSoup(r.content, 'html.parser')
soup = BeautifulSoup(r.content, 'html.parser')

table = soup.find('table', {'class': 'soccerGrid'})


def rowgetdatatext(tr, coltag='td', true=None):  # td (data) or th (header)
    cols = []
    for td in tr.find_all(coltag):
        cols.append(td.get_text(strip=true))
    return cols


def tabledatatext(table):
    rows = []
    trs = table.find_all('tr')
    headerow = rowgetdatatext(trs[0], 'th')
    if headerow:  # if there is a header row include first
        rows.append(headerow)
        trs = trs[1:]
    for tr in trs:  # for every table row
        rows.append(rowgetdatatext(tr, 'td'))  # data row
    return rows


d = tabledatatext(table)

pd.set_option('display.width', 400)
pd.set_option('display.max_columns', 20)
df = pd.DataFrame(d)

Frame = pd.DataFrame(df.values,
                     columns=["Competition", "Date", "Omit", "Home Team", "Score", "Away Team", "Omit",
                              "Omit", "Omit", "DateKeep"
                              ])
Frame = Frame.drop(columns=["Omit", "Date"])
Frame = Frame.drop([0, 1], axis=0)

Frame[['Home Score', 'Away Score']] = Frame['Score'].str.split('-', expand=True)
Frame = Frame.drop(columns="Score")
Frame = Frame[["Competition", "Home Team", "Home Score", "Away Team", "Away Score",
               "DateKeep"]]

Frame['Home Team'] = Frame['Home Team'].str[:-20]
Frame['Away Team'] = Frame['Away Team'].str[:-20]
Frame['DateKeep'] = Frame['DateKeep'].str[3:]
Frame['Competition'] = Frame['Competition'].str[:-18]

# Frame['Home Score'] = Frame['Home Score'].str.split()
# Frame['Away Score'] = Frame['Away Score'].str.split()

# pd.to_numeric(Frame['Away Score'], errors='coerce')
F2 = Frame.index(Frame)
print(Frame)
print(F2)

样品 output 是：

比赛 主队 主队 客队 客场 比分 DateKeep 2 英超 英超 曼联 4 切尔西 0 2019-08-11 16:30 3 欧洲超级杯 欧洲超级杯 利物浦 2 切尔西 2 2019-08-14 20:00 4 英超英超切尔西 1 莱斯特 1 2019-08-18 16:30 5 英超 英超 诺维奇 2 切尔西 3 2019-08-24 12:30 6 英超 英超 切尔西 2 谢夫联 2 2019-08-31 15:00 7英超 英超 狼队 2 切尔西 5 2019-09-14 15:00

如果我想添加 Home Score 和 Away Score 列，它会连接这两个值而不是相加。 我在哪里没有得到它？ 谢谢编辑：添加当前 output 和所需 output 的屏幕截图在此处输入图像描述

Answer 1

我将使用其中一个分数列的长度来收集每列感兴趣的值的列表，以将其他列列表大小限制为相同。 然后 zip 这些列表并转换为 df。 如果您已将先前的分数列转换为整数，则可以计算最后两列。

import pandas as pd
import requests
from bs4 import BeautifulSoup as bs

headers = ['Competition','Home Team','Home Score','Away Team','Away Score','Date Keep','Total Score (Home + Away Score)','Goal Difference (Home - Away Score)']
r = requests.get('https://www.soccerbase.com/teams/team.sd?team_id=536&comp_id=1&teamTabs=results')
soup = bs(r.content, 'lxml')

h_scores = [int(i.text) for i in soup.select('.score a em:first-child')]
a_scores = [int(i.text) for i in soup.select('.score a em + em')]
total_scores = [h+a for h,a in zip(h_scores, a_scores)]
diff_scores = [h-a for h,a in zip(h_scores, a_scores)]
limit = len(a_scores)
comps = [i.text for i in soup.select('.tournament a', limit=limit)]
dates = [i.text for i in soup.select('.dateTime .hide', limit=limit)]
h_teams = [i.text for i in soup.select('.homeTeam a', limit=limit)]
a_teams = [i.text for i in soup.select('.awayTeam a', limit=limit)]

df = pd.DataFrame(zip(comps, h_teams, h_scores, a_teams, a_scores, dates, total_scores, diff_scores), columns = headers)
print(df)