import requests
from bs4 import BeautifulSoup
import re
import pandas as pd
def tableData(data, attrs):
row = []
data = data.find(attrs=attrs)
tr = data.find_all('tr')
header = [ th.get_text(strip=True) for th in data.find_all('th') ]
if header:
row.append(header)
for tr in tr[1:]:
row.append([ td.get_text(strip=True) for td in tr.find_all('td')])
return row
url1 = 'https://www.nfl.com/standings/league/2019/REG'
page1 = requests.get(url1)
soup1 = BeautifulSoup(page1.text, 'lxml')
table = soup1.find('table', attrs={'summary': 'Standings - Detailed View'})
# print(table)
print(tableData(table, {'summary': 'Standings - Detailed View'}))
即使在调试器中,我也看到了包含排名 - 详细视图的数据值,但是当运行 data.find(attrs=attrs)
时,它似乎返回 None
答案 0 :(得分:1)
您已经拥有表:table
。它有行和所有内容,但没有任何进一步的“排名 - 详细视图”属性。直接进入行:
def tableData(data):#, attrs):
row = []
#data = data.find(attrs=attrs)
tr = data.find_all('tr')
更好的是,使用pandas(因为你导入它,无论如何)将表提取为数据框:
df = pd.read_html('https://www.nfl.com/standings/league/2019/REG')[0]