问如何从网站获取统计数据并将其转换为python上的DataFrame？

EN

import pandas as pd
import numpy as np
import requests
from bs4 import BeautifulSoup
from io import StringIO

url = 'http://mcubed.net/ncaab/seeds.shtml'

#Getting the website text
data = requests.get(url).text

#Parsing the website
soup = BeautifulSoup(data, "html5lib")

#Create an empty list
dflist = []

#If we look at the html, we don't want the tag b, but whats next to it
#StringIO(b.next.next), takes the correct text and makes it readable to pandas
for b in soup.findAll({"b"})[2:-1]:
    dflist.append(pd.read_csv(StringIO(b.next.next), sep = r'\s+', header = None))

dflist[0]

     0   1     2      3
0   vs. #1  (23-23) 50.0%
1   vs. #2  (40-35) 53.3%
2   vs. #3  (25-15) 62.5%

#We need to create a new list, due to the melt we are going to do not been able to replace
#the dataframes in DFList
meltedDF = []

#The second item in the loop is the team number starting from 1
for df, teamnumber in zip(dflist, (np.arange(len(dflist))+1)):

    #Creating the team name
    name = "Team " + str(teamnumber)

    #Making the team name a column, with the values in df[0] and df[1] in our dataframes
    df[name] = df[0] + df[1]

    #Melting the dataframe to make the team name its own column
    meltedDF.append(df.melt(id_vars = [0, 1, 2, 3]))

# Concat all the melted DataFrames
allTeamStats = pd.concat(meltedDF)

# Final cleaning of our new single DataFrame
allTeamStats = allTeamStats.rename(columns = {0:name, 2:'Record', 3:'Win Percent', 'variable':'Team' , 'value': 'VS'})\
                           .reindex(['Team', 'VS', 'Record', 'Win Percent'], axis = 1)

allTeamStats.head()

     Team    VS     Record  Win Percent
0   Team 1  vs.#1   (23-23) 50.0%
1   Team 1  vs.#2   (40-35) 53.3%
2   Team 1  vs.#3   (25-15) 62.5%
3   Team 1  vs.#4   (53-22) 70.7%
4   Team 1  vs.#5   (45-9)  83.3%

allTeamStats[allTeamStats['VS'] == 'vs.#1'].head()

     Team    VS     Record  Win Percent
0   Team 1  vs.#1   (23-23)   50.0%
0   Team 2  vs.#1   (35-40)   46.7%
0   Team 3  vs.#1   (15-25)   37.5%
0   Team 4  vs.#1   (22-53)   29.3%
0   Team 5  vs.#1   (9-45)    16.7%

allTeamStats['Win'] = allTeamStats['Record'].str.extract(r'\((\d+)')
allTeamStats['Lose'] = allTeamStats['Record'].str.extract(r'\(\d+-(\d+)')

allTeamStats.head()

     Team    VS     Record  Win Percent Win Lose
0   Team 1  vs.#1   (23-23)   50.0%     23  23
1   Team 1  vs.#2   (40-35)   53.3%     40  35
2   Team 1  vs.#3   (25-15)   62.5%     25  15
3   Team 1  vs.#4   (53-22)   70.7%     53  22
4   Team 1  vs.#5   (45-9)    83.3%     45  9