Python 如何将html切片到数据框架中

在导入一些HTML（例如）之后，我意识到应该是“表”的东西实际上不是表，因此我似乎需要自己重新构建表

from bs4 import BeautifulSoup
import re
import pandas as pd
import os
soup_level1=BeautifulSoup(driver.page_source, 'lxml')

---

让你开始的东西：

    Batsmen  R  B  4s  6s    SR
0  S Dhawan  4  8   0   0  50.0

哪个输出

from bs4 import BeautifulSoup
import numpy as np
import requests

html_doc= requests.get(r'http://www.espncricinfo.com/series/18886/scorecard/1157372/').content
soup = BeautifulSoup(html_doc, 'html.parser')

data = []
for div in soup.find_all('div',class_="cell runs"):
    data.append(div.text)

np.array(data).reshape(-1,5)

数组（[['R'，B'，4s'，6s'，SR']，
['14', '12', '2', '0', '116.66'],
['68', '55', '5', '1', '123.63'],
['39', '30', '2', '2', '130.00'],
['2', '3', '0', '0', '66.66'],
['9', '6', '1', '0', '150.00'],
['0', '1', '0', '0', '0.00'],
['0', '2', '0', '0', '0.00'],
['1', '2', '0', '0', '50.00'],
['0', '1', '0', '0', '0.00'],
['17', '8', '2', '1', '212.50'],
[R'，B'，4s'，6s'，SR']，
['0', '3', '0', '0', '0.00'],
['4', '2', '1', '0', '200.00'],
['14', '15', '2', '0', '93.33'],
['2', '7', '0', '0', '28.57'],
['0', '2', '0', '0', '0.00'],
['1', '3', '0', '0', '33.33'],
['19', '23', '2', '0', '82.60'],
['34', '29', '6', '0', '117.24'],
['3', '7', '0', '0', '42.85'],
['6', '3', '1', '0', '200.00'],
['2'，'7'，'0'，'0'，'28.57']]，dtype='你能链接到网站吗？当然，bs4可以为你从标签中提取文本，所以
soup\u level1.查找所有（'div'，class=“cell runs”）
可能有一个方法或属性，可以只获取没有标签的内容。@Dan谢谢Dan，下面是一个例子：查看文档的第一页，类似于汤中div的
。\u all（'div'，class=“cell runs”）：print（div.string）
啊，谢谢！就这样。我应该可以从那里操纵它。谢谢Dan！太完美了。它可以同时拉动两个记分卡，但我可以排序。干杯！
Stats = soup_level1.find_all('div',class_="cell runs")
pd.Series(Stats)
0     <div class="cell runs" data-reactid="184">R</div>
1     <div class="cell runs" data-reactid="185">B</div>
2     <div class="cell runs" data-reactid="186">4s</...
3     <div class="cell runs" data-reactid="187">6s</...
4     <div class="cell runs" data-reactid="188">SR</...
5     <div class="cell runs" data-reactid="194">4</div>
6     <div class="cell runs" data-reactid="195">8</div>
7     <div class="cell runs" data-reactid="196">1</div>
8     <div class="cell runs" data-reactid="197">0</div>
9     <div class="cell runs" data-reactid="198">50.0... 
...
94    <div class="cell runs" data-reactid="548">-</div>
Length: 95, dtype: object

    Batsmen  R  B  4s  6s    SR
0  S Dhawan  4  8   0   0  50.0

from bs4 import BeautifulSoup
import numpy as np
import requests

html_doc= requests.get(r'http://www.espncricinfo.com/series/18886/scorecard/1157372/').content
soup = BeautifulSoup(html_doc, 'html.parser')

data = []
for div in soup.find_all('div',class_="cell runs"):
    data.append(div.text)

np.array(data).reshape(-1,5)

array([['R', 'B', '4s', '6s', 'SR'],
       ['14', '12', '2', '0', '116.66'],
       ['68', '55', '5', '1', '123.63'],
       ['39', '30', '2', '2', '130.00'],
       ['2', '3', '0', '0', '66.66'],
       ['9', '6', '1', '0', '150.00'],
       ['0', '1', '0', '0', '0.00'],
       ['0', '2', '0', '0', '0.00'],
       ['1', '2', '0', '0', '50.00'],
       ['0', '1', '0', '0', '0.00'],
       ['17', '8', '2', '1', '212.50'],
       ['R', 'B', '4s', '6s', 'SR'],
       ['0', '3', '0', '0', '0.00'],
       ['4', '2', '1', '0', '200.00'],
       ['14', '15', '2', '0', '93.33'],
       ['2', '7', '0', '0', '28.57'],
       ['0', '2', '0', '0', '0.00'],
       ['1', '3', '0', '0', '33.33'],
       ['19', '23', '2', '0', '82.60'],
       ['34', '29', '6', '0', '117.24'],
       ['3', '7', '0', '0', '42.85'],
       ['6', '3', '1', '0', '200.00'],
       ['2', '7', '0', '0', '28.57']], dtype='<U6')