Парсинг данных

import requests
from bs4 import BeautifulSoup
 
url = "https://ru.betsapi.com/cs/tennis/2019-07-06/p.1"
 
response = requests.get(url)
 
html = response.text
 
soup = BeautifulSoup(html, "html.parser")
 
table = soup.find("table", {"class":"table table-sm"})
 
trr = table.find_all("tr")
 
flag1 = 0
flag2 = 0
flag3 = 0
 
for tr in trr:
    liga = tr.find_all("a")[0].text.replace(',', '').replace('M15 ', '').replace('M25 ', '').replace('W25 ', '').replace('W15 ', '').strip()
    name_player_one = tr.find_all("a")[1].text.replace(',', '')
    name_player_two = tr.find_all("a")[2].text.replace(',', '')
    result = tr.find_all("a")[3].text.strip().replace(',', ' ').replace('-', ' ').split()[0:4]
    
    print(result)

from builtins import print
import requests
import pygame
import os
import sys
import binascii
from pygame.locals import *
import shutil
import bs4
from bs4 import BeautifulSoup
from urllib.request import urlopen
import time
from smtplib import SMTP_SSL
from email.mime.multipart import MIMEMultipart
from email.mime.base import MIMEBase
from email import  encoders
import lxml.html
import sqlite3
import urllib
url='http://htmlbook.ru/samhtml5/ustarevshie-tegi-i-atributy/'
def get_html(url):
    f = myhtml = urlopen(url)
    sp = BeautifulSoup(myhtml, "html.parser")
    lnk=sp.find_all("span",class_="tag")
    for l in lnk:
        l=str(l)
        l=l.replace('"',' ')
        l=l.replace("<span class= tag >",'')
        l=l.replace('</span>',' ')
        l=l.replace('&gt','')
        l=l.replace('&lt','')
        l=l.replace(';',' ')
        print(l)
 
if __name__ == '__main__':
    get_html(url)

import lxml.html
import requests
import re
from pprint import pprint
 
url = 'https://ru.betsapi.com/cs/tennis/2019-07-06/p.1'
data = requests.get(url).text
root = lxml.html.fromstring(data)
 
def test():
    tds = root.cssselect('table[class="table table-sm"] td')
    it = [iter(tds)] * 6
    patt = re.compile(r'away|home|Cancelled')
    data = []
    for t in zip(*it):
         subdata = []
         for _ in t: 
            text = _.text_content().strip()
            if text:
                if not patt.match(text):
                    subdata += [text]
                else:
                    subdata = []
                    break        
         if subdata:
            data.append(subdata)       
       
    pprint(data)
    print(len(data))

def test1():
    trs = root.xpath('''
    //table[@class="table table-sm"]/tr[
        not(contains(.,"away")) and
        not(contains(.,"home")) and
        not(contains(.,"Cancelled"))
    ]
    ''')
    data = []
    for tr in trs:
        subdata = []
        for _ in tr.cssselect('td'): 
            text = _.text_content().strip()
            text = re.sub(r'(M|W)\d{2}','',text)  # удалить ненужные символы - одна регулярка вместо кучи replace
            if text:
                subdata += [text]    
        data.append(subdata) 
    pprint(data)
    print(len(data))