Python flashcore.com中的网页抓取

我正试图从Flashcore中刮取

当我尝试运行它时，我得到一个超出范围的列表索引

当

set1

不存在时，是否可以添加零

有人能帮我吗

from requests_html import AsyncHTMLSession
from collections import defaultdict
import pandas as pd 


url = 'https://www.flashscore.com/table-tennis/others-men/tt-star-series/results/'

asession = AsyncHTMLSession()
async def get_scores():
    r = await asession.get(url)
    await r.html.arender()
    return r

results = asession.run(get_scores)
results = results[0]


times = results.html.find("div.event__time")
home_players = results.html.find("div.event__participant.event__participant--home") 
scores_home = results.html.find('div > div.event__score.event__score--home')
scores_home_set1 = results.html.find('div > div.event__part.event__part--home.event__part--1')


dict_res = defaultdict(list)
for i in range(len(times)):
        dict_res['times'].append(times[i].text)
        dict_res['home_players'].append(home_players[i].text)
        dict_res['scores_home'].append(scores_home[i].text)
        dict_res['set1'].append(scores_home_set1[i].text)
        
df_res = pd.DataFrame(dict_res)
df_res.to_csv('ttstar.csv', index=False)

---

我在这篇文章中有一个答案。这是一种不同的方法来达到同样的效果。非常感谢您@AlbertoCastillo

from selenium import webdriver

driver = webdriver.Firefox(executable_path='/usr/local/bin/geckodriver')
url = 'https://www.flashscore.com/table-tennis/others-men/tt-star-series/results/'
driver.get(url)

data = driver.find_elements_by_class_name('event__match')
data_clean = []
for i in range(len(data)):
    data_clean.append(data[i].text)

data_clean = [x.replace("\n", "|") for x in data_clean]
data_clean