IndexError:如果条件匹配，则列表索引超出范围

Question

此代码剪贴Oddsortal网站:

import pandas as pd
from bs4 import BeautifulSoup as bs
from selenium import webdriver
import threading
from multiprocessing.pool import ThreadPool
import os
import re
from math import nan

class Driver:
def __init__(self):
options = webdriver.ChromeOptions()
options.add_argument("--headless")
# Un-comment next line to supress logging:
options.add_experimental_option('excludeSwitches', ['enable-logging'])
self.driver = webdriver.Chrome(options=options)
def __del__(self):
self.driver.quit()  # clean up driver when we are cleaned up
# print('The driver has been "quitted".')

threadLocal = threading.local()

def create_driver():
the_driver = getattr(threadLocal, 'the_driver', None)
if the_driver is None:
the_driver = Driver()
setattr(threadLocal, 'the_driver', the_driver)
return the_driver.driver

class GameData:
def __init__(self):
self.date = []
self.time = []
self.game = []
self.score = []
self.home_odds = []
self.draw_odds = []
self.away_odds = []
self.country = []
self.league = []

def generate_matches(table):
tr_tags = table.findAll('tr')
for tr_tag in tr_tags:
if 'class' in tr_tag.attrs and 'dark' in tr_tag['class']:
th_tag = tr_tag.find('th', {'class': 'first2 tl'})
a_tags = th_tag.findAll('a')
country = a_tags[0].text
league = a_tags[1].text
else:
td_tags = tr_tag.findAll('td')
yield [td_tags[0].text, td_tags[1].text, td_tags[2].text, td_tags[3].text,
td_tags[4].text, td_tags[5].text, country, league]

我得到一个列表错误:

yield [td_tags[0].text, td_tags[1].text, td_tags[2].text, td_tags[3].text,
IndexError: list index out of range

如何解决?

这是我当前的全部代码

当我检查时，列表索引为1，而我正确地获得国家和联赛值。如果列表中没有值，如何修改

yield [td_tags[0].text, td_tags[1].text, td_tags[2].text, td_tags[3].text,
td_tags[4].text, td_tags[5].text, country, league]

得到正确的值?

Answer 1

可以检查td_tags是否为空

td_tags = tr_tag.findAll('td')
if len(td_tags) > 0: # or just if td_tags
yield [td_tags[0].text, td_tags[1].text, td_tags[2].text, td_tags[3].text,
td_tags[4].text, td_tags[5].text, country, league]

Answer 2

您可以打开td_tags，所以如果它是空的，您将只有county和league:

yield [*[td_tag.text for td_tag in td_tags], country, league]

或者您可以使用简单的if检查它是否为空:

if td_tags:
yield [td_tags[0].text, td_tags[1].text, td_tags[2].text, td_tags[3].text,
td_tags[4].text, td_tags[5].text, country, league]

另一个选项，如果你不想抑制IndexError:

with suppress(IndexError):
yield [td_tags[0].text, td_tags[1].text, td_tags[2].text, td_tags[3].text,
td_tags[4].text, td_tags[5].text, country, league]