此代碼抓取 Oddsortal 網站：
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]
我收到一個串列錯誤：
yield [td_tags[0].text, td_tags[1].text, td_tags[2].text, td_tags[3].text,
IndexError: list index out of range
我該如何解決？
這是我目前的完整代碼
當我檢查時，串列索引為 1，而我正確獲取國家和聯賽值。如果串列中沒有值，我該如何修改
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]
獲得正確的價值？
uj5u.com熱心網友回復：
您可以檢查是否td_tags不為空
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]
uj5u.com熱心網友回復：
您可以打開包裝，td_tags因此如果它是空的，您將只有county和league：
yield [*[td_tag.text for td_tag in td_tags], country, league]
或者你可以用一個簡單的檢查if它不為空：
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]
如果您不想抑制， 另一種選擇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]
轉載請註明出處，本文鏈接：https://www.uj5u.com/ruanti/341174.html