0

在您的帮助下，我能够让刮刀运行，但现在我在迭代时遇到了困难。最终，我想通过爬虫来运行不同的 URL，但我对语法感到困惑。我正在使用 Selenium 打开网页，然后使用 BeautifulSoup 来提取数据。我想我需要定义 URL，然后使用类似的东西：

for url in urls

但我不确定如何使用它。阅读其他答案和视频让我摸不着头脑。

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import csv
import time
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
from bs4 import BeautifulSoup as soup
import pandas as pd

urls = ["https://racing.hkjc.com/racing/information/English/Racing/LocalResults.aspx?RaceDate=2021/02/06&Racecourse=ST&RaceNo=1","https://racing.hkjc.com/racing/information/English/Racing/LocalResults.aspx?RaceDate=2021/02/06&Racecourse=ST&RaceNo=2"]
driver = webdriver.Chrome()
driver.get(urls)

for url in urls:
    html = driver.execute_script("return document.getElementsByTagName('html')[0].innerHTML")
WebDriverWait(driver, 20).until(EC.visibility_of_all_elements_located((By.CLASS_NAME, "f_fs13")))
htmlStr = driver.page_source

soup_level1 = soup(htmlStr, 'html.parser')

race_soup = soup_level1.find('tbody',{'class':'f_fs13'}).find_parent('table')
results_soup = soup_level1.find('tbody',{'class':'f_fs12'}).find_parent('table')

df1 = pd.read_html(str(race_soup))[0]
print(df1)


df2 = pd.read_html(str(results_soup))[0]
print(df2)


print('good')


driver.close()
4

0 回答 0