Question

任何人都可以看到此代码有什么问题吗？

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions
from selenium.webdriver.support.ui import WebDriverWait
import csv

def races(main_url):
    driver = webdriver.Chrome()
    driver.get(main_url)
    driver.implicitly_wait(2)

    races = driver.find_elements_by_class_name('time-location')
    races = [race.text[:5] for race in races]
    races = [race.replace(':', '') for race in races]

    driver.close()

    return races

def scrape(url):
    driver = webdriver.Chrome()
    driver.get(url)
    driver.implicitly_wait(2)
    driver.find_elements_by_class_name('racecard-ajax-link')[1].click()

    WebDriverWait(driver, 5).until(expected_conditions.presence_of_element_located((By.XPATH, '//[@id="tab-racecard-sectional-times"]/div/div[1]/div[1]/div[2]/div/button')))

    for horse in driver.find_elements_by_class_name('card-item'):
        horseName = horse.find_element_by_class_name('form-link').text
        times = horse.find_elements_by_class_name('sectionals-time')
        times = [time.text for time in times]
        print('{}: {}'.format(horseName, times))
    print()

    driver.close()

因此，在下面的这一点上，我尝试将数据保存到df，但是在打开时会返回一个空白文档。 df = open（'jan1.csv'，'w +'）不应该将抓取的数据存储到csv文件中。我显然缺少了一些东西，但看不到。

def main():
    df = open('jan1.csv', 'w+')
    df.close()
    date = '1-January-2018'
    main_url = 'http://www.attheraces.com/racecard/Southwell/' + date
    for race in races(main_url):
        url = main_url + '/' + race
        print(url)
        scrape(url)

if __name__ == '__main__':
    main()

Answer 1

您的代码似乎在几个地方坏了，即使修复了，我也会遇到超时错误。

尝试以下步骤：

添加熊猫以方便数据处理：

import pandas as pd

def scrape(url):
    driver = webdriver.Chrome()
    driver.get(url)
    driver.implicitly_wait(2)
    driver.find_elements_by_class_name('racecard-ajax-link')[1].click()

    WebDriverWait(driver, 5).until(expected_conditions.presence_of_element_located((By.XPATH, '//[@id="tab-racecard-sectional-times"]/div/div[1]/div[1]/div[2]/div/button')))

    # add empty list to save scraped data 
    data = []

    for horse in driver.find_elements_by_class_name('card-item'):
        horseName = horse.find_element_by_class_name('form-link').text
        times = horse.find_elements_by_class_name('sectionals-time')
        times = [time.text for time in times]
        print('{}: {}'.format(horseName, times))
        data.append([horseName, times])
    print()

    driver.close()

    # return your data!
    return data

然后在您的主要功能中进行更改：

def main():

    date = '1-January-2018'
    main_url = 'http://www.attheraces.com/racecard/Southwell/' + date

    tmp = []

    for race in races(main_url):
        url = main_url + '/' + race
        print(url)
        tmp.append(scrape(url))

    df = pd.DataFrame(tmp)
        df.to_csv("jan1.csv")

或者如果您只想坚持使用csv（不使用大熊猫）：

with open("jan1.csv", "w+") as file:
    file.write(your_data_var_here)

抓取的数据未保存到csv文件，因为它一直返回空白的csv文件。

1 个答案: