python - 我如何从包含分页的网站中提取链接？(使用 Selenium )

Question

我想从以下站点提取链接，但它确实包含分页: I want to extract link under the MoreInfo Button:

我正在使用以下代码段:

import time
import requests
import csv
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
from selenium.webdriver.common.action_chains import ActionChains
import re


browser = webdriver.Chrome()
time.sleep(5)
browser.get('https://www.usta.com/en/home/play/facility-listing.html?searchTerm=&distance=5000000000&address=Palo%20Alto,%20%20CA')
wait = WebDriverWait(browser,15)

def extract_data(browser):
    links = browser.find_elements_by_xpath("//div[@class='seeMoreBtn']/a")
    return [link.get_attribute('href') for link in links]


element = WebDriverWait(browser, 10).until(EC.presence_of_element_located((By.XPATH, "//a[@class='glyphicon glyphicon-chevron-right']")))
max_pages = int(re.search(r'\d+ de (\d+)', element.text).group(1), re.UNICODE)
# extract from the current (1) page
print("Page 1")
print(extract_data(browser))

for page in range(2, max_pages + 1):
    print("Page %d" % page)
    next_page = browser.find_element_by_xpath("//a[@class='glyphicon glyphicon-chevron-right']").click()
    print(extract_data(browser))
    print("-----")

当我运行上面的脚本时，我得到了这个错误**(我对正则表达式不太熟悉，也只是探索这个概念)**:

Traceback (most recent call last):
  File "E:/Python/CSV/testingtesting.py", line 29, in <module>
    max_pages = int(re.search(r'\d+ de (\d+)', element.text).group(1), re.UNICODE)
AttributeError: 'NoneType' object has no attribute 'group'

如果可能，请给我建议解决方案。我以某种方式设法使用等待并单击分页链接来提取链接。但是它花费的时间增加了将近 13 秒的等待时间，工作代码如下:

import time
import requests
import csv
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
from selenium.webdriver.common.action_chains import ActionChains
import re



# ----------------------------------------------HANDLING-SELENIUM-STUFF-------------------------------------------------
linkList = []
driver = webdriver.Chrome()
time.sleep(5)
driver.get('https://www.usta.com/en/home/play/facility-listing.html?searchTerm=&distance=5000000000&address=Palo%20Alto,%20%20CA')
wait = WebDriverWait(driver,8)
time.sleep(7)

for i in range(1,2925):
    time.sleep(3)
    # wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "//div[@class='seeMoreBtn']/a")))
    links = driver.find_elements_by_xpath("//div[@class='seeMoreBtn']/a")
    # print(links.text)
    time.sleep(3)

    #appending extracted links to the list
    for link in links:
        value=link.get_attribute("href")
        # linkList.append(value)
        with open('test.csv','a',encoding='utf-8',newline='') as fp:
            writer = csv.writer(fp, delimiter=',')
            writer.writerow([value])
    # print(i,"  ",)
    time.sleep(1)
    driver.find_element_by_xpath("//a[@class='glyphicon glyphicon-chevron-right']").click()
    time.sleep(6)

Answer 1

尝试下面的代码来获取所需的数据而无需额外的“ sleep ”:

import requests
import csv
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
from selenium.common.exceptions import TimeoutException



# ----------------------------------------------HANDLING-SELENIUM-STUFF-------------------------------------------------
driver = webdriver.Chrome()
driver.get('https://www.usta.com/en/home/play/facility-listing.html?searchTerm=&distance=5000000000&address=Palo%20Alto,%20%20CA')
wait = WebDriverWait(driver, 8)

links = []

while True:
    new_links = wait.until(EC.visibility_of_all_elements_located((By.LINK_TEXT, "MORE INFO")))
    links.extend([link.get_attribute("href") for link in new_links])

    try:
        next_button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "li[title='Next page']>a")))
        next_button.click()
    except TimeoutException:
        break
    wait.until(EC.staleness_of(new_links[-1]))

#  Do whatever you need with links