Question

我正在尝试抓取下面适用于page的网站的数据。但是，只要单击复选框，作业就不起作用。之前您可以看到我只检测到24个元素并且没有点击复选框，这是正确的擦除。

单击复选框后，会有更多元素，但无法正常工作，如下所示。它为什么这样做？我相信Selenium通常会刮掉它看到的东西但是在这种情况下它并没有这样做......

driver = webdriver.Chrome()
driver.set_window_size(1024, 600)
driver.maximize_window()
try:
    os.remove('vtg121.csv')
except OSError:
    pass

driver.get('https://www.palmerbet.com/sports/soccer')

#SCROLL_PAUSE_TIME = 0.5


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

#clickMe = wait(driver, 3).until(EC.element_to_be_clickable((By.XPATH, ('//*[@id="TopPromotionBetNow"]'))))
#if driver.find_element_by_css_selector('#TopPromotionBetNow'):
    #driver.find_element_by_css_selector('#TopPromotionBetNow').click()

#last_height = driver.execute_script("return document.body.scrollHeight")

#while True:

    #driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")


    #time.sleep(SCROLL_PAUSE_TIME)


    #new_height = driver.execute_script("return document.body.scrollHeight")
    #if new_height == last_height:
        #break
    #last_height = new_height

time.sleep(1)

clickMe = wait(driver, 10).until(EC.element_to_be_clickable((By.XPATH, ('//*[contains(@class,"filter_labe")]'))))
clickMe.click()
time.sleep(0)
clickMe = wait(driver, 10).until(EC.element_to_be_clickable((By.XPATH,'(//*[contains(@class,"filter_labe")])')))
options = driver.find_elements_by_xpath('//*[contains(@class,"filter_labe")]')

indexes = [index for index in range(len(options))]
shuffle(indexes)
for index in indexes:
    time.sleep(0)
    #driver.get('https://www.bet365.com.au/#/AS/B1/')
    clickMe1 = wait(driver, 10).until(EC.element_to_be_clickable((By.XPATH,'(//ul[@id="tournaments"]//li//input)[%s]' % str(index + 1))))
    clickMe1 = wait(driver, 10).until(EC.element_to_be_clickable((By.XPATH,'(//ul[@id="tournaments"]//li//input)[%s]' % str(index + 1))))
    driver.find_element_by_tag_name('body').send_keys(Keys.UP)
    driver.find_element_by_tag_name('body').send_keys(Keys.UP)
    driver.find_element_by_tag_name('body').send_keys(Keys.UP)
    driver.execute_script("return arguments[0].scrollIntoView();", clickMe1)
    clickMe1.click()
    time.sleep(0)
    ##tournaments > li > input
    #//*[@id='tournaments']//li//input

    # Team

    #clickMe = wait(driver, 10).until(EC.element_to_be_clickable((By.CSS_SELECTOR,("#mta_row td:nth-child(1)"))))
    time.sleep(5)
    langs3 = driver.find_elements_by_xpath('//*[@id="mta_row"]/td[1]')
    langs3_text = []

    for lang in langs3:
        #print(lang.text)

        langs3_text.append(lang.text)
    time.sleep(0)

    # Team ODDS
    langs = driver.find_elements_by_css_selector("#mta_row   .mpm_teams_cell_click:nth-child(2)   .mpm_teams_bet_val")
    langs_text = []

    for lang in langs:
        #print(lang.text)
        langs_text.append(lang.text)
    time.sleep(0)


    # HREF
    #langs2 = driver.find_elements_by_xpath("//ul[@class='runners']//li[1]")
    #a[href*="/sports/soccer/"]
    url1 = driver.current_url

    #clickMe = wait(driver, 15).until(
        #EC.element_to_be_clickable((By.CSS_SELECTOR, ('.match-pop-market a[href*="/sports/soccer/"]'))))
    try:
        clickMe = wait(driver, 15).until(EC.element_to_be_clickable((By.XPATH, "//*[@class='match-pop-market']//a[contains(@href, '/sports/soccer/')]")))
        clickMe1.click()
    except TimeoutException:
        print("No link was found")
    elems = driver.find_elements_by_css_selector('.match-pop-market a[href*="/sports/soccer/"]')
    elem_href = []
    for elem in elems:
     #print(elem.get_attribute("href"))
     elem_href.append(elem.get_attribute("href"))


    print(("NEW LINE BREAK"))
    import sys
    import io


    with open('vtg121.csv', 'a', newline='', encoding="utf-8") as outfile:
        writer = csv.writer(outfile)
        for row in zip(langs3_text, langs_text, elem_href):
            writer.writerow(row)
            print(row)

Answer 1

您可以使用以下内容获取团队名称。添加更多代码

from selenium import webdriver
import json
import time

driver = webdriver.Chrome()

driver.get("https://www.palmerbet.com/sports/soccer")

values = []
time.sleep(5)
for elem in driver.find_elements_by_css_selector("li.sport-grp-filter.filter_item input"):
    val = elem.get_attribute("value")
    values.append(val)

for val in values:
    driver.get("https://www.palmerbet.com/sports/getroundmatches/socc/" + val)

    json_data = driver.find_element_by_tag_name("pre").text
    data = json.loads(json_data)

    for item in data["m"]:
        print (item["mta"]["cn"], item["mtb"]["cn"])

作业仅刮擦一页，单击所有复选框时不起作用

1 个答案: