我正试图从此链接中删除评论:
关于我正在使用以下代码加载页面的内容
from selenium import webdriver
import datetime
import time
import argparse
import os
import time
#Define the argument parser to read in the URL
url = "https://www.google.com/search?q=google+reviews+2nd+chance+treatment+40th+street&rlz=1C1JZAP_enUS697US697&oq=google+reviews+2nd+chance+treatment+40th+street&aqs=chrome..69i57j69i64.6183j0j7&sourceid=chrome&ie=UTF-8#lrd=0x872b7179b68e33d5:0x24b5517d86a95f89,1"
# Initialize the Chrome webdriver and open the URL
#driver = webdriver.Chromium()
profile = webdriver.FirefoxProfile()
profile.set_preference("general.useragent.override", "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; AS; rv:11.0) like Gecko")
#driver = webdriver.Firefox(profile)
# https://stackoverflow.com/questions/22476112/using-chromedriver-with-selenium-python-ubuntu
driver = webdriver.Chrome("/usr/lib/chromium-browser/chromedriver")
driver.get(url)
driver.implicitly_wait(2)
SCROLL_PAUSE_TIME = 0.5
# Get scroll height
last_height = driver.execute_script("return document.body.scrollHeight")
while True:
# Scroll down to bottom
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
# Wait to load page
time.sleep(SCROLL_PAUSE_TIME)
# Calculate new scroll height and compare with last scroll height
new_height = driver.execute_script("return document.body.scrollHeight")
if new_height == last_height:
break
last_height = new_height
该页面加载正常,它没有向下滚动,我已经在其他网站(例如,linkedn)中使用了相同的代码,并且在这里可以正常工作。
答案 0 :(得分:1)
以下是您无需使用javascript向下滚动即可使用的逻辑。使用location_once_scrolled_into_view
方法简单有效,该方法将滚动到该元素。
作为下面逻辑的一部分,我们将滚动到上一个评论,然后检查是否根据请求加载了所需的评论数量。
需要导入:
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
根据您在以下代码中的要求更改desiredReviewsCount
变量值。
wait = WebDriverWait(driver,10)
url = "https://www.google.com/search?q=google+reviews+2nd+chance+treatment+40th+street&rlz=1C1JZAP_enUS697US697&oq=google+reviews+2nd+chance+treatment+40th+street&aqs=chrome..69i57j69i64.6183j0j7&sourceid=chrome&ie=UTF-8#lrd=0x872b7179b68e33d5:0x24b5517d86a95f89,1"
driver.get(url)
x=0
desiredReviewsCount=30
wait.until(EC.presence_of_all_elements_located((By.XPATH,"//div[@class='gws-localreviews__general-reviews-block']//div[@class='WMbnJf gws-localreviews__google-review']")))
while x<desiredReviewsCount:
driver.find_element_by_xpath("(//div[@class='gws-localreviews__general-reviews-block']//div[@class='WMbnJf gws-localreviews__google-review'])[last()]").location_once_scrolled_into_view
x = len(driver.find_elements_by_xpath("//div[@class='gws-localreviews__general-reviews-block']//div[@class='WMbnJf gws-localreviews__google-review']"))
print (len(driver.find_elements_by_xpath("//div[@class='gws-localreviews__general-reviews-block']//div[@class='WMbnJf gws-localreviews__google-review']")))