找到以下3种方法:

请求处理

检查页面readyState(不可靠):

def page_has_loaded(self):
    self.log.info("Checking if {} page is loaded.".format(self.driver.current_url))
    page_state = self.driver.execute_script('return document.readyState;')
    return page_state == 'complete'

wait_for helper函数很好，但不幸的是，click_through_to_new_page处于竞速条件，在浏览器开始处理单击之前，我们设法在旧页面中执行脚本，而page_has_loaded直接返回true。

id

比较新页面id和旧页面id:

def page_has_loaded_id(self):
    self.log.info("Checking if {} page is loaded.".format(self.driver.current_url))
    try:
        new_page = browser.find_element_by_tag_name('html')
        return new_page.id != old_page.id
    except NoSuchElementException:
        return False

比较id可能不如等待过时的引用异常有效。

staleness_of

使用staleness_of方法:

@contextlib.contextmanager
def wait_for_page_load(self, timeout=10):
    self.log.debug("Waiting for page to load at {}.".format(self.driver.current_url))
    old_page = self.find_element_by_tag_name('html')
    yield
    WebDriverWait(self, timeout).until(staleness_of(old_page))

要了解更多细节，请查看Harry的博客。

另外，您可以检查DOM是否没有更多的修改，而不是向下滚动100次(在页面底部是AJAX惰性加载的情况下)

def scrollDown(driver, value):
    driver.execute_script("window.scrollBy(0,"+str(value)+")")

# Scroll down the page
def scrollDownAllTheWay(driver):
    old_page = driver.page_source
    while True:
        logging.debug("Scrolling loop")
        for i in range(2):
            scrollDown(driver, 500)
            time.sleep(2)
        new_page = driver.page_source
        if new_page != old_page:
            old_page = new_page
        else:
            break
    return True

如果您试图滚动并找到页面上的所有项目。您可以考虑使用以下方法。这是其他人在这里提到的一些方法的组合。它帮我完成了任务:

while True:
    try:
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        driver.implicitly_wait(30)
        time.sleep(4)
        elem1 = WebDriverWait(driver, 30).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "element-name")))
        len_elem_1 = len(elem1)
        print(f"A list Length {len_elem_1}")
        driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
        driver.implicitly_wait(30)
        time.sleep(4)
        elem2 = WebDriverWait(driver, 30).until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "element-name")))
        len_elem_2 = len(elem2)
        print(f"B list Length {len_elem_2}")
        if len_elem_1 == len_elem_2:
            print(f"final length = {len_elem_1}")
            break
    except TimeoutException:
            print("Loading took too much time!")

试图将find_element_by_id传递给构造函数的presence_of_element_locate(如已接受的答案所示)会引发NoSuchElementException异常。我不得不在fragles的评论中使用语法:

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

driver = webdriver.Firefox()
driver.get('url')
timeout = 5
try:
    element_present = EC.presence_of_element_located((By.ID, 'element_id'))
    WebDriverWait(driver, timeout).until(element_present)
except TimeoutException:
    print "Timed out waiting for page to load"

这与文档中的示例相匹配。这里是By文档的链接。

Selenium无法检测页面是否完全加载，但javascript可以。我建议你试试这个。

from selenium.webdriver.support.ui import WebDriverWait
WebDriverWait(driver, 100).until(lambda driver: driver.execute_script('return document.readyState') == 'complete')

这将执行javascript代码，而不是使用python，因为javascript可以检测页面何时完全加载，它将显示“完成”。这个代码的意思是在100秒内，继续尝试这个文档。readyState直到complete显示。

ajax页面连续加载数据的解决方案。所述的预览方法无效。我们可以做的是抓取页面dom并对其进行哈希，并在一段时间内比较新旧哈希值。

import time
from selenium import webdriver

def page_has_loaded(driver, sleep_time = 2):
    '''
    Waits for page to completely load by comparing current page hash values.
    '''

    def get_page_hash(driver):
        '''
        Returns html dom hash
        '''
        # can find element by either 'html' tag or by the html 'root' id
        dom = driver.find_element_by_tag_name('html').get_attribute('innerHTML')
        # dom = driver.find_element_by_id('root').get_attribute('innerHTML')
        dom_hash = hash(dom.encode('utf-8'))
        return dom_hash

    page_hash = 'empty'
    page_hash_new = ''
    
    # comparing old and new page DOM hash together to verify the page is fully loaded
    while page_hash != page_hash_new: 
        page_hash = get_page_hash(driver)
        time.sleep(sleep_time)
        page_hash_new = get_page_hash(driver)
        print('<page_has_loaded> - page not loaded')

    print('<page_has_loaded> - page loaded: {}'.format(driver.current_url))