selenium爬取异步加载的网站

import json
from selenium import webdriver
from selenium.webdriver import DesiredCapabilities
import os,time

def get_log_options():
    option = webdriver.ChromeOptions()
    option.add_argument('--no-sandbox')
    #option.add_argument('--headless')  # 设置无头浏览
    option.add_argument("--disable-extensions")
    option.add_argument('--disable-infobars') # 禁用浏览器正在被自动化程序控制的提示
    option.add_argument("--allow-running-insecure-content")
    option.add_argument("--ignore-certificate-errors")
    option.add_argument("--disable-single-click-autofill")
    option.add_argument("--disable-autofill-keyboard-accessory-view[8]")
    option.add_argument("--disable-full-form-autofill-ios")
    option.add_argument('user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:55.0) Gecko/20100101 Firefox/55.0')
    option.add_experimental_option('w3c', False)
    option.add_experimental_option('perfLoggingPrefs', {
        'enableNetwork': True,
        'enablePage': False,
    })
    option.add_experimental_option('prefs',{
        #不弹出去请求
        'profile.default_content_settings.popups':0,
        #设置默认下载文件目录
        'download.default_directory':save_folder,
        # 禁止提示
        'profile.default_content_setting_values':{
            'notifications': 2
        }
    })
    return option
 
    
def get_caps():
    caps = DesiredCapabilities.CHROME
    caps['loggingPrefs'] = {
        'browser': 'ALL',
        'performance': 'ALL',
    }
    caps['perfLoggingPrefs'] = {
        'enableNetwork': True,
        'enablePage': False,
        'enableTimeline': False
    }
    return caps

# 获取日志中的xhr结果
def get_xhr_logs(chrome):
    log_xhr_array = []
    for typelog in chrome.log_types:
        perfs = chrome.get_log(typelog)
        for row in perfs:
            log_data = row
            message_ = log_data['message']
            try:
                log_json = json.loads(message_)
                log = log_json['message']
                if log['method'] == 'Network.responseReceived':
                    # 去掉静态js、css等，仅保留xhr请求
                    type_ = log['params']['type']
                    if type_ == "XHR":
                        log_xhr_array.append(log)
            except:
                pass
    return log_xhr_array

# 根据id获取返回结果
def get_xhr_body(driver, requestId):
    response_body = driver.execute_cdp_cmd('Network.getResponseBody', {'requestId': requestId})
    return response_body

# 等待直到某个xhr出现,返回整个异步情况吧
def wait_until_xhr_do(url='',limit = 10):
    tick = 0
    while tick < limit:
        logs = get_xhr_logs(chrome)
        if url == '':
            if len(logs) > 0:
                return logs
        else:
            for log in logs:
                if url in logs['params']['response']['url']:
                    return logs
        tick = tick + 1
    return []

if __name__ == '__main__':
    # 使用工具类来获取options配置，而不是平时的webdriver.ChromeOptions()方法
    options = get_log_options()
    # 使用工具类来获取caps
    desired_capabilities = get_caps()
    # 这里也可以对options和caps加入其他的参数，比如代理参数等
    chrome = webdriver.Chrome(options=options, desired_capabilities=desired_capabilities)
    chrome.get("https://spa6.scrape.center/")  # "https://www.baidu.com/"
    chrome.maximize_window()
    
    # 点击下一页
    el= chrome.find_element_by_xpath('//button[@class="btn-next"]')
    el.click()
    # 执行等待
    logs = wait_until_xhr_do()
    # 输出结果
    if len(logs) > 0:
        print(logs[0]['params']['response']['url'])

        body = get_xhr_body(chrome, logs[0]['params']['requestId'])
        # 使用eval转换遇到null会有问题，改为使用Json转换
        response = json.loads((body['body']))
        print(response)