def get_movie_url(url):
data_dict = {}
i = 0
html = ask_url(url)
doc = etree.HTML(html)
# 所有级数的a标签和文本
all_url = doc.xpath('//div[@class="fed-play-item fed-drop-item fed-visible"]//ul[@class="fed-part-rows"]/li/a/@href')
all_title = doc.xpath('//div[@class="fed-play-item fed-drop-item fed-visible"]'
'//ul[@class="fed-part-rows"]/li/a/text()')
# 用selenium获取iframe里的src
c_service = Service('/usr/bin/chromedriver')
c_service.command_line_args()
c_service.start()
option = webdriver.ChromeOptions()
option.add_argument('--headless')
option.add_argument('--no-sandbox')
option.add_argument('--disable-dev-shm-usage')
browser = webdriver.Chrome('/usr/bin/chromedriver', options=option)
# print('正在爬取视频链接中')
for url in all_url:
browser.get('https://kuyun.tv'+url)
movie_url = browser.find_element_by_id('fed-play-iframe').get_attribute('src')
data_dict[all_title[i]] = movie_url
i = i+1
browser.quit()
c_service.stop()
return data_dict
def punch(StudentId, Name):
c_service = Service('/Users/wq//Downloads/chromedriver')
c_service.command_line_args()
c_service.start()
driver = webdriver.Chrome(
'/Users/wq/Downloads/chromedriver') # 选择Chrome浏览器
driver.get('http://xsc.sicau.edu.cn/SPCP') # 打开网站
#采用xpath定位
result = driver.find_element_by_xpath('//*[@id="code-box"]')
text = result.text
driver.find_element_by_xpath('//*[@id="StudentId"]').click()
driver.find_element_by_xpath('//*[@id="StudentId"]').send_keys(StudentId)
driver.find_element_by_xpath('//*[@id="Name"]').click()
driver.find_element_by_xpath('//*[@id="Name"]').send_keys(Name)
driver.find_element_by_xpath('//*[@id="codeInput"]').click()
driver.find_element_by_xpath('//*[@id="codeInput"]').send_keys(text)
driver.find_element_by_xpath('//*[@id="Submit"]').click()
driver.find_element_by_xpath('//*[@id="platfrom2"]').click()
try:
driver.find_element_by_xpath('//*[@id="ckCLS"]').click()
driver.find_element_by_xpath('//*[@id="SaveBtnDiv"]/button').click()
except:
driver.find_element_by_xpath(
'//*[@id="layui-layer1"]/div[3]/a').click()
driver.quit()
c_service.stop()
class ChromeDriverManager(DriverManager):
__chservice = None
def launch_browser(self):
chrome_option = Options()
chrome_option.add_argument("--disable-infobars")
chrome_option.add_argument("--start-maximized")
chrome_option.add_argument("--disable-popup-blocking")
cur_dir_path = os.path.dirname(os.path.realpath(__file__))
chromedriver = cur_dir_path.split(
sep='\\base')[0] + QEEnvironment.get_environment_dict().get(
'BrowserPath')
os.environ["webdriver.chrome.driver"] = chromedriver
driver = webdriver.Chrome(chromedriver, options=chrome_option)
driver.get('https://ui.cogmento.com/')
def start_service(self):
try:
if self.__chservice == None:
cur_dir_path = os.path.dirname(os.path.realpath(__file__))
driver_path = cur_dir_path.split(
sep='\\base')[0] + QEEnvironment.get_environment_dict(
).get('BrowserPath')
self.__chservice = Service(driver_path)
self.__chservice.start()
print('Service is started')
except:
print(traceback.print_exc())
def stop_service(self):
if self.__chservice != None and self.__chservice.is_connectable():
print('Stop service')
self.__chservice.stop()
def create_driver(self):
chrome_option = webdriver.ChromeOptions()
chrome_option.add_argument("--disable-infobars")
chrome_option.add_argument("--start-maximized")
chrome_option.add_argument("--disable-popup-blocking")
capabilities = DesiredCapabilities.CHROME.copy()
capabilities['browser'] = 'chrome'
capabilities = chrome_option.to_capabilities()
self.driver = webdriver.Remote(self.__chservice.service_url,
desired_capabilities=capabilities)
self.edriver = EventFiringWebDriver(self.driver, EventListener())
self.edriver.implicitly_wait(
QEEnvironment.get_environment_dict().get('ImplicitWait'))
self.edriver.get(QEEnvironment.get_environment_dict().get('URL'))
def getcook():
loginurl = 'http://113.57.169.227:8088/ccps/login.jsp' # 登录页面
path = r'd:\chromedriver.exe'
# 加载webdriver驱动，用于获取登录页面标签属性
# driver = webdriver.Chrome(r'd:\chromedriver.exe')
# option = webdriver.ChromeOptions()
# option.binary_location = r'C:\Program Files (x86)\Google\Chrome\Application\chrome.exe'
# option.add_argument('--headless') #增加无界面选项
# option.add_argument('--disable-gpu') #如果不加这个选项，有时定位会出现问题
# option.add_experimental_option('excludeSwitches', ['enable-logging'])
c_service = Service(path)
c_service.command_line_args()
c_service.start()
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
driver = webdriver.Chrome(executable_path=path, options=chrome_options)
driver.get(loginurl) # 请求登录页面
driver.find_element_by_id('wcode').clear() # 获取用户名输入框，并先清空
driver.find_element_by_id('wcode').send_keys(u'WHBK100') # 输入用户名
driver.find_element_by_id('password').clear() # 获取密码框，并清空
driver.find_element_by_id('password').send_keys(u'') # 输入密码
#captcha = driver.find_element_by_id('captcha_image') # 获取验证码标签
#submit = driver.find_element_by_css_selector('a[name="登录"]') # 获取提交按钮
submit = driver.find_element_by_link_text("登录")
# 判断是否需要验证码
captcha = []
if captcha:
captcha_field = driver.find_element_by_id('captcha_field') # 获取验证码输入框
text = input("请输入验证码：") # 控制栏输入验证码
captcha_field.send_keys(text) # 将输入的验证码传递给selenium打开的浏览器
submit.click() # 按钮提交并登录
else:
submit.click() # 无验证码则直接登录提交
cookies = driver.get_cookies() # 获取COOK
#driver.get('http://113.57.169.227:8088/ccps//workorder/findWorkOrderList.action?workOrder.range=yff&workOrder.standby3=order_deal') # 请求其他页面
time.sleep(1)
driver.quit()
c_service.stop()
#print(cookies)
return cookies # 返回cookies 之后其他方法可以调用，这样不用每次请求都返回登录
def get_urls(xingqi, A):
#由于在后台打开浏览器，因此不能很好的关闭，所以用service.start(),service.close()控制进程开关
c_service = Service(
'C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe')
c_service.command_line_args()
c_service.start()
#使用谷歌自带的无头浏览器模式，悄无声息地运行
opt = Options()
opt.add_argument('--headless')
browser = webdriver.Chrome(chrome_options=opt)
wait = WebDriverWait(browser, 10) #设置延迟10秒，等待网页加载
#
browser.get('http://www.qqshidao.com/index.php?c=home&a=bifen')
time.sleep(3)
submit = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="app"]/div[6]/div/span[6]')))
submit.click()
time.sleep(2)
js = 'var q=document.documentElement.scrollTop=100000' #设置往下拉网页的长度,设置大点，直接拉到底部
browser.execute_script(js) #发现当比赛较多时，往下拉一下后加载新的数据，因此，自动往下拉一下就停了
time.sleep(1)
browser.execute_script(js) #再往下拉一下，加载全部比赛
time.sleep(2)
yuanma = browser.page_source
browser.quit()
c_service.stop()
s = etree.HTML(yuanma)
urls = []
urls_ = s.xpath('//*[@id="app"]/div[7]/div/table/tbody/tr[@data-fid]')
for each in urls_:
fid = each.attrib['data-fid']
xingqiji = each.xpath('./td[3]/text()')[0]
if xingqi in xingqiji:
url = 'http://www.qqshidao.com/index.php?c=odds&a=betfair&fid={}'.format(
fid)
A['{}'.format(url)] = xingqiji
urls.append(url)
return urls
def download_by_webdriver(url, charset='utf-8', proxy=None, user_agent=None):
# 传入URL，使用浏览器下载后，返回页面。
print("[download_by_webdriver]: begin download the link %s" % url)
try:
# 进入浏览器设置
options = webdriver.ChromeOptions()
# 谷歌无头模式
options.add_argument('--headless')
options.add_argument('--disable-gpu')
# options.add_argument('window-size=1200x600')
# 设置中文
options.add_argument('lang=zh_CN.UTF-8')
# 设置代理
if proxy:
print("[download_by_webdriver]: use proxy %s" % proxy)
options.add_argument('proxy-server=' + proxy)
# 添加头
if user_agent:
options.add_argument('user-agent=' + user_agent)
else:
options.add_argument(
'user-agent=' + 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/71.0.3578.98 Safari/537.36')
# 设置驱动服务
c_service = Service('/usr/local/bin/chromedriver')
c_service.command_line_args()
c_service.start()
driver = webdriver.Chrome(chrome_options=options)
driver.get(url)
driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")
driver.implicitly_wait(10)
driver.set_page_load_timeout(15)
p_content = driver.page_source.encode(charset, "ignore").decode(charset, 'ignore')
current_url = driver.current_url
driver.quit()
c_service.stop()
except Exception as e:
print("[download_by_webdriver]:", e)
p_content, current_url = None, None
return p_content, current_url
def download_by_webdriver(url, charset='utf-8'):
# 传入URL，使用浏览器下载后，返回页面。
print("[download_by_webdriver]: begin download the link %s" % url)
try:
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
c_service = Service('/usr/local/bin/chromedriver')
c_service.command_line_args()
c_service.start()
driver = webdriver.Chrome(chrome_options=chrome_options)
driver.get(url)
driver.implicitly_wait(10)
content = driver.page_source.encode(charset, "ignore").decode(
charset, 'ignore')
current_url = driver.current_url
driver.quit()
c_service.stop()
except Exception as e:
print("[download_by_webdriver]:", e)
content, current_url = None, None
return content, current_url
class SeleniumExampleTest(unittest.TestCase):
def setUp(self):
print("Setting up")
self.__app_url = "http://192.168.56.101/wp-admin"
self.__app_logout_url = "http://192.168.56.101/wp-login.php?action=logout"
self.username = "******"
self.password = "******"
driver_path = ChromeDriverManager().install()
self.svc = Service(driver_path)
self.svc.start()
self.driver = webdriver.Remote(self.svc.service_url)
self.waiter = WebDriverWait(self.driver, 30)
def tearDown(self):
print("Cleaning up")
self.driver.quit()
self.svc.stop()
def test_wp_login(self):
self.driver.get(self.__app_url)
self.waiter.until(EC.presence_of_element_located((By.ID, "wp-submit")))
element = self.waiter.until(
EC.element_to_be_clickable((By.NAME, "log")))
element.send_keys(self.username)
element = self.waiter.until(
EC.element_to_be_clickable((By.NAME, "pwd")))
element.send_keys(self.password)
element = self.waiter.until(
EC.element_to_be_clickable(
(By.CSS_SELECTOR, "input[type *= 'sub']")))
element.click()
self.waiter.until(
EC.presence_of_element_located(
(By.XPATH, "//div[contains(*//text(), 'Welcome')]")))
self.driver.get()
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
base_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(base_dir + '/bin')
driver_path = base_dir + '/bin/chromedriver'
# 初始化 chrome service
chrome_service = Service(executable_path=driver_path)
chrome_service.command_line_args()
chrome_service.start()
# 初始化 driver
driver = webdriver.Chrome(driver_path)
driver.implicitly_wait(30)
driver.maximize_window()
driver.get("http://www.linkedsee.com/")
products = driver.find_elements_by_xpath("//ul[@class='drop box-1']/li/a")
print(products)
print("found " + str(len(products)) + "products")
for product in products:
print(product.get_attribute('textContent'))
driver.quit()
chrome_service.stop()
class Spider:
def __init__(self):
self.c_service = Service(
'C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe'
)
self.c_service.command_line_args()
self.c_service.start()
chrome_options = Options()
chrome_options.add_argument('--headless') #不显示界面
#chrome_options.add_argument('--disable-gpu')
self.driver = webdriver.Chrome(chrome_options=chrome_options)
self.url = "https://music.163.com/#/discover/toplist?id=3778678"
'''找到所有热门歌曲的URL和歌曲名称'''
def find_allSong(self):
# self.driver.implicitly_wait(10)
#print("start")
WebDriverWait(self.driver, 3, 0.5).until(
lambda driver: self.driver.find_element_by_id("g_iframe"))
#print("All download")
self.driver.switch_to.frame(self.driver.find_element_by_id("g_iframe"))
# with open("test3.html",'w',encoding='UTF-8') as file_obj:
# file_obj.write(self.driver.page_source)
# header = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'}
# response = driver.get(self.url,headers = header) #请求网址
# print(response.request.headers)
# print(response.headers)
# print(response.status_code)
# print(response.content.decode("utf-8"))
soup = BeautifulSoup(self.driver.page_source, "lxml") #
song_list = soup.find('tbody') # 找到所有歌曲
all_song = song_list.find_all('tr')
for each_song in all_song:
each_info = each_song.find('span', class_="txt")
# each_info_2 = each_song.find('span', class_="title")
#each_info = each_song.find_all('span')
long_time = each_song.find('span', class_="u-dur").text
author = each_song.find('span',
class_="icn icn-share")['data-res-author']
link = "https://music.163.com/" + each_info.find('a')['href']
name = each_info.find('b')['title']
print('歌曲连接 : {}, 歌曲名 : {},作者 : {}，时长 : {}'.format(
link, name, author, long_time))
self.comment(link, name) #爬取评论
def comment(self, link, name):
self.driver.execute_script("window.open('%s')" % link)
# print(self.driver.window_handles)
# print(self.driver.current_window_handle)
self.driver.switch_to.window(window_name=self.driver.window_handles[1])
# print(self.driver.current_window_handle)
WebDriverWait(self.driver, 3, 0.5).until(
lambda driver: self.driver.find_element_by_id("g_iframe"))
self.driver.switch_to.frame(self.driver.find_element_by_id("g_iframe"))
page = 0
with open(name + "-评论信息.csv", 'w', encoding="utf-8") as fp:
fp.write('评论者,评论内容,评论日期' + '\n')
while True:
page += 1
soup = BeautifulSoup(self.driver.page_source, "lxml")
all_comment = soup.find_all('div', class_='itm')
#print(soup)
for each_comment in all_comment:
comment_name = each_comment.find('a', class_='s-fc7').text
tmp = each_comment.find('div', class_='cnt f-brk').text
date = each_comment.find('div', class_='time s-fc4').text
comment = tmp.replace(comment_name + '：', '')
#print(comment_name, comment)
with open(name + "-评论信息.csv", 'a+', encoding="utf-8") as fp:
fp.write(comment_name + ',' + comment + ',' + date + '\n')
'''
下一页
'''
try:
print("{}--第{}页.".format(name, page))
next = self.driver.find_element_by_xpath(
'//*[starts-with(@class,"zbtn znxt") and not(contains(@class,"js-disabled"))]'
) #xpath路径匹配节点
except:
print(self.driver.current_window_handle)
self.driver.switch_to.window(
window_name=self.driver.window_handles[0])
print(self.driver.current_window_handle)
self.driver.close() # 关闭当前窗口
return
#last = self.driver.find_element_by_xpath('//*[starts-with(@class,"zbtn znxt js-n") and contains(@class,"js-disabled")]')
else:
next.send_keys(Keys.ENTER)
time.sleep(0.5)
def run(self):
self.driver.get(self.url) #启动浏览器
self.find_allSong()
#self.comment()
#self.driver.close() # 关闭当前窗口
self.driver.quit() # 关闭进程
def __del__(self):
self.c_service.stop()
class WebDriver(RemoteWebDriver):
"""
Controls the ChromeDriver and allows you to drive the browser.
You will need to download the ChromeDriver executable from
http://chromedriver.storage.googleapis.com/index.html
"""
def __init__(self,
executable_path="chromedriver",
port=0,
chrome_options=None,
service_args=None,
desired_capabilities=None,
service_log_path=None):
"""
Creates a new instance of the chrome driver.
Starts the service and then creates new instance of chrome driver.
:Args:
- executable_path - path to the executable. If the default is used it assumes the executable is in the $PATH
- port - port you would like the service to run, if left as 0, a free port will be found.
- desired_capabilities: Dictionary object with non-browser specific
capabilities only, such as "proxy" or "loggingPref".
- chrome_options: this takes an instance of ChromeOptions
"""
if chrome_options is None:
# desired_capabilities stays as passed in
if desired_capabilities is None:
desired_capabilities = self.create_options().to_capabilities()
else:
if desired_capabilities is None:
desired_capabilities = chrome_options.to_capabilities()
else:
desired_capabilities.update(chrome_options.to_capabilities())
self.service = Service(executable_path,
port=port,
service_args=service_args,
log_path=service_log_path)
self.service.start()
try:
RemoteWebDriver.__init__(
self,
command_executor=ChromeRemoteConnection(
remote_server_addr=self.service.service_url),
desired_capabilities=desired_capabilities)
except:
self.quit()
raise
self._is_remote = False
def launch_app(self, id):
"""Launches Chrome app specified by id."""
return self.execute("launchApp", {'id': id})
def quit(self):
"""
Closes the browser and shuts down the ChromeDriver executable
that is started when starting the ChromeDriver
"""
try:
RemoteWebDriver.quit(self)
except:
# We don't care about the message because something probably has gone wrong
pass
finally:
self.service.stop()
def create_options(self):
return Options()
def AutoInfoSpider(url):
# 启动服务
c_service = Service(
'C:/Users/gusisong/AppData/Local/Continuum/anaconda3/chromedriver.exe')
c_service.command_line_args()
c_service.start()
# 功能配置
option = webdriver.ChromeOptions()
option.add_argument('--headless')
option.add_argument('--disable-gpu')
option.add_argument('--disable-images')
option.add_argument('--disable-javascript')
option.add_argument('--disable-plugins')
option.add_argument('--no-sandbox')
driver = webdriver.Chrome(options=option)
driver.get(url)
output = []
for letter_index in range(1, 25):
# 按品牌抓取
brand_list = driver.find_elements_by_xpath(
'/html/body/div[8]/div[1]/div[2]/div/div[{}]//a/div'.format(
letter_index))
for brand_index in range(2, len(brand_list) + 2):
# 记录品牌名称
brand_name = driver.find_element_by_xpath(
'/html/body/div[8]/div[1]/div[2]/div/div[{0}]/div[{1}]/a/div'.
format(letter_index, brand_index)).text
# 进入车型目录
driver.find_element_by_xpath(
'/html/body/div[8]/div[1]/div[2]/div/div[{0}]/div[{1}]/a/div'.
format(letter_index, brand_index)).click()
# 按页码抓取
page_list = driver.find_elements_by_xpath(
'/html/body/div[8]/div[4]/div[5]/div/div/div/a')
for page_index in range(1, len(page_list) + 1):
if page_index > 1:
driver.find_element_by_xpath(
'/html/body/div[8]/div[4]/div[5]/div/div/div/a[{}]'.
format(page_index)).click()
model_list = driver.find_elements_by_xpath(
'/html/body/div[8]/div[4]/div[3]/div')
for model_index in range(1, len(model_list) + 1):
# 记录车型名称
model_name = driver.find_element_by_xpath(
'/html/body/div[8]/div[4]/div[3]/div[{}]/a/p[1]'.
format(model_index)).text
# 记录车型价格
price_range = driver.find_element_by_xpath(
'/html/body/div[8]/div[4]/div[3]/div[{}]/a/p[2]'.
format(model_index)).text
if '-' in price_range:
min_price = price_range[:-1].split('-')[0] + '万'
max_price = price_range[:-1].split('-')[1] + '万'
elif '暂无' in price_range:
min_price = '暂无'
max_price = '暂无'
else:
min_price = price_range
max_price = price_range
# 记录图片链接
pic_link = driver.find_element_by_xpath(
'/html/body/div[8]/div[4]/div[3]/div[{}]/a/img'.format(
model_index)).get_attribute("src")
print(brand_name, model_name, min_price, max_price,
pic_link)
output.append([
brand_name, model_name, min_price, max_price, pic_link
])
# 写入文件
df = DataFrame(output)
df.columns = ['品牌名', '车型', '最低价', '最高价', '图片链接']
df.to_csv('auto_info.csv', encoding='utf_8_sig')
# 后台完全关闭
driver.close()
driver.quit()
c_service.stop()
class MyWebBoost():
def __init__(self, chromedriver_path, target_url):
chromedriver = chromedriver_path
chrome_options = Options()
chrome_options.add_argument('--no-sandbox')
chrome_options.add_argument('--headless')
chrome_options.add_argument('--disable-gpu')
self.s = Service(chromedriver)
self.driver = webdriver.Chrome(service=self.s, options=chrome_options)
# 设置超时，双重保险
self.driver.set_page_load_timeout(30)
self.driver.set_script_timeout(30)
self.target_url = target_url
# 0.开始获取连接
def startConnect(self):
global maxConnectTime
# 最多尝试3次，不行就直接退出
if maxConnectTime == 3:
self.quit()
return
isSuccess = self.getUrl()
# 地址获取成功
if isSuccess:
self.startMyWork()
# 获取失败,递归加载，最多尝试3次
else:
maxConnectTime = maxConnectTime + 1
time.sleep(1)
self.startConnect()
# 1.尝试登录url
def getUrl(self):
try:
self.driver.get(self.target_url)
return True
except Exception as e:
logging.error(
"------------ts.js.vnet.cn 首次加载失败！------------")
return False
# 2、执行方法
def startMyWork(self):
global maxLoadTime
# 最多尝试3次，不行就直接退出
if maxLoadTime == 6:
self.quit()
return
# 开始操作
flag, d_time = self.startClick()
if flag:
logging.error("操作成功！")
self.quit()
# senWChat("提速成功!")
return
else:
# 失败，时间对不上，则sleep
maxLoadTime = maxLoadTime + 1
logging.error("需要休眠:%s秒" % str(d_time))
time.sleep(d_time + 5)
# 刷新
if self.getUrl():
self.startMyWork()
else:
self.quit()
return
# 3、点击事件
def startClick(self):
global maxRefreshTime
try:
self.driver.get_screenshot_as_file('/root/startClick.png')
# 1、点击同意书
readBtn = self.driver.find_elements(By.XPATH, '//*[@id="CheckAgree"]')[0]
if readBtn.is_displayed():
# logging.error(
# "-----------已查询到同意书-------------")
readBtn.click()
time.sleep(1)
self.driver.find_elements(By.XPATH, '//*[@id="ButtonAgree"]')[0].click()
time.sleep(3)
# self.driver.get_screenshot_as_file('/root/clicked_submit.png')
self.driver.find_elements(By.XPATH, '//div[@id="CmdBtn"]/div/input[2]')[0].click()
time.sleep(5)
# 2、点击试用按钮
else:
# logging.error(
# "-----------不需要查询同意书，直接试用-------------")
self.driver.find_elements(By.XPATH,
'//div[@id="CmdBtn"]/div[1]/input[2]')[0].click()
time.sleep(5)
except Exception as e:
# logging.error(e)
# self.driver.get_screenshot_as_file('/volume2/web/tryfailed.png')
maxRefreshTime = maxRefreshTime + 1
if maxRefreshTime == 8:
self.quit()
else:
if self.getUrl():
self.startMyWork()
else:
self.quit()
try:
self.driver.get_screenshot_as_file('/root/clicked_try.png')
# 查看是否已经到期
# WebDriverWait(self.driver, 10).until(
# EC.presence_of_element_located((By.ID, "btnExperiencesOK")))
# 已经到期——点击确定试用
time.sleep(5)
self.driver.find_element(By.XPATH, '//input[@id="btnExperiencesOK"]').click()
# text = driver.find_element_by_xpath(
# '//p[@id="OpenResMessage"]').text
# 截图
# self.driver.get_screenshot_as_file('/volume2/web/ss.png')
return True, 0
except Exception as e:
self.driver.get_screenshot_as_file('/root/clicked_fail.png')
# 没有到期，找到到期的日期
text = self.driver.find_element(By.XPATH, '//p[@id="OpenResMessage"]').text
# text = "亲，您今天的下行体验时间将于00点08分到期"
logging.error(text)
if len(text) > 0:
# TODO
delayTime = self.getDelayTime(text)
# logging.info("最后需要等待的时间(s):" + str(delayTime))
return False, delayTime
else:
maxRefreshTime = maxRefreshTime + 1
if maxRefreshTime == 10:
self.quit()
else:
if self.getUrl():
self.startMyWork()
else:
self.quit()
# 算出延迟的时间
@ staticmethod
def getDelayTime(text):
logging.info("提醒时间:" + text)
endTime = text.split('将于')[1].split("分到期")[0].replace('点', ':')
nowDay = time.strftime("%Y-%m-%d ", time.localtime())
# 拼接，具体的到期日期
finalTime = nowDay + endTime + ":59"
# 现在的具体日期
nowTime = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
d1 = datetime.datetime.strptime(nowTime, '%Y-%m-%d %H:%M:%S')
d2 = datetime.datetime.strptime(finalTime, '%Y-%m-%d %H:%M:%S')
# 服务器时间比现实时间慢200秒左右
d2 = d2 + datetime.timedelta(seconds=240)
# 比较日期,如果 到期日期 < 当前日期
if d1 > d2:
differSecond = (d1 - d2).seconds
else:
differSecond = (d2 - d1).seconds
logging.info("当前的时间:" + nowTime)
logging.info("到期的时间:" + finalTime)
# return 150 if differSecond < 130 else differSecond
return differSecond
# 退出Chromedriver
def quit(self):
# self.driver.close()
self.driver.quit()
self.s.stop()
os.system('ps -ef|grep chromedriver|grep -v grep|awk \'{print $2}\'|xargs kill -9')
os.system('ps -ef|grep chrome|grep -v grep|awk \'{print $2}\'|xargs kill -9')
class CaesarReaderWindow(QMainWindow, Ui_myMainWindow):
def __init__(self, parent=None):
super(CaesarReaderWindow, self).__init__(parent)
self.chromeDriverPath = os.path.abspath('chromedriver.exe')
self.driver = None
self.c_service = None
self.startReadFlag = False
self.stopReadFlag = False
self.stopPPPOEFlag = False
# 已完成文章篇数
self.readNum = 0
# 剩余文章篇数
self.unReadNum = 0
self.driverThread = DriverThread(self)
self.pppoeThread = PPPOETask(self)
self.setupUi(self)
self.connectPppoeBtn.clicked.connect(self.connect_pppoe_click)
self.disconnectPppoeBtn.clicked.connect(self.disconnect_pppoe_click)
self.saveConfigBtn.clicked.connect(self.save_config_click)
self.startReadBtn.clicked.connect(self.start_read_click)
self.stopReadBtn.clicked.connect(self.end_read_click)
self.init_config()
def init_config(self):
"""
初始化全局配置
:return:
"""
try:
initConfigTask = InitConfigTask(self)
pool = QThreadPool.globalInstance()
pool.start(initConfigTask)
except Exception as e:
self.print_log(str(e))
pass
def popen(self, cmd):
try:
popen = subprocess.Popen(cmd, stdout=subprocess.PIPE)
popen.wait()
lines = popen.stdout.readlines()
return [line.decode('gbk') for line in lines]
except Exception as e:
self.print_log("获取ip异常")
return -1
def save_config_click(self):
"""
保存全局配置信息
:return:
"""
startTime = self.startTimeEdit.text()
endTime = self.endTimeEdit.text()
pauseTimeFrom = self.pauseTimeFromEdit.text()
pauseTimeTo = self.pauseTimeToEdit.text()
slipTimesFrom = self.slipTimesFromEdit.text()
slipTimesTo = self.slipTimesToEdit.text()
pxFrom = self.pxFromEdit.text()
pxTo = self.pxToEdit.text()
chromeLocation = self.chromeLocationEdit.text()
if not (startTime and endTime and pauseTimeFrom and pauseTimeTo
and slipTimesFrom and slipTimesTo and pxFrom and pxTo
and chromeLocation):
return
configObj = {
'startTime': startTime,
'endTime': endTime,
'pauseTimeFrom': pauseTimeFrom,
'pauseTimeTo': pauseTimeTo,
'slipTimesFrom': slipTimesFrom,
'slipTimesTo': slipTimesTo,
'pxFrom': pxFrom,
'pxTo': pxTo,
'chromeLocation': chromeLocation
}
with open(os.path.abspath('config.ini'), 'w', encoding='utf-8') as f:
f.write(json.dumps(configObj))
f.flush()
f.close()
pass
def start_read_click(self):
"""
开始阅读按钮点击
:return:
"""
self.startReadFlag = True
self.stopReadFlag = False
try:
if not self.driverThread.isRunning():
self.driverThread.trigger.connect(self.reconnect_pppoe)
self.driverThread.start()
except Exception as e:
self.print_log(str(e))
pass
def end_read_click(self):
"""
停止阅读按钮点击
:return:
"""
self.startReadFlag = False
self.stopReadFlag = True
try:
if self.driver is not None:
self.driver.quit()
self.driver = None
except Exception as msg:
pass
try:
if self.c_service is not None:
self.c_service.stop()
self.c_service = None
except Exception as msg:
pass
pass
def connect_pppoe_click(self):
"""
开始拨号按钮点击
:return:
"""
self.stopPPPOEFlag = False
try:
if not self.pppoeThread.isRunning():
self.pppoeThread.trigger.connect(self.read_next)
self.pppoeThread.start()
except Exception as e:
self.print_log(str(e))
pass
def disconnect_pppoe_click(self):
"""
停止拨号按钮点击
:return:
"""
self.stopPPPOEFlag = True
data = self.check_for_broadband()
if data is not None:
for p in data:
self.show_ip_address()
if self.disconnect_pppoe(p[0]) == "success":
self.print_log("宽带%s已经断开" % p[1])
sleep(5)
pass
def read_next(self):
"""
阅读下一篇
:return:
"""
if not self.startReadFlag:
return
if self.stopReadFlag or self.stopPPPOEFlag:
return
self.start_read_click()
pass
def reconnect_pppoe(self):
"""
重新连接pppoe
:return:
"""
if self.stopReadFlag or self.stopPPPOEFlag:
return
self.connect_pppoe_click()
pass
def build_driver(self, url):
"""
构建阅读driver
:return:
"""
if not url:
self.stopReadFlag = True
self.print_log("已全部阅读完成\n")
return
self.readNum = self.readNum + 1
self.print_log("开始阅读第 %d 篇，剩余 %d 篇" % (self.readNum, self.unReadNum))
self.print_log("当前：%s" % url)
self.c_service = Service(self.chromeDriverPath)
self.c_service.command_line_args()
self.c_service.start()
mobileEmulation = {
"deviceMetrics": {
"width": 320,
"height": 640,
"pixelRatio": 3.0
},
"userAgent":
'Mozilla/5.0 (Linux; Android 4.1.1; GT-N7100 Build/JRO03C) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/35.0.1916.138 Mobile Safari/537.36 T7/6.3'
}
# mobileEmulation = {'deviceName': 'Apple iPhone 5'}
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--window-size=250,640')
chrome_options.add_argument('--disable-gpu')
chrome_options.add_argument('--hide-scrollbars')
chrome_options.add_argument('--disable-javascript')
chrome_options.add_argument('--log-level=3')
chrome_options.binary_location = self.chromeLocationEdit.text()
chrome_options.add_experimental_option('mobileEmulation',
mobileEmulation)
chrome_options.add_experimental_option("excludeSwitches",
['enable-automation'])
chrome_options.add_experimental_option('w3c', False)
self.driver = webdriver.Chrome(options=chrome_options)
# 操作这个对象.
self.driver.get(url)
num = random.randint(int(self.slipTimesFromEdit.text()),
int(self.slipTimesToEdit.text()))
# 下滑次数
hasNum = 0
for n in range(num):
if not self.stopReadFlag:
holdTime = random.randint(int(self.pauseTimeFromEdit.text()),
int(self.pauseTimeToEdit.text()))
px = random.randint(int(self.pxFromEdit.text()),
int(self.pxToEdit.text()))
self.print_log("第 %d 次下滑，等待 %d 秒, 下滑 %d 像素" %
(n + 1, holdTime, px))
# 每次下滑停顿时间
sleep(holdTime)
action = TouchActions(self.driver)
action.scroll(0, 200).perform()
hasNum = hasNum + 1
else:
break
try:
if self.driver is not None:
self.driver.quit()
self.driver = None
except Exception as msg:
pass
try:
if self.c_service is not None:
self.c_service.stop()
self.c_service = None
except Exception as msg:
pass
if self.stopReadFlag:
self.print_log("第 %d 篇阅未完成，共下滑 %d 次\n" % (self.readNum, hasNum))
return
else:
self.print_log("第 %d 篇阅读完成，共下滑 %d 次\n" % (self.readNum, hasNum))
try:
# 删除第一行
with open(os.path.abspath('unread.txt'), 'r',
encoding='utf-8') as f:
content = f.readlines()
with open(os.path.abspath('unread.txt'),
'w+',
encoding='utf-8') as f1:
f1.writelines(content[1:])
f1.flush()
f1.close()
f.close()
# 追加到最后一行
with open(os.path.abspath('read.txt'), 'a', encoding='utf-8') as f:
f.write(url)
f.close()
except Exception as e:
print(e)
pass
def build_pppoe(self):
"""
构建pppoe
:return:
"""
data = self.check_for_broadband()
if data is not None:
for p in data:
self.show_ip_address()
if self.disconnect_pppoe(p[0]) == "success":
self.print_log("宽带%s已经断开" % p[1])
sleep(5)
else:
try:
pid, res = self.dial_broadband()
if res == 0:
self.show_ip_address()
sleep(5)
except Exception as ee:
pass
pass
def print_log(self, message):
"""
异度打印日志
:param message: 日志信息
:return:
"""
try:
logTask = LogTask(self, message)
pool = QThreadPool.globalInstance()
pool.start(logTask)
except Exception as msg:
print(msg)
pass
def setUnReadNum(self, num):
self.unReadNum = num
def connect_pppoe(self, dialname, account, passwd):
dial_params = (dialname, '', '', account, passwd, '')
return win32ras.Dial(None, None, dial_params, None)
def dial_broadband(self):
"""
宽带拨号
:return:
"""
self.pppoeStatusLbl.setText("正在拨号...")
dialname = '宽带连接' # just a name
account = self.accountEdit.text()
passwd = self.passwordEdit.text()
self.print_log("正在拨号")
try:
# handle is a pid, for disconnect or showipadrress, if connect success return 0.
# account is the username that your ISP supposed, passwd is the password.
handle, result = self.connect_pppoe(dialname, account, passwd)
if result == 0:
self.print_log("拨号成功")
self.pppoeStatusLbl.setText("拨号成功")
return handle, result
else:
if self.stopPPPOEFlag:
self.print_log("拨号失败")
self.pppoeStatusLbl.setText("拨号失败")
return -1, -1
else:
self.print_log("拨号失败，3秒后重试")
self.pppoeStatusLbl.setText("正在重试")
sleep(3)
return self.dial_broadband()
except Exception as e:
self.print_log("拨号异常" + str(e))
return -1, -1
def disconnect_pppoe(self, handle):
self.print_log("正在断开宽带!")
self.pppoeStatusLbl.setText("正在断开")
if handle is not None:
try:
win32ras.HangUp(handle)
self.print_log("宽带断开成功!")
self.pppoeStatusLbl.setText("断开成功")
return "success"
except Exception as e:
self.print_log("宽带断开失败，3秒后重试")
self.pppoeStatusLbl.setText("断开失败")
sleep(3)
return self.disconnect_pppoe(handle)
else:
self.print_log("宽带断开异常")
self.pppoeStatusLbl.setText("断开失败")
return "fail"
def check_for_broadband(self):
connections = win32ras.EnumConnections()
if len(connections) == 0:
self.print_log("系统未运行任何宽带连接")
return
else:
self.print_log("系统正在运行%d个宽带连接" % len(connections))
return connections
def show_ip_address(self):
self.print_log("正在查询IP")
self.pppoeIpLbl.setText("")
ipconfig_result_list = self.popen('ipconfig')
if ipconfig_result_list == -1:
return
ip_str = None
have_ppp = 0
for line in ipconfig_result_list:
if line.find("宽带连接") >= 0:
have_ppp = 1
if have_ppp == 1:
if line.strip().startswith("IPv4 地址"):
ip_str = line.split(":")[1].strip()
have_ppp = 0
if ip_str is not None:
self.print_log("IP地址为： " + ip_str)
self.pppoeIpLbl.setText(ip_str)
pass
class ICloud(object):
TIMEOUT = 100
id = None
account = None
browser = None
chrome = None
wait = None
tab = None
deleted = False
mapping = set()
c_service = None
def __init__(self):
gc.collect()
self.id = random.randint(0, 100)
self.c_service = Service('chromedriver')
self.c_service.command_line_args()
self.c_service.start()
self.start_browser()
logger.info('Start a browser.')
def __wait_for_visible(self, xpath):
return self.wait.until(
expected_conditions.visibility_of_element_located(
(By.XPATH, xpath)))
def run_login(self, account, password):
logger.info('"{account}" is logging in.'.format(account=account))
self.account = account
# Get the login page.
self.browser.get('https://www.icloud.com/#fmf')
auth_frame = self.__wait_for_visible('//*[@id="auth-frame"]')
self.browser.switch_to.frame(auth_frame)
logger.info('Login page is loaded.')
# Process input: account name and password.
remember_me_input = self.browser.find_element_by_xpath(
'//*[@id="remember-me"]')
remember_me_input.click()
account_name_text_field = self.browser.find_element_by_xpath(
'//*[@id="account_name_text_field"]')
account_name_text_field.send_keys(account)
account_name_text_field.send_keys(Keys.RETURN)
password_text_field = self.__wait_for_visible(
'//*[@id="password_text_field"]')
password_text_field.send_keys(password)
password_text_field.send_keys(Keys.RETURN)
try:
# Wait until the code controls are visible.
self.__wait_for_visible('//*[@id="char0"]')
return True
except TimeoutException:
# Login failed.
return False
def run_codes(self, codes):
# Write codes to each controls.
for i in range(6):
char = self.browser.find_element_by_xpath(
'//*[@id="char{i}"]'.format(i=i))
char.send_keys(codes[i])
try:
# Click trust button
trust_browser = self.__wait_for_visible(
'//*[starts-with(@id, "trust-browser-")]')
trust_browser.click()
except TimeoutException:
# Codes were incorrect.
return False
self.save_cookies()
logger.info('Start network listening...')
self.tab = self.chrome.list_tab()[-1]
self.tab.Network.responseReceived = self.response_received
self.tab.start()
self.tab.Network.enable()
# Start auto refresh.
Timer(60, self.auto_refresh).start()
return True
def save_cookies(self):
cookies = self.browser.get_cookies()
jsonCookies = json.dumps(cookies)
with open('./logs/{id}.cookies'.format(id=self.id), 'w') as f:
f.write(jsonCookies)
def load_cookies(self):
self.browser.delete_all_cookies()
with open('./logs/{id}.cookies'.format(id=self.id), 'r') as f:
listCookies = json.loads(f.read())
for cookie in listCookies:
self.browser.add_cookie({
'domain': cookie['domain'],
'name': cookie['name'],
'value': cookie['value'],
'path': '/',
'expires': None
})
logger.info('Browser cookies loaded.')
def start_browser(self):
# Start chromedriver
options = webdriver.ChromeOptions()
options.add_argument('--disable-background-networking=false')
options.add_argument('--no-sandbox')
retry_count = 0
while True:
try:
self.browser = webdriver.Chrome(
chrome_options=options,
service_args=[
'--verbose',
'--log-path=./logs/{id}.log'.format(id=self.id)
])
break
except ConnectionResetError as e:
retry_count += 1
if retry_count >= 10:
raise e
self.browser.set_page_load_timeout(self.TIMEOUT)
self.wait = WebDriverWait(self.browser, self.TIMEOUT)
# Get debug url
url = None
with open('./logs/{id}.log'.format(id=self.id), 'r') as log:
for line in log:
if 'DevTools request: http://localhost' in line:
url = line[line.index('http'):].replace(
'/json/version', '').strip()
break
if not url:
raise Exception('Invalid protocol url.')
# Start pychrome
self.chrome = pychrome.Browser(url=url)
def restart_browser(self):
try:
if self.browser:
self.browser.close()
self.browser.quit()
except Exception:
pass
self.start_browser()
logger.info('Browser restarted.')
retry = 0
while True:
try:
self.browser.get('https://www.icloud.com/#fmf')
self.load_cookies()
self.browser.refresh()
break
except Exception as e:
retry += 1
if retry >= 5:
raise e
logger.info('Start network listening...')
self.tab = self.chrome.list_tab()[-1]
self.tab.Network.responseReceived = self.response_received
self.tab.start()
self.tab.Network.enable()
# Start auto refresh.
Timer(60, self.auto_refresh).start()
def auto_refresh(self):
if self.deleted:
return
try:
self.browser.switch_to.default_content()
frame = self.__wait_for_visible('//*[@id="fmf"]')
self.browser.switch_to.frame(frame)
nearby = self.__wait_for_visible(
'/html/body/div[2]/div/div/div[2]/div[1]/div/div[3]/div[1]/div[1]'
)
friends = self.browser.find_elements_by_xpath(
'/html/body/div[2]/div/div/div[2]/div[1]/div/div[3]/div[1]/div[not(contains(@class, "nearby"))]'
)
for friend in friends:
friend.click()
nearby.click()
self.save_cookies()
Timer(60, self.auto_refresh).start()
except WebDriverException as e:
logger.error(e.args)
self.refresh_page()
def refresh_page(self, retry=1):
if self.deleted:
return
if retry >= 5:
logger.error('SERVICE DOWN! restarting...')
try:
self.restart_browser()
except Exception as e:
ICLOUD_DICT.pop(self.account)
app.mail.send(
'FMF: SERVICE DOWN',
'<p>{account} unavailable, login again.</p><p>{e}</p>'.
format(account=self.account, e=e.args),
img='logs/{id}.png'.format(id=self.id))
return
logger.info('REFRESHING...')
try:
self.browser.save_screenshot('logs/{id}.png'.format(id=self.id))
self.browser.refresh()
Timer(60, self.auto_refresh).start()
except Exception as e:
logger.error(e.args)
retry += 1
Timer(10, self.refresh_page, [retry]).start()
def response_received(self, **kwargs):
response = kwargs.get('response')
request_id = kwargs.get('requestId')
if 'refreshClient' in response.get('url'):
try:
content = self.tab.Network.getResponseBody(
requestId=request_id)['body']
except pychrome.CallMethodException:
return
logger.info('{request_id}: {content}'.format(request_id=request_id,
content=content))
obj = json.loads(content)
if 'locations' in obj:
contacts = {}
for contact in obj['contactDetails']:
id = contact['id']
name = '{first} {middle} {last}'.format(
first=contact['firstName'],
middle=contact['middleName'],
last=contact['lastName']).strip()
contacts[id] = name
for loc in obj['locations']:
if loc['location'] is None:
continue
id = loc['id']
locid = loc['location']['locationId']
if loc['location']['address'] is None:
address = 'UNKNOWN'
elif 'formattedAddressLines' in loc['location']['address']:
address = ' '.join(loc['location']['address']
['formattedAddressLines'])
else:
address = '{streetAddress} {locality} {administrativeArea}'.format(
streetAddress=loc['location']['address']
['streetAddress'],
locality=loc['location']['address']['locality'],
administrativeArea=loc['location']['address']
['administrativeArea'])
time = loc['location']['timestamp'] / 1000.0
accuracy = loc['location']['horizontalAccuracy']
latitude = loc['location']['latitude']
longitude = loc['location']['longitude']
self.save_model({
'locid': locid,
'account': self.account,
'uid': id,
'name': contacts[id],
'time': time,
'accuracy': accuracy,
'latitude': latitude,
'longitude': longitude,
'address': address
})
def save_model(self, obj):
if obj['uid'] not in self.mapping:
res = requests.get('http://yingyan.baidu.com/api/v3/entity/list',
params={
'ak':
BMAP_AK,
'service_id':
YINGYAN_ID,
'filter':
'entity_names:{uid}'.format(uid=obj['uid'])
})
jo = json.loads(res.text)
if jo['status'] != 0:
res = requests.post(
'http://yingyan.baidu.com/api/v3/entity/add',
data={
'ak': BMAP_AK,
'service_id': YINGYAN_ID,
'entity_name': obj['uid'],
'entity_desc': obj['name']
})
logger.info('YingYan ADD entity: {res}'.format(res=res.text))
self.mapping.add(obj['uid'])
if Location.objects.filter(locid=obj['locid']):
return
try:
Location.objects.create(locid=obj['locid'],
account=obj['account'],
uid=obj['uid'],
name=obj['name'],
time=datetime.datetime.fromtimestamp(
obj['time']),
accuracy=obj['accuracy'],
latitude=obj['latitude'],
longitude=obj['longitude'],
address=obj['address'])
except IntegrityError:
pass
res = requests.post('http://yingyan.baidu.com/api/v3/track/addpoint',
data={
'ak': BMAP_AK,
'service_id': YINGYAN_ID,
'entity_name': obj['uid'],
'latitude': obj['latitude'],
'longitude': obj['longitude'],
'loc_time': int(obj['time']),
'radius': obj['accuracy'],
'coord_type_input': 'wgs84',
'address': obj['address']
})
logger.info('YingYan ADD point: {res}'.format(res=res.text))
def __del__(self):
self.deleted = True
if self.browser:
self.browser.quit()
self.c_service.stop()
logger.info('A browser is Closed.')
user32.TranslateMessage(ctypes.byref(msg))
user32.DispatchMessageA(ctypes.byref(msg))
finally:
del msg
user32.UnregisterHotKey(None, 98)
user32.UnregisterHotKey(None, 99)
if __name__ == "__main__":
try:
c_service = Service("chromedriver.exe")
c_service.command_line_args()
c_service.start()
except WebDriverException as e:
logging.error("Failed to start broswer service")
try:
init_log_config()
thread_hotKey = HotKey("thread_hotKey")
thread_hotKey.setDaemon(True)
thread_hotKey.start()
print("The thread listening event from keyboard is running...")
driver = Driver()
driver.run()
except KeyboardInterrupt as e:
logging.warning("Handle KeyboardInterrupt.")
c_service.stop()
os.sys.exit(1)
class ChromeDriverAdapter:
def __init__(self, console: Console) -> None:
self.console = console
self.service = Service((os.path.dirname(__file__) or '.') + ('/bin/%s/chromedriver' % system()) )
#self.service = Service()
self.drivers = []
self.tempfolder = []
self.service.start()
def purge(self) -> None:
for driver in self.drivers:
try:
driver.quit()
except:
pass
for folder in self.tempfolder:
shutil.rmtree(path=folder, ignore_errors=True)
self.service.stop()
def getNewInstance(self, uid, user, proxy=None, headless=False) -> WebDriver:
pluginfile = None
try:
if proxy is None:
if 'proxy' in user:
proxy = user['proxy']
options = Options()
options.add_argument('--no-sandbox')
options.add_argument("--disable-dev-shm-usage")
#options.add_argument("--log-level=3")
#options.add_argument("--single-process")
options.add_argument('media.eme.enabled')
options.add_argument("--disable-gpu")
options.add_argument('--disable-popup-blocking')
#options.add_argument("--window-position=-32000,-32000");
options.add_argument("--disable-blink-features")
options.add_argument("--disable-blink-features=AutomationControlled")
#options.add_argument("--log-path=" + (os.path.dirname(__file__) or '.') + "/../chrome.log")
options.add_argument('--ignore-certificate-errors-spki-list')
options.add_argument('--ignore-certificate-errors')
options.add_argument('--ignore-ssl-errors')
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)
userDataDir = mkdtemp()
self.tempfolder.append(userDataDir)
options.add_argument('--user-data-dir=%s' % userDataDir)
if 'windowSize' in user:
options.add_argument("--window-size=%s" % user['windowSize'])
if headless:
#options.add_argument("--disable-gpu")
options.add_argument("--headless")
# Set user agent if available
if 'userAgent' in user:
options.add_argument('user-agent=%s' % user['userAgent'])
#incognito argument disable the use of the proxy, DO NOT SET !
#options.add_argument("--incognito")
desired_capabilities = DesiredCapabilities.CHROME.copy()
# add a proxy if available
if proxy:
pluginfile = self.buildChromeExtension(proxy)
options.add_extension(pluginfile)
#Instantiate the driver
#driver = WebDriver('bin/chromedriver',options=options, desired_capabilities=desired_capabilities)
driver = webdriver.Remote(self.service.service_url, desired_capabilities=desired_capabilities, options=options)
#Make webdriver = undefined
script = '''
Object.defineProperty(navigator, 'webdriver', {
get: () => undefined
})
'''
driver.execute_script(script)
if pluginfile:
os.remove(pluginfile)
pluginfile = None
return driver
except:
self.console.exception()
if pluginfile:
os.remove(pluginfile)
return None
class Meeting:
"""
* Stores all the meeting data and houses the meeting functions
"""
def __init__(self, meeting_url):
"""
* Reads the config file and imports meeting data
! Raises exception in case of no file found / invalid file
"""
super().__init__()
self.email = "*****@*****.**"
self.password = "******"
self.sleep_time = 12
self.meeting_url = meeting_url
self.port = random.randint(1024, 65535)
self.service = Service("chromedriver", port=self.port)
def init_driver(self):
"""
* Initialises webdriver and sets options for headless Chrome
"""
options = webdriver.ChromeOptions()
options.headless = True
options.binary_location = os.environ["GOOGLE_CHROME_BIN"]
options.add_argument('--disable-gpu')
options.add_argument('--no-sandbox')
options.add_argument('--disable-dev-shm-usage')
self.service.start()
self.driver = webdriver.Remote(
command_executor="http://127.0.0.1:{}".format(str(self.port)),
options=options,
)
self.driver.implicitly_wait(self.sleep_time)
self.driver.set_window_size(3840, 2160)
def try_to_join(self):
"""
* Tries to join meeting as per meeting data
! Raises exception if meeting data invalid
"""
self.driver.get(self.meeting_url)
join_from_browser_link = self.driver.find_element_by_xpath(
"//div[@class='desc24 webclient hideme']//a").get_attribute("href")
self.driver.get(join_from_browser_link)
self.driver.find_element_by_id("email").send_keys(self.email)
self.driver.find_element_by_id("password").send_keys(self.password)
self.driver.find_element_by_xpath("//div[@class='signin']").click()
self.random_hash = ''.join(
random.choices(
string.ascii_letters + string.digits,
k=16,
))
self.driver.find_element_by_id("inputname").clear()
self.driver.find_element_by_id("inputname").send_keys(self.random_hash)
self.driver.find_element_by_id("joinBtn").click()
def get_participants_list(self):
"""
* Collects participants and exports them to a CSV
! Might raise an exception if the internet is slow
"""
# * Sleep for a while in order to wait for the partipants list to load
# ? Any better alternative
time.sleep(self.sleep_time)
self.driver.find_elements_by_class_name(
"footer-button__button.ax-outline")[0].click()
self.partipants_list = [
name.get_attribute("aria-label").split() for name in
self.driver.find_elements_by_class_name("item-pos.participants-li")
]
if not self.partipants_list:
sys.exit(1)
def leave_meeting(self):
"""
* Leaves the ongoing meeting and closes the browser window
"""
self.driver.find_element_by_class_name(
"footer__leave-btn.ax-outline").click()
self.driver.find_element_by_class_name(
"zm-btn.zm-btn-legacy.zm-btn--primary.zm-btn__outline--blue"
).click()
self.driver.quit()
self.service.stop()
def export_data(self):
"""
* Exports data to a 'participants.csv' file
"""
for idx, row in enumerate(self.partipants_list):
self.partipants_list[idx] = row[0:row.index("audio") - 1]
self.partipants_list.sort()
return_object = ""
for idx, row in enumerate(self.partipants_list):
if row[-1] not in ["(Me)", "(Host)"]:
return_object += " ".join(row) + "\n"
return return_object
class CookiesGenerator(object):
def __init__(self, website='default'):
"""
父类, 初始化一些对象
:param website: 名称
:param browser: 浏览器, 若不使用浏览器则可设置为 None
"""
self.website = website
self.cookies_db = RedisClient('cookies', self.website)
self.accounts_db = RedisClient('accounts', self.website)
self.init_browser()
def __del__(self):
self.close()
def init_browser(self):
"""
通过browser参数初始化全局浏览器供模拟登录使用
:return:
"""
if BROWSER_TYPE == 'PhantomJS':
caps = DesiredCapabilities.PHANTOMJS
caps[
"phantomjs.page.settings.userAgent"] = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36'
self.browser = webdriver.PhantomJS(desired_capabilities=caps)
self.browser.set_window_size(1400, 500)
elif BROWSER_TYPE == 'Chrome':
# 启用谷歌浏览器
self.driver_service = Service(
executable_path=chromedriver_path) # 括号内填写 驱动路径
chrome_options = Options()
chrome_options.add_argument('--headless')
chrome_options.add_argument('--no-sandbox') # 这个配置很重要
# desired_capabilities = selenium_proxy() #添加代理IP
# driver = webdriver.Chrome(chrome_options=chrome_options, executable_path=chromedriver_path,desired_capabilities=desired_capabilities)
# , desired_capabilities = desired_capabilities
self.browser = webdriver.Chrome(chrome_options=chrome_options,
executable_path=chromedriver_path)
def new_cookies(self, username, password):
"""
新生成Cookies，子类需要重写
:param username: 用户名
:param password: 密码
:return:
"""
raise NotImplementedError
def process_cookies(self, cookies):
"""
处理Cookies
:param cookies:
:return:
"""
dict = {}
for cookie in cookies:
dict[cookie['name']] = cookie['value']
return dict
def run(self):
"""
运行, 得到所有账户, 然后顺次模拟登录
:return:
"""
accounts_usernames = self.accounts_db.usernames()
cookies_usernames = self.cookies_db.usernames()
for username in accounts_usernames:
# if not username in cookies_usernames:
if username not in cookies_usernames:
password = self.accounts_db.get(username)
print('正在生成Cookies', '账号', username, '密码', password)
result = self.new_cookies(username, password)
# 成功获取
if result.get('status') == 1:
cookies = self.process_cookies(result.get('content'))
print('成功获取到Cookies', cookies)
if self.cookies_db.set(username, json.dumps(cookies)):
print('成功保存Cookies')
# 密码错误，移除账号
elif result.get('status') == 2:
print(result.get('content'))
if self.accounts_db.delete(username):
print('成功删除账号')
else:
print(result.get('content'))
else:
print('所有账号都已经成功获取Cookies')
def close(self):
"""
关闭
:return:
"""
try:
print('Closing Browser')
self.browser.close()
self.driver_service.stop()
del self.browser
except TypeError:
print('Browser not opened')
class SeleniumDriverDispatcher:
def __init__(self):
self.__config = None
self.__driver = None
self.__proxy_server = None
self.__proxy = None
self.__driver_service = None
def __create_gui_element_dispatcher(self, element):
return SeleniumDriverElementDispatcher.create_dispatcher(self, element)
@property
def driver(self):
return self.__driver
@property
def proxy(self):
return self.__proxy
def launch(self, config):
self.__config = config
from .browser_launcher import BrowserLauncher
svc_url = config["arjuna_options"]["SELENIUM_SERVICE_URL"]
driver_download = config["arjuna_options"]["SELENIUM_DRIVER_DOWNLOAD"]
browser_name = config["arjuna_options"]["BROWSER_NAME"]
driver_path = config["arjuna_options"]["SELENIUM_DRIVER_PATH"]
if svc_url.lower() == "not_set":
from arjuna.tpi.constant import BrowserName
driver_service = None
driver_downloader = None
if browser_name == BrowserName.CHROME:
from selenium.webdriver.chrome.service import Service
driver_service = Service
from webdriver_manager.chrome import ChromeDriverManager
driver_downloader = ChromeDriverManager
elif browser_name == BrowserName.FIREFOX:
from selenium.webdriver.firefox.service import Service
driver_service = Service
from webdriver_manager.firefox import GeckoDriverManager
driver_downloader = GeckoDriverManager
if driver_download:
driver_path = driver_downloader().install()
self.__driver_service = Service(driver_path)
self.__driver_service.start()
svc_url = self.__driver_service.service_url
else:
if not svc_url.lower().endswith("/wd/hub"):
svc_url += "/wd/hub"
# BrowserMob
from arjuna import Arjuna
bmproxy_server = Arjuna._get_bmproxy_server()
if bmproxy_server is not None:
self.__proxy = bmproxy_server.create_proxy()
self.__driver = BrowserLauncher.launch(config, svc_url=svc_url, proxy=self.__proxy)
def quit(self):
DriverCommands.quit(self.__driver)
if self.__driver_service:
self.__driver_service.stop()
if self.__proxy:
self.__proxy.close()
def go_to_url(self, url):
DriverCommands.go_to_url(self.__driver, url)
def go_back_in_browser(self):
DriverCommands.go_back_in_browser(self.__driver)
def go_forward_in_browser(self):
DriverCommands.go_forward_in_browser(self.__driver)
def refresh_browser(self):
DriverCommands.refresh_browser(self.__driver)
def get_source(self):
return DriverCommands.get_source(self.__driver)
def send_keys(self, key_str):
DriverCommands.send_keys(self.__driver, key_str)
def execute_javascript(self, script, *args):
return DriverCommands.execute_javascript(self.__driver, script,
*[
isinstance(arg, SeleniumDriverElementDispatcher) and arg.driver_element or arg for arg in args
]
)
def take_screenshot(self, file_path):
DriverCommands.take_screenshot(self.__driver, file_path)
def take_screenshot_as_base64(self):
return DriverCommands.take_screenshot_as_base64(self.__driver)
def find_element(self, with_type, with_value, *, relations=None, filters=None):
element = SeleniumElementFinder.find_element(self.__driver, with_type, with_value, relations=relations, filters=filters)
return 1, self.__create_gui_element_dispatcher(element)
def __process_single_js_element(self, element):
# JS returns null, undefined
if element is None:
raise Exception("JavaScript could not find element.")
elif not isinstance(element, WebElement):
raise Exception("JavaScript returned a non-element object.")
else:
return element
def __process_js_element_list(self, elements):
if not elements: raise Exception("JavaScript could not find element.")
return [self.__process_single_js_element(e) for e in elements]
def __process_js_element(self, element):
if type(element) is list:
element = self.__process_js_element_list(element)[0]
else:
element = self.__process_single_js_element(element)
return element
def __process_js_multielement(self, elements):
if type(elements) is list:
elements = self.__process_js_element_list(elements)
else:
elements = [self.__process_single_js_element(elements)]
return elements
def find_element_with_js(self, js):
element = self.execute_javascript(js)
element = self.__process_js_element(element)
return 1, self.__create_gui_element_dispatcher(element)
def find_multielement(self, with_type, with_value, *, relations=None, filters=None):
web_elements = SeleniumElementFinder.find_elements(self.__driver, with_type, with_value, relations=relations, filters=filters)
melement = MultiElement([SeleniumDriverElementDispatcher(self, web_element) for web_element in web_elements])
return melement.get_size(), melement
def find_multielement_with_js(self, js):
web_elements = self.execute_javascript(js)
web_elements = self.__process_js_multielement(web_elements)
melement = MultiElement([SeleniumDriverElementDispatcher(self, web_element) for web_element in web_elements])
return melement.get_size(), melement
def get_current_window_handle(self):
return DriverCommands.get_current_window_handle(self.__driver)
def get_current_window_title(self):
return DriverCommands.get_window_title(self.__driver)
def maximize_current_window(self):
DriverCommands.maximize_window(self.__driver)
def get_current_window_size(self):
res = DriverCommands.get_current_window_size(self.__driver)
return {"width" : res[0], "height" : res[1]}
def get_all_window_handles(self):
return DriverCommands.get_all_winodw_handles(self.__driver)
def focus_on_window(self, handle):
DriverCommands.focus_on_window(self.__driver, handle)
def close_current_window(self):
DriverCommands.close_current_window(self.__driver)
def is_web_alert_present(self):
return DriverCommands.is_web_alert_present(self.__driver)
def confirm_web_alert(self):
DriverCommands.confirm_web_alert(self.__driver)
def dismiss_web_alert(self):
DriverCommands.dismiss_web_alert(self.__driver)
def get_text_from_web_alert(self):
return DriverCommands.get_text_from_web_alert(self.__driver)
def send_text_to_web_alert(self, text):
DriverCommands.send_text_to_web_alert(self.__driver, text)
def focus_on_frame(self, element_dispatcher):
DriverCommands.focus_on_frame(self.__driver, element_dispatcher.driver_element)
def get_element_for_setu_id(self, id):
return self.__driver_elements[id]
def focus_on_parent_frame(self):
DriverCommands.focus_on_parent_frame(self.__driver)
def focus_on_dom_root(self):
DriverCommands.focus_on_dom_root(self.__driver)
def perform_action_chain(self, action_chain):
DriverCommands.perform_action_chain(self, self.__driver, action_chain)
def hover_on_element(self, element_dispatcher):
DriverCommands.hover_on_element(self.__driver, element_dispatcher.driver_element)
def mouse_click_on_element(self, element_dispatcher):
DriverCommands.mouse_click_on_element(self.__driver, element_dispatcher.driver_element)
def double_click_on_element(self, element_dispatcher):
DriverCommands.double_click_on_element(self.__driver, element_dispatcher.driver_element)
def scroll_to_element(self, element_dispatcher):
DriverCommands.scroll_to_element(self.__driver, element_dispatcher.driver_element)
browser.quit()
continue
# random body temperature
input_fields = browser.find_elements_by_tag_name('input')
for i in input_fields:
if i.get_attribute("name").find("DZ_JSDTCJTW") >= 0:
# scroll down until body temperature textfield is visible
browser.execute_script("arguments[0].scrollIntoView();", i)
i.click()
i.send_keys(str(random.randint(362, 370) / 10.0))
break
time.sleep(10)
# save
save_btn = browser.find_element_by_css_selector(
"div#save.bh-btn.bh-btn-primary")
time.sleep(5)
save_btn.click()
time.sleep(5)
# confirm
confirm_btn = browser.find_element_by_css_selector(
"a.bh-dialog-btn.bh-bg-primary.bh-color-primary-5")
confirm_btn.click()
time.sleep(5)
browser.quit()
print("Successfully fill in!")
driver_service.stop()
return True
username = ['201xxx', '201xxx']
password = ['xxx', 'xxx']
province = ['河南省', '河南省']
city = ['郑州市', '郑州市']
receiver = ['@qq.com', '@163.com']
num = len(username)
res = []
for i in range(num):
res.append(dk(username[i], password[i], province[i], city[i]))
driver.quit()
service.stop()
os.system('taskkill /im chromedriver.exe /F')
os.system('taskkill /im chrome.exe /F')
#sender_username为发件人的账号
sender_username = '******'
#pwd为邮箱的授权码
pwd = 'xxx'
#邮件的正文内容
fenxiang_img = get_jsciba()
djt = get_djt()
mail_content = f'''
<p>{today_md}打卡完成</p>
<img src="{fenxiang_img}">
<p>{djt}</p>
class Chrome(WebDriver):
"""
Controls the ChromeDriver and allows you to drive the browser.
You will need to download the ChromeDriver executable from
http://chromedriver.storage.googleapis.com/index.html
"""
def __init__(self,
executable_path="chromedriver",
port=0,
options=None,
service_args=None,
desired_capabilities=None,
service_log_path=None,
chrome_options=None,
keep_alive=True):
"""
Creates a new instance of the chrome driver.
Starts the service and then creates new instance of chrome driver.
:Args:
- executable_path - path to the executable. If the default is used it assumes the executable is in the $PATH
- port - port you would like the service to run, if left as 0, a free port will be found.
- options - this takes an instance of ChromeOptions
- service_args - List of args to pass to the driver service
- desired_capabilities - Dictionary object with non-browser specific
capabilities only, such as "proxy" or "loggingPref".
- service_log_path - Where to log information from the driver.
- chrome_options - Deprecated argument for options
- keep_alive - Whether to configure ChromeRemoteConnection to use HTTP keep-alive.
"""
if chrome_options:
warnings.warn('use options instead of chrome_options',
DeprecationWarning,
stacklevel=2)
options = chrome_options
if options is None:
# desired_capabilities stays as passed in
if desired_capabilities is None:
desired_capabilities = self.create_options().to_capabilities()
else:
if desired_capabilities is None:
desired_capabilities = options.to_capabilities()
else:
desired_capabilities.update(options.to_capabilities())
self.service = Service(executable_path,
port=port,
service_args=service_args,
log_path=service_log_path)
self.service.start()
try:
WebDriver.__init__(self,
command_executor=ChromeRemoteConnection(
remote_server_addr=self.service.service_url,
keep_alive=keep_alive),
desired_capabilities=desired_capabilities)
except Exception:
self.quit()
raise
self._is_remote = False
def launch_app(self, id):
"""Launches Chrome app specified by id."""
return self.execute("launchApp", {'id': id})
def get_network_conditions(self):
"""
Gets Chrome network emulation settings.
:Returns:
A dict. For example:
{'latency': 4, 'download_throughput': 2, 'upload_throughput': 2,
'offline': False}
"""
return self.execute("getNetworkConditions")['value']
def set_network_conditions(self, **network_conditions):
"""
Sets Chrome network emulation settings.
:Args:
- network_conditions: A dict with conditions specification.
:Usage:
driver.set_network_conditions(
offline=False,
latency=5, # additional latency (ms)
download_throughput=500 * 1024, # maximal throughput
upload_throughput=500 * 1024) # maximal throughput
Note: 'throughput' can be used to set both (for download and upload).
"""
self.execute("setNetworkConditions",
{'network_conditions': network_conditions})
def execute_cdp_cmd(self, cmd, cmd_args):
"""
Execute Chrome Devtools Protocol command and get returned result
The command and command args should follow chrome devtools protocol domains/commands, refer to link
https://chromedevtools.github.io/devtools-protocol/
:Args:
- cmd: A str, command name
- cmd_args: A dict, command args. empty dict {} if there is no command args
:Usage:
driver.execute_cdp_cmd('Network.getResponseBody', {'requestId': requestId})
:Returns:
A dict, empty dict {} if there is no result to return.
For example to getResponseBody:
{'base64Encoded': False, 'body': 'response body string'}
"""
return self.execute("executeCdpCommand", {
'cmd': cmd,
'params': cmd_args
})['value']
def quit(self):
"""
Closes the browser and shuts down the ChromeDriver executable
that is started when starting the ChromeDriver
"""
try:
WebDriver.quit(self)
except Exception:
# We don't care about the message because something probably has gone wrong
pass
finally:
self.service.stop()
@staticmethod
def create_options():
return Options()
def register(country_code, email, password):
global cache
# Login
try:
c_service = Service("/usr/bin/chromedriver")
c_service.command_line_args()
c_service.start()
selenium_list = [x.strip() for x in open("node.txt", "r").readlines()]
entry = random.choice(selenium_list)
driver = webdriver.Remote(
command_executor='http://%s:4444/wd/hub' % entry,
desired_capabilities=chrome_options.to_capabilities())
print("Choose Node:", entry)
if email in cache:
session, schedule_id, group_id = cache[email]
new_session = change_region(country_code, session, group_id)
driver.get("https://ais.usvisa-info.com")
driver.add_cookie({
'name': '_yatri_session',
'value': new_session,
'path': '/',
'domain': 'ais.usvisa-info.com',
'secure': True
})
driver.get("https://ais.usvisa-info.com/%s/niv/groups/%s" %
(country_code, group_id))
else:
driver.get("https://ais.usvisa-info.com/%s/niv/users/sign_in" %
country_code)
email_box = driver.find_element_by_id("user_email")
email_box.clear()
email_box.send_keys(email)
password_box = driver.find_element_by_id("user_password")
password_box.clear()
password_box.send_keys(password)
driver.execute_script(
"document.getElementById('policy_confirmed').click()")
signin_button = driver.find_element_by_name("commit")
signin_button.click()
def wait_loading(xpath, option="locate"):
try:
if option == "locate":
element_present = EC.presence_of_element_located(
(By.XPATH, xpath))
elif option == "clickable":
element_present = EC.element_to_be_clickable(
(By.XPATH, xpath))
WebDriverWait(driver, wait_timeout).until(element_present)
except TimeoutException:
print("Timed out waiting for page to load")
driver.execute_script("window.scrollTo(0, 1080)")
driver.save_screenshot("test.png")
# Continue
continue_button_xpath = "//a[contains(text(), 'Continue')]"
wait_loading(continue_button_xpath)
current_url = driver.current_url
group_id = current_url.split("/")[-1]
continue_button = driver.find_element_by_xpath(continue_button_xpath)
continue_button.click()
# Choose action
pay_button_xpath = "//a[contains(text(), 'Pay Visa Fee')]"
wait_loading(pay_button_xpath)
banner = driver.find_element_by_tag_name('h5')
banner.click()
wait_loading(pay_button_xpath, option="clickable")
pay_button = driver.find_element_by_xpath(pay_button_xpath)
pay_button.click()
# Collect result
title_xpath = "//h2[contains(text(), 'MRV Fee Details')]"
wait_loading(title_xpath)
time_table = driver.find_element_by_class_name('for-layout')
result = []
if time_table:
trs = time_table.find_elements_by_tag_name('tr')
for tr in trs:
tds = tr.find_elements_by_tag_name('td')
if not len(tds) == 2:
continue
place = tds[0].text
date_str = tds[1].text
s = date_str.split()
year, month, day = 0, 0, 0
if len(s) >= 3 and s[0] != "No":
day_str, month_str, year_str = s[-3], s[-2].replace(
",", ""), s[-1]
year, month, day = int(year_str), g.MONTH[month_str], int(
day_str)
result.append([place, (year, month, day)])
current_url = driver.current_url
schedule_id = current_url.split("/")[-2]
session = driver.get_cookie("_yatri_session")["value"]
driver.quit()
c_service.stop()
if result:
cache[email] = [session, schedule_id, group_id]
else:
del cache[email]
return result, session, schedule_id
except Exception as e:
if email in cache:
del cache[email]
print(str(e))
if driver:
driver.quit()
if c_service:
c_service.stop()
return None, None, None
def donghangcrawler(city1, city2, date_in):
print("东方航空爬虫开始运行")
infolist = []
pricelist = []
resultlist = []
cell = {}
date_in = date_in[0:4] + '-' + date_in[4:6] + '-' + date_in[6:8]
c_service = Service('./webdriver/chromedriver.exe')
c_service.command_line_args()
browser = webdriver.Chrome(executable_path='./webdriver/chromedriver.exe')
c_service.start()
browser.get('http://www.ceair.com/')
ad = browser.find_element_by_id("appd_wrap_close")
citya = browser.find_element_by_id("label_ID_0") # 出发城市
cityb = browser.find_element_by_id("label_ID_1") # 到达城市
date = browser.find_element_by_id("depDt")
datex = browser.find_element_by_id("deptDtRt")
search = browser.find_element_by_id("btn_flight_search") # 查询按钮
time.sleep(0.5) # 必须等待页面加载结束后开始操作，否则会被当机器人
ad.click() # 关闭广告，会遮挡查询页面
time.sleep(0.5)
citya.clear() # 删除默认输入
time.sleep(0.5)
citya.send_keys(city1)
time.sleep(0.5)
citya.send_keys(Keys.TAB)
cityb.send_keys(city2)
time.sleep(0.5)
cityb.send_keys(Keys.TAB)
time.sleep(0.5)
date.send_keys(Keys.BACKSPACE, Keys.BACKSPACE, Keys.BACKSPACE,
Keys.BACKSPACE, Keys.BACKSPACE, Keys.BACKSPACE,
Keys.BACKSPACE, Keys.BACKSPACE, Keys.BACKSPACE,
Keys.BACKSPACE, date_in) # 清除默认值重新赋值，不能用clear
time.sleep(0.5)
date.send_keys(Keys.TAB) # 消除弹出菜单
time.sleep(0.5)
datex.send_keys(Keys.TAB) # 消除日历菜单
time.sleep(0.5)
search.click()
time.sleep(3)
try:
browser.switch_to.window(browser.window_handles[1]) # 定位到跳转后的查询结果页面
except BaseException:
time.sleep(3)
search.click()
time.sleep(3)
browser.switch_to.window(browser.window_handles[1]) # 定位到跳转后的查询结果页面
time.sleep(5)
info = browser.find_elements_by_xpath(
"//section[@class='summary']") # 信息模块组
price = browser.find_elements_by_xpath(
"//dd[@data-type='economy']") # 价格方块组
if info is None or price is None:
print("----东航--nodata----")
return resultlist
for i in info:
clean = str(i.text).strip().split() # 解析机票基本信息
# ['东方航空', '|', 'MU5104|直达|', '09:00', '首都国际机场', 'T2', '直达', '11:15', '虹桥国际机场', 'T2', '02小时15分钟']
clean.remove('|')
clean[1] = clean[1].split('|')[0] # 提取航班号
infolist.append(clean)
for j in price:
clean = str(j.text)
if clean:
clean = clean.split()[1]
else:
clean = '售完'
pricelist.append(clean)
for info_, price_ in zip(infolist, pricelist):
cell['Airline'] = info_[0]
cell['FlightNumber'] = info_[1]
cell['dTime'] = info_[2]
cell['dAirport'] = info_[3]
cell['aTime'] = info_[6]
cell['aAirport'] = info_[7]
cell['LowestPrice'] = price_
resultlist.append(cell.copy())
browser.quit()
c_service.stop()
# with open('./data/donghang.csv', 'w', encoding='utf-8') as csvfile: # 运行整个项目时解除此注释
# writer = csv.writer(csvfile, delimiter=',')
# for i in resultlist:
# writer.writerow([city1, city2, i.get("Airline"), i.get('FlightNumber'), i.get('dAirport'),
# i.get('aAirport'), i.get('dTime'), i.get('aTime'), i.get('LowestPrice'), '东方航空'])
# csvfile.close()
print("东方航空爬虫运行结束")
return resultlist
