def create_task_order_log(data):
url = 'http://third.gets.com/api/index.php?sec=20171212getscn&act=aliexpressCreateTaskOrderLog'
resp = requests.post(url, data)
if resp.json()['status'] == 0:
logger.info('新增刷单操作日志成功!')
else:
logger.info('新增刷单操作日志失败!')
def update_brushing_status(data):
# 测试机
# url = 'http://testthird.gets.com:8383/api/index.php?sec=20171212getscn&act=aliexpressModifyTaskOrderStatus'
# 线上
url = 'http://third.gets.com/api/index.php?sec=20171212getscn&act=aliexpressModifyTaskOrderStatus'
resp = requests.post(url=url, data=data)
# print(resp.text)
if resp.json()['msg'] == 'ok':
logger.info('刷单状态更新成功！')
else:
logger.info('刷单状态更新失败！')
def parse_list_page(self, html):
parseHtml = etree.HTML(html)
good_detail_urls = parseHtml.xpath(
'//ul[@id="hs-below-list-items"]/li/div[1]/div[1]/div/a/@href')
#绑定当前页的所有商品详情链接
self.good_detail_urls = good_detail_urls
for detail_url in good_detail_urls:
if re.search(self.target_id, detail_url):
detail_url = "https:" + detail_url
self.target_good_detail_url = detail_url
logger.info('目标商品的详情链接是：%s' % self.target_good_detail_url)
self.good_detail_urls = good_detail_urls
# logger.info('目标商品所在列表页的所有商品的详情链接是：%s' % self.good_detail_urls)
return True
return False
def get_detail_page_to_add(self, url):
self.driver.get(url)
#弹窗处理
try:
WebDriverWait(self.driver, 20).until(
EC.element_to_be_clickable((By.CLASS_NAME, 'close-layer')))
self.driver.find_element_by_class_name('close-layer').send_keys(
Keys.ENTER)
except TimeoutException:
pass
try:
#有些商品是没有颜色可选的，需要做异常处理
WebDriverWait(driver=self.driver, timeout=10).until(
EC.element_to_be_clickable(
(By.XPATH, '//ul[@id="j-sku-list-1"]/li[1]/a')))
self.driver.find_element_by_xpath(
'//ul[@id="j-sku-list-1"]/li[1]/a').send_keys(Keys.ENTER)
except TimeoutException:
pass
time.sleep(random.randint(1, 4))
try:
#有些商品是没有规格可选的，需要做异常处理
WebDriverWait(driver=self.driver, timeout=10).until(
EC.element_to_be_clickable(
(By.XPATH, '//ul[@id="j-sku-list-2"]/li[1]/a')))
self.driver.find_element_by_xpath(
'//ul[@id="j-sku-list-2"]/li[1]/a').click()
except TimeoutException:
pass
time.sleep(random.randint(1, 4))
self.driver.find_element_by_id('j-add-cart-btn').send_keys(Keys.ENTER)
if self.target_id in url:
logger.info('目标商品已成功添加到购物车！')
else:
logger.info('非目标商品已成功添加到购物车！')
#关闭添加购物车后的提示窗口
try:
WebDriverWait(driver=self.driver, timeout=10).until(
EC.element_to_be_clickable(
(By.XPATH, '//a[@class="ui-window-close"]')))
self.driver.find_element_by_xpath(
'//a[@class="ui-window-close"]').click()
except TimeoutException:
pass
def delete_other_goods_from_cart(self):
WebDriverWait(driver=self.driver, timeout=20).until(
EC.element_to_be_clickable(
(By.XPATH, '//div[@class="nav-cart nav-cart-box"]/a[1]')))
self.driver.find_element_by_xpath(
'//div[@class="nav-cart nav-cart-box"]/a[1]').send_keys(Keys.ENTER)
items = self.driver.find_elements_by_class_name("item-group-wrapper")
try:
for item in items:
good_detail_url = item.find_element_by_xpath(
'.//a[@target="_blank"]').get_attribute('href')
if not re.search(self.target_id, good_detail_url):
#非目标商品，直接从购物车删除
item.find_element_by_xpath(
'.//div[@class="product-remove"]/form[1]/a').click()
logger.info('非目标商品已从购物车中删除！')
time.sleep(2)
#点击删除后，网页会刷新，元素已发生改变，需捕获异常并处理
except StaleElementReferenceException:
self.delete_other_goods_from_cart()
def fill_in_and_save_payment_information(self):
logger.info('正在进入支付信息的填写流程...')
WebDriverWait(driver=self.driver, timeout=60).until(
EC.element_to_be_clickable((By.XPATH, '//input[@name="cardNum"]')))
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('cardNum').send_keys(
self.task_infos[str(self.task_id)]["payment"]["CreditCardNumber"])
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('dateM').send_keys(
self.task_infos[str(self.task_id)]["payment"]["ccMonth"])
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('dateY').send_keys(
self.task_infos[str(self.task_id)]["payment"]["ccYear"])
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('cvv2').send_keys(self.task_infos[str(
self.task_id)]["payment"]["cvv"])
# 切割全名并判断长度
FullName_text = self.task_infos[str(
self.task_id)]["address"]["FullName"].split()
if len(FullName_text) == 1:
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('cardHolderF').send_keys(
FullName_text[0])
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('cardHolderL').send_keys(
FullName_text[0])
else:
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('cardHolderF').send_keys(
FullName_text[0])
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('cardHolderL').send_keys(
FullName_text[1])
# time.sleep(random.uniform(0.5, 1.0))
# self.driver.find_element_by_name('saveinfo').click()
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_xpath(
'//div[@class="payment-line"]/button[1]').click()
logger.info('完成支付信息的填写!')
def main():
#单进程模式：循环获取待刷单任务，一次获取一个；若获取不到任务，程序退出。
while True:
#测试机地址，获取刷单任务，返回字典格式的json串
# url = 'http://testthird.gets.com:8383/api/index.php?sec=20171212getscn&act=aliexpressGetTaskOrdersList2&get_type=1&limit=1&debug_list=0&debug_allot=0'
#线上地址，获取刷单任务，返回字典格式的json串
url = 'http://third.gets.com/api/index.php?sec=20171212getscn&act=aliexpressGetTaskOrdersList2&get_type=1&limit=1'
resp = requests.get(url)
# if json.loads(resp.text,strict=False) == []:
try:
# if 'status' in resp.json():
if resp.json() == []:
logger.info('未获取到待刷单列表的数据，程序结束！')
sys.exit(0)
else:
logger.info('成功获取到一条待刷单的数据！')
task_infos = resp.json()
# print(task_infos)
for key in task_infos.keys():
task_id = int(key)
spider = AliexpressOrderSpider(task_infos, task_id)
spider.run()
except json.decoder.JSONDecodeError:
pass
def run(self):
try:
self.driver.get('http://www.aliexpress.com/')
#过滤弹窗
try:
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.CLASS_NAME, 'close-layer'))
)
self.driver.find_element_by_class_name('close-layer').click()
except TimeoutException:
pass
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.XPATH, '//span[@class="register-btn"]/a'))
)
#点击登录
self.driver.find_element_by_xpath('//span[@class="register-btn"]/a').click()
# WebDriverWait(self.driver, 40).until(
# EC.frame_to_be_available_and_switch_to_it
# )
time.sleep(10)
#切换到子iframe
self.driver.switch_to.frame('alibaba-login-box')
#输入登录信息
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.XPATH, '//input[@id="fm-login-id"]'))
)
self.driver.find_element_by_id('fm-login-id').send_keys(self.task_infos[str(self.task_id)]["account"]["login_aliexpress_email"])
time.sleep(random.randint(1, 5))
self.driver.find_element_by_id('fm-login-password').send_keys(self.task_infos[str(self.task_id)]["account"]["login_aliexpress_password"])
time.sleep(random.randint(1, 5))
self.driver.find_element_by_id('fm-login-submit').submit()
#此处判断登录过程中是否有滑块验证码，有则终止程序
if 'display: block' in self.driver.find_element_by_id('fm-login-checkcode-title').get_attribute('style'):
logger.info('登录时发现滑块验证码，程序退出！')
self.driver.quit()
sys.exit(0)
#弹窗处理
try:
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.CLASS_NAME, 'close-layer'))
)
self.driver.find_element_by_class_name('close-layer').click()
except TimeoutException:
pass
if self.driver.current_url == 'https://www.aliexpress.com/':
#插入账号登录日志
login_log_data = {
'data':{
"account_id":self.task_infos[str(self.task_id)]["account"]["account_id"],
"header":self.task_infos[str(self.task_id)]['account']['header'],
"cookies": json.dumps(self.driver.get_cookies()),
"login_status": "1",
"note": "登录成功"
}
}
self.insert_account_login_log(json.dumps(login_log_data))
#当账户成功登录时, 把登录的header和cookie修改对应账户表的字段
login_success_info_data = {
'data':{
"account_id": self.task_infos[str(self.task_id)]["account"]["account_id"],
"header": self.task_infos[str(self.task_id)]['account']['header'],
"cookies": json.dumps(self.driver.get_cookies())
}
}
self.update_account_login_success_info(json.dumps(login_success_info_data))
elif 'passport.aliexpress.com' in self.driver.current_url:
logger.info('登录后发现验证码，账户已被封！')
#账户被封，也更新刷单状态
brushing_data = {
str(self.task_id): {
"task_id": self.task_id,
"status": 10,
# "order_no": '',
# "payment_date": '',
# "actual_order_amount": 0.00
}
}
self.update_brushing_status(json.dumps(brushing_data))
self.driver.quit()
logger.info('程序退出！')
sys.exit(0)
# 先检查cofirm_pay_file文件夹下，是否存在一个taskid_xx.txt文件，xx为本次任务id。
# 若存在，则进入个人订单中心，获取订单号和定价总价等信息，更新刷单状态。并删除该文件。
# 若不存在，则正常走流程。
confirm_receive_dir = os.path.join(os.path.dirname(__file__), 'confirm_receive_files')
confirm_receive_filename = confirm_receive_dir + '/' + 'taskid_' + str(self.task_id) + '.txt'
if os.path.exists(confirm_receive_filename):
logger.info('发现任务id: %d之前已确认收货，准备进入个人订单中心，确认是否留评状态，并进行相应的处理...' % self.task_id)
## 点击首页中的"My Orders"，进入个人订单页面
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.XPATH, '//div[@id="user-benefits"]//ul/li[2]/a'))
)
self.driver.find_element_by_xpath('//div[@id="user-benefits"]//ul/li[2]/a').click()
# 搜索按钮可点击
# WebDriverWait(self.driver, 40).until(
# EC.element_to_be_clickable((By.ID, 'id="search-btn"'))
# )
time.sleep(5)
# 先找到所有的订单items，再根据订单号或者商品asin，定位到目标订单所在的item
items = self.driver.find_elements_by_xpath('//*[@id="buyer-ordertable"]/tbody')
for item in items:
if item.find_element_by_xpath('./tr[1]/td[2]/p[1]/span[2]').text == self.task_infos[str(self.task_id)]["import_aliexpress_order"]:
logger.info('找到目标订单所在的tbody!')
# 根据当前订单的状态做判断
if item.find_element_by_xpath('./tr[2]/td[4]/button[3]').text.strip() == 'Leave Feedback':
logger.info('当前账户已收货，但未成功留评，准备执行留评的流程...')
item.find_element_by_xpath('./tr[2]/td[4]/button[3]').click()
# 进入评论页面
WebDriverWait(self.driver, 60).until(
EC.element_to_be_clickable((By.XPATH, '//div[@name="eval_star_node"]/span[1]'))
# EC.element_to_be_clickable((By.XPATH, '//*[@id="star_%s"]/span[1]' % '99723247396644'))
)
logger.info('进入评论填写页面...')
logger.info('当前url:%s' % self.driver.current_url)
# 此处需要根据接口数据，来判断好评与差评，再调整星级的点按位置（修改Xpath,可使用占位符，设置星级数为一个实例属性，这样可以简化减少代码臃肿）
# 点星商品描述时，需要上传图片
if self.task_infos[str(self.task_id)]['review']['title'] == 'bad':
stars_num = 1
else:
stars_num = 5
self.driver.find_element_by_xpath(
'//div[@name="eval_star_node"]/span[%s]' % stars_num).click()
time.sleep(10)
# self.driver.find_element_by_xpath('//*[@id="image_uploader_99723247396644"]/div/button')
self.driver.find_element_by_xpath('//div[@class="feedback-main"]/textarea').send_keys(
self.task_infos[str(self.task_id)]['review']["content"])
time.sleep(random.randint(1, 5))
img_url = self.task_infos[str(self.task_id)]['review']["images"]
if img_url:
logger.info('发现图片链接，正在下载图片并将图片上传到评论页面中...')
# img_path = ' '#图片的绝对路径或者相对路径
img_path = self.get_img_path(img_url=img_url)
self.driver.find_element_by_xpath('//div[@class="ui-uploader"]/button[1]').send_keys(
img_path)
# 时间延迟，使图片上传完,此处的时间延迟应该怎么做？多久合适？
time.sleep(30)
else:
logger.info('未发现图片链接，将不上传图片到评论页面！')
time.sleep(random.randint(1, 3))
# 服务态度
self.driver.find_element_by_xpath(
'//*[@id="j-leave-feedback-container"]/div/div[4]/div[2]/div/div[1]/span[%s]' % stars_num).click()
# 物流速度
time.sleep(random.randint(1, 3))
self.driver.find_element_by_xpath(
'//*[@id="j-leave-feedback-container"]/div/div[4]/div[3]/div/div[1]/span[%s]' % stars_num).click()
# 勾选，设置为匿名评论
time.sleep(random.randint(1, 3))
self.driver.find_element_by_id('j-anonymous-feedback').click()
# 点击按钮留下反馈
time.sleep(random.randint(1, 3))
self.driver.find_element_by_id('buyerLeavefb-submit-btn').click()
# 留评后的url
# 'https://feedback.aliexpress.com/management/leaveFeedback.htm?parentOrderId=99723247396644'
time.sleep(20)
# 评论完成时，url中没有'isOrderCompleted=Y'
# if not 'isOrderCompleted=Y' in self.driver.current_url:
if 'Your feedback has been submitted' in self.driver.page_source:
logger.info('留评成功！')
# 更新刷单状态
review_data = {
str(self.task_id): {
"task_id": self.task_id,
"status": 6,
}
}
self.update_brushing_status(json.dumps(review_data))
# 新增刷单操作日志
log_data = {
"task_id": self.task_id,
"info": "留评成功！",
'ip': self.get_ip_info(proxies={'https': self.proxy})
}
self.create_task_order_log(json.dumps(log_data))
os.remove(confirm_receive_filename)
logger.info('删除了一个文件:%s' % confirm_receive_filename)
else:
logger.info('留评失败！')
review_data = {
str(self.task_id): {
"task_id": self.task_id,
"status": 61,
}
}
# 更新刷单状态
self.update_brushing_status(json.dumps(review_data))
# 新增刷单操作日志
log_data = {
"task_id": self.task_id,
"info": "留评失败！",
'ip': self.get_ip_info(proxies={'https': self.proxy})
}
self.create_task_order_log(json.dumps(log_data))
os.remove(confirm_receive_filename)
logger.info('删除了一个文件:%s' % confirm_receive_filename)
break
else:
self.review()
logger.info('当前账户操作完毕，关闭当前浏览器！')
self.driver.quit()
except NoSuchFrameException:
logger.info('切换到登录的frame超时，正在重新请求主页，继续执行登录操作')
self.run()
except (TimeoutException, WebDriverException):
logger.info('等待超时,或者元素位未完全加载导致定位出错!')
logger.info('关闭当前浏览器，结束当前线程！')
logger.info('系统会自动生成新的线程来执行下单任务！')
self.driver.quit()
sys.exit(0)
def update_account_login_success_info(data):
url = 'http://third.gets.com/api/index.php?sec=20171212getscn&act=aliexpressUpdateAccountLoginSuccessInfo'
requests.post(url, data)
logger.info('对应账户的header和cookies字段已成功修改!')
def insert_account_login_log(data):
url = 'http://third.gets.com/api/index.php?sec=20171212getscn&act=aliexpressInsertAccountLoginLog'
requests.post(url, data)
logger.info('账户登录日志已成功插入！')
def review(self):
# 点击首页中的"My Orders"，进入个人订单页面
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.XPATH, '//div[@id="user-benefits"]//ul/li[2]/a'))
)
self.driver.find_element_by_xpath('//div[@id="user-benefits"]//ul/li[2]/a').click()
#点击确认收货
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.XPATH, '//table[@id="buyer-ordertable"]/tbody/tr[2]/td[4]/button[2]'))
)
#此处先进行判断，如果卖家发货，则可以走留评的流程，否则，程序退出。
if self.driver.find_element_by_xpath('//table[@id="buyer-ordertable"]/tbody/tr[2]/td[4]/button[2]').text.strip() == 'Confirm Goods Received':
logger.info('卖家已发货，正在执行留评的流程...')
self.driver.find_element_by_xpath('//table[@id="buyer-ordertable"]/tbody/tr[2]/td[4]/button[2]').click()
# 进入订单明细页面，勾选目标商品所在的订单，再次点击确认收货
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="button-confirmOrderReceived"]'))
)
trs = self.driver.find_elements_by_xpath('//*[@id="confirm-receiving"]/tbody/tr')
for tr in trs:
good_detail_url = tr.find_element_by_xpath('./td[4]/div[1]/a').get_attribute('href')
if re.search(self.target_id, good_detail_url):
tr.find_element_by_xpath('./td[2]/input').click()
time.sleep(random.randint(1, 3))
self.driver.find_element_by_xpath('//*[@id="button-confirmOrderReceived"]').click()
# 点击弹出的“comfirm”按钮
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.ID, 'confirm_cpf'))
)
self.driver.find_element_by_id('confirm_cpf').click()
logger.info('点击了最终确认收货的按钮！')
# 在项目的根目录下，新建一个文件夹confirm_receive_files,并在该文件夹下生成一个文件，文件名命名为'taskid_xx.txt'文件，‘xx’代表任务id
confirm_receive_dir = os.path.join(os.path.dirname(__file__), 'confirm_receive_files')
if not os.path.exists(confirm_receive_dir):
os.mkdir(confirm_receive_dir)
confirm_receive_filename = confirm_receive_dir + '/' + 'taskid_' + str(self.task_id) + '.txt'
f = open(confirm_receive_filename, 'w', encoding='utf-8')
f.close()
logger.info('同时创建了一个文件：%s' % confirm_receive_filename)
#进入评论页面
WebDriverWait(self.driver, 60).until(
EC.element_to_be_clickable((By.XPATH, '//div[@name="eval_star_node"]/span[1]'))
# EC.element_to_be_clickable((By.XPATH, '//*[@id="star_%s"]/span[1]' % '99723247396644'))
)
logger.info('进入评论填写页面...')
logger.info('当前url:%s' % self.driver.current_url)
#此处需要根据接口数据，来判断好评与差评，再调整星级的点按位置（修改Xpath,可使用占位符，设置星级数为一个实例属性，这样可以简化减少代码臃肿）
#点星商品描述时，需要上传图片
if self.task_infos[str(self.task_id)]['review']['title'] == 'bad':
stars_num = 1
else:
stars_num = 5
self.driver.find_element_by_xpath('//div[@name="eval_star_node"]/span[%s]' % stars_num).click()
time.sleep(10)
# self.driver.find_element_by_xpath('//*[@id="image_uploader_99723247396644"]/div/button')
self.driver.find_element_by_xpath('//div[@class="feedback-main"]/textarea').send_keys(self.task_infos[str(self.task_id)]['review']["content"])
time.sleep(random.randint(1, 5))
img_url = self.task_infos[str(self.task_id)]['review']["images"]
if img_url:
logger.info('发现图片链接，正在下载图片并将图片上传到评论页面中...')
# img_path = ' '#图片的绝对路径或者相对路径
img_path = self.get_img_path(img_url=img_url)
self.driver.find_element_by_xpath('//div[@class="ui-uploader"]/button[1]').send_keys(img_path)
#时间延迟，使图片上传完,此处的时间延迟应该怎么做？多久合适？
time.sleep(30)
else:
logger.info('未发现图片链接，将不上传图片到评论页面！')
time.sleep(random.randint(1, 3))
#服务态度
self.driver.find_element_by_xpath('//*[@id="j-leave-feedback-container"]/div/div[4]/div[2]/div/div[1]/span[%s]' % stars_num).click()
#物流速度
time.sleep(random.randint(1, 3))
self.driver.find_element_by_xpath('//*[@id="j-leave-feedback-container"]/div/div[4]/div[3]/div/div[1]/span[%s]' % stars_num).click()
#勾选，设置为匿名评论
time.sleep(random.randint(1, 3))
self.driver.find_element_by_id('j-anonymous-feedback').click()
#点击按钮留下反馈
time.sleep(random.randint(1, 3))
self.driver.find_element_by_id('buyerLeavefb-submit-btn').click()
#留评后的url
# 'https://feedback.aliexpress.com/management/leaveFeedback.htm?parentOrderId=99723247396644'
time.sleep(20)
#评论完成时，url中没有'isOrderCompleted=Y'
# if not 'isOrderCompleted=Y' in self.driver.current_url:
if 'Your feedback has been submitted' in self.driver.page_source:
logger.info('留评成功！')
# 更新刷单状态
review_data = {
str(self.task_id): {
"task_id": self.task_id,
"status": 6,
}
}
self.update_brushing_status(json.dumps(review_data))
# 新增刷单操作日志
log_data = {
"task_id": self.task_id,
"info": "留评成功！",
'ip': self.get_ip_info(proxies={'https': self.proxy})
}
self.create_task_order_log(json.dumps(log_data))
os.remove(confirm_receive_filename)
logger.info('删除了一个文件:%s' % confirm_receive_filename)
else:
logger.info('留评失败！')
review_data = {
str(self.task_id): {
"task_id": self.task_id,
"status": 61,
}
}
#更新刷单状态
self.update_brushing_status(json.dumps(review_data))
# 新增刷单操作日志
log_data = {
"task_id": self.task_id,
"info": "留评失败！",
'ip': self.get_ip_info(proxies={'https': self.proxy})
}
self.create_task_order_log(json.dumps(log_data))
os.remove(confirm_receive_filename)
logger.info('删除了一个文件:%s' % confirm_receive_filename)
else:
logger.info('卖家尚未发货，暂时不能留评，程序退出！')
self.driver.quit()
sys.exit(0)
def main(task_infos, task_id):
spider = AliexpressReviewSpider(task_infos, task_id)
spider.run()
if __name__ == '__main__':
# 多线程循环模式：默认一次最多获取5个待评论任务,自动根据获取到的任务数量创建相应数量的线程数，去执行各自分配到的刷单任务；当获取不到任务时，程序退出。
#修改limit参数即可设置获取的任务数量，现在是1
while True:
url = 'http://third.gets.com/api/index.php?sec=20171212getscn&act=aliexpressGetTaskOrdersList2&get_type=3&limit=2'
resp = requests.get(url)
try:
if resp.json() == []:
# logger.info('未获取到待评论列表的数据，程序结束！')
# sys.exit(0)
logger.info('当前未获取到待评论的数据，程序将启动休眠模式，60分钟后自动唤醒...')
time.sleep(60 * 60)
else:
task_infos = resp.json()
task_id_str_list = []
for task_id_str in task_infos:
task_id_str_list.append(task_id_str)
logger.info('成功获取到%d条待评论的数据！' % len(task_id_str_list))
logger.info('将创建%d个线程来分别执行评论任务!' % len(task_id_str_list))
threads = []
for i in range(len(task_id_str_list)):
task_id = int(task_id_str_list[i])
t = threading.Thread(target=main, args=(task_infos, task_id))
threads.append(t)
t.start()
time.sleep(30)
def run(self):
try:
self.driver.get('http://www.aliexpress.com/')
#过滤弹窗
try:
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.CLASS_NAME, 'close-layer')))
self.driver.find_element_by_class_name('close-layer').click()
except TimeoutException:
pass
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable(
(By.XPATH, '//span[@class="register-btn"]/a')))
#点击登录
self.driver.find_element_by_xpath(
'//span[@class="register-btn"]/a').click()
# WebDriverWait(self.driver, 40).until(
# EC.frame_to_be_available_and_switch_to_it
# )
time.sleep(10)
#切换到子iframe
self.driver.switch_to.frame('alibaba-login-box')
#输入登录信息
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable(
(By.XPATH, '//input[@id="fm-login-id"]')))
# time.sleep(random.randint(1,3))
self.driver.find_element_by_id('fm-login-id').send_keys(
self.task_infos[str(
self.task_id)]["account"]["login_aliexpress_email"])
time.sleep(random.randint(1, 5))
self.driver.find_element_by_id('fm-login-password').send_keys(
self.task_infos[str(
self.task_id)]["account"]["login_aliexpress_password"])
time.sleep(random.randint(1, 5))
self.driver.find_element_by_id('fm-login-submit').click()
#此处判断登录过程中是否有滑块验证码，有则终止程序
if 'display: block' in self.driver.find_element_by_id(
'fm-login-checkcode-title').get_attribute('style'):
logger.info('登录时发现滑块验证码，程序退出！')
self.driver.quit()
sys.exit(0)
#弹窗处理
try:
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.CLASS_NAME, 'close-layer')))
self.driver.find_element_by_class_name('close-layer').click()
except TimeoutException:
pass
if self.driver.current_url == 'https://www.aliexpress.com/':
#插入账号登录日志
login_log_data = {
'data': {
"account_id":
self.task_infos[str(
self.task_id)]["account"]["account_id"],
"header":
self.task_infos[str(
self.task_id)]['account']['header'],
"cookies":
json.dumps(self.driver.get_cookies()),
"login_status":
"1",
"note":
"登录成功"
}
}
self.insert_account_login_log(json.dumps(login_log_data))
#当账户成功登录时, 把登录的header和cookie修改对应账户表的字段
login_success_info_data = {
'data': {
"account_id":
self.task_infos[str(
self.task_id)]["account"]["account_id"],
"header":
self.task_infos[str(
self.task_id)]['account']['header'],
"cookies":
json.dumps(self.driver.get_cookies())
}
}
self.update_account_login_success_info(
json.dumps(login_success_info_data))
elif 'passport.aliexpress.com' in self.driver.current_url:
logger.info('登录后发现验证码，账户已被封！')
#账户被封，也更新刷单状态
brushing_data = {
str(self.task_id): {
"task_id": self.task_id,
"status": 10,
# "order_no": '',
# "payment_date": '',
# "actual_order_amount": 0.00
}
}
self.update_brushing_status(json.dumps(brushing_data))
self.driver.quit()
logger.info('程序退出！')
sys.exit(0)
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable((By.ID, "search-key")))
self.driver.find_element_by_id('search-key').send_keys(
self.task_infos[str(self.task_id)]["asin"]["keywords"])
time.sleep(random.uniform(0.5, 1.5))
self.driver.find_element_by_class_name('search-button').send_keys(
Keys.ENTER)
for i in range(1, 3):
#弹窗处理
try:
WebDriverWait(self.driver, 20).until(
EC.element_to_be_clickable(
(By.CLASS_NAME, 'close-layer')))
self.driver.find_element_by_class_name(
'close-layer').click()
except TimeoutException:
pass
WebDriverWait(driver=self.driver, timeout=30).until(
EC.element_to_be_clickable((
By.XPATH,
'//span[@class="ui-pagination-active"]/following-sibling::a[1]'
)))
source = self.driver.page_source
result = self.parse_list_page(source)
if result:
self.get_detail_page_to_add(self.target_good_detail_url)
break
else:
next_page_btn = self.driver.find_element_by_xpath(
'//span[@class="ui-pagination-active"]/following-sibling::a[1]'
)
next_page_btn.click()
logger.info('第%d列表搜索页没找到目标商品，正在跳转到第%d列表搜索页...' %
(i, i + 1))
time.sleep(3)
else:
logger.info('前2页中没有找到目标商品，正在拼接目标商品的详情url,进行特殊处理...')
self.target_good_detail_url = 'https://www.aliexpress.com/item/-a/' + self.target_id + '.html'
self.get_detail_page_to_add(self.target_good_detail_url)
self.add_other_goods()
self.delete_other_goods_from_cart()
brushing_data = self.place_order()
# 更新刷单状态. place_order（）成功下单时返回json数据，否则返回None.
if brushing_data:
self.update_brushing_status(brushing_data)
# 新增刷单操作日志
data = {
"task_id": self.task_id,
"info": "下单成功！",
'ip': self.get_ip_info(proxies={'https': self.proxy})
}
self.create_task_order_log(json.dumps(data))
self.driver.quit()
logger.info('当前账户操作完毕，关闭当前浏览器！')
except NoSuchFrameException:
logger.info('切换到登录的frame超时，正在重新请求主页，继续执行登录操作')
self.run()
# except NoSuchElementException:
# logger.info('定位不到对应的元素，将重新访问首页，继续走流程！')
# self.run()
# except WebDriverException:
# logger.info('点击下一页连接时出错，将重新访问首页，继续走流程！')
# self.run()
except (TimeoutException, WebDriverException) as e:
# 在操作过程中等待超时，先退出当前登录状态，再重新执行run方法回调，重新走流程。也可直接结束程序，只适合在多线程的情况下操作。
logger.info('等待超时,或者元素位未完全加载导致点击出错，正在检查登录状态，若已登录，则退出登录状态,重新走流程！')
self.driver.execute_script(
'window.scrollTo(document.body.scrollWidth,0 );')
time.sleep(3)
try:
element = self.driver.find_element_by_xpath(
'//div[@id="nav-user-account"]/div[1]')
actions = ActionChains(self.driver)
actions.move_to_element(element)
actions.perform()
WebDriverWait(self.driver, 60).until(
EC.element_to_be_clickable(
(By.XPATH,
'//div[@id="nav-user-account"]/div[2]/div[1]/a')))
self.driver.find_element_by_xpath(
'//div[@id="nav-user-account"]/div[2]/div[1]/a').click()
time.sleep(4)
# 此处必须有关闭浏览器的操作，否则登录状态退出不彻底，不能正常run回调
self.driver.close()
except NoSuchElementException:
pass
#是否需要close?
self.run()
def place_order(self):
#页面刷新，可有可无
self.driver.refresh()
WebDriverWait(driver=self.driver, timeout=20).until(
EC.element_to_be_clickable(
(By.XPATH, '//div[@class="product-price-info3"]/a[1]')))
quantity = self.driver.find_element_by_xpath(
'//input[@readonly="readonly"]').get_attribute('value')
# 发现一个有意思的情况，同一款商品同规格同颜色，多次添加到购物车，进入购物车查看时，商品数量依然为1。
# 所以，商品数量的处理，可以简化。
if quantity == '1':
price_text = self.driver.find_element_by_xpath(
'//span[@class="total-price ui-cost notranslate"]/b').text
price = re.sub(r'US \$', '', price_text)
#此处购物车中的待支付金额是否超出单笔最大额度，若超出，则终止刷单。
logger.info('删除非目标商品后，购物车中查看到的待支付金额：%s' % price)
if float(price) > float(self.task_infos[str(
self.task_id)]["payment"]["single_max_trade"]):
logger.info('删除非目标商品后，购物车中查看到的待支付金额超出单笔最大额度，终止刷单!')
# 新增刷单操作日志
data = {
"task_id": self.task_id,
"info": "删除非目标商品后，购物车中查看到的待支付金额超出单笔最大额度，终止刷单!",
'ip': self.get_ip_info(proxies={'https': self.proxy})
}
self.create_task_order_log(json.dumps(data))
logger.info('程序结束！')
sys.exit(0)
self.driver.find_element_by_xpath(
'//div[@class="product-price-info3"]/a[1]').send_keys(
Keys.ENTER)
logger.info('走下单流程！准备进入个人信息和支付信息的填写流程...')
#跳转到个人信息填写页面,需要加以判断，是否已有地址信息
WebDriverWait(driver=self.driver, timeout=30).until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="page"]/div[1]/div[1]/ol/li[1]')))
try:
default_address_info_element = self.driver.find_element_by_xpath(
'//*[@id="address-main"]/div[2]/ul/li/div/div[1]')
if 'selected' in default_address_info_element.get_attribute(
'class'):
logger.info('已有默认收货地址！')
self.driver.execute_script(
'window.scrollTo(0,document.body.scrollHeight)')
time.sleep(3)
try:
# if self.driver.find_element_by_xpath('//*[@id="j-payment-method"]/div[4]/ul/li[1]/span/span'):
if self.driver.find_element_by_xpath(
'//ul[@class="pay-method-list"]/li[1]/span/span'
):
logger.info('已有默认支付信息!')
except NoSuchElementException:
# 找不到对应的元素，即没有默认支付信息，则继续走支付信息的填写流程
self.fill_in_and_save_payment_information()
except NoSuchElementException as e:
logger.info('没有默认收货地址，正在新建收货地址...')
WebDriverWait(driver=self.driver, timeout=30).until(
EC.element_to_be_clickable(
(By.XPATH, '//div[@class="sa-btn-group"]/a')))
self.driver.find_element_by_name('contactPerson').send_keys(
self.task_infos[str(self.task_id)]["address"]["FullName"])
time.sleep(random.uniform(0.5, 1.0))
country_selectBtn = Select(
self.driver.find_element_by_name('country'))
country_selectBtn.select_by_visible_text('United States')
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('address').send_keys(
self.task_infos[str(
self.task_id)]["address"]["AddressLine1"])
if self.task_infos[str(
self.task_id)]["address"]["AddressLine2"]:
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('address2').send_keys(
self.task_infos[str(
self.task_id)]["address"]["AddressLine2"])
state_selectBtn = Select(
self.driver.find_element_by_xpath(
'//input[@name="province"]/following-sibling::select[1]'
))
try:
time.sleep(random.uniform(0.5, 1.0))
state_selectBtn.select_by_visible_text(self.task_infos[str(
self.task_id)]["address"]["StateOrRegion"])
except Exception:
logger.info('从接口获取的StateOrRegion信息对应不上，默认为下拉列表的第一个州或地区！')
StateOrRegion = self.driver.find_element_by_xpath(
'//input[@name="province"]/following-sibling::select[1]/option[2]'
).text
print(StateOrRegion)
time.sleep(random.uniform(0.5, 1.0))
state_selectBtn.select_by_visible_text(StateOrRegion)
# 此处需要时间延迟，来加载城市的下拉列表
time.sleep(12)
city_selectBtn = Select(
self.driver.find_element_by_xpath(
'//input[@name="city"]/following-sibling::select[1]'))
#amazon的城市信息与速卖通的城市信息不一定匹配，比如大小写不一致，需要做异常处理
try:
time.sleep(random.uniform(0.5, 1.0))
city_selectBtn.select_by_visible_text(self.task_infos[str(
self.task_id)]["address"]["City"])
except Exception:
logger.info('从接口获取的城市信息对应不上，正在进行异常处理...')
try:
city_text = self.task_infos[str(
self.task_id)]["address"]["City"].split()
city_text[-1] = city_text[-1].lower()
city = " ".join(city_text)
print(city)
time.sleep(random.uniform(0.5, 1.0))
city_selectBtn.select_by_visible_text(city)
except Exception:
logger.info('大小写处理失败，默认为下拉列表的第一个城市!')
city = self.driver.find_element_by_xpath(
'//input[@name="city"]/following-sibling::select[1]/option[2]'
).text
# print(city)
time.sleep(random.uniform(0.5, 1.0))
city_selectBtn.select_by_visible_text(city)
# city_selectBtn.select_by_visible_text('Jersey city')
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('zip').send_keys(
self.task_infos[str(
self.task_id)]["address"]["PostalCode"])
#电话号码需要处理，若有"+1"前缀，则去掉"+1"前缀
PhoneNumber = self.task_infos[str(
self.task_id)]["address"]["PhoneNumber"]
if re.match(r'\+1', PhoneNumber):
PhoneNumber = re.sub(r'\+1', '', PhoneNumber)
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('mobileNo').send_keys(
PhoneNumber)
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_name('isDefault').click()
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_xpath(
'//div[@class="sa-btn-group"]/a[1]').click()
self.fill_in_and_save_payment_information()
WebDriverWait(driver=self.driver, timeout=30).until(
EC.element_to_be_clickable(
(By.XPATH,
'//div[@class="place-order-button"]/button[1]')))
#点击"Confirm & Pay"
time.sleep(random.uniform(0.5, 1.0))
self.driver.find_element_by_xpath(
'//div[@class="place-order-button"]/button[1]').click()
WebDriverWait(driver=self.driver, timeout=30).until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="header"]/div/div[2]/div[1]/a')))
time.sleep(15)
if 'payOnlineSuccess' in self.driver.current_url:
self.driver.save_screenshot('PaySuccess.png')
logger.info('下单成功！')
# logger.info("成功下单后的url:%s" % self.driver.current_url)
payment_date = datetime.datetime.now().strftime(
'%Y-%m-%d %H:%M:%S')
logger.info('下单时间：%s' % payment_date)
self.driver.back()
time.sleep(2)
self.driver.execute_script(
'window.scrollTo(document.body.scrollWidth,0 );')
WebDriverWait(driver=self.driver, timeout=30).until(
EC.presence_of_element_located(
(By.XPATH, '//div[@id="nav-user-account"]/div[1]')))
element = self.driver.find_element_by_xpath(
'//div[@id="nav-user-account"]/div[1]')
# print(element)
actions = ActionChains(self.driver)
actions.move_to_element(element)
actions.perform()
time.sleep(1)
WebDriverWait(self.driver, 40).until(
EC.element_to_be_clickable(
(By.XPATH,
'//ul[@class="flyout-quick-entry"]/li[2]/a')))
self.driver.find_element_by_xpath(
'//ul[@class="flyout-quick-entry"]/li[2]/a').click()
time.sleep(4)
order_no = self.driver.find_element_by_xpath(
'//*[@id="buyer-ordertable"]//tr[1]/td[2]/p[1]/span[2]'
).text
logger.info("订单号为：%s" % order_no)
price_text = self.driver.find_element_by_xpath(
'//*[@id="buyer-ordertable"]/tbody[1]/tr[1]/td[4]/div/p[2]'
).text.strip()
actual_order_amount = re.sub(r'\$ ', '', price_text)
logger.info('订单总价：%s' % actual_order_amount)
brushing_data = {
str(self.task_id): {
"task_id": self.task_id,
"status": 2,
"order_no": order_no,
"payment_date": payment_date,
"actual_order_amount": float(actual_order_amount)
}
}
# print(json.dumps(data))
return json.dumps(brushing_data)
else:
logger.info('支付失败！')
self.driver.save_screenshot('PayFailed.png')
logger.info('支付失败的url:%s' % self.driver.current_url)
#新增刷单操作日志
data = {
"task_id": self.task_id,
"info": "支付失败！导致下单失败！",
'ip': self.get_ip_info(proxies={'https': self.proxy})
}
self.create_task_order_log(json.dumps(data))
