def __open_browser(self):
self.browser = webdriver.Chrome(chrome_options=self.options)
self.browser.set_window_size(1800, 1000)
sleep_time(1)
self.browser.get('https://weibo.com/')
sleep_time(1)
log.info('打开浏览器，准备登陆')
def __clear_info(self):
sleep_time(1)
self.browser.find_element_by_xpath(
'.//div[@class="W_login_form"]/div[contains(@class,"username")]//input'
).clear()
self.browser.find_element_by_xpath(
'.//div[@class="W_login_form"]/div[contains(@class,"password")]//input'
).clear()
def __has_verify_code(self):
sleep_time(1)
html = etree.HTML(self.browser.page_source)
res = html.xpath('.//div[@node-type="verifycode_box"]/@style')[0]
if res == 'display: none;':
log.info('没有验证码')
return False
else:
log.info('有验证码')
return True
def __is_succeed(self):
sleep_time(2)
try:
self.browser.find_element_by_xpath(
'.//div[@class="gn_nav"]/ul/li[5]')
log.info('登录成功！')
return True
except:
log.info('登录失败')
return False
def is_into_recommend(self):
sleep_time(2)
try:
self.browser.find_element_by_xpath(
'/html/body/div/div[1]/div/div/div[2]/div[1]/a').click()
log.info('进入了推荐页')
return True
except:
log.info('没有进入推荐页')
return False
def follow(self, follow_page):
"""
直接打开被关注的人的主页进行关注
:param follow_page: 被关注人的主页链接
:return:
"""
sleep_time(2)
self.__open_page(follow_page)
if not self.__is_followed():
self.__click_follow()
def __inter_info(self, acc, pwd):
sleep_time(1)
log.info('输入用户名')
self.browser.find_element_by_xpath(
'.//div[@class="W_login_form"]/div[contains(@class,"username")]//input'
).send_keys(acc)
sleep_time(1)
log.info('输入密码')
self.browser.find_element_by_xpath(
'.//div[@class="W_login_form"]/div[contains(@class,"password")]//input'
).send_keys(pwd)
def __is_followed(self):
sleep_time(1)
html = etree.HTML(self.browser.page_source)
res = html.xpath(
'.//div[contains(@class,"opt_box")]/div[1]/a[1]/text()')[0]
if res == '关注':
log.info('未关注')
return False
elif res == '已关注':
log.info('已关注')
return True
def is_into_verify(self):
"""
判断是否进入了验证页面
:return:
"""
sleep_time(2)
try:
self.browser.find_element_by_xpath(
'.//div[contains(@class,"geetest_holder")]')
log.warning('为了解除帐号异常，请点击按钮进行验证')
return True
except:
log.info('账号正常，不需要验证身份')
return False
def is_follow_failed(self):
"""
判断是否出现'抱歉，关注失败(>_<) ，稍后再试啦。'的弹窗，这个弹窗说明还没有把本机养成常用设备。
:return:
"""
sleep_time(2)
try:
self.browser.find_element_by_xpath(
'.//div[contains(@class,"W_layer")]/div[contains(@class,"content")]/div[contains(@class,"W_layer_btn")]/a'
).click()
log.warning('抱歉，关注失败(>_<) ，稍后再试啦。')
return True
except:
log.info('没有出现关注失败')
return False
def is_account_abnormal(self):
"""
判断页面是否弹出了‘你的帐号存在异常，暂时无法发博、发评论、加关注等，请先验证身份解除异常。(100003)’
:return:
"""
sleep_time(2)
try:
self.browser.find_element_by_xpath(
'.//div[contains(@class,"W_layer")]//div[contains(@class,"W_layer_btn")]/a[1]'
)
log.warning('你的帐号存在异常，暂时无法发博、发评论、加关注等，请先验证身份解除异常。(100003)')
return True
except:
log.info('账号正常')
return False
def __to_login(self, acc, pwd):
for i in range(10):
self.__clear_info()
self.__inter_info(acc, pwd)
if self.__has_verify_code():
self.__deal_with_code()
self.__click_login()
if self.__is_succeed():
return True
elif self.__has_verify_code():
self.__deal_with_code()
self.__click_login()
if self.__is_succeed():
return True
if self.login_abnormal.is_into_inter_phone_num():
return False
sleep_time(2)
return False
def do_forward(self):
sleep_time(2)
comment = self.__get_comment()
self.browser.find_element_by_xpath(
'.//div[contains(@class,"WB_feed_publish")]//textarea[@node-type]'
).send_keys(comment)
sleep_time(1)
self.browser.find_element_by_xpath(
'.//div[contains(@class,"WB_feed_publish")]//input[@id="ipt11"]'
).click()
sleep_time(1)
self.browser.find_element_by_xpath(
'.//div[contains(@class,"WB_feed_publish")]//a[contains(@class,"W_btn_a")]'
).click()
sleep_time(1)
def __into_main_page(self):
sleep_time(1)
self.browser.find_element_by_xpath(
'.//div[@class="gn_nav"]/ul/li[5]').click()
log.info("进入个人主页，查看自己转发的微博内容")
def into_host(self):
sleep_time(2)
self.browser.find_element_by_xpath(
'.//div[@class="lev"]/a[@page_id="102803_ctg1_1760_-_ctg1_1760"]//span[2]'
).click()
log.info("点击进入热门")
def __click_login(self):
sleep_time(1)
log.info('点击登录')
self.browser.find_element_by_xpath(
'.//div[@class="login_innerwrap"]/div[3]/div[contains(@class,"login_btn")]'
).click()
def into_new_page(self, url):
sleep_time(2)
self.browser.get(url)
def __click_follow(self):
sleep_time(2)
self.browser.find_element_by_xpath(
'.//div[contains(@class,"opt_box")]/div[1]/a[1]').click()
log.info('点击了关注')
def __open_page(self, follow_page):
sleep_time(1)
self.browser.get(follow_page)
log.info('打开被关注者主页：{}'.format(follow_page))
def get_self_forward(self):
self.__into_main_page()
sleep_time(2)
res = []
html = etree.HTML(self.browser.page_source)
item_list = html.xpath(
'.//div[@node-type="feed_list"]//div[contains(@class,"WB_detail")]'
)
if item_list:
for item in item_list:
try:
timestamp = item.xpath(
'./div[contains(@class,"WB_from")]/a[1]/@date')[0]
log.debug(timestamp)
except:
timestamp = ''
try:
action_url = 'https://weibo.com' + item.xpath(
'./div[contains(@class,"WB_from")]/a[1]/@href')[0]
log.debug(action_url)
except:
action_url = ''
try:
robot_name = item.xpath(
'./div[contains(@class,"WB_info")]/a/text()')[0]
log.debug(robot_name)
except:
robot_name = ''
try:
robot_comment_list = []
robot_comment_res = item.xpath(
'./div[contains(@class,"WB_text")]/text()')
for comment in robot_comment_res:
robot_comment_list.append(comment.strip())
robot_comment = ' '.join(robot_comment_list)
log.debug(robot_comment)
except:
robot_comment = ''
try:
client_acc_name = item.xpath(
'./div[contains(@class,"WB_feed_expand")]//div[contains(@class,"WB_info")]/a/@title'
)[0]
log.debug(client_acc_name)
except:
client_acc_name = ''
try:
client_title_list = []
client_title_res = item.xpath(
'./div[contains(@class,"WB_feed_expand")]//div[contains(@class,"WB_text")]/text()'
)
for title in client_title_res:
client_title_list.append(title.strip())
client_post_title = ' '.join(client_title_list)
log.debug(client_post_title)
except:
client_post_title = ''
try:
client_acc = item.xpath(
'./div[contains(@class,"WB_feed_expand")]//div[contains(@class,"WB_func")]/div[contains(@class,"WB_from")]/a[1]/@href'
)[0]
client_acc_id, client_post_id = client_acc.split('/')[1:]
client_post_url = 'https://weibo.com' + client_acc
log.debug("客户ID: {} 文章ID: {}".format(
client_acc_id, client_post_id))
except:
client_acc_id = ''
client_post_id = ''
client_post_url = ''
weibo_data = {
'ActionTyp': 3,
'RobotName': robot_name,
'Comment': robot_comment,
'ActionUrl': action_url,
'PlatformId': 2,
'ClientAccId': client_acc_id,
'ClientPostUrl': client_post_url,
'ClientPostId': client_post_id,
'ClientPostTitle': client_post_title,
}
res.append(weibo_data)
return res
def __inter_code(self, verify_code):
sleep_time(2)
self.browser.find_element_by_xpath(
'.//input[@node-type="verifycode"]').send_keys(verify_code)