def testEle(self):
global text_list, urls
for url in urls:
my_selenium = Selenium(url)
driver = my_selenium.driver
driver.switch_to.default_content()
while len(text_list) <= 100:
# 下拉滚动条，使浏览器加载出动态加载的内容，可能像这样要拉很多次，中间要适当的延时（跟网速也有关系）。
driver.execute_script("window.scrollBy(0,40000)")
time.sleep(1)
elements = my_selenium.wait_until_exists(
'//div[@class="comment-list"]//p[@class="text"]')
for e in elements:
try:
text = e.text
if text not in text_list:
print(text)
handle_text(text, 'BilibiliComments.txt')
text_list.append(text)
else:
pass
except Exception as e:
print(e)
elements = my_selenium.wait_until_exists(
'//a[@class="next"]') # and @href="javascript:;"]')
driver.execute_script("arguments[0].click();", elements[0])
text_list = []
driver.close()
def testEle(self):
my_selenium = Selenium("https://h5.qzone.qq.com/mqzone/index")
driver = my_selenium.driver
# 账号输入框输入已知qq账号
driver.find_element_by_id("u").send_keys(self.user)
# 密码框输入已知密码
driver.find_element_by_id("p").send_keys(self.pw)
# 自动点击登陆按钮
driver.find_element_by_id("go").click()
# 如果登录比较频繁或者服务器繁忙的时候，一次模拟点击可能失败，所以想到可以尝试多次，
# 但是像QQ空间这种比较知名的社区在多次登录后都会出现验证码，验证码自动处理又是一个
# 大问题，本例不赘述。本例采用手动确认的方式。即如果观察到自动登陆失败，手动登录后
# 再执行下列操作。
r = ''
while r != 'y':
print("Login seccessful?[y]")
r = input()
# 让webdriver操纵当前页
driver.switch_to.default_content()
while True:
# 下拉滚动条，使浏览器加载出动态加载的内容，可能像这样要拉很多次，中间要适当的延时（跟网速也有关系）。
elements = []
elements += list(
driver.find_elements_by_xpath('//*[@class="reply-txt"]'))
elements += list(
driver.find_elements_by_xpath('//*[@class="comment-text"]'))
for e in elements:
text = e.text
if text not in text_list:
print(text)
text_list.append(e.text)
handle_text(text, 'QQZoneComments.txt')
else:
pass
element = my_selenium.wait_until_exists(
'//*[@class="btn js_morebtn"]')
driver.execute_script("arguments[0].click();", element)
my_selenium.wait_until_exists('//*[@class="comment-text"]')
time.sleep(1)
def testEle(self):
global urls, text_list
for url in urls:
my_selenium = Selenium(url)
driver = my_selenium.driver
# 让webdriver操纵当前页
driver.switch_to.default_content()
# 下拉滚动条，使浏览器加载出动态加载的内容，可能像这样要拉很多次，中间要适当的延时（跟网速也有关系）。
driver.execute_script("window.scrollBy(0,40000)")
time.sleep(1)
elements = []
elements += list(
my_selenium.wait_until_exists(
'//div[contains(@id, "log")]/h3[@class="title"]/a'))
for e in elements:
try:
url = e.get_attribute("href")
my_selenium2 = Selenium(url)
driver2 = my_selenium2.driver
elements2 = list(
my_selenium2.wait_until_exists(
'//div[@class="cont"]/p'))
for e2 in elements2:
try:
text = e2.text
if text not in text_list:
print(text)
text_list.append(e.text)
handle_text(text, 'DuanZi.txt')
else:
pass
except Exception as e:
print(e)
except Exception as e:
print(e)
driver2.close()
driver.close()
predicted = model.predict(features)[0]
predicted = np.array(predicted)
probab = predicted.max()
predition = sentiment_tag[predicted.argmax()]
return predition, probab
loadModel()
from auto_everything.web import Selenium
while 1:
url = input("请输入你想要分析的网站url: ")
if url.strip('\n ') == "":
continue
my_selenium = Selenium(url)
driver = my_selenium.driver
driver.execute_script("window.scrollBy(0,40000)")
time.sleep(1)
elements = my_selenium.wait_until_exists('//p')
for e in elements:
try:
text = e.text.strip('\n ')
if text != "":
r = predictResult(text)
print(text, '\n', r, '\n' * 2)
except Exception as e:
pass
from auto_everything.web import Selenium
from time import sleep
from auto_everything.terminal import Terminal
t = Terminal()
t.kill("chrome")
my_selenium = Selenium("https://www.google.com",
headless=False,
user_data_dir="/home/yingshaoxo/.config/google-chrome/")
d = my_selenium.driver
# get input box
xpath = '/html/body/div[1]/div[3]/form/div[2]/div[1]/div[1]/div/div[2]/input'
elements = my_selenium.wait_until_exists(xpath)
# text inputing
elements[0].send_keys('\b' * 20, "yingshaoxo")
# click search button
elements = my_selenium.wait_until_exists('//input[@value="Google Search"]')
if len(elements):
elements[0].click(
) # d.execute_script("arguments[0].click();", elements[0])
# exit
sleep(30)
d.quit()
——————————————
"""
f.write(text)
'''
urls = """
https://www.bilibili.com/video/av1415480
https://www.bilibili.com/video/av25255526
"""
urls = [url.strip(' \n') for url in urls.split('\n') if url.strip(' \n') != ""]
'''
top_url = "https://www.bilibili.com/ranking/all/155/0/3"
my_selenium = Selenium(top_url)
driver = my_selenium.driver
elements = my_selenium.wait_until_exists(
'//a[@class="title" and @target="_blank"]')
urls = [e.get_attribute("href") for e in elements]
driver.close()
text_list = []
class seleniumTest(unittest.TestCase):
def setUp(self):
pass
def testEle(self):
if model is None:
print("Please run \"loadModel\" first.")
return None
features = findFeatures(text)
predicted = model.predict(features)[0] # we have only one sentence to predict, so take index 0
predicted = np.array(predicted)
probab = predicted.max()
predition = sentiment_tag[predicted.argmax()]
return predition, probab
model = loadModel()
import time
from auto_everything.web import Selenium
my_selenium = Selenium("https://baidu.com")
driver = my_selenium.driver
print('\n'*12)
while True:
url = input("请输入你想要分析的网站url: ")
if url.strip('\n ') == "":
continue
driver.get(url)
driver.execute_script("window.scrollBy(0,40000)")
time.sleep(1)
elements = my_selenium.wait_until_exists('//div') # //p
for e in elements:
try: