def start_and_login():
while True:
opts = chromeOpts()
opts.add_argument(f"user-agent={ua.random}")
prefs = {
'profile.managed_default_content_settings.images': 2
} # Disallow images from loading
opts.add_experimental_option("prefs", prefs)
driver = helium.start_chrome(
"https://www.udemy.com/random_page_that_does_not_exist/",
headless=False,
options=opts)
driver.add_cookie({
'name': 'client_id',
'value': client_id,
'domain': udemy_domain
})
driver.add_cookie({
'name': 'access_token',
'value': access_token,
'domain': udemy_domain
})
helium.go_to("https://www.udemy.com/?persist_locale=&locale=en_US")
if 'upgrade-your-browser' in driver.current_url:
driver.quit()
else:
break
try:
helium.wait_until(helium.Button('Log in').exists, timeout_secs=3.5)
helium.kill_browser()
raise InvalidCookiesException()
except TimeoutException:
return driver
def get_interactive_page_source(url):
"""Obtém código-fonte completo da página."""
# inicia o chrome para renderizar o código-fonte
try:
start_chrome(url, headless=True)
except Exception:
print(
"Erro: você precisa instalar o Google Chrome e o ChromeDriver par"
"a executar esse raspador.")
sys.exit(1)
driver = get_driver()
# clica em todos os botões "Veja mais!" para liberar os dados dos resumos
print(
f"Raspando a página \"{driver.title}\". Isso pode demorar alguns segundos..."
)
buttons = find_all(S("//span[@onClick]"))
for _ in tqdm(range(len(buttons))):
click("Veja mais!")
print('Fim da raspagem da página.')
# obtém objeto soup a partir do código-fonte renderizado pelo helium
soup = BeautifulSoup(driver.page_source, 'html.parser')
# fecha o chrome
kill_browser()
return soup
def test_invalid_credentials(self):
driver = helium.start_chrome('https://goantifraud.com/manager',
headless=True)
helium.write(TEST_DATA['invalid_credentials']['log'], into='login')
helium.write(TEST_DATA['invalid_credentials']['pass'], into='password')
helium.press(helium.ENTER)
check = helium.Text('Login or password is incorrect').value
helium.kill_browser()
self.assertEqual(check, 'Login or password is incorrect')
def test_recover_pass_with_invalid_user(self):
driver = helium.start_chrome('https://goantifraud.com/manager',
headless=True)
helium.click('Forgot your password?')
helium.write(TEST_DATA['invalid_credentials']['log'], into='login')
helium.click('SEND')
time.sleep(0.5)
validation_msg_list = helium.find_all(helium.S(".error.error_show"))
helium.kill_browser()
self.assertEqual(len(validation_msg_list), 2)
def submit_request(song,
artist,
url='www.harmonixmusic.com/games/rock-band/request'):
"Uses helium framework to open chrome, open a website, and submit a song"
logging.info("Logging into %s", url)
start_chrome(url, headless=True)
write(song, into='Song Title')
write(artist, into='Artist')
logging.info("Submitting request for '%s' by '%s'", song, artist)
click('Submit')
kill_browser()
def run_url_catcher():
try:
wait_until(fetch_download_url, timeout_secs=15)
except TimeoutException as e:
print("Failed!")
print(e)
else:
return URL
finally:
kill_browser()
if URL is None:
sys.exit(1)
def getDemons(name):
list1 = []
list0 = []
start_chrome('https://pointercrate.com/demonlist/')
press(END)
press(PAGE_UP)
click('Open the stats viewer!')
write(name, into='Enter to search...')
click(name)
time.sleep(1)
main_is_empty = 1
extended_is_empty = 1
mainverifs_is_empty = 1
extendedverifs_is_empty = 1
for x in range(75):
counter = x + 1
if main_is_empty:
mainlist = find_all(S('//*[@id="beaten"]/b[%d]/a' % (counter)))
if extended_is_empty:
extendedlist = find_all(
S('//*[@id="beaten"]/span[%d]/a' % (counter)))
if mainverifs_is_empty:
verifications_main = find_all(
S('//*[@id="verified"]/b[%d]/a' % (counter)))
if extendedverifs_is_empty:
verifications_extended = find_all(
S('//*[@id="verified"]/span[%d]/a' % (counter)))
if mainlist == []:
main_is_empty = 0
if extendedlist == []:
extended_is_empty = 0
if verifications_main == []:
mainverifs_is_empty = 0
if verifications_extended == []:
extendedverifs_is_empty = 0
list0.append(mainlist)
list0.append(extendedlist)
list0.append(verifications_main)
list0.append(verifications_extended)
list0 = [element for element in list0 if element != []]
for demon in list0:
demon = str(demon)
start = [m.start() for m in re.finditer(">", demon)][0]
end = [m.start() for m in re.finditer("<", demon)][1]
demon = demon[(start + 1):end]
list1.append(demon)
kill_browser()
return list1
def exit(self):
helium.kill_browser()
import helium
import hashlib
driver = helium.start_chrome("https://temp-mail.org/en/", headless=True)
helium.wait_until(
lambda: "@" in helium.TextField("Your Temporary email address").value)
email = helium.TextField("Your Temporary email address").value
password = hashlib.sha1(email.encode()).hexdigest()
print(email, password)
helium.kill_browser()
driver = helium.start_chrome("https://www.kartable.fr/inscription")
helium.click("élève")
helium.click("1ère")
helium.click("s'inscrire avec un e-mail")
helium.write("Cld", into="prénom")
helium.write("Lokidod", into="nom")
helium.write(email, into="adresse e-mail")
helium.write(password, into="mot de passe")
helium.click("terminer")
helium.wait_until(helium.Text("plus tard").exists)
helium.click("plus tard")
#helium.kill_browser()
def using_firefox():
start_firefox()
try:
yield
finally:
kill_browser()
def tearDownModule():
global _TEST_BROWSER
if _TEST_BROWSER is not None:
kill_browser()
_TEST_BROWSER = None
def tearDownClass(cls):
if cls.started_browser:
kill_browser()
def stop_and_save(fileName, listPosts):
print("Save crawled data...")
with open(fileName, "w", encoding="utf-8") as file:
json.dump(listPosts, file, ensure_ascii=False, indent=4)
kill_browser()
import helium
# 比较适合新手的自动化库
from time import sleep
home_url = 'https://mail.163.com/' # 网站主地址
user_name = 'luobomc' # 登陆用户名
password = '******' # 密码
driver = helium.start_chrome(home_url) # 打开浏览器 并且打开home_url地址页面
sleep(5) # 睡眠5s等待页面加载
helium.write(user_name,
helium.TextField('邮箱帐号或手机号码')) # 锁定'邮箱账号或手机号码'并且锁定 然后传入用户名
sleep(2) # 睡眠2秒
helium.write(password, helium.TextField('输入密码')) # 锁定密码输入框并且输入
helium.press(helium.ENTER) # 模拟按回车 登录
sleep(5) # 睡眠5秒等待页面刷新
helium.click(helium.Text('收 信')) # 点击收信按钮 查看邮件
helium.kill_browser() # 关闭浏览器
def run(self, dispatcher: CollectingDispatcher, tracker: Tracker,
domain: Dict[Text, Any]) -> List[Dict[Text, Any]]:
kill_browser()
dispatcher.utter_message("已关闭")
return []
/ args.slide_path_or_directory_name
)
slides = list(slide_directory.glob("*.html"))
assert len(slides) == 1, str(slides)
slide_html_path = slides[0]
else:
# Case: slide path
slide_html_path = Path(args.slide_path_or_directory_name).resolve()
slide_page_url = slide_html_path.as_uri()
# タイトルが長い場合は2枚めを使う運用をしている
if args.is_long_title:
slide_page_url += "#/1"
if not args.output_path:
args.output_path = (
project_root
/ "docs"
/ "_images"
/ "ogps"
/ f"{slide_html_path.stem}.png"
)
options = FirefoxOptions()
options.add_argument("--width=800")
options.add_argument("--height=485") # ブラウザウィンドウ上部が85px分ある
start_firefox(options=options, headless=True)
go_to(slide_page_url) # TODO: #/1 のようにページの指定を追加可能に
get_driver().save_screenshot(str(args.output_path))
kill_browser()