def get_max_page_num(self):
max_num = WebDriverWait(self.driver, 20, 0.1).until(
lambda d: d.find_element_by_class_name(self.TOTAL_NUM))
size = max_num.get_attribute("innerText")
if not size:
size = max_num.text
return int(size)
def __init__(self):
name = ""
pw = ""
while((name == "") | (pw == "")):
name = input("Loginname: ")
print("Login :"******"Password: "******"PW :", pw)
dcap = dict(DesiredCapabilities.PHANTOMJS)
dcap["phantomjs.page.settings.userAgent"] = (
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/53 (KHTML, like Gecko) Chrome/15.0.87")
self.driver = webdriver.PhantomJS(desired_capabilities=dcap, service_args=['--ignore-ssl-errors=true'])
#goto isis page because direct access is not permitted
self.driver.get("https://isis.tu-berlin.de/")
#wait until page is up
wait = WebDriverWait(self.driver, 10)
wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "div.content")))
#click shibbolethbutton to go to login page
self.driver.find_element_by_id('shibbolethbutton').click()
# Fill the login form and submit it
self.driver.find_element_by_name('j_username').send_keys(name)
self.driver.find_element_by_id('password').send_keys(pw)
self.driver.find_element_by_name('Submit').submit()
def test_onclick_popup_modal_and_presents_articles_titles(self):
# self.create_database_record()
# Visitor goes to home page and clicks on airplane word.
self.browser.get(self.live_server_url)
self.get_word('airplane').click()
# Visitor waits until modal windows pop up.
block = WebDriverWait(self.browser, 10)
modal = block.until(expected_conditions.visibility_of_element_located((By.ID, 'word-details-modal')))
# Visitor gets articles titles.
self.check_for_title_in_article_table('airplane is faster than ship.')
self.check_for_title_in_article_table('airplane crashed yesterday.')
self.check_title_does_not_exist_in_article_table('rocket took off today morning.')
# Visitor closes modal window, refreshes browser and clicks on rocket word.
self.browser.find_element(By.XPATH, '//button[@class="btn btn-default"]').click()
self.browser.refresh()
self.browser.find_element_by_link_text('rocket').click()
# Visitor waits until modal windows pop up.
block = WebDriverWait(self.browser, 10)
modal = block.until(expected_conditions.visibility_of_element_located((By.ID, 'word-details-modal')))
# Visitor gets articles titles.
self.check_title_does_not_exist_in_article_table('airplane is faster than ship.')
self.check_title_does_not_exist_in_article_table('airplane crashed yesterday.')
self.check_for_title_in_article_table('rocket took off today morning.')
def test_see_group(self):
"""
I should be able to log in as the first user.
I should be able to see one group.
When clicking on that group, I should be able to see 1 file for thar group.
"""
welcome_url = '%s%s' % (self.live_server_url, '/welcome')
self.driver.get(welcome_url)
css_selector_email="input#login_user_email"
css_selector_password="******"
css_selector_submit="button#auth_submit"
css_selector_loginname="a#login-name"
def try_to_login(user):
self.bycss(css_selector_email).send_keys(user.email)
self.bycss(css_selector_password).send_keys(user.password)
self.bycss(css_selector_submit).click()
element = WebDriverWait(self.driver, 10).until(lambda x: x.find_element_by_css_selector(css_selector_loginname))
self.assertEqual(element.text, "%s %s" % (user.firstname, user.lastname), "user name didn't match")
try_to_login(User.objects.all().order_by("id")[0]) #try to login as first user.
self.driver.get(self.live_server_url)
a = self.bycss(".jstree-leaf[rel=ensemble][id_item='1']")
ensemble_name=Ensemble.objects.get(pk=1).name
self.assertEqual(a.text, ensemble_name, "ensemble name didn't match")
#now try and click the link:
a2 = a.find_element_by_tag_name("a")
a2.click()
file_elt = WebDriverWait(self.driver, 3).until(lambda x: x.find_element_by_css_selector(".filesview_ftitle>a"))
self.assertEqual(file_elt.text, Source.objects.get(pk=1).title, "source title didn't match")
file_elt.click()
#check for instance that NB.pers.store.o.file[1].title is the same title
pass
class Application(object):
def __init__(self, driver):
self.wd = driver
self.base_url = "http://localhost/"
self.session = SessionHelper(self)
self.movie = MovieHelper(self)
# self.wait = WaitHelper(self)
self.wait = WebDriverWait(self.wd, 30)
def wait_element_off(self, element):
self.wait.until(staleness_of(element))
def wait_element_on(self):
wd = self.wd
element = self.wait.until(presence_of_element_located((By.XPATH, "//div[@class='movie_box']")))
if element != wd.find_element_by_xpath("//div[@class='movie_box']"):
pass
#self.session.logout()
def open_add_movie_page(self):
wd = self.wd
wd.get(self.base_url + "/php4dvd/?go=add")
def open_home_page(self):
wd = self.wd
wd.get(self.base_url + "/php4dvd/")
def destroy(self):
self.wd.quit()
def test_check_all_admin_pages(self):
wait = WebDriverWait(self.driver, 5)
self.driver.get(SIGN_IN_PAGE)
self.driver.find_element_by_name("username").send_keys(LOGIN)
self.driver.find_element_by_name("password").send_keys(PASSWORD)
self.driver.find_element_by_name("login").click()
first_menu_elements = wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, "#app->a")))
first_menu_links = [x.get_attribute("href") for x in first_menu_elements]
for link in first_menu_links:
self.driver.get(link)
first_menu_item_header = self.driver.find_elements_by_css_selector("#content>h1")
self.assertTrue(first_menu_item_header)
second_menu_elements = self.driver.find_elements_by_css_selector(".docs a")
second_menu_links = [x.get_attribute("href") for x in second_menu_elements]
if second_menu_elements:
for link in second_menu_links:
self.driver.get(link)
second_menu_item_header = self.driver.find_elements_by_css_selector("#content>h1")
self.assertTrue(second_menu_item_header)
def get_page_num_from_browser(self):
current_num = WebDriverWait(self.driver, 20, 0.1).until(
lambda d: d.find_element_by_xpath(self.CURRENT_NUM))
size = current_num.get_attribute("innerText")
if not size:
size = current_num.text
return int(size)
def delete_user(self, name=None):
#local locators
_locUser = (By.XPATH, "//h3[attribute::title='"+name+"']/preceding-sibling::div[attribute::class='controls']")
_locDelButton = (By.CSS_SELECTOR, "button")
#[H] move to the user page
self.__move_to_user_page()
#[M] find the user to leave out of the user list
isGivenUserFound = False
try:
user = WebDriverWait(self.selenium,self._TimeOut). \
until(lambda s: self.find_element(*_locUser))
#take a delete action on the element
delButton = WebDriverWait(self.selenium,self._TimeOut). \
until(lambda s: user.find_element(*_locDelButton))
isGivenUserFound = True
except Exceptions.TimeoutException:
print "let us move on..\n"
if isGivenUserFound == True:
#click the button
delButton.click()
#return the outcome in boolean
return isGivenUserFound
def get(self, url):
super(WebDriverMixin, self).get('about:blank')
full_url = urljoin(self._base_url, url)
self.execute_script(
"""
window.name = "{}" + window.name;
window.location.replace("{}");
""".format(DEFER_LABEL, full_url)
)
wait = WebDriverWait(self, 10)
wait.until_not(self._location_equals, 'about:blank')
if not self.ignore_synchronization:
test_result = self._test_for_angular()
angular_on_page = test_result[0]
if not angular_on_page:
message = test_result[1]
raise AngularNotFoundException(
'Angular could not be found on page: {}:'
' {}'.format(full_url, message)
)
# TODO: inject scripts here
# return self.execute_script(
# 'angular.resumeBootstrap(arguments[0]);'
# )
self.execute_script('angular.resumeBootstrap();')
def _get_keyspaces(self):
"""Get list of all present keyspaces."""
wait = WebDriverWait(self.driver, 10)
wait.until(expected_conditions.visibility_of_element_located((By.TAG_NAME, "vt-dashboard")))
dashboard_content = self.driver.find_element_by_tag_name("vt-dashboard")
toolbars = dashboard_content.find_elements_by_class_name("vt-card-toolbar")
return [t.find_element_by_class_name("vt-title").text for t in toolbars]
class appledailyAndroidTests(unittest.TestCase):
def setUp(self):
desired_caps = {}
desired_caps['browserName'] = ''
desired_caps['device'] = 'Android'
desired_caps['platformName'] = 'Android'
desired_caps['platformVersion'] = '4.2。2'
desired_caps['deviceName'] = 'S5'
desired_caps['app'] = PATH(
u'D:/测试APP/com.nextmedia.apk'
)
desired_caps['appPackage'] = 'com.nextmedia'
desired_caps['appActivity'] = 'com.nextmedia.apple.hk.Loading'
self.driver = webdriver.Remote('http://localhost:4723/wd/hub', desired_caps)
self.wait = WebDriverWait(self.driver, 60)
def tearDown(self):
self.driver.quit()
def gettextviewtext(self):
textview=self.driver.find_elements_by_class_name('android.widget.TextView')
i=0
list = []
while i<len(textview):
list.append(textview[i].text)
i=i+1
return list
def entermainpage(self):
self.driver.find_element_by_id('com.nextmedia:id/tutorial_show').click()
self.driver.find_element_by_name(u'略過').click()
self.wait.until(EC.element_to_be_clickable((By.ID,'com.nextmedia:id/ranking_button')))
def _get_keyspace_shards(self):
wait = WebDriverWait(self.driver, 10)
wait.until(expected_conditions.visibility_of_element_located(
(By.TAG_NAME, 'vt-keyspace-view')))
keyspace_content = self.driver.find_element_by_tag_name('vt-keyspace-view')
return [sh.text for sh in
keyspace_content.find_elements_by_class_name('vt-serving-shard')]
def wait_until_element_not_visible(webdriver, locator_lambda_expression,
timeout=WTF_TIMEOUT_MANAGER.NORMAL, sleep=0.5):
"""
Wait for a WebElement to disappear.
Args:
webdriver (Webdriver) - Selenium Webdriver
locator (lambda) - Locator lambda expression.
Kwargs:
timeout (number) - timeout period
sleep (number) - sleep period between intervals.
"""
# Wait for loading progress indicator to go away.
try:
stoptime = datetime.now() + timedelta(seconds=timeout)
while datetime.now() < stoptime:
element = WebDriverWait(webdriver, WTF_TIMEOUT_MANAGER.BRIEF).until(
locator_lambda_expression)
if element.is_displayed():
time.sleep(sleep)
else:
break
except TimeoutException:
pass
def add_service(self):
count = self.items_in_cart()
Find(by=By.CSS_SELECTOR, value='.add-to-cart', context=self).click()
if not self.item_is_sold_out():
wait = WebDriverWait(self._driver, 10)
wait.until(lambda x: count < self.items_in_cart())
def banner_save(self):
self.wait_banner_image()
element = WebDriverWait(self.driver, 30, 3).until(
lambda el: el.find_element_by_css_selector(self.BANNER_SAVE)
)
element.click()
def _attempt_download(self, query, offset):
real_offset = self._calculate_real_offset(offset)
real_offset = int(real_offset)
dictionary = {AbsWebsiteCommonApi._QUERY_MASK: query, AbsWebsiteCommonApi._OFFSET_MASK: str(real_offset)}
url = self._multiple_replace(dictionary, self.base_url)
page_source = None
for i in range(0, AbsWebsiteCommonApi._DOWNLOAD_TRY_NUMBER):
time.sleep(AbsWebsiteCommonApi._CRAWL_DELAY)
web_page = None
try:
web_page = webdriver.PhantomJS()
web_page.get(url)
wait = WebDriverWait(web_page, AbsWebsiteCommonApi._PAGE_LOAD_TIMEOUT)
wait.until(self.test_page_loaded)
except Exception as exception:
print(str(exception))
if web_page is not None:
web_page.close()
page_source = None
continue
page_source = web_page.execute_script(AbsWebsiteCommonApi._JAVASCRIPT_GET_PAGE_SOURCE_CODE)
web_page.close()
self.inc_download()
break
if page_source is None:
print("ERROR - Internet connection failure")
os.kill(os.getpid(), signal.SIGUSR1)
return page_source
def wait_element_load_end(self, element):
wait = WebDriverWait(self.driver, waiting_time)
try:
wait.until(ec.presence_of_element_located(*element))
wait.until(ec.element_to_be_clickable(*element))
except:
time.sleep(1)
def finds( identifier, context=None, timeout=-1, condition=None):
"""
@return: Returns the web element found by identifier
@rtype: selenium.webdriver.remote.webelement.WebElement
"""
if timeout == -1:
timeout = default_timeout
if isinstance(identifier, WebElement):
return identifier
if context is None:
context = driver
locator = get_identifier(identifier)
if condition is None:
condition = count_non_zero_and_visible(locator)
else:
condition = condition(locator)
wdw = WebDriverWait(driver, timeout)
try:
elems = wdw.until(condition)
return elems if isinstance(elems, list) else []
except TimeoutException:
return []
def _get_keyspace_element(self, keyspace_name):
"""Get a specific keyspace element given a keyspace name."""
element_id = '%s-card' % keyspace_name
wait = WebDriverWait(self.driver, self.WEBDRIVER_TIMEOUT_S)
wait.until(expected_conditions.visibility_of_element_located(
(By.ID, element_id)))
return self.driver.find_element_by_id(element_id)
def _login(self):
fb_login_button = self._css('.fb-login-button')
self._assert_visible(fb_login_button)
time.sleep(0.1)
fb_login_button.click()
wait = WebDriverWait(self.driver, 2)
wait.until(window_opened)
self.driver.switch_to_window(self.driver.window_handles[1])
wait.until(lambda d: d.find_element_by_name('email'))
email_input = self.driver.find_element_by_name('email')
pass_input = self.driver.find_element_by_name('pass')
email_input.send_keys('*****@*****.**')
pass_input.send_keys('flowtestpass')
pass_input.submit()
self.driver.switch_to_window(self.driver.window_handles[0])
wait = WebDriverWait(self.driver, 10)
wait.until(EC.title_contains('Welcome'))
wait.until(lambda d: d.find_element_by_class_name("transcript-text"))
def test_select_suggest(self):
self.driver.execute_script("mobile: OnScreenKeyboard.Disable")
pivots = self.driver.find_elements_by_class_name("Windows.UI.Xaml.Controls.Primitives.PivotHeaderItem")
pivots[1].click()
waiter = WebDriverWait(self.driver, timeout=5)
autosuggestion_box = waiter.until(EC.presence_of_element_located((By.ID, 'MySuggestBox')))
autosuggestion_input = autosuggestion_box.find_element_by_class_name('Windows.UI.Xaml.Controls.TextBox')
autosuggestion_input.send_keys('A')
suggestions_list = waiter.until(EC.presence_of_element_located((By.XNAME, 'SuggestionsList')))
suggestions = suggestions_list.find_elements_by_class_name('Windows.UI.Xaml.Controls.TextBlock')
expected_text = 'A2'
for suggest in suggestions:
if suggest.text == expected_text:
# When AutoSuggest is focused it moves whole view up
# but it is not reflected coordinates that we get from driver,
# instead of suggest.click() we will have to use Select pattern
point = self.driver.execute_script('automation: GetClickablePoint', suggest)
x, y = [float(v) for v in point.split(',')]
ActionChains(self.driver).move_by_offset(x, y).click().perform()
break
assert expected_text == autosuggestion_input.text
def test_check_countries(self):
wait = WebDriverWait(self.driver, 5)
self.sign_in()
self.driver.get(COUNTRIES_PAGE)
current_countries = []
not_null_zones_country_links = []
country_rows = wait.until(EC.presence_of_all_elements_located((By.CSS_SELECTOR, ".row")))
for row in country_rows:
country = row.find_element_by_css_selector("td:nth-child(5) a")
current_countries.append(country.text)
zones = row.find_element_by_css_selector("td:nth-child(6)")
if int(zones.text) > 0:
not_null_zones_country_links.append(country.get_attribute("href"))
expected_countries = sorted(current_countries)
self.assertListEqual(current_countries, expected_countries)
for link in not_null_zones_country_links:
self.driver.get(link)
current_country_zones = [x.text for x in wait.until(EC.presence_of_all_elements_located(
(By.XPATH, "(.//*[@id=\"table-zones\"]//td[3])[position() < last()]")
))]
expected_country_zones = sorted(current_country_zones)
self.assertListEqual(current_country_zones, expected_country_zones)
def click_first_nearby_stop(self, place_name):
self.click_first_search_place(place_name)
wait = WebDriverWait(self.driver, 15)
first_nearby_stop = wait.until(
lambda driver: self.driver.find_element_by_xpath("//android.widget.TextView[@index='0' and @resource-id='nexti.android.bustaipei:id/text_stopname']")
)
first_nearby_stop.click()
def is_business_node_checked(self, business_node_number):
checkbox = WebDriverWait(self.driver, 30, 0.5).until(
lambda d: d.find_elements_by_css_selector(self.BUSINESS_NODES_CHECKBOXES)[business_node_number + 1]
)
if checkbox.is_selected():
return True
return False
def test_sort_routes(self):
wait = WebDriverWait(self.driver, 15)
self.click_first_nearby_stop('Taipei Station')
wait.until(
lambda driver: self.driver.find_element_by_id('nexti.android.bustaipei:id/menu_passby_sort')
).click()
sleep(0.5)
estimates = self.driver.find_elements_by_id('nexti.android.bustaipei:id/text_estimate')
current_estimate = 0
is_depart = False
serv_over = False
for estimate in estimates:
if is_depart:
self.assertEqual(estimate.text, 'Depart')
elif serv_over:
self.assertEqual(estimate.text, 'Serv Over')
if estimate.text == 'Depart':
is_depart = True
continue
elif estimate.text == 'Serv Over':
serv_over = True
continue
elif estimate.text == 'Approach':
continue
match = re.search('(\d{0,2}) min', estimate.text)
next_estimate = int(match.group(1))
self.assertLessEqual(current_estimate, next_estimate)
current_estimate = next_estimate
def test_compare_products_removal_alert(self):
# get the search textbox
search_field = self.driver.find_element_by_name("q")
search_field.clear()
# enter search keyword and submit
search_field.send_keys("phones")
search_field.submit()
# click the Add to compare link
self.driver.\
find_element_by_link_text("Add to Compare").click()
# click on Remove this item link, this will display # an alert to the user
self.driver.find_element_by_link_text("Clear All").click()
# switch to the alert
#alert = self.driver.switch_to_alert()
alert = WebDriverWait(self.driver,10).until(expected_conditions.alert_is_present())
# get the text from alert
alert_text = alert.text
# check alert text
self.assertEqual("Are you sure you would like to remove all products from your comparison?", alert_text)
# click on Ok button
alert.accept()
def is_checked(self, compared_to_average):
checkbox = WebDriverWait(self.driver, 30, 0.5).until(
lambda d: d.find_elements_by_css_selector(self.COMPARED_TO_AVERAGE)[compared_to_average]
)
if checkbox.is_selected():
return True
return False
def is_element_present(self, locator, timeout=3):
try:
wait = WebDriverWait(self.driver, timeout)
wait.until(expected_conditions.presence_of_element_located(locator))
except WebDriverException:
return False
return True
def publish(link):
driver.get(link)
find_click(".org-module-link[href*=members]")
type(".auto-search-input", username)
l = lambda _driver: _driver.find_element_by_css_selector("a[href*=publicize]")
elm = WebDriverWait(driver, 25).until(l)
elm.click()
def setUp(self):
super().setUp()
wait = WebDriverWait(self.driver, 15)
button = wait.until(
lambda driver: self.driver.find_element_by_android_uiautomator('new UiSelector().text("Nearby")')
)
button.click()
def wait_for_click(self, locator, timeout=10):
ele = WebDriverWait(self.driver, timeout).until(
expected_conditions.element_to_be_clickable(locator))
return ele
def choose_ticket_2(self): # for type 2, i.e., piao.damai.cn
self.time_start = time()
print("###开始进行日期及票价选择###")
while self.driver.title.find('订单结算页') == -1: # 如果跳转到了确认界面就算这步成功了，否则继续执行此步
self.num += 1 # 记录抢票轮数
if self.date != 0: # 如果要选择日期
datepicker = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located(
(By.CLASS_NAME, "month")))
datelist = datepicker.find_elements_by_tag_name("span") # 找出所有日期
# print(len(datelist))
validlist = []
for i in range(len(datelist)): # 筛选出所有可选择日期
j = datelist[i]
k = j.get_attribute('class')
if k == 'itm z-show itm-undefined z-sel' \
or k == 'itm z-show itm-undefined' \
or k == 'itm itm-end z-show itm-undefined':
validlist.append(j)
# print(len(validlist))
validlist[self.date - 1].click()
session = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located(
(By.ID, "performList")))
# session = self.driver.find_element_by_id('performList')
session_list = session.find_elements_by_tag_name('li')
print('可选场次数量为：{}'.format(len(session_list)))
for i in self.session: # 根据优先级选择一个可行场次,目前暂时没有找到有不可行日期的案例
j = session_list[i - 1]
k = j.get_attribute('class').strip()
if k == 'itm' or k == 'itm j_more': # 未选中
j.find_element_by_tag_name('a').click()
break
elif k == 'itm itm-sel' or k == 'itm j_more itm-sel': # 已选中
break
elif k == 'itm itm-oos': # 无法选中
continue
sleep(self.intersect_wait_time)
price = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located(
(By.ID, "priceList")))
# price = self.driver.find_element_by_id('priceList')
price_list = price.find_elements_by_tag_name('li')
print('可选票档数量为：{}'.format(len(price_list)))
for i in self.price:
j = price_list[i - 1]
k = j.get_attribute('class').strip()
if k == 'itm' or k == 'itm j_more': # 未选中
j.find_element_by_tag_name('a').click()
break
elif k == 'itm itm-sel' or k == 'itm j_more itm-sel': # 已选中
break
elif k == 'itm itm-oos': # 无法选中
continue
buybutton = None
try:
buybutton = self.driver.find_element_by_id('btnBuyNow') # 要改成立即预订按钮的id
self.status = 3
except:
try:
buybutton = self.driver.find_element_by_id('btnBuyNow')
self.status = 4
except:
print('###无法立即购买，尝试自行选座###')
try:
buybutton = self.driver.find_element_by_id('btnXuanzuo')
self.status = 5
print("###请自行选择位置和票价###")
break
except:
print('---尚未开售，刷新等待---')
self.status = 2
self.driver.refresh()
# 需要先判断是否存在按钮，才能确定是否会出现添加票
if self.ticket_num > 1 and self.status not in [2, 5]: # 自动添加购票数
# add = self.driver.find_element_by_class_name('btn btn-add')
add = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located(
(By.CLASS_NAME, "btn-add")))
for i in range(self.ticket_num - 1):
add.click()
buybutton.click()
def wait_until_and_get_elem_by_xpath(self, elem):
return WebDriverWait(self.driver, 5).until(EC.visibility_of_element_located((By.XPATH, elem)))
def test_4(app_setup, task4_url):
driver = app_setup
driver.get(task4_url)
wait = WebDriverWait(driver, 10)
numberOfGroups = len(driver.find_elements_by_xpath(
'/html/body/div/div/h5')) # number of groups in the task
numberOfSteps = len(
driver.find_elements_by_xpath(
'/html/body/div/table/tbody/tr')) # number of steps in instruction
numberOfOptions = len(
driver.find_elements_by_xpath('/html/body/div/div[1]/input')
) # number of radio buttons to select in group
colorsName = [
'Beluga Brown', 'Mango Orange', 'Verdoro Green', 'Freudian Gilt',
'Pink Kong', 'Duck Egg Blue', 'Anti - Establishment Mint',
'Amberlite Firemist'
] # Posible color names to select
instructions = [] # empty list for instructions in the task
optDict = {
} # empty dictionary for group, color name keys with radio button value
currentOut = driver.find_element_by_id('trail') # outcome web element
currentOutTxt = currentOut.text # string for compare changes after selected option (Trail...)
btnCheck = driver.find_element_by_id('solution')
for i in range(2, numberOfSteps + 1): # create list of steps to execute
step = driver.find_element_by_xpath(
"/html/body/div/table/tbody/tr[{}]/td[2]/code".format(i)).text
instructions.append(step)
for g in range(1, numberOfGroups +
1): # create dictionary to all radio button groups
group = driver.find_elements_by_xpath(
'/html/body/div/div[{}]/input'.format(g))
for x in range(1, numberOfOptions +
1): # create 2 keys dictionary for a group.
valueName = group[x - 1].get_attribute('value')
groupIdx = group[x - 1].get_attribute('name')
optDict[groupIdx,
colorsName[x -
1]] = valueName # eg. (s0, Beluga Brown) = v01
for select, groupNumber in zip(
instructions,
range(numberOfGroups)): # loop to execute instruction steps
keys = ('s' + str(groupNumber), select)
if keys in optDict:
value = optDict[
keys] # value for specific radio button in the group
driver.find_element_by_xpath(
".//input[@type='radio' and @value='{}']".format(value)).click()
wait.until_not(
EC.text_to_be_present_in_element(
(By.ID, 'trail'), currentOutTxt)) # waiting until text change
currentOutTxt = currentOut.text # assigne new text value to compare in next loop step
btnCheck.click()
wait.until(EC.text_to_be_present_in_element(
(By.ID, 'trail'),
'OK')) # wait until possible outcome appear (NOT OK / Ok. Good answer)
currentOutTxt = currentOut.text # assigne new text value to assert
assert currentOutTxt == 'OK. Good answer'
def __init__(self, driver, wait=2):
self.driver = driver
self.wait = WebDriverWait(driver, wait)
self.logger = logging.getLogger(type(self).__name__)
def __init__(self, driver):
self.driver = driver
self.wait = WebDriverWait(self.driver, 15)
self.base_url = 'https://www.boatsgroup.com/'
def check_order_2(self):
if self.status in [3, 4]:
print('###开始确认订单###')
if self.real_name: # 实名者信息不为空
print('###选择购票人信息###')
try:
tb = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located(
(By.CLASS_NAME, 'from-1')))
tb.find_element_by_tag_name('a').click() # 点击选择购票人按钮
sleep(self.intersect_wait_time)
# 此处好像定位不到实名者框，还没有解决
lb_list = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located(
(By.XPATH, '/html/body/div[3]/div[3]/div[12]/div/div[2]/div/div[2]/div/table/tbody'))) # 定位弹窗
lb = lb_list.find_elements_by_tag_name('input')
for i in range(len(self.real_name)):
lb[self.real_name[i] - 1].find_element_by_tag_name('input').click() # 选择第self.real_name个实名者
except Exception as e:
print(e)
input('halt')
WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located(
(By.ID, 'orderConfirmSubmit'))).click() # 同意以上协议并提交订单
# self.driver.find_element_by_id('orderConfirmSubmit').click()
element = WebDriverWait(self.driver, 10, self.refresh_wait_time).until(EC.title_contains('选择支付方式'))
element.find_element_by_xpath('/html/body/div[5]/div/div/div/ul/li[2]/a').click() # 默认选择支付宝
element.find_element_by_xpath('/html/body/div[5]/div/div/form/div[2]/ul/li[1]/label/input').click()
element.find_element_by_id('submit2').click() # 确认无误，支付
self.status = 6
print('###成功提交订单,请手动支付###')
self.time_end = time()
def _wait_for_element_to_disappear(self, locator, timeout=0):
wait = WebDriverWait(self.driver, timeout)
wait.until(invisibility_of_element((locator['by'], locator['value'])))
def test_contains_elements(self):
driver = self.driver
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//h1[contains(text(),'Online Quiz')]")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//p[contains(text(),'Please answer the Online Quiz below. You will rece')]")))
for i in range(0, 2):
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//input[@id='00000008_" + str(i) + "']")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[contains(text(),'What is the longest river in the world?')]")))
for i in range(0, 2):
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//input[@id='0000000a_" + str(i) + "']")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[contains(text(),'Which of the following inventions occured in the 17th century?')]")))
for i in range(0, 4):
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//input[@id='0000000c_" + str(i) + "']")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[contains(text(),'What name is given to the programs ran by a computer')]")))
for i in range(0, 3):
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//input[@id='0000000e_" + str(i) + "']")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[contains(text(),'What food group has the highest level')]")))
for i in range(0, 2):
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//input[@id='00000010_" + str(i) + "']")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[text()='Your Email']")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH, "//input[@type='email']")))
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH, "//button[@type='submit']")))
def choose_ticket_1(self): # for type 1, i.e., detail.damai.cn
self.time_start = time()
print("###开始进行日期及票价选择###")
while self.driver.title.find('确认订单') == -1: # 如果跳转到了确认界面就算这步成功了，否则继续执行此步
self.num += 1 # 记录抢票轮数
if self.date != 0: # 如果需要选择日期
calendar = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located((By.CLASS_NAME, "functional-calendar")))
datelist = calendar.find_elements_by_css_selector("[class='wh_content_item']") # 找到能选择的日期
datelist = datelist[7:] # 跳过前面7个表示周一~周日的元素
datelist[self.date - 1].click() # 选择对应日期
selects = self.driver.find_elements_by_class_name('perform__order__select')
# print('可选区域数量为：{}'.format(len(selects)))
for item in selects:
if item.find_element_by_class_name('select_left').text == '场次':
session = item
# print('\t场次定位成功')
elif item.find_element_by_class_name('select_left').text == '票档':
price = item
# print('\t票档定位成功')
session_list = session.find_elements_by_class_name('select_right_list_item')
print('可选场次数量为：{}'.format(len(session_list)))
if len(self.session) == 1:
j = session_list[self.session[0] - 1].click()
else:
for i in self.session: # 根据优先级选择一个可行场次
j = session_list[i - 1]
k = self.isClassPresent(j, 'presell', True)
if k: # 如果找到了带presell的类
if k.text == '无票':
continue
elif k.text == '预售':
j.click()
break
else:
j.click()
break
price_list = price.find_elements_by_class_name('select_right_list_item')
print('可选票档数量为：{}'.format(len(price_list)))
if len(self.price) == 1:
j = price_list[self.price[0] - 1].click()
else:
for i in self.price:
j = price_list[i - 1]
k = self.isClassPresent(j, 'notticket')
if k: # 存在notticket代表存在缺货登记，跳过
continue
else:
j.click()
break
try:
buybutton = self.driver.find_element_by_class_name('buybtn')
buybutton_text = buybutton.text
# print(buybutton_text)
def add_ticket(): # 设置增加票数
try:
for i in range(self.ticket_num - 1):
addbtn = WebDriverWait(self.driver, self.total_wait_time, self.refresh_wait_time).until(
EC.presence_of_element_located((By.XPATH, "//div[@class='cafe-c-input-number']/a[2]")))
addbtn.click()
except:
raise Exception("***错误：票数增加失败***")
if buybutton_text == "即将开抢" or buybutton_text == "即将开售":
self.status = 2
self.driver.refresh()
print('---尚未开售，刷新等待---')
continue
elif buybutton_text == "立即预订":
add_ticket()
buybutton.click()
self.status = 3
elif buybutton_text == "立即购买":
add_ticket()
buybutton.click()
self.status = 4
elif buybutton_text == "选座购买": # 选座购买暂时无法完成自动化
# buybutton.click()
self.status = 5
print("###请自行选择位置和票价###")
break
elif buybutton_text == "提交缺货登记":
print('###抢票失败，请手动提交缺货登记###')
break
except:
self.driver.refresh()
print("下一次")
import os
import pickle
import time
from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.common.action_chains import ActionChains
brower = webdriver.Chrome()
wait = WebDriverWait(brower, 10)
def getCookies():
# get login taobao cookies
url = "https://www.kjjxjy.com/center/myStudy/goods/detail?year=2019"
brower.get("https://www.kjjxjy.com/index/")
while True:
print("Please login in")
time.sleep(3)
# if login in successfully,
while brower.current_url == url:
Cookies = brower.get_cookies()
brower.quit()
cookies = {}
for item in Cookies:
cookies[item['name']] = item['value']
outputPath = open('jxjycookies.pickle', 'wb')
pickle.dump(cookies, outputPath)
outputPath.close()
return cookies
def test_clickable_elements(self):
driver = self.driver
sleep(2)
for i in range(0, 2): # radio animal
WebDriverWait(driver, 3).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='00000008_" + str(
i) + "']"))).click()
WebDriverWait(driver, 3).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='00000008_" + str(
i) + "' and @aria-checked='true']")))
for i in range(0, 2): # radio river
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='0000000a_" + str(
i) + "']"))).click()
WebDriverWait(driver, 3).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='0000000a_" + str(
i) + "' and @aria-checked='true']")))
for i in range(0, 4): # checkbox inventions
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='0000000c_" + str(
i) + "']"))).click()
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='0000000c_" + str(
i) + "' and @aria-checked='true']")))
for i in range(0, 3): # checkbox program
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='0000000e_" + str(
i) + "']"))).click()
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='0000000e_" + str(
i) + "' and @aria-checked='true']")))
for i in range(0, 2): # checkbox food
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='00000010_" + str(
i) + "']"))).click()
WebDriverWait(driver, 5).until(EC.visibility_of_element_located((By.XPATH,
"//label[@for='00000010_" + str(
i) + "' and @aria-checked='true']")))
WebDriverWait(driver, 5).until(
EC.visibility_of_element_located((By.XPATH, "//input[@type='email']"))).send_keys('*****@*****.**')
driver.find_element_by_tag_name('html').send_keys(Keys.TAB)
def search_elements(self,loc,to=10):
return WebDriverWait(self.driver,timeout=to).until(lambda x : x.find_elements(*loc))
right = code_element.size['width'] + left
height = code_element.size['height'] + top
im = Image.open("E:/Imooc/imooc2.png")
img = im.crop((left, top, right, height))
img.save("E:/Imooc/imooc3.png")
r = ShowapiRequest("http://route.showapi.com/932-2", "164135",
"7eb4c4b4448e4fe3a9dad2cd2c8e0e02")
r.addBodyPara("length", "5")
r.addBodyPara("specials", "false")
r.addBodyPara("secure", "false")
r.addBodyPara("image", r"E:/imooc1.png")
res = r.post()
print(res.text)
text = res.json()['showapi_res_body']['code']
print(text)
time.sleep(2)
driver.find_element_by_id('captcha_code').send_keys(text)
# for i in range(5):
# user_email = ''.join(random.sample('1234567890abcdefg', 6))
# print(user_email)
locator = (By.CLASS_NAME, "controls")
WebDriverWait(driver, 2).until(EC.visibility_of_element_located(locator))
print(email_element.get_attribute('placeholder'))
email_element.send_keys("*****@*****.**")
print(email_element.get_attribute('value'))
time.sleep(5)
driver.close()
def __init__(self, driver):
self.driver = driver
self.wait = WebDriverWait(self.driver, 15)
self.helper = Helper(self.driver)
class AccountHttp(object):
def __init__(self):
self.url = 'https://weixin.sogou.com/weixin?type=1&s_from=input&query={}&ie=utf8&_sug_=n&_sug_type_='
self.account = ''
self.name = ''
self.s = requests.session()
self.s.keep_alive = False # 关闭多余连接
self.s.adapters.DEFAULT_RETRIES = 5 # 增加重连次数
self.headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36',
}
self.cookies = {}
# chrome_options = webdriver.ChromeOptions()
# chrome_options.add_argument('--headless')
# # 多线程driver共享
self.driver = driver
self.wait = WebDriverWait(self.driver, 4)
self.rcon = redis.StrictRedis(db=8)
self.queue = 'analyse'
self.status = 4
@async
def listen_task(self):
while True:
try:
if not self.driver:
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
self.driver = webdriver.Chrome(
chrome_options=chrome_options)
account_char = self.rcon.brpop(self.queue, 0)[1]
self.name = account_char.decode(encoding="utf-8")
self.run()
log("消耗一个account")
except Exception as e:
log('error', '重启', e)
if self.driver:
self.driver.quit()
continue
def send_info(self, info):
loop_count = 0
while True:
loop_count += 1
if loop_count > 3:
break
send_info = dict()
send_info['account'] = info.get('account', '')
send_info['name'] = info.get('name', '')
# send_info['imageUrl'] = path
send_info['imageUrl'] = info.get('imageUrl', '')
send_info['message'] = info.get('message', True)
send_info['feature'] = info.get('features', '')
send_info['certification'] = info.get('certified', '')
send_info['status'] = 3
send_url = 'http://58.56.160.39:38012/MediaManager/api/weixinInfo/add'
r = requests.post(send_url, data=json.dumps(send_info))
if r.status_code == 200:
log("发送weixininfo成功")
break
def handle_img(self, img_b, image_id, info, path):
url_img = 'http://47.99.50.93:8009/SaveImage'
data_img = {'content': base64.b64encode(img_b), 'account_id': image_id}
r = requests.post(url_img, data=data_img)
log('头像上传:', r.status_code)
# 更新数据库
config_mysql_old = get_mysql_old()
db = pymssql.connect(**config_mysql_old)
cursor = db.cursor()
try:
sql_insert = """UPDATE WXAccount SET ImageUrl='{}' WHERE ID='{}'""".format(
path, image_id)
cursor.execute(sql_insert)
db.commit()
log('更新数据成功', info.get('name'))
except Exception as e:
log('更新数据错误', e)
db.rollback()
def uploads_account_info(self, e):
info = dict()
info['Name'] = e(".tit").text()
info['Account'] = self.name
show_list = e("dl")
features, certified = '', ''
for show in show_list:
if '功能介绍' in pq(show).text():
features = pq(show).text().replace('功能介绍：\n', '')
if '认证' in pq(show).text():
certified = pq(show).text().split('\n')[-1]
info['Feature'] = features
info['Certification'] = certified
info['message'] = True
info['status'] = 1
# 获取头像二进制
img_find = e(".img-box").find('img').attr('src')
url_img_get = 'http:' + img_find
info['ImageUrl'] = url_img_get
return info
# self.send_info(info)
def account_homepage(self, choice=''):
# 搜索并进入公众号主页
count = 0
while True:
count += 1
if count > 3:
break
log('start', self.name)
search_url = self.url.format(self.name)
resp_search = self.s.get(search_url,
headers=self.headers,
cookies=self.cookies)
e = pq(resp_search.text)
log(e('title').text())
if '搜狗' not in e('title').text():
log('初始化session')
self.s = requests.session()
if self.name in e(".info").eq(0).text():
if choice:
account_info = self.uploads_account_info(e)
return account_info
account_link = e(".tit").find('a').attr('href')
# self.uploads_account_info(e)
homepage = self.s.get(account_link, cookies=self.cookies)
if '<title>请输入验证码 </title>' in homepage.text:
self.crack_sougou(account_link)
homepage = self.s.get(account_link, cookies=self.cookies)
return homepage.text, self.name
elif len(e(".tit").eq(0).text()) > 1:
log("不能匹配正确的公众号: {}".format(self.name))
break
if '相关的官方认证订阅号' in resp_search.text:
log("搜狗找不到该公众号: {}".format(self.name))
return '搜狗无该账号', self.name
else:
log('url cookie 失效', search_url)
try_count = 0
while True:
try_count += 1
self.crack_sougou(search_url)
if '搜公众号' in self.driver.page_source:
log('------cookies更新------')
cookies = self.driver.get_cookies()
new_cookie = {}
for items in cookies:
new_cookie[items.get('name')] = items.get('value')
self.cookies = new_cookie
log('------cookies已更新------', self.cookies)
break
elif try_count > 6:
log("浏览器验证失败")
break
log("验证完毕")
time.sleep(2)
# 被跳过的公众号要不要抓取 大概 4次
continue
def set_name(self):
url = 'http://124.239.144.181:7114/Schedule/dispatch?type=8'
resp = self.s.get(url)
data_json = resp.text.get('data')
if len(data_json) == 0:
return ''
data = json.loads(data_json)
self.name = data.get('name')
def urls_article(self, html):
items = re.findall('"content_url":".*?,"copyright_stat"', html)
urls = []
for item in items:
url_last = item[15:-18].replace('amp;', '')
url = 'https://mp.weixin.qq.com' + url_last
# 部分是永久链接
if '_biz' in url_last:
url = re.search('http://mp.weixin.qq.*?wechat_redirect',
url_last).group()
urls.append(url)
continue
# 可能匹配过多，再次匹配
if 'content_url' in url:
item = re.search('"content_url":".*?wechat_redirect',
url).group()
url = item[15:].replace('amp;', '')
urls.append(url)
return urls
def emotion_judge(self, content):
key_words_list = []
seg_list = jieba.cut(content)
for s in seg_list:
if re.search('[\u4e00-\u9fff]+', s):
key_words_list.append(s)
# log(key_words_list)
with open('positive.txt', 'r', encoding='utf-8') as f:
positive = f.read()
with open('nagetive.txt', 'r', encoding='utf-8') as f:
nagetive = f.read()
# key_list = list(key_words_counter)
count_positive = 0
count_nagetive = 0
for key in key_words_list:
if key in positive.split('\n'):
count_positive += 1
if key in nagetive.split('\n'):
count_nagetive += 1
return count_positive, count_nagetive
def send_result(self):
# 向前端发送成功请求
# article_detaile = db['newMedia'].find_one({'Account': self.name})
try:
log("发前端")
account_id = hash_md5(self.name)
status_url = 'http://58.56.160.39:38012/MediaManager/api/drafts/updateAnalysisStatusByAnalysisId'
params = {
'type': 3,
'analysisId': account_id,
# 3 成功 4 失败
'status': self.status,
}
r = requests.get(status_url, params=params)
log('status_code', r.status_code)
except Exception as e:
log("发送前端结果错误", e)
def run(self, name, choice=''):
# choice 选择是返回账号主体信息（True） or 分析结果('')
self.name = name
html_account = self.account_homepage(choice)
# 返回账户信息
if choice:
return html_account
if html_account:
html, account_of_homepage = html_account
else:
# self.send_result()
return
log('start 公众号: ', self.name)
urls_article = self.urls_article(html)
account = Account()
account.name = self.name
account.account = account_of_homepage
account.get_account_id()
articles = []
backpack_list = []
positive_article = 0
nagetive_article = 0
for page_count, url in enumerate(urls_article):
# if page_count > 2:
# break
article = Article()
log('url:', url)
article.create(url, self.name)
log('文章标题:', article.title)
log("第{}条".format(page_count))
# 超过7天不管
if article.time:
article_date = datetime.datetime.fromtimestamp(
int(article.time[:-3]))
day_diff = datetime.datetime.now().date() - article_date.date()
if day_diff.days > 6:
break
# 统计文章正负面
count_positive, count_nagetive = self.emotion_judge(
article.content)
if count_positive > count_nagetive:
positive_article += 1
else:
nagetive_article += 1
entity = JsonEntity(article, account)
backpack = Backpack()
backpack.create(entity)
backpack_list.append(backpack.create_backpack())
# 所有文章
article_info = backpack.to_dict()
articles.append(article_info)
log('所有文章抓取完毕')
content_all_list = ''
for article in articles:
content_all_list += article.get('Content')
log('文章长度', len(content_all_list))
# 分词处理
key_words_list = []
data = {
"texts": [content_all_list],
}
log('请求分词')
response = requests.post(url=GETNER_API_URL, data=data, timeout=180)
ner_result = response.json().get('rst')[0]
if ner_result.get('status') == 'success':
org_dic = ner_result.get('ner').get('ORG')
loc_dic = ner_result.get('ner').get('LOC')
per_dic = ner_result.get('ner').get('PER')
if org_dic:
for i in org_dic.items():
key_words_list.append(i)
if loc_dic:
for i in loc_dic.items():
key_words_list.append(i)
if per_dic:
for i in per_dic.items():
key_words_list.append(i)
# 返回前20个出现频率最高的词
key_words = dict()
key_words['list'] = []
key_words_list = sorted(key_words_list,
key=lambda x: x[1],
reverse=True)[:21]
for k in key_words_list:
key_words['list'].append({"times": k[1], "keyword": k[0]})
log('分词完成')
# 处理文章
result = handle(articles)
result['KeyWord'] = key_words
result['ArtPosNeg'] = {
'Indicate': {
'Positive': positive_article,
'Negative': nagetive_article
}
}
result['Success'] = True
result['Account'] = self.name
result['Message'] = 'Successful'
mongo_conn_sentiment().update_one({'Account': self.name}, {
'$set': {
'Addon': time_strftime(),
'Message': 'Successful',
'Data': result
}
},
upsert=True)
log('{} 抓取完成'.format(self.name))
return result
def crack_sougou(self, url):
log('------开始处理未成功的URL：{}'.format(url))
if re.search('weixin\.sogou\.com', url):
log('------开始处理搜狗验证码------')
self.driver.get(url)
time.sleep(2)
if '搜公众号' in self.driver.page_source:
for i in range(30):
self.driver.get(url)
log('浏览器页面正常')
if '搜公众号' not in self.driver.page_source:
break
try:
img = self.wait.until(
EC.presence_of_element_located((By.ID, 'seccodeImage')))
log('------出现验证码页面------')
location = img.location
size = img.size
left = location['x']
top = location['y']
right = location['x'] + size['width']
bottom = location['y'] + size['height']
screenshot = self.driver.get_screenshot_as_png()
screenshot = Image.open(BytesIO(screenshot))
captcha = screenshot.crop((left, top, right, bottom))
captcha_path = os.path.join(IMAGE_DIR, CAPTCHA_NAME)
captcha.save(captcha_path)
try:
captch_input = ''
files = {
'img': (CAPTCHA_NAME, open(captcha_path,
'rb'), 'image/png', {})
}
res = requests.post(url=GetCaptcha_url, files=files)
res = res.json()
if res.get('Success'):
captch_input = res.get('Captcha')
except Exception as e:
log('搜狗验证码验证错误', e)
with open(captcha_path, "rb") as f:
filebytes = f.read()
captch_input = captch_upload_image(filebytes)
log('------验证码：{}------'.format(captch_input))
if captch_input:
input_text = self.wait.until(
EC.presence_of_element_located(
(By.ID, 'seccodeInput')))
input_text.clear()
input_text.send_keys(captch_input)
submit = self.wait.until(
EC.element_to_be_clickable((By.ID, 'submit')))
submit.click()
time.sleep(2)
try:
if '搜公众号' not in self.driver.page_source:
log('验证失败')
return
log('------验证码正确------')
except:
log('--22222222----验证码输入错误------')
except Exception as e:
log(e)
log('------未跳转到验证码页面，跳转到首页，忽略------')
elif re.search('mp\.weixin\.qq\.com', url):
log('------开始处理微信验证码------')
cert = random.random()
image_url = 'https://mp.weixin.qq.com/mp/verifycode?cert={}'.format(
cert)
respones = self.s.get(image_url, cookies=self.cookies)
captch_input = captch_upload_image(respones.content)
log('------验证码：{}------'.format(captch_input))
data = {'cert': cert, 'input': captch_input}
self.s.post(image_url, cookies=self.cookies, data=data)
log('------微信验证码处理完成------')
def verify_link_presence(self, locator_type, locator):
wait = WebDriverWait(self.driver, 10)
wait.until(ec.presence_of_element_located((locator_type, locator)))
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
driver = webdriver.Chrome(
executable_path=r'D:\Naveen\Selenium\chromedriver_win32\chromedriver.exe')
driver.maximize_window()
driver.get(r'http://the-internet.herokuapp.com/dynamic_controls')
driver.find_element_by_xpath("//button[text()='Remove']").click()
wait = WebDriverWait(driver, 5)
message = wait.until(EC.visibility_of_element_located((By.ID, 'message'))).text
assert message == "It's gone!"
try:
driver.find_element_by_id('checkbox')
except NoSuchElementException as err:
pass
def get_user_nickname(self):
#等待页面元素出现
WebDriverWait(self.driver, 15, 0.5).until(
EC.visibility_of_all_elements_located(
(By.XPATH, HL.userinfo_link_xpath)))
return self.driver.find_element_by_xpath(HL.userinfo_link_xpath).text
class DriverInfo:
def __init__(self, driver):
self.driver = driver
self.wait = WebDriverWait(self.driver, 15)
self.helper = Helper(self.driver)
def enter_driver_info(self, state_id):
self.wait.until(
EC.presence_of_element_located(
(By.CSS_SELECTOR,
'.is-current a[href="#/drivers/driver_summary"]')))
self.enter_firstname().send_keys('Carmine')
self.enter_lastname().send_keys('Falcone')
self.enter_dob().send_keys(7777)
self.select_gender('1').click()
# for CA state
if state_id == 'CA':
self.wait.until(
EC.element_to_be_clickable(
(By.CSS_SELECTOR,
'label[data-field="was_license_suspended"]:nth-of-type(1)'
)))
self.select_license_status().click()
self.select_license_age('18')
else:
pass
# for CA state
if state_id == 'CA':
pass
else:
self.wait.until(
EC.element_to_be_clickable(
(By.CSS_SELECTOR,
'label[data-analytics-label="excellent"]')))
self.select_credit_score('Good').click()
self.wait.until(
EC.element_to_be_clickable(
(By.CSS_SELECTOR,
'label[data-analytics-label="some_college_no_degree"]')))
self.select_level_of_education('Doctoral').click()
self.save_and_continue_button().click()
def enter_firstname(self):
firstname = self.driver.find_element_by_css_selector(
'input[name="first_name"]')
return firstname
def enter_lastname(self):
lastname = self.driver.find_element_by_css_selector(
'input[id="last_name"]')
return lastname
def enter_dob(self):
dob = self.driver.find_element_by_css_selector(
'input[id="driver_info_dob"]')
return dob
def select_gender(self, gender_type):
gender = self.driver.find_element_by_css_selector(
'label[data-field="gender"]:nth-of-type(' + gender_type + ')')
return gender
def select_credit_score(self, credit_score):
credit_scores = self.driver.find_elements_by_css_selector(
'label[data-field="credit_score"]')
for credit in credit_scores:
if credit.text == credit_score:
return credit
def select_level_of_education(self, education):
education_level = self.driver.find_elements_by_css_selector(
'label[data-field="education"]')
for edu in education_level:
if edu.text == education:
return edu
def select_license_status(self):
license_status = self.driver.find_element_by_css_selector(
'label[data-field="was_license_suspended"]:nth-of-type(1)')
return license_status
def select_license_age(self, driver_license_age):
license_age = self.driver.find_elements_by_css_selector(
'div[id="driver_info_license_age_container"] label')
for age in license_age:
if age.text == driver_license_age:
return age
def save_and_continue_button(self):
driver_info_btn = self.driver.find_element_by_css_selector(
'button[id="driver_info_continue_btn"]')
return driver_info_btn
def wait_for_element_visibility(self, element_id, delay=5):
WebDriverWait(self.driver, delay).until(
EC.visibility_of_element_located((By.ID, element_id)))
def base_find_element(self, loc, timeout=10, poll=0.5):
return WebDriverWait(
self.driver, timeout=timeout,
poll_frequency=poll).until(lambda x: x.find_element(*loc))
def selenium(keywords_1, index, time_1, time_2, head, type):
"""网页获取"""
# 无弹窗
path = "E:\Firefox\Download"
if not os.path.exists(path):
os.makedirs(path)
profile = webdriver.FirefoxProfile()
profile.set_preference('browser.download.dir', path.strip('\u202a'))
profile.set_preference('browser.download.folderList', 2)
profile.set_preference('browser.download.manager.showWhenStarting', False)
profile.set_preference('browser.helperApps.neverAsk.saveToDisk',
'application/zip,application/octet-stream')
#无图
profile.set_preference('browser.migration.version', 9001)
profile.set_preference('permissions.default.image', 2)
#无头
ops = Options()
if head == 1:
ops.add_argument('--headless')
"""网页获取"""
browser = webdriver.Firefox(firefox_profile=profile, options=ops)
actions = ActionChains(browser)
try:
browser.get('http://wenshu.court.gov.cn')
wait = WebDriverWait(browser, 30)
send = wait.until(
EC.presence_of_element_located(
(By.XPATH,
'//*[@id="_view_1540966814000"]/div/div[1]/div[2]/input')))
send.send_keys(keywords_1)
button = wait.until(
EC.element_to_be_clickable(
(By.XPATH,
'//*[@id="_view_1540966814000"]/div/div[1]/div[3]')))
button.click()
try:
"""优化为：：高级检索 """
click1 = wait.until(
EC.element_to_be_clickable(
(By.XPATH,
'//*[@id="_view_1545034775000"]/div/div[1]/div[1]')))
click1.click()
#发送country,
"""
send1 = wait.until(EC.presence_of_element_located((By.XPATH, '//*[@id="s2"]')))
send1.send_keys(country)
"""
# 具体案由选择
"""案件类型选择:刑事案件"""
if type == 1:
click_type = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="s8"]')))
click_type.click()
click_this = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="gjjs_ajlx"]/li[3]')))
click_this.click()
else:
click_ = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="selectCon_other_ajlx"]')))
click_.click()
click_type = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="gjjs_ajlx"]/li[4]')))
click_type.click()
if type == 1:
"""审判程序选择:一审程序"""
click_type = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="s9"]')))
click_type.click()
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="0201_anchor"]')))
click_this.click()
else:
"""审判程序选择:一审程序"""
click_type = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="s9"]')))
click_type.click()
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="0301_anchor"]')))
click_this.click()
"""案由选择:选择案由、刑事案由、具体案由、确定的案由"""
try:
# 案由选择
click_type = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="s16"]')))
click_type.click()
click_t = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="1"]/i')))
click_t.click()
if type == 1:
# 贪污渎职罪案由选择
# 具体案由选择2,15,161,199,212,341,363,376,408,440
# 小下拉框
if 2 <= int(index) < 15:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="2"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
# 贪污：//*[@id="363_anchor"]
click_crime.click()
elif 15 <= index < 58:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="15"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 58 <= index < 161:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="58"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 161 <= index < 199:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="161"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 199 <= index < 212:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="199"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 212 <= index < 341:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="212"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 341 <= index < 363:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="341"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 363 <= index < 376:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="363"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 376 <= index < 408:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="376"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif 408 <= index < 440:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="408"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
elif index == 440:
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="440"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
else:
print("民事案例检索中")
click_this = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="9000"]/i')))
click_this.click()
click_crime = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//*[@id="%d_anchor"]' % index)))
click_crime.click()
except:
pass
"""审判日期：2019"""
time_send = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="cprqStart"]')))
time_send.click()
# 开始日期,直接sendkeys不行
actions.send_keys_to_element(time_send, time_1).perform()
time_send_end = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="cprqEnd"]')))
time_send_end.click()
# time_send_end.clear()
actions.send_keys_to_element(time_send_end,
time_2).perform() # 结束日期
"""检索确定"""
button_1 = wait.until(
EC.element_to_be_clickable((By.XPATH, '//*[@id="searchBtn"]')))
button_1.click()
"""再次点击限制条件为省市,限制条件下循环"""
#xpath制造
a = ['//*[@id="%d_anchor"]' % (i * 100) for i in range(1, 10)]
b = [
'//*[@id="{name}00_anchor"]'.format(name=chr(x).upper())
for x in range(ord('a'),
ord('x') + 1)
]
list_xpath = a + b
if '//*[@id="W00_anchor"]' in list_xpath:
list_xpath.remove('//*[@id="W00_anchor"]')
for xpath_ in list_xpath:
try:
time.sleep(1)
browser.find_element_by_xpath(xpath_)
except:
pass
else:
button_xpath = wait.until(
EC.element_to_be_clickable((By.XPATH, xpath_)))
button_xpath.click()
browser.refresh()
"""文书数量：15"""
button_ = wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="left_7_3"]/div/select')))
button_.click()
button_ = wait.until(
EC.element_to_be_clickable(
(By.XPATH,
'//div[@class="left_7_3"]/div/select/option[3]')))
button_.click()
time.sleep(4)
"""目的：减少遍历次数，进行页数遍历"""
condition = browser.find_element_by_xpath(
'//div[@class="LM_con clearfix"]/div[@class="fr con_right"]/span'
)
# return (condition.text) # 不能直接//text()原因不明
conditions = math.ceil(int(condition.text) /
15) # 最长12，最短6
if int(condition.text) == 0 or conditions == 0:
"""取消省份限制"""
button_xpath = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//p[@data-key="s33"]/i')))
button_xpath.click()
time.sleep(1)
elif int(conditions) > 40: # condition本身已经除了15
with open('裁判文书超过600页.txt', 'a+',
encoding='utf-8') as file:
file.write('出现超过600条的裁判文书,其所在区域为：' + '，其数量为：' +
str(condition.text) + '\n')
elif 0 < int(conditions) <= 40:
for index in range(conditions):
# print('运行至遍历处。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。。')
try:
'''全选的点击'''
click_1 = wait.until(
EC.presence_of_element_located((
By.XPATH,
'//div[@class="LM_tool clearfix"]/div[4]/a[1]/label'
)))
click_1.click()
'''批量下载的点击'''
click_2 = wait.until(
EC.presence_of_element_located((
By.XPATH,
'//html/body/div/div[4]/div[2]//div[@class="LM_tool clearfix"]/div[4]/a[3]'
)))
click_2.click()
"""下一页"""
button_ = wait.until(
EC.presence_of_element_located((
By.XPATH,
'//div[@class="left_7_3"]/a[last()]')))
button_.click()
time.sleep(4)
message = "正在进行第%d页爬取中-----------------------" % index + "xpath为： {}".format(
xpath_)
yield message
except Exception as e:
print("此处退出-------3-----------")
print("出现错误： ", e, xpath_)
else:
"""取消省份限制"""
button_xpath = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//p[@data-key="s33"]/i')))
button_xpath.click()
time.sleep(1)
"""取消省份限制"""
button_xpath = wait.until(
EC.element_to_be_clickable(
(By.XPATH, '//p[@data-key="s33"]/i')))
button_xpath.click()
time.sleep(1)
except Exception as e:
print("第一个", e)
pass
except Exception as e:
print("第二个", e)
pass
def test_sIPPermissaoUsuario2UnTeste2x50(self):
self.driver.get(
"http://sei3.nuvem.gov.br//sip/login.php?sigla_orgao_sistema=ME&sigla_sistema=SIP"
)
self.driver.find_element(By.ID, "txtUsuario").send_keys("teste")
self.driver.find_element(By.ID, "pwdSenha").click()
self.driver.find_element(By.ID, "pwdSenha").send_keys("teste")
self.driver.find_element(By.ID, "sbmLogin").click()
self.vars["iLoop"] = self.driver.execute_script("return 2")
for i in range(0, 50):
self.vars["iLoop"] = self.driver.execute_script(
"return arguments[0] +1", self.vars["iLoop"])
WebDriverWait(self.driver, 30000).until(
expected_conditions.visibility_of_element_located(
(By.XPATH, "//ul[@id=\'main-menu\']/li[1]/a")))
self.driver.find_element(
By.XPATH, "//ul[@id=\'main-menu\']/li[1]/a").click()
print(str("un6"))
self.driver.find_element(By.LINK_TEXT, "Nova").click()
WebDriverWait(self.driver, 30000).until(
expected_conditions.element_to_be_clickable(
(By.ID, "selOrgaoSistema")))
self.driver.find_element(By.ID, "selOrgaoSistema").click()
dropdown = self.driver.find_element(By.ID, "selOrgaoSistema")
dropdown.find_element(By.XPATH, "//option[. = 'ME']").click()
self.driver.find_element(By.ID, "selOrgaoSistema").click()
WebDriverWait(self.driver, 30000).until(
expected_conditions.element_to_be_clickable(
(By.ID, "selSistema")))
dropdown = self.driver.find_element(By.ID, "selSistema")
dropdown.find_element(By.XPATH, "//option[. = 'SEI']").click()
self.driver.find_element(By.ID, "selSistema").click()
WebDriverWait(self.driver, 30000).until(
expected_conditions.element_to_be_clickable(
(By.ID, "selOrgaoUnidade")))
self.driver.find_element(By.ID, "selOrgaoUnidade").click()
dropdown = self.driver.find_element(By.ID, "selOrgaoUnidade")
dropdown.find_element(By.XPATH, "//option[. = 'ME']").click()
self.driver.find_element(By.ID, "selOrgaoUnidade").click()
WebDriverWait(self.driver, 30000).until(
expected_conditions.element_to_be_clickable(
(By.ID, "selUnidade")))
dropdown = self.driver.find_element(By.ID, "selUnidade")
dropdown.find_element(By.CSS_SELECTOR,
"*[value='110000003']").click()
self.driver.find_element(By.ID, "selUnidade").click()
self.driver.find_element(By.ID, "selOrgaoUsuario").click()
dropdown = self.driver.find_element(By.ID, "selOrgaoUsuario")
dropdown.find_element(By.XPATH, "//option[. = 'ME']").click()
self.driver.find_element(By.ID, "selOrgaoUsuario").click()
self.driver.find_element(By.ID, "txtUsuario").click()
print(str("aqui"))
self.driver.find_element(By.ID, "txtUsuario").clear()
self.driver.find_element(
By.ID,
"txtUsuario").send_keys("usuario" + str(self.vars["iLoop"]))
# self.driver.save_screenshot("teste.png")
WebDriverWait(self.driver, 30000).until(
expected_conditions.visibility_of_element_located(
(By.CSS_SELECTOR, "b:nth-child(1)")))
element = self.driver.find_element(By.CSS_SELECTOR,
"b:nth-child(1)")
actions = ActionChains(self.driver)
actions.move_to_element(element).click_and_hold().perform()
element = self.driver.find_element(By.ID, "divInfraAreaDados")
actions = ActionChains(self.driver)
actions.move_to_element(element).release().perform()
self.driver.find_element(By.CSS_SELECTOR, "body").click()
self.driver.find_element(By.ID, "selPerfil").click()
dropdown = self.driver.find_element(By.ID, "selPerfil")
dropdown.find_element(By.XPATH, "//option[. = 'Básico']").click()
self.driver.find_element(By.NAME, "sbmCadastrarPermissao").click()
import time
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
driver = webdriver.Chrome()
driver.maximize_window()
driver.get('https://www.jd.com/')
#显式等待
wait = WebDriverWait(driver, 10, 1)
wait.until(EC.presence_of_element_located((By.ID,'key')))
driver.find_element(By.ID , 'key').send_keys("华为")
driver.find_element(By.ID , 'key').send_keys(Keys.ENTER)
time.sleep(3)
driver.quit()
def __init__(self, driver):
self.driver = driver
self.wait = WebDriverWait(self.driver, 20)
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from selenium.common.exceptions import TimeoutException
from urllib.parse import quote
broswer=webdriver.Chrome()
wait=WebDriverWait(broswer,20)
KEYWORD="ipad"
def index_page(page):
print("正在爬取第",page,"页")
try:
url="https://s.taobao.com/search?q="+quote(KEYWORD)
broswer.get(url)
if page>1:
input=wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager div.form>input')))
submit=wait.until(
EC.element_to_be_clickable((By.CSS_SELECTOR,'#mainsrp-pager div.form>span.btn.J_Submit')))
input.clear()
input.send_keys(page)
submit.click()
wait.until(
EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#mainsrp-pager li.item.active>span'),str(page)))
wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR,'.m-itemlist.item.item')))
get_products()
def _register_ted(driver, job_data):
time.sleep(1)
navigation.switch_to_frame(driver, "CORPO")
time.sleep(1)
small_wait = WebDriverWait(driver, 8)
logger.info("Filling in TED form...")
try:
# TEF amount
_fill_input(small_wait, '//input[@id="dia"]', job_data['day'])
_fill_input(small_wait, '//input[@id="mes"]', job_data['month'])
_fill_input(small_wait, '//input[@id="ano"]', job_data['year'])
_fill_input(small_wait, '//input[@name="valor" and @size="16"]', job_data['amount'])
except TimeoutException as ex:
logger.critical('Timeout when filling in form: {}'.format(str(ex)))
return operation_codes.OP_TIMEOUT
# If checking account, must select "Credit on account" purpose of the operation
if job_data['account_type'] == 'CH':
try:
# Operation code: Credit on account
credit_op_xpath = '//select[@id="Finalidade"]/option[@value="9"]'
op_element = driver.find_element(By.XPATH, credit_op_xpath)
op_element.click()
except NoSuchElementException:
logger.critical("Unable to select operation code element : {}".format(credit_op_xpath))
return operation_codes.OP_FAILED
# navigation.switch_to_frame(driver, "CORPO")
logger.info("Locating submit button...")
submit_xtag = '//input[@name="Incluir" and @type="button"]'
try:
submit_btn = small_wait.until(EC.element_to_be_clickable((By.XPATH, submit_xtag)))
hover = ActionChains(driver).move_to_element(submit_btn)
hover.perform()
logger.info("Submitting TED...")
click_action = ActionChains(driver).click(submit_btn)
click_action.perform()
except TimeoutException:
logger.critical("Unable to locate submit button: {}".format(submit_xtag))
return operation_codes.OP_FAILED
time.sleep(3)
logger.info("TED submitted, checking if operation was approved...")
success_xpath = '//*[contains(text(), "sucesso")]'
try:
small_wait.until(EC.visibility_of_element_located((By.XPATH, success_xpath)))
except TimeoutException as ex:
logger.critical("Unable to find operation approval status!")
return operation_codes.OP_FAILED
logger.info("TEF successfully registered!")
return operation_codes.OP_SUCCESS
def find_by_xpath(self, xpath):
"""Return the element by its xpath"""
return WebDriverWait(self.driver, self.ui_wait_time).until(
EC.visibility_of_element_located((By.XPATH, xpath)))
#Setup Webdriver, navigate to a page and take a screenshot
driver = webdriver.Firefox()
width = 800
height = 600
driver.set_window_size(width, height)
driver.get("https://google.com")
screenshot = driver.get_screenshot_as_png()
#Send the screenshot to AWS Textract
client = boto3.client('textract')
response = client.detect_document_text(Document={'Bytes': screenshot})
blocks = response['Blocks']
#Analyse response and find the location for a given text string
x, y = find_average_pixel(width, height, blocks, "Store", "WORD")
#Tell the browser to click the location via Javascript
script = 'el = document.elementFromPoint(%d, %d); el.click();' % (x, y)
driver.execute_script(script)
#Check to see if we successfully navigated to the correct page
try:
WebDriverWait(driver, 10).until(
expected_conditions.title_contains("Google Store"))
print("Yay it worked")
except TimeoutException:
print("It didn't work")
driver.close()
