def fetch_flight_data(webdriver):
table_elem = webdriver.find_element(By.ID, 'faresOutbound')
soup = BeautifulSoup(table_elem.get_attribute('innerHTML'))
result_rows = soup.findAll('tr',
id=lambda x: x and 'outbound_flightRow' in x)
for elem in result_rows:
# get departure time
depart_time = elem.find('td', {
'class': 'depart_column'
}).find('span', {'class', 'bugText'}).get_text()
print 'departure time: ' + depart_time
# get arrival time
arrive_time = soup.find('td', {
'class': 'arrive_column'
}).find('span', {'class', 'bugText'}).get_text()
arrive_time = arrive_time.replace('\n', ' ').strip() # clean up
print 'arrival time: ' + arrive_time
# get flight number(s)
flight_info = soup.find('td', {'class': 'flight_column'})
# get all flights (connecting/final)
flights = flight_info.find_all(
'div',
class_=lambda x: x and 'aircraft_information' and 'right' in x)
flight_info_dict = {}
index = 0
for flight_info in flights:
flight_num, plane_type, seat_num = parse_flight_info(
flight_info.text)
flight_info_dict[index] = [flight_num, plane_type, seat_num]
for key in flight_info_dict.keys():
print 'flight number: ' + flight_info_dict[key][0]
print 'plane type: ' + flight_info_dict[key][1]
print 'number seats: ' + flight_info_dict[key][2]
# get number of connecting stops
connect_num = soup.find('div', {
'class': 'flightDetailsContainer'
}).find('span', {'class': 'headerText'})
connect_num = connect_num.text.strip('(').split()[0]
# get connecting stops
connecting_stops = parse_routing_info(
soup.find('table', {'class': 'routingDetailsContainer'}),
int(connect_num))
def replied():
# _3ExzF
#
# document.getElementsByClassName("_3XpKm _20zqk")[11].children[0].getAttribute("aria-label")
input("Press")
sleep(5)
ele = webdriver.find_element(
By.XPATH,
"/html/body/div/div[1]/div[1]/div[4]/div[1]/div[3]/div/div/div[3]/div[20]/div/div/div/div[1]/div"
)
print(ele)
print(ele.text)
ele
def get_table_content(tableId, queryContent):
arr = []
arr1 = []
table_loc = webdriver.find_element_by_id(tableId)
# 按行查询表格的数据，取出的数据是一整行，按空格分隔每一列的数据
table_tr_list = webdriver.find_element(*table_loc).find_elements(
By.TAG_NAME, "tr")
for tr in table_tr_list:
arr1 = (tr.text).split(" ") #以空格拆分成若干个(个数与列的个数相同)一维列表
print(tr.text)
# print(arr1)
arr.append(arr1) #将表格数据组成二维的列表
#循环遍历table数据，确定查询数据的位置
for i in range(len(arr)):
for j in range(len(arr[i])):
if queryContent == arr[i][j]:
print("%r坐标为(%r,%r)" % (queryContent, i + 1, j + 1))
def checkOnline():
while (True):
# _7yrSq _3-8er selectable-text copyable-text
try:
# 86400
# isOnline = WebDriverWait(webdriver, 86400).until(EC.presence_of_element_located((
# By.XPATH, '/html/body/div/div[1]/div[1]/div[4]/div[1]/header/div[2]/div[2]/span')))
isOnline = webdriver.find_element(
By.XPATH,
'/html/body/div/div[1]/div[1]/div[4]/div[1]/header/div[2]/div[2]/span'
)
if isOnline != None:
return True
except Exception as e:
# print("Error checking online ")
# print(e)
return False
webdriver.get('https://www.skincare-junkie.com/new-members')
sleep(5)
for i in range(1, 2):
webdriver.execute_script(
"window.scrollTo(0, document.body.scrollHeight);")
sleep(randint(1, 5))
elements = webdriver.find_elements(By.CLASS_NAME, 'member-list-item')
user_ids = [x.get_attribute('data-member-item') for x in elements]
sleep(randint(10, 30))
webdriver.get('https://www.skincare-junkie.com/sign_in')
sleep(5)
email_field = webdriver.find_element(By.CLASS_NAME, 'email-input')
email_field.send_keys('*****@*****.**')
next_button = webdriver.find_element(By.CLASS_NAME, 'submit-button')
next_button.click()
password_field = webdriver.find_element(By.CLASS_NAME, 'password-input')
password_field.send_keys('5?58BHDq@Z4FkKW')
sleep(randint(3, 5))
next_button = webdriver.find_element(By.CLASS_NAME, 'submit-button')
next_button.click()
sleep(randint(10, 20))
count = 0
for user_id in user_ids:
webdriver.get('https://www.skincare-junkie.com/chats/new?user_id=' +
user_id)
# chrome_options.add_argument("--headless")
chrome_options.add_argument("--window-size=1920x1080")
chrome_options.add_argument(
"--user-agent=Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36"
)
driver = webdriver.Chrome(options=chrome_options,
executable_path='./chromedriver')
# setting up test meeting
driver.get("https://www.webex.com/test-meeting.html")
driver.find_element(By.ID, "full-name").send_keys("Gerard Kensington")
driver.find_element(By.ID, "email-address").send_keys("*****@*****.**")
driver.find_element(By.CSS_SELECTOR, ".form_button").click()
time.sleep(4)
driver.find_element(By.ID, "push_download_webapp_buttom_join_link").click()
driver.find_element(By.CSS_SELECTOR,
".style-arrow-2f8xt > .style-icon-2HDxh").click()
element = webdriver.find_element(By.CSS_SELECTOR,
".style-arrow-2f8xt > .style-icon-2HDxh")
actions = webdriver.ActionChains(driver)
actions.move_to_element(element).perform()
element = driver.find_element(By.CSS_SELECTOR, "body")
actions = webdriver.ActionChains(driver)
actions.move_to_element(element, 0, 0).perform()
driver.find_element(By.CSS_SELECTOR, "li:nth-child(3)").click()
driver.find_element(By.ID, "interstitial_join_btn").click()
"""
<a id="push_download_webapp_buttom_join_link" href="javascript:void(0);">Join from your browser</a>
"""
from selenium import webdriver
from selenium.webdriver.chrome.webdriver import WebDriver
from selenium.webdriver.common.by import By
webdriver = webdriver.Chrome() # type: WebDriver
#Assert.assertEquals(expectedUrl, driver.getCurrentUrl());
#website = websiteDesired
#print ("enter website: ")
#input (website)
#print (website)
webdriver.get("http://www.google.com")
webdriver.find_element(By.NAME, "q").click()
webdriver.find_element(By.NAME, "q").send_keys("wikipedia")
webdriver.find_element(By.NAME, "btnK").click()
#trying to find a clickable first link, by copying JS and XPath from CSS
#document.querySelector('#rso > div:nth-child(1) > h2')
#//*[@id="cnt"]/div[9] Xpath
#document.querySelector('#rso > div:nth-child(1) > div > link')
#webdriver.find_element(By.CSS_SELECTOR, "#rso > div:nth-child(1) > h2").click()
#webdriver.find_element(By.CSS_SELECTOR, "#rso > div:nth-child(1) > div > link").click()
#document.querySelector('#rso > div:nth-child(1) > div > div > div.r > a')
#found a clickable element!
webdriver.find_element(
By.CSS_SELECTOR,
"#rso > div:nth-child(1) > div > div > div.r > a").click()
def find_element():
element = webdriver.find_element(By.ID, "xx")
style_yellow = 'arguments[0].style.border="5px solid yellow"'
webdriver.execute_script(style_yellow, element)
print("我在find element")
webdriver.find_element_by_tag_name("")
webdriver.find_element_by_link_text("")
webdriver.find_element_by_partial_link_text("")
webdriver.find_element_by_css_selector("")
webdriver.find_element_by_xpath("")
# 定位一组元素，返回对象列表 8种
webdriver.find_elements_by_id("") # id复数定位
webdriver.find_elements_by_name("") # name复数定位
webdriver.find_elements_by_class_name("") # class复数定位
webdriver.find_elements_by_tag_name("") # teg复数定位
webdriver.find_elements_by_link_text("") # link复数定位
webdriver.find_elements_by_partial_link_text("") # partial_link复数定位
webdriver.find_elements_by_css_selector("") # css_selector 复数定位
webdriver.find_elements_by_xpath("") # xpath复数定位
# 这两种是参数化的方法，对上面各8种的总结
webdriver.find_element(by='id', value="")
webdriver.find_elements(by='id', value="")
'''
1、xpath语法：
指明标签 //*或者 //input[@id="kw"]
根据@属性定位，id name class 或其他属性
逻辑运算and or not，用的最多的是and，同时满足两个属性，//*[@id="kw" and @name="aa"]
层级定位/，
索引定位，从1开始，input[1],多个相同标签，用索引定位
模糊匹配：标签对之间的文本信息的模糊匹配//*[contains(text(),"hao123)]
模糊匹配某个属性//*[contains(@id,"kw")]
模糊匹配以什么开头//*[starts-with(@id,"kw")]
模糊匹配以什么结尾//*[ends-with(@id,"kw")]
还支持最强的正则表达式 //*[match(text(),"kw")] 后边是我的猜测//*[match(@id,"^kw")]
2、css选择器语法：官方说法，css定位更快，语法更简洁，但是xpath更直观，更好理解一些。
response = urllib2.urlopen(request)
print(response.read())
import requests
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
url1 = "https://www.rakuten.com.tw/shop/food-collect/product/apple2017072100/?s-id=Event-supersale-170814-index-081820-003"
ChromeDriver = "D:/chromedriver_win32/chromedriver.exe"
browser = webdriver.Chrome(executable_path=ChromeDriver)
browser.get(url1)
#assert "afv" in browser.title
webdriver.find_element(By.XPATH, '//button[text()="Some text"]')
browser.find_elements(By.XPATH, '//button')
browser.find_element_by_class_name("b-btn")
elem = browser.find_element_by_name("q")
elem.send_keys("pycon")
elem.send_keys(Keys.RETURN)
print(browser.page_source)
class PythonOrgSearch(unittest.TestCase):
def setUp(self):
self.driver = webdriver.Chrome()
def test_search_in_python_org(self):
driver = self.driver
5).until(ec.presence_of_element_located(
(By.ID, "check")))
driver.find_element(By.ID, "check").click()
WebDriverWait(driver,
5).until(ec.element_to_be_clickable((By.ID, "nextword")))
driver.find_element(By.ID, "nextword").click()
else:
return learn(driver, questions, answers)
return {"questions": questions, "answers": answers}
if __name__ == "__main__":
settings = argument_parse()
webdriver = webdriver_generate(settings["headless"])
lists = read_words(settings["file"])
login(webdriver, settings["username"], settings["password"])
while True:
try:
lists = answer(webdriver, lists["questions"], lists["answers"],
settings["delay"])
except (ElementNotInteractableException, TimeoutException):
dismiss_popup(webdriver)
if webdriver.find_element(By.ID, "return_mainpage").is_displayed():
settings["sessions_to_do"] = session_end(
webdriver,
settings["sessions_to_do"],
settings["file"],
lists["questions"],
lists["answers"],
)
def southwest_search(webdriver, one_way, origin, destination, departure_date,
return_date):
# first have to make sure we can send keys to boxes
WebDriverWait(webdriver, 10).until(
EC.element_to_be_clickable((By.NAME, 'originAirport')))
# specify if looking for 1 way or round trip
if one_way:
webdriver.find_element(By.ID, "trip-type-one-way").click()
else:
webdriver.find_element(By.ID, "trip-type-round-trip").click()
# make sure we've deleted all pre-inputted input
N = 9
webdriver.find_element(By.NAME,
'originAirport').send_keys(Keys.BACKSPACE * N)
webdriver.find_element(By.NAME,
'destinationAirport').send_keys(Keys.BACKSPACE * N)
webdriver.find_element(By.ID,
'air-date-departure').send_keys(Keys.BACKSPACE * N)
if not one_way:
webdriver.find_element(By.ID,
'air-date-return').send_keys(Keys.BACKSPACE * N)
# input specified parameters
webdriver.find_element(By.NAME, 'originAirport').send_keys(origin)
webdriver.find_element(By.NAME,
'destinationAirport').send_keys(destination)
webdriver.find_element(By.ID, 'air-date-departure').send_keys(
departure_date) #has to be MM/DD format!
if not one_way:
webdriver.find_element(By.ID, 'air-date-return').send_keys(return_date)
webdriver.find_element(By.ID, 'jb-booking-form-submit-button').send_keys(
Keys.ENTER)