class AcceptanceTest(StaticLiveServerTestCase):
def setUp(self):
options = Options()
options.headless = True
self.driver = Firefox(options=options)
def tearDown(self):
self.driver.quit()
def test_two_inputs(self):
driver = self.driver
driver.get('{live_server_url}/two-field-test/'.format(
live_server_url=self.live_server_url
))
WebDriverWait(driver, 5).until(
wait_for_utils_script()
)
inputs = driver.find_elements_by_css_selector('input.intl-tel-input')
inputs[0].send_keys('555-5555')
inputs[1].send_keys('555-4444')
inputs[1].send_keys(Keys.RETURN)
WebDriverWait(driver, 5).until(
EC.presence_of_element_located((By.ID, 'success-text'))
)
self.assertIn('Form is valid', driver.page_source)
def add_advert():
print("Add new advertisement.")
g = Grab(log_file="2.html")
g.load_cookies('cookies.txt')
g.go("http://m.avito.ru/add")
#login_test()
from selenium.webdriver import Firefox
from selenium.webdriver.common.keys import Keys
import selenium
from PIL import Image
browser = Firefox()
driver = selenium.webdriver.Firefox()
browser.get('http://m.avito.ru/profile/login')
driver.implicitly_wait(10)
elem = driver.find_element_by_css_selector(".control-self.control-self-email")
elem.send_keys("*****@*****.**")
"""
driver.find_element_by_name("password")
element.send_keys("ivveqaem")
driver.find_element_by_class_name("control-self control-self-submit button button-solid button-blue button-large")
driver.find_element_by_partial_link_text("Войти")
element.send_keys(Keys.ENTER)
"""
#browser.get('http://m.avito.ru/add')
browser.save_screenshot('current_page')
current_page_img = Image.open('current_page')
w, h = current_page_img.size
captcha_img = current_page_img#.crop((575, 505, w-155, h-1820))
captcha_img.save('captcha.jpg', 'jpeg')
class Scraper(object):
'''
classdocs
'''
def __init__(self):
'''
Constructor
'''
self.url = 'http://www.jerryvarghese.com/Job-Search/ReqSearch.aspx?p=0&locID=121&loc=Saudi%20Arabia'
#self.base_job_url = 'https://sjobs.brassring.com/TGWebHost/jobdetails.aspx?'
self.browser = Firefox()
self.first_page_search_opening_id = 'srchOpenLink'
self.second_page_search_btn_id = 'ctl00_MainContent_submit2'
self.next_link_id = 'yui-pg0-0-next-link'
def page_links(self):
job_link_id = 'Openings1_Rptr_FieldName_ct{}_lknReqTitle'
for i in range(100, 115):
link_id = job_link_id.format(str(i))
link = self.browser.find_element_by_id(link_id)
link.click()
def main(self):
try:
self.browser.get(self.url)
self.page_links()
counter = 1
except Exception as e:
print 'exception= ', str(e)
#print 'stacktrace= ', traceback.print_exc()
print 'Line Number= ' + str(sys.exc_traceback.tb_lineno)
def driver(capabilities):
options = Options()
driver = Firefox(
capabilities=capabilities,
firefox_options=options)
yield driver
driver.quit()
def __init__(self, url, headless=False):
if headless:
self.makeHeadLess()
ffx.__init__(self)
self.url = url
self.minimum_timeout = 60
self.headless = headless
self.timed_out = False
self.load_time = -99
self.login_time = -99
self.logout_time = -99
# Logging
logfmt = '%(levelname)s [%(asctime)s]:\t %(message)s'
datefmt= '%m/%d/%Y %I:%M:%S %p'
formatter = logging.Formatter(fmt=logfmt,datefmt=datefmt)
self.logger = logging.getLogger('__main__')
logging.root.setLevel(logging.DEBUG)
rfh = RotatingFileHandler(filename="/diska/home/jonny/sw/python/stress/stress/gp_timings.log",maxBytes=1048576,backupCount=3,mode='a')
rfh.setFormatter(formatter)
ch = logging.StreamHandler()
ch.setFormatter(formatter)
self.logger.handlers = []
self.logger.addHandler(ch)
self.logger.addHandler(rfh)
def test_test2(self):
"""
test_test2
"""
driver = Firefox()
driver.get('https://www.google.com/')
print('TestCaseCustomSearch test_test2')
class CaptchaPage():
def __init__(self):
print "Captcha Page Initializing"
parser = ConfigParser.ConfigParser()
base_path = os.path.join(os.environ['HOME'], '.mozilla/firefox/')
parser.read(os.path.join(base_path, "profiles.ini"))
profile_path = os.path.join(base_path, filter(lambda x: x[0].lower() == 'path', parser.items('Profile0'))[0][1])
try:
profile = FirefoxProfile(profile_path)
except OSError:
raise Exception("You must execute the following command:\nsudo chmod +r -R %s" % profile_path)
self.driver = Firefox(profile)
self.driver.get("file://%s/index.html" % os.getcwdu())
def get_url_sound(self):
self.driver.find_element_by_xpath('//*[@id="recaptcha_switch_audio"]').click()
return self.driver.find_element_by_xpath('//*[@id="recaptcha_audio_download"]').get_attribute('href')
def get_recaptcha_challenge_field(self):
return self.driver.find_element_by_xpath('//*[@id="recaptcha_challenge_field"]').get_attribute('value')
def get_captcha_textbox(self):
print "Getting Captcha Textbox"
return Textbox(self.driver.find_element_by_xpath('//*[@id="recaptcha_response_field"]'))
def get_submit_button(self):
print "Getting Submit Form Button"
return Button(self.driver.find_element_by_xpath("/html/body/form/input"))
def close(self):
print "Closing Captcha Page"
self.driver.close()
def __init__(self):
CrawlSpider.__init__(self)
print "szlibspider start"
self.verificationErrors = []
self.selenium = selenium("localhost", 4444, "*firefox /usr/lib/firefox/firefox", "http://www.szlib.gov.cn/libraryNetwork/selfLib/id-5.html")
ffdriver = Firefox()
self.selenium.start(driver=ffdriver)
# self.selenium.start()
sel = self.selenium
# sel.open("http://www.szlib.gov.cn/libraryNetwork/selfLib/id-5.html")
ffdriver.get("http://www.szlib.gov.cn/libraryNetwork/selfLib/id-5.html")
WebDriverWait(ffdriver,30).until(ajax_complete, "Timeout waiting page to load")
#Wait for javscript to load in Selenium
# time.sleep(20)
# sel.wait_for_condition("condition by js", 20000);
# print "ul/li visible? %s" % sel.is_element_present("//ul[@class='servicepointlist']")
elements = ffdriver.find_elements_by_xpath("//ul[@class='servicepointlist']/li[@class='item']")
for element in elements[:5]:
print "%s" % element.find_element_by_class_name("num").text
print "%s" % element.find_element_by_class_name("title").text
print "%s" % element.find_element_by_class_name("text").text
print "---------------"
def ff():
browser = Firefox()
browser.get('https://www.charter.com/browse/content/new-channel-lineup')
wait = WebDriverWait('browser', 20)
button = browser.find_element_by_xpath('//*[@id="select-state"]/div[2]') # find and click Choose State button
button.click()
def temp_main():
urls = map(lambda x: x[1], gen_url_contactinfo())
urls = map(lambda x: x + "?spm=a2615.7691481.0.0.OCyk7j", urls)
driver = Firefox()
driver.maximize_window()
for url in urls:
print(url)
get_parser(url, driver)
def control(request):
driver = Firefox()
site = os.path.abspath(os.path.dirname(__file__))
site = os.path.join(site, 'test.html')
driver.get(site)
request.instance.page = MainPage(driver)
def fin():
driver.quit()
request.addfinalizer(fin)
def driver(request):
browser = request.param
if browser == 'firefox':
driver = Firefox()
elif browser == 'chrome':
driver = Chrome()
else:
raise ValueError("Unknown browser '{}'".format(browser))
request.addfinalizer(lambda: driver.quit())
return driver
def test_rendering_utf8_iframe():
iframe = elem.IFrame(html=u'<p>Cerrahpaşa Tıp Fakültesi</p>')
options = Options()
options.add_argument('-headless')
driver = Firefox(options=options)
driver.get('data:text/html,' + iframe.render())
driver.switch_to.frame(0)
assert u'Cerrahpaşa Tıp Fakültesi' in driver.page_source
def test_we_can_launch_multiple_firefox_instances(capabilities):
driver1 = Firefox(capabilities=capabilities)
driver2 = Firefox(capabilities=capabilities)
driver3 = Firefox(capabilities=capabilities)
driver1.quit()
driver2.quit()
driver3.quit()
def print_prices():
driver = Firefox()
driver.get("https://cars.mail.ru/sale/msk/all/?order=price&dir=asc")
elements = [None] * 20
for i in range(0, 20):
print 'finding by xpath', i
elements[i] = WebDriverWait(driver, 10).until(
lambda d: d.find_element_by_xpath('(//span[@class="offer-card__price__value"])[%d]' % (i + 1,)))
for i in range(0, 20):
print 'text', elements[i].text
driver.quit()
def test_that_we_can_accept_a_profile(capabilities, webserver):
profile1 = FirefoxProfile()
profile1.set_preference("browser.startup.homepage_override.mstone", "")
profile1.set_preference("startup.homepage_welcome_url", webserver.where_is('simpleTest.html'))
profile1.update_preferences()
profile2 = FirefoxProfile(profile1.path)
driver = Firefox(
capabilities=capabilities,
firefox_profile=profile2)
title = driver.title
driver.quit()
assert "Hello WebDriver" == title
def test_add_extension_web_extension_without_id(capabilities, webserver):
current_directory = os.path.dirname(os.path.realpath(__file__))
root_directory = os.path.join(current_directory, '..', '..', '..', '..', '..')
extension_path = os.path.join(root_directory, 'third_party', 'firebug', 'mooltipass-1.1.87.xpi')
profile = FirefoxProfile()
profile.add_extension(extension_path)
driver = Firefox(capabilities=capabilities, firefox_profile=profile)
profile_path = driver.firefox_profile.path
extension_path_in_profile = os.path.join(profile_path, 'extensions', '[email protected]')
assert os.path.exists(extension_path_in_profile)
driver.quit()
def test_add_extension_legacy_extension(capabilities, webserver):
current_directory = os.path.dirname(os.path.realpath(__file__))
root_directory = os.path.join(current_directory, '..', '..', '..', '..', '..')
extension_path = os.path.join(root_directory, 'third_party', 'firebug', 'firebug-1.5.0-fx.xpi')
profile = FirefoxProfile()
profile.add_extension(extension_path)
driver = Firefox(capabilities=capabilities, firefox_profile=profile)
profile_path = driver.firefox_profile.path
extension_path_in_profile = os.path.join(profile_path, 'extensions', '*****@*****.**')
assert os.path.exists(extension_path_in_profile)
driver.quit()
def __init__(self, base_url, query_params):
self.__take_results_backup()
options = Options()
options.add_argument("--headless")
try:
self.driver=Chrome(options=options)
except Exception as e:
print(f'Error occured during Chrome driver : {e}')
self.driver=Firefox()
self.driver.get(base_url + query_params)
# set up the next page element
self.nextpage_element=self.driver.find_element_by_css_selector(
".pager-next a")
def get_air_data(positionsets):
# Dictionary hourdata is for holding data, DataStructure like:
# {'baiyunshan': [44, 5], 'haizhubaogang': [55, 6]}
hourdata = {}
# Calling selenium, need linux X
browser = Firefox()
browser.get(URL)
# Added 10 seconds for waiting page for loading.
time.sleep(10)
# Click button one-by-one
for position in positionsets:
# After clicking, should re-get the page_source.
browser.find_element_by_id(position).click()
page_source = browser.page_source
# Cooking Soup
soup = BeautifulSoup(page_source, 'html.parser')
# pm2.5 value would be something like xx 微克/立方米, so we need an regex for
# matching, example: print int(pattern.match(input).group())
try:
PM25 = int(pattern.match(soup.find('td',{'id': 'pmtow'}).contents[0]).group())
PM25_iaqi = int(pattern.match(soup.find('td',{'id': 'pmtow_iaqi'}).contents[0]).group())
PM10 = int(pattern.match(soup.find('td',{'id': 'pmten'}).contents[0]).group())
PM10_iaqi = int(pattern.match(soup.find('td',{'id': 'pmten_iaqi'}).contents[0]).group())
SO2 = int(pattern.match(soup.find('td',{'id': 'sotwo'}).contents[0]).group())
SO2_iaqi = int(pattern.match(soup.find('td',{'id': 'sotwo_iaqi'}).contents[0]).group())
NO2 = int(pattern.match(soup.find('td',{'id': 'notwo'}).contents[0]).group())
NO2_iaqi = int(pattern.match(soup.find('td',{'id': 'notwo_iaqi'}).contents[0]).group())
# Special notice the CO would be float value
CO = float(floatpattern.match(soup.find('td',{'id': 'co'}).contents[0]).group())
CO_iaqi = int(pattern.match(soup.find('td',{'id': 'co_iaqi'}).contents[0]).group())
O3 = int(pattern.match(soup.find('td',{'id': 'othree'}).contents[0]).group())
O3_iaqi = int(pattern.match(soup.find('td',{'id': 'othree_iaqi'}).contents[0]).group())
hourdata_key = pinyin.get(position)
hourdata[hourdata_key] = []
hourdata[hourdata_key].append(PM25)
hourdata[hourdata_key].append(PM25_iaqi)
hourdata[hourdata_key].append(PM10)
hourdata[hourdata_key].append(PM10_iaqi)
hourdata[hourdata_key].append(SO2)
hourdata[hourdata_key].append(SO2_iaqi)
hourdata[hourdata_key].append(NO2)
hourdata[hourdata_key].append(NO2_iaqi)
hourdata[hourdata_key].append(CO)
hourdata[hourdata_key].append(CO_iaqi)
hourdata[hourdata_key].append(O3)
hourdata[hourdata_key].append(O3_iaqi)
except ValueError, Argument:
# won't add the data, simply ignore this position
print "The argument does not contain numbers\n", Argument
def load_search_results(context_id=None):
flashcards = load_flashcards_data()
if context_id is not None:
flashcards = flashcards[flashcards['context_id'] == context_id]
to_process = list(flashcards[['term_id', 'term_name']].drop_duplicates().dropna(subset=['term_name']).values)
random.shuffle(to_process)
global BROWSER
BROWSER = Firefox()
try:
result = []
for term_id, term_name in progress.bar(to_process):
result.append(_load_search_results_apply(term_id, term_name))
return pandas.DataFrame(result)
finally:
BROWSER.quit()
def __init__(self):
CrawlSpider.__init__(self)
log.start(logfile="./log/szlib-%s.log" % strftime("%m%d-%H-%M",localtime(time())), loglevel=log.INFO,logstdout=False)
log.msg("szlibspider start")
print "szlibspider start"
self.verificationErrors = []
self.selenium = selenium("localhost", 4444, "*firefox /usr/lib/firefox/firefox", "http://www.szlib.gov.cn/libraryNetwork/selfLib/id-5.html")
ffdriver = Firefox()
self.selenium.start(driver=ffdriver)
# self.selenium.start()
sel = self.selenium
# sel.open("http://www.szlib.gov.cn/libraryNetwork/selfLib/id-5.html")
ffdriver.get("http://www.szlib.gov.cn/libraryNetwork/selfLib/id-5.html")
WebDriverWait(ffdriver,30).until(ajax_complete, "Timeout waiting page to load")
#Wait for javscript to load in Selenium
# time.sleep(20)
# sel.wait_for_condition("condition by js", 20000);
# print "ul/li visible? %s" % sel.is_element_present("//ul[@class='servicepointlist']")
elements = ffdriver.find_elements_by_xpath("//div[@class='boxtext']/div[@class='filterbox_1']/div[@class='text tab_4_tit district_list']/a")
num = "wijefowaeofjwejf SSL0011"
selflibs_num = []
for district in elements[1:]:
log.msg("%s selflibs:" % district.text)
log.msg("==================")
district.click()
WebDriverWait(ffdriver,30).until(ajax_complete, "Timeout waiting to load selflibs")
selflibs_elements = ffdriver.find_elements_by_xpath("//ul[@class='servicepointlist']/li[@class='item']")
for selflib_ele in selflibs_elements:
# num = selflib_ele.find_element_by_class_name("num").text
num = selflib_ele.find_element_by_class_name("num").get_attribute("textContent")
log.msg("num %s" % num)
selflibs_num.append(num[-7:])
log.msg("numid %s" % num[-7:] )
log.msg("%s" % selflib_ele.find_element_by_class_name("title").get_attribute("textContent"))
log.msg("%s" % selflib_ele.find_element_by_class_name("text").get_attribute("textContent"))
log.msg("---------------")
log.msg("------1---------")
# ffdriver.quit()
# numstr = unicode("编号","utf-8")
# numstr = unicode(num,"utf-8")
# log.msg("numstr is in num? %s" % (numstr in num))
# log.msg("%s,%s, %s" % (num,num[1], num[-7:]))
for selflibnum in selflibs_num:
selflib_url ="http://www.szlib.gov.cn/libraryNetwork/dispSelfLibBook/id-5/%s.html" % selflibnum
log.msg("selflib url %s" % selflib_url)
ffdriver.get(selflib_url)
WebDriverWait(ffdriver,30).until(ajax_complete, "Timeout waiting to load booklist")
categorys_elements = ffdriver.find_elements_by_xpath("//div[@class='boxtext']/div[@class='filterbox_1']/div[@class='text tab_4_tit category']/a")
for category_ele in categorys_elements[1:]:
log.msg("%s" % category_ele.text)
class ContentRetrieverUsingSelenium:
def __init__(self, timeout):
self.browser = Firefox()
self.timeout = timeout
def getContentOfPage(self, url):
self.browser.get(url)
time.sleep(self.timeout)
page_source = self.browser.page_source
page_source = page_source.encode('gbk', 'ignore')
return (self.browser.current_url, BeautifulSoup(page_source))
def close(self):
self.browser.close()
def setUp(self):
if _CI:
self.driver = self.sauce_chrome_webdriver()
elif settings.SELENIUM is True:
options = FirefoxOptions()
options.add_argument('-headless')
self.driver = Firefox(firefox_options=options)
self.driver.implicitly_wait(10)
def open_browser(self):
# Open Firefox to charter using Selenium
browser = Firefox()
browser.get('https://www.charter.com/browse/content/new-channel-lineup')
# Click the "choose state" menu using Selenium
wait = WebDriverWait('browser', 20)
button = browser.find_element_by_css_selector('.drop-down-current')
button.click()
# # Identify all states in the list, read as text using Selenium
list_item = browser.find_element_by_class_name('drop-down-list')
states = list_item.text
# print states
# sel_st = raw_input('Type in 2 letter st abbreviation: ')
def prompt(self)
def __init__(self):
self.comment_root_url = "http://waimai.baidu.com/shopui/?qt=shopcomment&shop_id="
self.comment_root_path = "files/baiduwaimai_comments-%s.json" % datetime.now().strftime("%Y-%m-%d")
self.browser = Firefox()
self.ids = defaultdict(list)
self.crawled_ids = []
self.crawled_id_filepath = "files/crawled_ids.txt"
self.get_crawled_ids()
def setup_browser():
browser = Firefox()
browser.set_window_size(1280, 800)
# WORKAROUND for recordmydesktop bug
browser.set_window_position(10, 10)
yield browser
browser.quit()
def __init__(self):
self.start_page = START_PAGE
self.end_page = END_PAGE
self.weixin_url = REFER_FIRST
self.driver = Firefox()
self.client = MongoClient(HOST, PORT)
self.collection = self.client[DB][COLLECTION]
self.all_uids = self.uids
def __init__(self):
'''
Constructor
'''
self.url = 'http://www.jerryvarghese.com/Job-Search/ReqSearch.aspx?p=0&locID=121&loc=Saudi%20Arabia'
#self.base_job_url = 'https://sjobs.brassring.com/TGWebHost/jobdetails.aspx?'
self.browser = Firefox()
self.first_page_search_opening_id = 'srchOpenLink'
self.second_page_search_btn_id = 'ctl00_MainContent_submit2'
self.next_link_id = 'yui-pg0-0-next-link'
def read_url(url):
driver = Firefox(options=options)
driver.maximize_window()
driver.get(url)
time.sleep(4)
height = driver.execute_script("return document.body.scrollHeight")
print(height)
position = 0
while position < height:
driver.execute_script(f"window.scrollTo(0, {position});")
delta = random.randint(50, 500)
position += delta
duration = delta // 20
# print(height, position, delta, duration)
time.sleep(duration)
driver.close()
#! python3.8.2
from selenium.webdriver import Firefox
from time import sleep
url = 'https://curso-python-selenium.netlify.app/exercicio_02.html'
navegador = Firefox()
try:
navegador.get(url)
sleep(1)
p = navegador.find_elements_by_tag_name('p')
[esperado_texto, numero_esperado] = p[1].text.split(':')
botao = navegador.find_element_by_id('ancora')
valor_atual_p = ''
# while f'Você ganhou:{numero_esperado}' != valor_atual_p:
# botao.click()
# p = navegador.find_elements_by_tag_name('p')
# valor_atual_p = p[-1].text
# print(valor_atual_p)
while 'Você ganhou' not in valor_atual_p:
botao.click()
p = navegador.find_elements_by_tag_name('p')
valor_atual_p = p[-1].text
print(valor_atual_p)
sleep(3)
navegador.quit()
"""
1 - Check if the change occurs in span (focus, blus)
2 - Check if the change occurs in p (change)
"""
from selenium.webdriver import Firefox
browser = Firefox()
browser.get('https://selenium.dunossauro.live/aula_07_d')
text_input = browser.find_element_by_tag_name('input')
span = browser.find_element_by_tag_name('span')
p = browser.find_element_by_tag_name('p')
"""
When input is clicked
Then the text `está com foco` should be the content of `span`
When span is clicked
Then the text `está sem foco` should be the content of `span`
"""
text_input.click()
assert 'está com foco' == span.text, 'Failed - span out of focus'
span.click()
assert 'está sem foco' == span.text, 'Failed - span in focus'
"""
Given that `p` content is `1`
When `text` is sent in element `input`
Then the text `está com foco` should be the content of `span`
When span is clicked
Then the text `está sem foco` should be the content of `span`
import base64, time
downloadDir = './'
options = Options()
options.add_argument('--headless')
options.add_argument('--disable-gpu')
fp = FirefoxProfile()
fp.set_preference("browser.download.folderList", 2)
fp.set_preference("browser.download.dir", downloadDir)
fp.set_preference("browser.download.manager.showWhenStarting", False)
fp.set_preference("browser.helperApps.neverAsk.saveToDisk", "attachment/csv")
driverpath = './geckodriver'
driver = Firefox(executable_path=driverpath, options=options, firefox_profile=fp)
driver.get("https://www.boce.com") #前往這個網址
url_input = driver.find_element_by_class_name('el-input__inner')
url_input.send_keys('www.tonnyshanghai.com')
url_enter = driver.find_elements_by_class_name('el-button--primary')[1]
url_enter.click()
while(True):
try:
result_button = driver.find_element_by_css_selector('.result-wrap .detail-wrap .el-button')
result_button.click()
break
except:
pass
# Test data
td={"url":"https://www.amazon.com","browser":"chrome"}
from selenium.webdriver import Chrome,Firefox
pathChrome = "../driver/chromedriver"
pathFF ="../driver/geckodriver"
if td["browser"]=="chrome":
driver= Chrome(pathChrome)
else:
driver = Firefox(pathFF)
driver.get(td["url"])
driver.fullscreen_window()
driver.quit()
def run():
try:
print(menu)
choice = input(
f"{COLORS.REDL} └──>{COLORS.GNSL} Выберите опцию {COLORS.GNSL}[ {COLORS.REDL}main_menu{COLORS.GNSL} ]{COLORS.GNSL}: "
)
if choice == '1':
show_banner(clear=True)
from module.info_ip import dnsdumpster
domain = input(
f'{COLORS.REDL} └──>{COLORS.WHSL} Введите домен для поиска информации:{COLORS.GNSL} '
)
dnsdumpster(domain)
elif choice == '2':
from urllib.parse import urlparse
show_banner(clear=True)
print(f'\n Пример ввода ссылки: http://google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n [ + ] Headers :\n')
response = requests.get(target, verify=True, timeout=10)
for k, v in response.headers.items():
print(f' [ + ] {k} : {v}')
run()
elif choice == '3':
show_banner(clear=True)
dnslookup = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
dnslookup = 'https://api.hackertarget.com/dnslookup/?q=' + dnslookup
info = requests.get(dnslookup)
print(info.text)
print(info.text)
run()
elif choice == '4':
show_banner(clear=True)
revers = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
reversedns = 'https://api.hackertarget.com/reversedns/?q=' + revers
info = requests.get(reversedns)
print(info.text)
run()
elif choice == '5':
from grab import Grab
from selenium.webdriver import Firefox
from selenium.webdriver.firefox.options import Options
opts = Options()
opts.headless = True
br = Firefox(options=opts)
show_banner(clear=True)
print(
f' {COLORS.WHSL}Примеры ввода запроса: {COLORS.GNSL}google.com, pornohub.com, ruvds.com \n'
)
inp = input(
f'{COLORS.REDL} ──> {COLORS.GNSL}Введите domain: {COLORS.WHSL}'
)
print(
f"\n {COLORS.GNSL}Ожидайте пока закончится сбор информации.{COLORS.WHSL} \n"
)
br.get(f'https://viewdns.info/reversewhois/?q={inp}')
try:
all_list = br.find_elements_by_xpath(
'/html/body/font/table[2]/tbody/tr[3]/td/font/table/tbody/tr'
)
if not all_list:
br.quit()
print(f' Ничего не найдено по вашему запросу')
else:
for elem in all_list:
domain, date, registrar = elem.find_elements_by_xpath(
'td')
print(
f' {domain.text}\t\t{date.text}\t\t{registrar.text}'
)
print(f" {COLORS.REDL}={COLORS.WHSL}" * 70)
print()
br.quit()
except:
br.quit()
elif choice == '6':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/findshareddns/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '7':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: google.com, vsechastikino.ru \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/zonetransfer/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '8':
import whois
print(' Пример ввода: google.com \n')
data = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите доменное имя: "
)
test = whois.whois(data)
show_banner(clear=True)
print(test)
elif choice == '9':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/geoip/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '10':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/reverseiplookup/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '11':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: http://google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/nmap/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '12':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: http://google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/subnetcalc/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '13':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: http://google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/httpheaders/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '14':
show_banner(clear=True)
print(f'\n Пример ввода ссылки: http://google.com \n')
target = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print('\n')
request_urls = "https://api.hackertarget.com/pagelinks/?q="
request_url = request_urls
url = request_url + target
request = requests.get(url)
print(request.text)
run()
elif choice == '15':
show_banner(clear=True)
host = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
print(
f'\n{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Получение субдоменов цели...\n'
)
if not virustotal_api:
print(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Проблемы с ключом api, напишите разработчикам !"
)
return
url = 'https://www.virustotal.com/vtapi/v2/domain/report'
params = {
'apikey': virustotal_api,
'domain': host,
}
response = requests.get(url, params=params)
subdomains = response.json()
for x in subdomains['subdomains']:
print(x)
run()
elif choice == '16':
requests.packages.urllib3.disable_warnings()
show_banner(clear=True)
domain = input(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Введите address: "
)
if not cms_detect_api:
print(
f"{COLORS.GNSL} [ {COLORS.REDL}+{COLORS.GNSL} ] {COLORS.WHSL} Проблемы с ключом api, напишите разработчикам !"
)
return
payload = {'key': cms_detect_api, 'url': domain}
cms_url = "https://whatcms.org/APIEndpoint/Detect"
response = requests.get(cms_url, params=payload)
cms_data = response.json()
cms_info = cms_data['result']
if cms_info['code'] == 200:
print(f' Detected CMS : {cms_info["name"]}')
print(f' Detected Version : {cms_info["version"]}')
print(f' Confidence : {cms_info["confidence"]}')
else:
print(cms_info['msg'])
print(f' Detected CMS : {cms_info["name"]}')
print(f' Detected Version : {cms_info["version"]}')
run()
elif choice == '0':
import os
print(
f' {COLORS.GNSL}Благодарим вас за использование !!! Вы прекрасны.\n'
)
os.system('pkill -9 -f osintsan.py')
exit()
elif choice == '99':
show_banner(clear=True)
return
except KeyboardInterrupt:
print("\nAborted!")
exit()
import time
from selenium.webdriver import Firefox
from selenium.webdriver.firefox.options import Options
from gazpacho import Soup
from tqdm import tqdm
import numpy as np
import pandas as pd
options = Options()
options.headless = True
browser = Firefox(executable_path="/usr/local/bin/geckodriver",
options=options)
links = []
pages = [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 100, 101, 102, 200, 201, 202, 300, 301, 302
]
for page in tqdm(pages):
url = f"https://boardgamegeek.com/browse/boardgame/page/{page}"
browser.get(url)
soup = Soup(browser.page_source)
li = [
a.attrs["href"] for a in soup.find("a", {
"class": "primary",
"href": "boardgame"
})
]
links.extend(li)
time.sleep(1)
class TreeScraper(object):
"""Scrape Wikipedia's Special Category Tree page: https://en.wikipedia.org/wiki/Special:CategoryTree
EXAMPLE USE:
import wikiscraper
scraper = wikiscraper.WikiTreeScraper()
scraper.scrape(category='mathematics', search_depth=3, save='csv')
"""
def __init__(self, all_pages=True):
self.all_pages = all_pages
def _get_expand_buttons(self):
"""Return a list of expand buttons to click on."""
return self.browser.find_elements_by_xpath("//span[@title='expand']")
def _expand_all_categories(self):
"""Expand all categories on page."""
self.depth = 0
self.df = pd.DataFrame(columns=['url', 'depth'])
self.duplicated = 0
url_list = []
depth_list = []
html = self.browser.page_source
soup = bs(html, 'html.parser')
atag = soup.find_all('a', class_='CategoryTreeLabel')
for a in atag:
url_list.append(a['href'])
depth_list.append(self.depth)
self.depth += 1
while self.depth < self.search_depth:
start = default_timer()
time.sleep(30)
expand_buttons = self._get_expand_buttons()
time.sleep(30)
for button in expand_buttons:
time.sleep(.05)
if button.is_displayed():
button.click()
else:
continue
end = default_timer()
print(
f'depth of { self.depth } took {str(round((end-start)/60, 2))} minutes to open'
)
html = self.browser.page_source
soup = bs(html, 'html.parser')
atag = soup.find_all('a', class_='CategoryTreeLabel')
for a in atag:
link = a['href']
if link not in url_list:
url_list.append(a['href'])
depth_list.append(self.depth)
elif link in url_list:
self.duplicated += 1
self.depth += 1
self.df = pd.DataFrame(list(zip(url_list, depth_list)),
columns=['url', 'depth'])
self._convert_utf8()
if self.save == 'csv':
start = default_timer()
self._save_csv()
end = default_timer()
print(
str(round((end - start) / 60, 2)) + f' minutes to save to csv')
def _save_csv(self):
"""Save to a csv file"""
# Save pages and categories to a 'seed_pages' dir
self.df.to_csv(f'seed/{ self.category }_d{ self.depth }.csv',
sep='\t',
encoding='utf-8',
index=False)
def _convert_utf8(self):
"""Convert the url column to utf-8 encoding"""
self.df['url'] = self.df['url'].map(unquote)
def scrape(self, category, search_depth=3, save='csv'):
"""Scrape for either categories or all categories and pages"""
self.category = category.replace(' ', '_')
self.search_depth = search_depth
self.save = save
self.browser = Firefox()
if self.all_pages == True:
time.sleep(1)
self.browser.get(
f'https://en.wikipedia.org/wiki/Special:CategoryTree?target={ self.category }&mode=all&namespaces=&title=Special%3ACategoryTree'
)
time.sleep(1)
self._expand_all_categories()
else:
time.sleep(1)
self.browser.get(
f'https://en.wikipedia.org/wiki/Special:CategoryTree?target={ self.category }&mode=categories&namespaces=&title=Special%3ACategoryTree'
)
time.sleep(1)
self._expand_all_categories()
def _setup_firefox():
opts = Options()
opts.set_headless()
assert opts.headless
browser = Firefox(executable_path=GECKODRIVER_PATH, options=opts)
return browser
from selenium.webdriver import Firefox
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
import time
webDriver = Firefox()
webDriver.get("https://www.tradingview.com/#signin")
#Log in to tradingview
def login(exchange):
#need two seperate tradingview accounts, premium if available, in order to prevent crashes, these are the accounts I created
# you may use them if they work
if exchange == "binance":
tradingViewuserName = "******"
else:
tradingViewuserName = "******"
tradingViewPassword = "******"
inputusername = webDriver.find_element_by_name("username")
inputusername.send_keys(tradingViewuserName)
inputpassword = webDriver.find_element_by_name("password")
inputpassword.send_keys(tradingViewPassword)
inputpassword.submit()
time.sleep(3)
def get_trading_view_graph(interval, currency, exchange):
webDriver.get("https://www.tradingview.com/chart/?symbol=" + exchange +
":" + currency)
intervalSelector = webDriver.find_element_by_class_name("value-DWZXOdoK-")
intervalSelector.click()
intervals = webDriver.find_elements_by_class_name("item-2xPVYue0-")
class webDriverFirefox():
driver = None
wait = None
url = None
browserRunning = False
def __init__(self, url): # 브라우저 실행
self.url = url
def driverRun(self):
try:
os.remove('./geckodriver.log')
except:
pass
if (not (self.browserRunning)):
options = Options()
options.add_argument('-headless')
self.driver = Firefox(executable_path='./geckodriver',
options=options)
self.wait = WebDriverWait(self.driver, timeout=10)
self.driver.get(self.url)
self.browserRunning = True
return 'online'
def driverQuit(self):
if (self.browserRunning):
self.driver.quit()
self.browserRunning = False
return 'offline'
def driverControl(self, url):
driver = self.driver
wait = self.wait
# wait = WebDriverWait(driver, timeout=10)
driver.get(url)
# wait.until(expected.visibility_of_element_located((By.NAME, 'q'))).send_keys('headless firefox' + Keys.ENTER)
# wait.until(expected.visibility_of_element_located((By.CSS_SELECTOR, '#ires a'))).click()
# print(driver.page_source)
def googleTranslate(self, translateString): # 구글번역
driver = self.driver
wait = self.wait
driver.find_element_by_css_selector(
'textarea#source.orig.tlid-source-text-input.goog-textarea').clear(
)
wait.until(
expected.invisibility_of_element_located(
(By.CSS_SELECTOR, 'span.tlid-translation.translation')))
# driver.get('https://translate.google.com/#auto|ko|{}'.format(translateString))
driver.find_element_by_css_selector(
'textarea#source.orig.tlid-source-text-input.goog-textarea'
).send_keys(translateString)
try:
wait.until(
expected.visibility_of_element_located(
(By.CSS_SELECTOR, 'span.tlid-translation.translation')))
except:
html = driver.page_source
driver.find_element_by_css_selector(
'textarea#source.orig.tlid-source-text-input.goog-textarea'
).clear()
if (sv.select_one('div.result-error',
BeautifulSoup(html, 'html.parser'))):
return {
"data1":
sv.select_one('span.tlid-result-error',
BeautifulSoup(html, 'html.parser')).text
}
html = driver.page_source
driver.find_element_by_css_selector(
'textarea#source.orig.tlid-source-text-input.goog-textarea').clear(
)
# driver.implicitly_wait(5)
select1 = str(
sv.select_one('div.homepage-content-wrap',
BeautifulSoup(html, 'html.parser'))) # 번역창 분리
# 1
resultString1 = ''
select4 = sv.select_one('span.tlid-translation.translation',
BeautifulSoup(select1, 'html.parser'))
resultString1 = str(select4).replace('<br/>', '<span>\n</span>')
resultString1 = BeautifulSoup(resultString1, 'html.parser').text
# print(resultString1)
# 2
resultString2 = ''
if ('<div class="gt-cd gt-cd-mbd gt-cd-baf" style="display: none;"'
in select1):
pass
elif ('<div class="gt-cd gt-cd-mbd gt-cd-baf" style=""' in select1):
select2 = str(
sv.select_one('table.gt-baf-table',
BeautifulSoup(select1, 'html.parser')))
select3 = sv.select(
'span.gt-cd-pos, span.gt-baf-cell.gt-baf-word-clickable',
BeautifulSoup(select2, 'html.parser'))
for data in select3:
strData = str(data)
if ('gt-baf-cell' in strData):
resultString2 += "{}, ".format(data.text)
elif ('gt-cd-pos' in strData):
resultString2 = resultString2.rstrip(", ")
resultString2 += "\n* {} *\n: ".format(data.text)
resultString2 = resultString2.lstrip("\n")
resultString2 = resultString2.rstrip(", ")
# print(resultString2)
return {"data1": resultString1, "data2": resultString2}
# headers = {'User-Agent': generate_user_agent()}
#
# response = requests.get(url, headers=headers)
# print(response.text)
from selenium.webdriver import Firefox, FirefoxProfile
from selenium.webdriver.firefox.options import Options
import os
dir_path = os.path.dirname(os.path.realpath(__file__))
opts = Options()
# opts.set_headless()
profile = FirefoxProfile()
profile.set_preference("javascript.enabled", False)
browser = Firefox(firefox_profile=profile,
options=opts,
executable_path=os.path.join(dir_path, 'geckodriver'))
print("Getting page...")
browser.get(
'https://www.usnews.com/best-colleges/university-of-chicago-1774/paying')
widget_class_name = 'hero-stats-widget-stats'
print("Finding stats section...")
stats_wrapper = browser.find_element_by_xpath(
'//section[@class="hero-stats-widget-stats"]')
print("Finding stats list region")
stats_ul = stats_wrapper.find_element_by_tag_name('ul')
stats_li_list = stats_ul.find_elements_by_tag_name('li')
for li in stats_li_list:
span_title = li.find_element_by_tag_name("span").text
strong_content = li.find_element_by_tag_name("strong")
from selenium.webdriver import Firefox
from selenium.webdriver.common.action_chains import ActionChains
from time import sleep
from pprint import pprint
browser = Firefox(executable_path='./geckodriver')
browser.get("https://www.diariooficial.ma.gov.br")
#Code
sleep(5)
# Fechar modal Alert
modal_close = browser.find_element_by_css_selector('a[role=button]')
if modal_close:
modal_close.click()
# Pegar Div e do Select
sleep(5)
div_select = browser.find_element_by_css_selector('div .span10')
# Pegar Combo Select
select = div_select.find_element_by_xpath(
'//select[@id="formPesq:comboCaderno"]')
select.click()
option_combo = select.find_element_by_xpath('//option[@value="JU"]')
option_combo.click()
# Set data in input
input_data_ini = browser.find_element_by_xpath(
'//input[@name="formPesq:calendarInic_input"]')
from selenium.webdriver import Firefox
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import Select
from openpyxl import load_workbook
browser = Firefox(executable_path='/opt/WebDriver/bin/geckodriver')
def spreadsheet(column):
wb = load_workbook('/home/johntg/Documents/columbia_WIP_11-7.xlsx')
ws = wb["main"]
data = []
mfnum = 'a' + str(column)
upc = 'b' + str(column)
department = 'c' + str(column)
item = 'd' + str(column)
manufacturer = 'e' + str(column)
name = 'f' + str(column)
cost = 'g' + str(column)
price = 'h' + str(column)
data.extend([
ws[mfnum].value, ws[upc].value, ws[department].value, ws[item].value,
ws[manufacturer].value, ws[name].value, ws[cost].value, ws[price].value
])
def write_tf(self, filesize, threadnum):
'''This function writes tfrecords. Input parameters are: filesize (number of images in one tfrecord), threadnum(thread id)'''
options = tf.compat.v1.io.TFRecordOptions(
tf.compat.v1.io.TFRecordCompressionType.GZIP)
opts = Options()
opts.set_headless()
assert opts.headless
#driver=PhantomJS()
driver = Firefox(options=opts)
if True:
starttime = time.time()
# randomly select a name of length=20 for tfrecords file.
output_file_name = ''.join(
random.choices(string.ascii_uppercase + string.digits,
k=20)) + '.tfrecord'
print('\nThread: ', threadnum, ' Started:', output_file_name)
# data_arr contains the images of generated tables and all_table_categories contains the table category of each of the table
# flag = 1
# while flag:
# try:
# data_arr,all_table_categories = self.generate_tables(driver, filesize, output_file_name)
# flag = 0
# except:
# flag = 1
data_arr, all_table_categories = self.generate_tables(
driver, filesize, output_file_name)
if (data_arr is not None):
if (len(data_arr) == filesize):
with tf.io.TFRecordWriter(os.path.join(
self.outtfpath, output_file_name),
options=options) as writer:
for imgindex, subarr in enumerate(data_arr):
arr = subarr[0]
img = np.asarray(subarr[1][0], np.int64)[:, :, 0]
colmatrix = np.array(arr[1], dtype=np.int64)
cellmatrix = np.array(arr[2], dtype=np.int64)
rowmatrix = np.array(arr[0], dtype=np.int64)
bboxes = np.array(arr[3])
tablecategory = arr[4][0]
seq_ex = self.generate_tf_record(
img, cellmatrix, rowmatrix, colmatrix, bboxes,
tablecategory, imgindex, output_file_name)
writer.write(seq_ex.SerializeToString())
print('\nThread :', threadnum, ' Completed in ',
time.time() - starttime, ' ', output_file_name,
'with len:', (len(data_arr)))
print('category 1: ', all_table_categories[0],
', category 2: ', all_table_categories[1],
', category 3: ', all_table_categories[2],
', category 4: ', all_table_categories[3])
# except Exception as e:
# print('Exception occurred in write_tf function for file: ',output_file_name)
# traceback.print_exc()
# self.logger.write(traceback.format_exc())
# print('Thread :',threadnum,' Removing',output_file_name)
# os.remove(os.path.join(self.outtfpath,output_file_name))
driver.stop_client()
driver.quit()
exit()
from selenium.webdriver import Firefox
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.common.keys import Keys
url = "https://selenium.dunossauro.live/caixinha"
browser = Firefox()
browser.get(url)
caixa = browser.find_element_by_id('caixa')
h1 = browser.find_element_by_tag_name('h1')
ac = ActionChains(browser)
def caixinha_colorida(key1, key2=None):
ac.key_down(key1)
if key2:
ac.key_down(key2)
ac.move_to_element(caixa)
ac.pause(1)
ac.click()
ac.pause(1)
ac.double_click()
ac.pause(1)
ac.move_to_element(h1)
ac.key_up(key1)
if key2:
ac.key_up(key2)
#!python3
from selenium.webdriver import Firefox
url = 'https://selenium.dunossauro.live/aula_09_a.html'
browser = Firefox()
browser.get(url)
browser.implicitly_wait(30)
btn = browser.find_element_by_css_selector('button')
btn.click()
sucesso = browser.find_element_by_id('finished')
assert sucesso.text == 'Carregamento concluído'
for bs in f.find_all('a'):
runnerurl.append(bs['href'])
runner.append(bs['href'])
else:
runner.append(f.text.strip())
if len(runner) != 0:
# this is to get a number to compare with results found against all users with the name given
expectedfinish = runner[3]
numofracesfromrace = runner[2]
agerange = runner[4]
if len(runnerurl) != 0:
# paste ultraparticipant here
URL = (BASEURL + runnerurl[0])
opts = Options()
opts.add_argument('--headless')
browser = Firefox(options=opts)
browser.get(URL)
time.sleep(1)
acchead = browser.find_elements_by_class_name('accordion-heading')
accordion = browser.find_elements_by_class_name('accordion-content')
for num, runner in enumerate(acchead, start=0):
runarray = runner.text.split('\n')
run = Runner(runarray, URL, expectedfinish)
races = accordion[num].find_elements_by_class_name('rowlines')
print(run.url)
for r in races:
racelist = r.text.split('\n')
#print(racelist)
obj = Race(racelist)
run.events.append(vars(obj))
complete = []
def get_browser(headless: bool = True,
browser_class: int = 1,
init_args: dict = None) -> Firefox:
"""
获取一个浏览器
:param headless:
:param browser_class: 浏览器种类,0是谷歌, 1 是火狐, 服务器端不能使用谷歌
:param init_args: 初始化字典
:return:
"""
"""
selenium安装方法: pip3 install selenium
firefox的headless浏览器
因为headless的浏览器的语言跟随操作系统,为了保证爬回来的数据是正确的语言,
这里必须设置浏览器的初始化参数,
注意，使用headless必须先安装对应浏览器正常的版本,然后再安装headless版本
比如火狐的headless
下载火狐的geckodriver驱动。(当前文件夹下已经有一个了)地址是：
https://github.com/mozilla/geckodriver/releases
下载后解压是一个geckodriver 文件。拷贝到/usr/local/bin目录下，然后加上可执行的权限
sudo chmod +x /usr/local/bin/geckodriver
chrome的headless浏览器
https://chromedriver.storage.googleapis.com/index.html?path=2.35/
你也可以自行搜索chromedriver的下载地址,解压是个可执行文件,放到chrome的目录即可.
一般ubuntu下面,chrome的目录是/opt/google/chrome/
据说使用root权限运行的话,chrome的headless浏览器会报异常.而firefox的headless浏览器不会!
"""
if browser_class == 1:
profile = FirefoxProfile()
profile.set_preference("intl.accept_languages", "zh-cn")
if isinstance(init_args, dict):
for k, v in init_args.items():
profile.set_preference(k, v)
else:
pass
options = FirefoxOptions()
options.add_argument("--headless")
if headless:
try:
browser = Firefox(firefox_profile=profile,
executable_path=firefox_driver,
firefox_options=options)
except Exception as e:
title = "{} Firefox headless浏览器打开失败".format(
datetime.datetime.now())
content = "错误原因是：{}".format(e)
send_mail(title=title, content=content)
logger.exception(e)
raise e
else:
try:
browser = Firefox(
firefox_profile=profile,
executable_path=firefox_driver,
)
except Exception as e:
title = "{} Firefox headless浏览器打开失败".format(
datetime.datetime.now())
content = "错误原因是：{}".format(e)
send_mail(title=title, content=content)
logger.exception(e)
raise e
else:
options = ChromeOptions()
options.add_experimental_option("excludeSwitches",
["ignore-certificate-errors"])
if headless:
options.add_argument("--headless")
try:
browser = Chrome(executable_path=chrome_driver,
chrome_options=options)
except Exception as e:
title = "{} Chrome headless浏览器打开失败".format(
datetime.datetime.now())
content = "错误原因是：{}".format(e)
send_mail(title=title, content=content)
logger.exception(e)
raise e
else:
try:
browser = Chrome(executable_path=chrome_driver,
chrome_options=options)
except Exception as e:
title = "{} Chrome headless浏览器打开失败".format(
datetime.datetime.now())
content = "错误原因是：{}".format(e)
send_mail(title=title, content=content) # 这是我自定义的方法
logger.exception(e)
raise e
return browser
# Selenium com Python #05 - Procurando e interagindo com elementos p.I
# Atributos (Globais, Css, Dom)
# Find (id, class, name)
# Elementos Web (input, form)
from selenium.webdriver import Firefox
driver = Firefox()
url = "https://selenium.dunossauro.live/aula_05_a.html"
driver.get(url)
python = driver.find_element_by_id("python")
haskell = driver.find_element_by_id("haskell")
print(python.text)
print(haskell.text)
def setUp(self):
path = 'C:\\Automation\\geckodriver'
self.driver = Firefox(executable_path=path)
self.driver.implicitly_wait(10)
self.driver.get('https://teatrocolon.org.ar/es')
self.indexPage = PageIndex(self.driver)
from selenium.webdriver import Firefox
import datetime
driver = Firefox()
driver.get("http://orteil.dashnet.org/experiments/cookie/")
cookie = driver.find_element_by_id('cookie')
store_elements = driver.find_elements_by_css_selector("#store div")
check_time = datetime.datetime.now() + datetime.timedelta(seconds=10)
to_reach = datetime.datetime.now() + datetime.timedelta(minutes=5)
while datetime.datetime.now() < to_reach:
cookie.click()
if datetime.datetime.now() >= check_time:
store_prices = driver.find_elements_by_css_selector("#store b")
prices = [
(int("0" +
price.text.strip().split('-')[-1].replace(",", "").strip()),
idx) for idx, price in enumerate(store_prices)
]
prices.sort(reverse=True)
my_money = int("0" + driver.find_element_by_id(
"money").text.strip().split('-')[-1].replace(",", "").strip())
for i in range(len(prices)):
if my_money >= prices[i][0] and prices[i][0]:
store_prices[prices[i][1]].click()
break
def answer_stones_riddle(browser: webdriver.Firefox) -> None:
input1 = browser.find_element_by_id("r1Input")
input1.send_keys("rock")
button1 = browser.find_element_by_id("r1Btn")
button1.click()
def test_file_upload(self, application: str,
ff_browser: webdriver.Firefox):
# Run logout to clean session
ff_browser.get(application + "/logout")
# Open the login page
ff_browser.get(application + "/login")
# Get username and password elements on page
username = ff_browser.find_element_by_name("username")
password = ff_browser.find_element_by_name("password")
# Get submit button element
btnSubmit = ff_browser.find_element_by_xpath(
"/html/body/div[2]/form/input")
# Inject username and password of test user
username.send_keys(username_test)
password.send_keys(password_test)
# Click on submit button
btnSubmit.click()
# Open the create faculty page
ff_browser.get(application + "/create_faculty")
# Get faculty name input
facName = ff_browser.find_element_by_xpath(
"/html/body/div[2]/form/p/input")
# Send value for new faculty
facName.send_keys(newFacTest)
# Get save faculty button
btnSaveFac = ff_browser.find_element_by_xpath(
"/html/body/div[2]/form/input")
# Click on submit button
btnSaveFac.click()
# Get title element
titleSaved = ff_browser.find_element_by_xpath("/html/body/div[2]/h1")
assert (titleSaved.text == "Manage Faculties:")
class TeatroColon(unittest.TestCase):
def setUp(self):
path = 'C:\\Automation\\geckodriver'
self.driver = Firefox(executable_path=path)
self.driver.implicitly_wait(10)
self.driver.get('https://teatrocolon.org.ar/es')
self.indexPage = PageIndex(self.driver)
def test_donaciones(self):
self.driver.find_element_by_css_selector('.nav-entradas').click()
self.assertEqual(
self.driver.find_element_by_css_selector(
'h1.page-header > span:nth-child(1)').text, 'DONACIONES')
def test_busqueda_orquesta(self):
self.indexPage.search('orquesta')
self.driver.find_element_by_css_selector(
'div.item_search:nth-child(4) > span:nth-child(1) > h4:nth-child(1) > strong:nth-child(1) > a:nth-child(1)'
).click()
self.assertEqual(
self.driver.find_element_by_css_selector(
'h1.page-header > span:nth-child(1)').text,
'ORQUESTA FILARMÓNICA DE BUENOS AIRES')
def test_noticias(self):
self.driver.find_element_by_xpath(
'/html/body/div[1]/header/div[2]/div/nav[2]/ul/li[9]/a').click()
self.driver.find_element_by_css_selector('.link-vermas').click()
self.driver.find_element_by_name('categories[23]').click()
self.assertTrue(
'ISATC en Mar del Plata' in self.driver.
find_element_by_partial_link_text('ISATC en Mar del Plata').text)
def tearDown(self):
self.driver.close()
self.driver.quit()
from selenium.webdriver import Firefox
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.support import expected_conditions as expected
from selenium.webdriver.support.wait import WebDriverWait
from selenium.common.exceptions import TimeoutException
import time
text = raw_input()
if __name__ == "__main__":
options = Options()
options.add_argument('-headless')
driver = Firefox(executable_path='geckodriver', firefox_options=options)
try:
driver.get('https://www.ncts.ie/1263')
driver.find_element_by_xpath("//button[@id='CloseCookie']").click()
driver.refresh()
nctInput=driver.find_element_by_xpath("//input[@name='RegistrationID']")
nctInput.clear()
nctInput.send_keys(text+ Keys.ENTER )
WebDriverWait(driver, 10).until(expected.presence_of_element_located((By.ID, "confirmVehicleYes")))
driver.find_element_by_xpath("//input[@id='confirmVehicleYes']").send_keys(Keys.ENTER)
WebDriverWait(driver, 10).until(expected.presence_of_element_located((By.ID, "tab3")))
print (driver.find_element_by_xpath('//*[@id="tab3"]/form[1]/div[2]/div[1]/div[1]/table/tbody/tr[1]/td').text)
except TimeoutException as ex:
print 'Invalid reg plate/Script crash'
isrunning = 0
driver.quit()
driver.quit()
def test_case_firefox():
path = ".\Driver\geckodriver.exe"
driver = Firefox(executable_path=path)
driver.get("http://www.theTestingWorld.com/testings")
# Maximize browser
driver.maximize_window()
# Enter Data to the textbox
driver.find_element_by_name("fld_username").send_keys("helloworld")
driver.find_element_by_xpath("//input[@name='fld_email']").send_keys(
"*****@*****.**")
driver.find_element_by_name("fld_password").send_keys("abcd123")
driver.find_element_by_name("fld_cpassword").send_keys("abcd123")
driver.find_element_by_name("fld_username").clear()
driver.find_element_by_name("fld_username").send_keys("abcd123")
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from time import sleep
class SearchElement:
def __init__(self, locator):
self.locator = locator
def __call__(self, webdriver):
print(f'Searching for {self.locator}')
if webdriver.find_elements(*self.locator):
return True
return False
driver = Firefox()
driver_wait = WebDriverWait(driver, 10, poll_frequency=0.5)
driver.get('https://selenium.dunossauro.live/exercicio_10.html')
driver.maximize_window()
# preencher formulario
driver.find_element_by_css_selector('input#todo-name').send_keys('Lavar o carro')
driver.find_element_by_css_selector('textarea#todo-desc').send_keys('Usando agua e sabão e fechando a tonerira para n gastar agua')
driver.find_element_by_css_selector('button#todo-submit').click()
# moving Todo to doing
locator = (By.CSS_SELECTOR, 'div.body_a fieldset div div')
driver_wait.until(
SearchElement(locator),
'Não achou a div'
)
from selenium.webdriver import Firefox
from time import sleep
from urllib.parse import urlparse
from json import loads
url = 'http://selenium.dunossauro.live/aula_05.html'
firefox = Firefox()
firefox.get(url)
def preenche_form(browser, nome, email, senha, telefone):
browser.find_element_by_name("nome").send_keys(nome)
browser.find_element_by_name("email").send_keys(email)
browser.find_element_by_name("senha").send_keys(senha)
browser.find_element_by_name("telefone").send_keys(telefone)
browser.find_element_by_name("btn").click()
sleep(2)
estrutura = {
'nome': 'Miquéias',
'email': '*****@*****.**',
'senha': '124',
'telefone': '987654321'
}
preenche_form(firefox, **estrutura)
def setUp(self):
self.driver = Firefox(
executable_path='/Users/reginameshkova/Desktop/mine/geckodriver')
from selenium.webdriver import Firefox
from selenium.webdriver.firefox.options import Options
opts = Options()
browser = Firefox(options=opts)
browser.get('https://bandcamp.com')
#browser.find_element_by_class_name('play-btn').click()
tracks = browser.find_elements_by_class_name('discover-item')
#print(len(tracks))
#tracks[2].click()
discover_results = browser.find_element_by_class_name('discover-result')
print(tracks[2].text)
browser.close()
quit()
