class AddAToDoText(unittest.TestCase):
def setUp(self):
options = EdgeOptions()
options.use_chromium = True
options.binary_location = "C:\\Program Files (x86)\\Microsoft\\Edge Dev\\Application\\msedge.exe"
dir = os.path.dirname(os.path.realpath(__file__))
edge_driver_path = dir + "\\edgedriver_win64\\msedgedriver.exe"
self.service = Service(edge_driver_path)
self.service.start()
self.driver = Edge(options=options, service=self.service)
self.driver.implicitly_wait(30)
self.driver.maximize_window()
self.driver.get("http://*****:*****@class='toggle']/following-sibling::label").get_attribute(
"innerText")
self.assertEqual("The test is adding this todo", addedToDoText)
def tearDown(self):
self.driver.quit()
self.service.stop()
class HeaderText(unittest.TestCase):
def setUp(self):
options = EdgeOptions()
options.use_chromium = True
options.binary_location = "C:\\Program Files (x86)\\Microsoft\\Edge Dev\\Application\\msedge.exe"
dir = os.path.dirname(os.path.realpath(__file__))
edge_driver_path = dir + "\\edgedriver_win64\\msedgedriver.exe"
self.service = Service(edge_driver_path)
self.service.start()
self.driver = Edge(options=options, service=self.service)
self.driver.implicitly_wait(30)
self.driver.maximize_window()
self.driver.get("http://localhost:4200")
def test_HeaderText(self):
headerText = self.driver.find_element(By.CSS_SELECTOR,
"h1").get_attribute("innerText")
self.assertEqual("todos", headerText)
def tearDown(self):
self.driver.quit()
self.service.stop()
def getcomponies():
"""
Get Companies from web and write to excel file
:return:
"""
_bases.kill_web_driver_edge()
driver = Edge()
componies = []
driver.get('https://www.dosab.org.tr/Alfabetik-Firmalar-Listesi')
# Get links
# links = []
# datalinks = driver.find_elements(By.XPATH, '/html/body/div[2]/div/ul/li/div/a')
# for link in datalinks:
# linkobj = {
# 'link': link.get_attribute('href'),
# 'name': link.text
# }
# links.append(linkobj)
# Downlaod Mail Images
# for complink in componies:
# parsedlink = str(complink['link']).split('/')
# mailimg = f'https://www.dosab.org.tr/dosyalar/emailler/{parsedlink[4]}_EMail.jpg'
# wget.download(mailimg, "imgs")
# OCR Image to text
pytesseract.pytesseract.tesseract_cmd = r'C:\Users\abdul\AppData\Local\Tesseract-OCR\tesseract.exe'
imgfiles = os.listdir('imgs')
imgfiles.sort()
for imgfile in imgfiles:
compid = imgfile.split('_EMail.jpg')[0]
driver.get(f'https://www.dosab.org.tr/Firma/{compid}')
compname = driver.find_element(By.XPATH,
'/html/body/div[2]/div/div[2]/h4').text
img = cv2.imread(f'imgs/{imgfile}')
emailtext = str(pytesseract.image_to_string(img, lang='eng')).replace(
'\n\f', '')
if '@' not in emailtext:
emailtext = ''
company = {'mail': emailtext, 'name': compname}
componies.append(company)
workbook = Workbook(excel_file_name)
worksheet = workbook.add_worksheet('dosab')
row = 0
hformat = workbook.add_format()
hformat.set_bold()
worksheet.write(row, 0, "Firma Adi", hformat)
worksheet.write(row, 1, 'Mailler', hformat)
row += 1
for comp in componies:
worksheet.write(row, 0, comp["name"])
if '@' in comp['mail']:
worksheet.write(row, 1, comp['mail'])
row += 1
workbook.close()
driver.close()
class SeleniumRuntime:
"""
This class works like a singleton containing a single instance of the browser environment
Attributes:
logger: logger instance gathered from logging module, acts like a singleton
"""
def __init__(self):
self.logger = logging.getLogger(LOGGER_INSTANCE)
if TARGET_BROWSER == 'chrome':
self.browser = Chrome()
elif TARGET_BROWSER == 'firefox':
self.browser = Firefox()
elif TARGET_BROWSER == 'edge':
self.browser = Edge()
def go_to_page(self, url):
self.browser.get(url)
def submit_form(self):
form = self.browser.find_element_by_tag_name('form')
form.submit()
def fill_form(self, table):
for field, value in table.items():
element = self.browser.find_element_by_id(field)
element.clear()
element.send_keys(value)
def fill_selects(self, table):
for field_name, field_value in table.items():
self.wait_for_element(field_value, By.XPATH).click()
def click(self, value, by=By.ID):
element = self.browser.find_element(by, value)
element.click()
def get_element(self, value, by=By.ID):
return self.browser.find_element(by, value)
def get_elements(self, value, by=By.ID):
return self.browser.find_elements(by, value)
def assert_presence(self, value, by=By.ID):
try:
self.browser.find_element(by, value)
return True
except NoSuchElementException:
return False
def back(self):
self.browser.back()
def forward(self):
self.browser.forward()
def refresh(self):
self.browser.refresh()
def current_title(self):
return self.browser.title
def current_url(self):
return self.browser.current_url
def wait_for_element(self, value, by=By.ID, timeout=30):
return WebDriverWait(self.browser, timeout).until(
expected_conditions.presence_of_element_located((by, value)))
def wait_for_redirect(self, target_url, timeout=30):
return WebDriverWait(self.browser, timeout).until(
expected_conditions.url_to_be(target_url))
@staticmethod
def assert_class(element, class_name):
class_attr = element.get_attribute('class')
return class_attr.find(class_name) >= 0
@staticmethod
def assert_attribute(element, attribute_name, attribute_value):
attr_value = element.get_attribute(attribute_name)
return attr_value.find(attribute_value) >= 0
def getcomponies():
"""
Get Companies from web and write to excel file
:return:
"""
_bases.kill_web_driver_edge()
driver = Edge()
componies = []
driver.get('https://www.nosab.org.tr/firmalar/tr')
alphabetslinks = []
for links in driver.find_elements(By.XPATH, '//*[@id="accordion-2"]/li/a'):
link = {
'Sector': links.text,
'Name': links.get_attribute('href')
}
alphabetslinks.append(link)
for anchor in alphabetslinks:
driver.get(anchor['Name'])
companies_sector = {
'Sector': anchor['Sector'],
'comps': []
}
componies_count = len(driver.find_elements(By.XPATH, '/html/body/div[7]/div/div[2]/div[3]/ul/li/a'))
for indx in range(1, componies_count + 1):
comp = driver.find_element(By.XPATH, f'/html/body/div[7]/div/div[2]/div[3]/ul/li[{indx}]/a')
comp.click()
companies_sector['Sector'] = anchor['Sector']
company = {
'Name': driver.find_element(By.XPATH, '/html/body/div[7]/div/div[2]/div[1]/div').text,
'Data': str(driver.find_element(By.XPATH, '/html/body/div[7]/div/div[2]/div[4]').text)
}
companies_sector['comps'].append(company)
driver.back()
componies.append(companies_sector)
row = 0
workbook = Workbook(excel_file_name)
worksheet = workbook.add_worksheet('nosab')
hformat = workbook.add_format()
hformat.set_bold()
hformat.set_align('center')
hformat.set_align('vcenter')
worksheet.write(row, 0, 'Firma Adi', hformat)
worksheet.set_column('A:A', 100)
worksheet.write(row, 1, 'Bilgileri', hformat)
worksheet.set_column('B:B', 120)
row += 1
fwarp = workbook.add_format()
fwarp.set_text_wrap()
fname_centralize = workbook.add_format()
fname_centralize.set_align('center')
for company in componies:
if 'Sector' in company:
worksheet.write(row, 0, company['Sector'], hformat)
row += 1
if 'comps' in company:
for comp in company['comps']:
if 'Name' in comp:
worksheet.write(row, 0, comp['Name'], fname_centralize)
if 'Data' in comp:
worksheet.write(row, 1, comp['Data'], fwarp)
row += 1
if os.path.exists(excel_file_name):
os.remove(excel_file_name)
time.sleep(_bases.timeout)
workbook.close()
driver.close()
def get_componies():
"""
Get Companies from web and write to excel file
:return:
"""
_bases.kill_web_driver_edge()
driver = Edge()
componies = []
driver.get('https://bursaderiosb.com/uyeler')
componies_data = driver.find_elements(
By.XPATH, '//*[@id="main"]/div/div/div[2]/div')
compscount = None
if len(componies_data) > 0:
compscount = len(componies_data)
for i in range(1, compscount):
company_anchor = driver.find_element(
By.XPATH, f'//*[@id="main"]/div/div/div[2]/div[{i}]/div[2]/a')
company_anchor.click()
company = {
'Name':
driver.find_element(By.XPATH,
'//*[@id="main"]/div/div/div[1]').text,
}
company_data = str(
driver.find_element(
By.XPATH,
'//*[@id="main"]/div/div/div[2]/div').text).split('\n')
for compdata in company_data:
mailstr = 'Mail:'
if compdata.startswith(mailstr):
company['Mail'] = compdata.split(mailstr)[1]
phonestr = 'Telefon:'
if compdata.startswith(phonestr):
company['Tel'] = compdata.split(phonestr)[1]
componies.append(company)
driver.back()
# region > Write to excel
row = 0
workbook = Workbook(excel_file_name)
worksheet = workbook.add_worksheet('Bursa Deri OSB')
hformat = workbook.add_format()
hformat.set_bold()
hformat.set_align('center')
hformat.set_align('vcenter')
worksheet.write(row, 0, 'Firma Adi', hformat)
worksheet.write(row, 1, 'Mail Adresi', hformat)
worksheet.write(row, 2, 'Telefon', hformat)
worksheet.set_column('A:A', 100)
worksheet.set_column('B:B', 80)
worksheet.set_column('C:C', 50)
row += 1
for cmpy in componies:
if 'Name' in cmpy:
worksheet.write(row, 0, str(cmpy['Name']))
if 'Mail' in cmpy:
worksheet.write(row, 1, str(cmpy['Mail']))
if 'Tel' in cmpy:
worksheet.write(row, 2, str(cmpy['Tel']))
row += 1
if os.path.exists(excel_file_name):
os.remove(excel_file_name)
workbook.close()
# endregion
time.sleep(3)
driver.quit()