def up(name, ema, pas):
browser = TorBrowserDriver(tbb_dir, tor_cfg=cm.USE_STEM)
# connect to site
browser.load_url(
"https://www.udemy.com/join/signup-popup/?locale=en_US&response_type=html&next=https%3A%2F%2Fwww.udemy.com%2F",
wait_on_page=5,
wait_for_page_body=True)
# find link button
#reg_el = browser.find_element_by_link_text("Sign up")
# https://www.udemy.com/join/login-popup/?locale=en_US&response_type=html&next=https%3A%2F%2Fwww.udemy.com%2F
# click
# reg_el.click()
# enter full name
full_name = browser.find_element_by_id("id_fullname")
full_name.send_keys(name)
# enter email
email_el = browser.find_element_by_id("email--1")
email_el.send_keys(ema)
# enter password
pass_el = browser.find_element_by_id("password")
pass_el.send_keys(pas)
# Scroll
browser.execute_script("window.scrollBy(0,200)")
browser.execute_script(
'document.getElementById("id_subscribe_to_emails").checked = false')
# find submit link
sub_el = browser.find_element_by_id('submit-id-submit')
# click submit
sub_el.click()
sleep(1)
# check
if 'occupation' in browser.current_url:
# find submit link
sleep(3)
try:
browser.execute_script(
'document.getElementsByClassName("ot-sdk-container").sytle.display = "none"'
)
except:
pass
cl = browser.find_elements_by_class_name("udlite-btn")
try:
cl[0].click()
except:
browser.execute_script(
'document.getElementsByClassName("ot-sdk-container").sytle.display = "none"'
)
cl[0].click()
sleep(3)
browser.close()
return True
if '=1' in browser.current_url:
browser.close()
return True
class TruliaHelper():
def __init__(self):
self.url = 'https://www.trulia.com'
# need to set chrome path here.
tbpath = "/home/XX/XXXX/tor-browser-linux64-8.0.8_en-US/tor-browser_en-US"
self.driver = TorBrowserDriver(tbb_path=tbpath, tbb_logfile_path='test.log')
# self.driver = webdriver.Firefox(firefox_profile=profile, firefox_binary=binary)
# self.driver = webdriver.Chrome(executable_path='../utility/chromedriver.exe', chrome_options=chrome_options)
# method to get items from given link.
def getItems(self):
df=pd.read_excel("/home/XXXXX/XXXXX/XXXXXX.xlsx")
a=df['Site Address']
b=df['Site City']
c=df['Site State']
d=df['Site Zip']
items = []
# keywords = ['512 W 10th St Perris CA 92570', 'New York, NY', 'San Francisco, CA', 'Washington, CA']
for keyword in (pd.concat([a,b,c,d],axis=1)).values.tolist():
# keywords = ['512 W 10th St Perris CA 92570'] * 10
# for keyword in keywords:
self.driver.get(self.url)
search_box = self.driver.find_element_by_id("homepageSearchBoxTextInput")
search_box.clear()
search_box.send_keys(str(keyword))
search_btn = self.driver.find_element_by_xpath("//button[@data-auto-test-id='searchButton']")
if search_btn:
search_btn.click()
time.sleep(10)
items.append(self.getItemDetail())
# break
self.driver.close()
return items
def getItemDetail(self):
data = {}
try:
soup = BeautifulSoup(self.driver.page_source, u'html.parser')
#image = soup.find("div", attrs={"class": "Tiles__TileBackground-fk0fs3-0 cSObNX"}).find("img")["src"]
price = soup.find("div", attrs={"class": "Text__TextBase-sc-1cait9d-0-div Text__TextContainerBase-sc-1cait9d-1 hlvKRM"}).text
# container = soup.find("div", attrs={"class": "resultsColumn"}).find("ul")
# items = container.findAll("li", recursive=False)
print(price)
except:
pass
return data
# method to start process.
def start(self):
items = self.getItems()
print("Items : ",items)
def loggin(ema, pas):
try:
browser = TorBrowserDriver(tbb_dir, tor_cfg=cm.USE_STEM)
except:
# selenium.common.exceptions.WebDriverException: Message: Access is denied. (os error 5)
# mozilla is updating
print('probably updating sleep 30')
sleep(30)
browser = TorBrowserDriver(tbb_dir, tor_cfg=cm.USE_STEM)
# connect to site
try:
browser.load_url(
"https://www.udemy.com/join/login-popup/?locale=en_US&response_type=html&next=https%3A%2F%2Fwww.udemy.com%2F",
wait_on_page=5,
wait_for_page_body=True)
except:
# selenium.common.exceptions.NoSuchWindowException: Message: Browsing context has been discarded
try:
browser = TorBrowserDriver(tbb_dir, tor_cfg=cm.USE_STEM)
except:
# selenium.common.exceptions.WebDriverException: Message: Access is denied. (os error 5)
# mozilla is updating
print('probably updating sleep 30')
sleep(30)
browser = TorBrowserDriver(tbb_dir, tor_cfg=cm.USE_STEM)
browser.load_url(
"https://www.udemy.com/join/login-popup/?locale=en_US&response_type=html&next=https%3A%2F%2Fwww.udemy.com%2F",
wait_on_page=5,
wait_for_page_body=True)
# reg_el.click()
# maximise
browser.maximize_window()
# Scroll
browser.execute_script("window.scrollTo(0,100)")
try:
email_el = browser.find_element_by_id("email--1")
except:
sleep(10)
try:
email_el = browser.find_element_by_id("email--1")
except:
return False
email_el.send_keys(ema)
# enter password
pass_el = browser.find_element_by_id("id_password")
pass_el.send_keys(pas)
# find submit link
sub_el = browser.find_element_by_id('submit-id-submit')
# click submit
sub_el.click()
sleep(2)
# check
try:
avatar = browser.find_element_by_id('u711-popover-trigger--18')
except:
avatar = None
if avatar:
return browser
elif 'udemy.com' in browser.current_url:
return browser
else:
return None
class TruliaHelper():
def __init__(self):
self.url = 'https://www.trulia.com'
# need to set Tor Browser path here.
tbpath = "/home/gc14/Documents/softwares/tor-browser_en-US"
self.driver = TorBrowserDriver(tbb_path=tbpath,
tbb_logfile_path='test.log')
# self.driver = webdriver.Firefox(firefox_profile=profile, firefox_binary=binary)
# self.driver = webdriver.Chrome(executable_path='../utility/chromedriver.exe', chrome_options=chrome_options)
# method to get items from given link.
def getItems(self):
items = []
# keywords = ['512 W 10th St Perris CA 92570', 'New York, NY', 'San Francisco, CA', 'Washington, CA']
keywords = ['512 W 10th St Perris CA 92570'] * 2
for keyword in keywords:
self.driver.get(self.url)
search_box = self.driver.find_element_by_id(
"homepageSearchBoxTextInput")
search_box.clear()
search_box.send_keys(keyword)
search_btn = self.driver.find_element_by_xpath(
"//button[@data-auto-test-id='searchButton']")
if search_btn:
print("Going to click")
search_btn.click()
time.sleep(10)
items.append(self.getItemDetail())
self.driver.close()
return items
def getItemDetail(self):
data = {}
try:
soup = BeautifulSoup(self.driver.page_source, u'html.parser')
image = soup.find("div",
attrs={
"class":
"Tiles__TileBackground-fk0fs3-0 cSObNX"
}).find("img")["src"]
price = soup.find(
"div",
attrs={
"class":
"Text__TextBase-sc-1cait9d-0-div Text__TextContainerBase-sc-1cait9d-1 hlvKRM"
}).text
# container = soup.find("div", attrs={"class": "resultsColumn"}).find("ul")
# items = container.findAll("li", recursive=False)
data.update({"image": image, "price": price})
except:
pass
return data
# method to write csv file
def writeCSVFile(self, data):
try:
with open(
'/home/gc14/Documents/fiverr/custom_scrapers/home/trulia.csv',
mode='w') as csv_file:
fieldnames = ['Image', 'Price']
writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
writer.writeheader()
for d in data:
writer.writerow({'Image': d['image'], 'Price': d['price']})
csv_file.close()
print("File written successfully.")
except:
print(sys.exc_info())
pass
# method to start process.
def start(self):
items = self.getItems()
print("Items : ", len(items))
if items:
self.writeCSVFile(items)
