def run():
email = read_decrypt(efile)
password = read_decrypt(pfile)
cemail = str(email)
cpassword = str(password)
print(cemail)
print(cpassword)
with open("browserdetails.txt", "r") as f:
data = [line.rstrip('\n') for line in f]
browser = data[0].lower()
gpu = data[1].lower()
if browser == 'edge':
try:
requests.get("http://www.google.com")
print('Connection Found')
options = EdgeOptions()
options.use_chromium = True
options.add_argument("--start-maximized")
if gpu == 'no':
options.add_argument("window-size=1920,1080")
options.add_argument("--headless")
options.add_argument("disable-gpu")
options.add_argument("-inprivate")
driver = Edge(executable_path='msedgedriver.exe', options=options)
driver.get('https://gokano.com/')
try:
email = WebDriverWait(driver, 3).until(
EC.presence_of_element_located((By.NAME, 'email')))
print("Page is ready!")
email.send_keys(cemail)
password = driver.find_element_by_name('password')
password.send_keys(cpassword)
time.sleep(3)
button = driver.find_element_by_class_name('submit')
button.click()
print('Login sucessful')
except TimeoutException:
print("Error logining in") #[email protected]
time.sleep(3)
driver.quit()
time.sleep(3)
try:
cdp = driver.find_element_by_link_text('Collect daily points')
cdp.click()
write_time()
time.sleep(3)
driver.quit()
except NoSuchElementException:
print('Already collected')
time.sleep(3)
driver.quit()
print('Automation completed')
time.sleep(3)
driver.quit()
except requests.ConnectionError:
print('Could not connect')
username = driver.find_element_by_xpath('//input[@name="session[username_or_email]"]')
username.send_keys(user)
password = driver.find_element_by_xpath('//input[@name="session[password]"]')
password.send_keys(my_password)
password.send_keys(Keys.RETURN)
sleep(1)
# find search input and search for term
search_input = driver.find_element_by_xpath('//input[@aria-label="Search query"]')
search_input.send_keys(search_term)
search_input.send_keys(Keys.RETURN)
sleep(1)
# navigate to historical 'latest' tab
driver.find_element_by_link_text('Latest').click()
# get all tweets on the page
tweet_ids = set()
last_position = driver.execute_script("return window.pageYOffset;")
scrolling = True
while scrolling:
page_cards = driver.find_elements_by_xpath('//div[@data-testid="tweet"]')
for card in page_cards[-15:]:
if card is not None:
tweet = get_tweet_data(card)
if tweet is not None:
tweetL = list(tweet)
tweetL.append(x)
tweetL.append(j)
tweet = tuple(tweetL)
def run():
email = read_decrypt(efile)
password = read_decrypt(pfile)
cemail = str(email)
cpassword = str(password)
with open("browserdetails.txt", "r") as f:
data = [line.rstrip('\n') for line in f]
browser = data[0].lower()
gpu = data[1].lower()
if browser == 'edge':
try:
requests.get("http://www.google.com")
print('Connection Established.')
l1 = tk.Label(top, text=" Connection Established. ", bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
options = EdgeOptions()
options.use_chromium = True
options.add_argument("--start-maximized")
if gpu == 'no':
options.add_argument("window-size=1920,1080")
options.add_argument("--headless")
options.add_argument("disable-gpu")
options.add_argument("-inprivate")
driver = Edge(resource_path('msedgedriver.exe'), options=options)
driver.get('https://gokano.com/')
try:
email = WebDriverWait(driver, 3).until(
EC.presence_of_element_located((By.NAME, 'email')))
print("Page is ready!")
l1 = tk.Label(top,
text=" Page is Ready. ",
bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
email.send_keys(cemail)
password = driver.find_element_by_name('password')
password.send_keys(cpassword)
time.sleep(3)
button = driver.find_element_by_class_name('submit')
button.click()
try:
driver.find_element_by_class_name('gokan-alert-error')
print("Invalid Credintials")
l1 = tk.Label(top,
text=" Invalid Credintials. ",
bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
time.sleep(3)
driver.quit()
except NoSuchElementException:
print('Login sucessful')
l1 = tk.Label(top, text=" Login Successful. ", bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
except TimeoutException:
print("Login Error!")
l1 = tk.Label(top, text=" Login Error! ", bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
# [email protected]
time.sleep(3)
driver.quit()
time.sleep(3)
try:
cdp = driver.find_element_by_link_text('Collect daily points')
cdp.click()
write_time()
time.sleep(3)
driver.quit()
except NoSuchElementException:
print('Already collected')
l1 = tk.Label(top,
text=" Points Already Collected. ",
bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
time.sleep(3)
driver.quit()
print('Automation completed')
l1 = tk.Label(top, text=" Automation Completed. ", bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
time.sleep(3)
write_time()
driver.quit()
except requests.ConnectionError:
print('Could not connect')
l1 = tk.Label(top, text=" Couldn't Connect. ", bg='white')
l1.config(font=('helvetica', 15, "bold"))
canvas.create_window(200, 410, window=l1)
driver.quit()
def scrape(secure=False):
options = EdgeOptions()
options.use_chromium = True
driver = Edge(options=options)
query = input("▁ ▂ ▄ ▅ ▆ ▇ █ 𝐄𝐧𝐭𝐞𝐫 𝐭𝐡𝐞 𝐓𝐞𝐱𝐭 𝐭𝐨 𝐬𝐞𝐚𝐫𝐜𝐡 █ ▇ ▆ ▅ ▄ ▂ ▁\n\n ")
print("\n𝘚𝘵𝘢𝘳𝘵𝘦𝘥 𝘚𝘤𝘳𝘢𝘱𝘪𝘯𝘨 ↦↦↦↦↦↦↦↦↦↦")
print("\nPlease Wait ............\n")
driver.get("https://www.twitter.com/login")
driver.maximize_window()
username = driver.find_element_by_xpath(
'//input[@name="session[username_or_email]"]')
username.send_keys("*****@*****.**")
#password=getpass()
userpas = driver.find_element_by_xpath(
'//input[@name="session[password]"]')
userpas.send_keys('-----')
userpas.send_keys(Keys.RETURN)
sleep(2)
if secure:
username = driver.find_element_by_xpath(
'//input[@name="session[username_or_email]"]')
username.send_keys("031-----")
userpas = driver.find_element_by_xpath(
'//input[@name="session[password]"]')
userpas.send_keys('----')
userpas.send_keys(Keys.RETURN)
sleep(2)
search = driver.find_element_by_xpath(
'//input[@aria-label="Search query"]')
search.send_keys('"پاک فوج" lang:ur -filter:links filter:replies')
search.send_keys(Keys.RETURN)
sleep(1.5)
driver.find_element_by_link_text("Latest").click()
data = []
tweet_ids = set()
last_position = driver.execute_script("return window.pageYOffset;")
scrolling = True
while scrolling:
posts = driver.find_elements_by_xpath('//div[@data-testid="tweet"]')
for post in posts[-15:]:
tweet = scrap_tweets(post)
if tweet:
tweet_id = "".join(tweet)
if tweet_id not in tweet_ids:
tweet_ids.add(tweet_id)
data.append(tweet)
scroll_attempt = 0
while True:
driver.execute_script(
"window.scrollTo(0,document.body.scrollHeight);")
sleep(1)
curr_position = driver.execute_script("return window.pageYOffset;")
if last_position == curr_position:
scroll_attempt += 1
if scroll_attempt >= 3:
scrolling = False
break
else:
sleep(2)
else:
last_position = curr_position
break
return data
curtidas_num = card.find_element_by_xpath(
'.//div[@data-testid="like"]').text
tweet = (apelido, username, data_postagem, respondendo, comentario,
link_img, comentarios_num, retweets_num, curtidas_num)
return tweet
options = EdgeOptions()
options.use_chromium = True
options.headless = True
driver = Edge(options=options)
driver.get('https://twitter.com/search?q=vacina&src=typed_query')
driver.find_element_by_link_text('Mais recentes').click()
data = []
tweet_ids = set()
last_position = driver.execute_script("return window.pageYOffset;")
scrolling = True
scroll_attempt = 0
i = 0
while scrolling:
page_cards = driver.find_elements_by_xpath('//div[@data-testid="tweet"]')
for card in page_cards[-15:]:
tweet = get_tweet_data(card)
if tweet:
tweet_id = ''.join(tweet)
if tweet_id not in tweet_ids:
tweet_ids.add(tweet_id)
def main():
args = sys.argv
f = open(args[4], "r")
Lines = f.readlines()
names, profession, nationality, job = [], [], [], []
for line in Lines:
array = line.split(",")
names.append(array[0])
profession.append(array[1])
nationality.append(array[2])
job.append(array[3].replace("\n", ""))
for name in names:
print("Query:", name, ".\nProcessing...")
user = '******'
search_term = f'{name} filter:verified'
options = EdgeOptions()
options.use_chromium = True
driver = Edge(options=options)
driver.get('https://www.twitter.com/login')
driver.maximize_window()
sleep(2)
username = driver.find_element_by_xpath(
'//input[@name="session[username_or_email]"]')
username.send_keys(user)
password = driver.find_element_by_xpath(
'//input[@name="session[password]"]')
password.send_keys('donkey123')
password.send_keys(Keys.RETURN)
sleep(1)
search_input = driver.find_element_by_xpath(
'//input[@aria-label="Search query"]')
search_input.send_keys(search_term)
search_input.send_keys(Keys.RETURN)
sleep(1)
driver.find_element_by_link_text('People').click()
sleep(3)
driver.find_element_by_xpath(
'//div[@class="css-1dbjc4n r-j7yic r-qklmqi r-1adg3ll r-1ny4l3l"]'
).click()
sleep(3)
data = []
tweet_data = []
start = 0
end = 500
for i in range(0, 5):
sleep(1)
cards = driver.find_elements_by_xpath(
'//div[@data-testid="tweet"]')
card = cards[i]
tweet = get_tweet_data(card)
for card in cards:
data = get_tweet_data(card)
if data:
tweet_data.append(data)
driver.execute_script(f'window.scrollTo({start},{end});')
start += 500
end += 500
driver.close()
tweets = set(tweet_data)
write_to_csv(name, tweets)
df = pd.read_csv(f'{name}.csv')
Twitter_sentiment = Twitter_sentiment_model(df)
Twitter_toxic = Twitter_toxic_model(df)
Big5 = Big5_model(df)
create_report(name, tweets, Twitter_sentiment, Twitter_toxic, Big5)
