def read_records_to_list(txt_file,
encoding='utf-8',
file_not_found_error=False,
exit_all=True):
records = []
message = ''
error_text = ''
error_def = False
try:
file = open(txt_file, 'r', encoding=encoding) # latin-1 | utf-8
for line in file:
line = line.replace('\n', '')
records.append(line)
file.close()
except FileNotFoundError:
if file_not_found_error:
error_def = True
message = "--> File coulnd't be found in folder. --> '%s'" % txt_file
error_text = None
except Exception as e:
error_def = True
message = '--> An error occurred while reading file. --> "%s"' % txt_file
error_text = e
if error_def:
Progress.exit_app(message=message, e=error_text, exit_all=exit_all)
return records
def check_run(program_code, program='', reload_time=30, sound_error=True):
# This def checks API and get the value of 'program_code'.
# if program_code is True, def returns
# else, def stucks untill program_code comes as True.
message_pasted = False
length_of_last_message = 0
length_of_last_message_MAX = 0
while True:
try:
run = connect_api(
code=program_code, program=program
) # Mostly returns True or False Boolean up to what you set on API
if run != True: # run only if "run" is True.
run = None
except Exception as e:
run = None
if run:
if message_pasted:
# If there was "False calistir" and 'count down' printed,
# paste space as much as pasted text before.
# Because after pyinstaller execution, print flush prints in bad view.
message = 'Program is working now.'
length_of_new_message = len(message)
if length_of_last_message - length_of_new_message > 0:
message = message + ' ' * (length_of_last_message_MAX -
length_of_new_message)
print("\r%s" % message, flush=True, end="")
print()
print('-' * 40)
print()
# Continue to run main program (RETURN DEF)
break
else:
if not message_pasted:
print()
print('-' * 10)
print()
if sound_error:
Progress.sound_notify()
message_pasted = True
now = time.time()
time.sleep(0.01)
message = ''
while time.time() - now < reload_time:
remaining_time = int(reload_time - (time.time() - now))
net_time_string = Progress.time_definition(remaining_time)
message = '--> An error occurred while running program. Trying again in %s.' % net_time_string
print("\r%s" % message, flush=True, end="")
time.sleep(1)
length_of_last_message = len(message)
if length_of_last_message_MAX < length_of_last_message:
length_of_last_message_MAX = length_of_last_message
def create_folder(folder_name, path='./', exit_all=True):
folder_name = windows_folder_name(folder_name)
path = path + folder_name
try:
if not os.path.exists(path):
os.mkdir(path)
return True
except Exception as e:
message = '--> An error occurred while creating folder. Please try again with running program as administrator or create folder by yourself.\n' \
'Folder Name: %s' % folder_name
Progress.exit_app(message=message, e=e, exit_all=exit_all)
return False
def save_records_list(txt_file, records_list, overwrite=False, exit_all=True):
try:
if overwrite:
file = open(txt_file, 'w', encoding='utf-8')
else:
file = open(txt_file, 'a', encoding='utf-8')
for record in records_list:
file.write('%s\n' % record)
file.close()
except Exception as e:
message = '--> An error occurred while creating file. --> "%s"' % txt_file
Progress.exit_app(message=message, e=e, exit_all=exit_all)
def turn_off_all_alerts(browser, accept=True, show_error=False, sound_for_error=False, exit_all=False):
# options.add_argument("--disable-popup-blocking") # This is argument for selenium browser to block everything
try:
alert = browser.switch_to.alert
if accept:
alert.accept()
else:
alert.dismiss()
except Exception as e:
if sound_for_error:
Progress.sound_notify()
if show_error:
Progress.exit_app(e=e, exit_all=exit_all)
def save_dict_with_pprint_pformat(file, dict_as_string, exit_all=False):
if isinstance(dict_as_string, str):
try:
file_name, file_extension = os.path.splitext(file)
if file_extension != '.txt':
file = file_name + '.txt'
dict_as_string_list = dict_as_string.split('\n')
save_records_list(file,
dict_as_string_list,
overwrite=True,
exit_all=exit_all)
except Exception as e:
message = '--> An error occurred while creating file. --> "%s"' % file
Progress.exit_app(message=message, e=e, exit_all=exit_all)
def scroll_div(num):
xpath_scroll_elem = '//div[contains(@role, "dialog")]//div/ul/..'
class_scroll = browser.find_element_by_xpath(
xpath_scroll_elem).get_attribute('class')
jscommand = """
followers = document.querySelector(".%s");
followers.scrollTo(0, followers.scrollHeight);
var lenOfPage=followers.scrollHeight;
return lenOfPage;
""" % class_scroll
lenOfPage = browser.execute_script(jscommand)
match = False
now = time.time()
time.sleep(0.01)
count = 0
fetched = False
while (match == False):
lastCount = lenOfPage
time.sleep(1)
lenOfPage = browser.execute_script(jscommand)
num_current_follows = len(
browser.find_elements_by_xpath(
"//a[contains(@class,'notranslate')]"))
if lastCount == lenOfPage:
if num > num_current_follows:
fetched = False
else:
match = True
else:
fetched = True
if fetched:
count = 0
else:
count += 1
Progress.progress(count=num_current_follows,
total=num,
now=now,
message='Fetching...')
if count > 15:
print(
'\n--> It has been too long time that program could not fetch new data. Now will ignore and continue to process.'
)
match = True
def save_records_data(txt_file,
val_list,
message='File updating...',
exit_all=True):
# This def is for saving data with columns like excel but into the txt file
try:
print(message)
file = open(txt_file, 'a', encoding='utf-8')
for val in val_list:
file.write(str(val))
file.write('\n')
file.write('-' * 20)
file.write('\n')
file.write('-' * 40)
file.write('\n')
file.close()
print('File saved.')
except Exception as e:
message = '--> An error occurred while saving file.'
Progress.exit_app(message=message, e=e, exit_all=exit_all)
def dump_data(file, data, exit_all=False):
try:
if isinstance(data, dict) or isinstance(data, list):
file_name, file_extension = os.path.splitext(file)
if file_extension != '.pickle':
file = file_name + '.pickle'
pickle_out = open(file, "wb")
pickle.dump(data, pickle_out)
pickle_out.close()
# elif isinstance(data, list):
# file_name, file_extension = os.path.splitext(file)
# if file_extension != '.npy':
# file = file_name + '.npy'
#
# np.save(file, data)
else:
message = "--> Data type is not acceptable. Data type only can be a 'list' or 'dict'."
Progress.exit_app(message=message, exit_all=exit_all)
except Exception as e:
message = '--> An error occurred while creating file. --> "%s"' % file
Progress.exit_app(message=message, e=e, exit_all=exit_all)
def timestamp_def(seperate=False,
exit_all=True,
alternative='timestamp_error',
with_space=False):
try:
now_date = datetime.now()
date = now_date.strftime("%Y.%m.%d")
hour = now_date.strftime("%H.%M.%S")
if with_space:
now = date + ' - ' + hour
else:
now = date + '-' + hour
except Exception as e:
message = "--> An error occurred while creating timestamp."
Progress.exit_app(message=message, e=e, exit_all=exit_all)
now = alternative
date = alternative
hour = alternative
if seperate:
return date, hour
else:
return now
def read_dumped_data(file,
data_type=dict,
file_not_found_error=False,
exit_all=True):
result = None
try:
if data_type == dict:
file_name, file_extension = os.path.splitext(file)
if file_extension != '.pickle':
file = file_name + '.pickle'
if not os.path.exists(file):
if file_not_found_error:
message = "! ! File couldn't be found in folder. --> '%s'" % (
file)
Progress.exit_app(message=message, exit_all=exit_all)
return None
pickle_in = open(file, "rb")
result = pickle.load(pickle_in)
elif data_type == list:
file_name, file_extension = os.path.splitext(file)
if file_extension != '.npy':
file = file_name + '.npy'
if not os.path.exists(file):
if file_not_found_error:
message = "! ! File couldn't be found in folder. --> '%s'" % (
file)
Progress.exit_app(message=message, exit_all=exit_all)
return None
result = np.load(file).tolist()
else:
message = "--> File extension is not acceptable. File extension only can be '.pickle' or '.npy'."
Progress.exit_app(message=message, exit_all=exit_all)
except Exception as e:
message = '--> An error occurred while reading file. --> "%s"' % file
Progress.exit_app(e=e, message=message, exit_all=exit_all)
return result
def captcha_solve(browser, cost_file='costs.txt', ANTICAPTCHA_KEY=None, save_cost=True, captcha_sound=True, domain=None):
if not ANTICAPTCHA_KEY:
ANTICAPTCHA_KEY = os.getenv('ANTICAPTCHA_KEY')
if not domain:
domain = browser.current_url
xpath = '//*[@id = "g-recaptcha-response"]'
try:
browser.find_element_by_xpath(xpath)
# Captcha found in page
exist_captcha = True
except:
# Captcha CAN NOT found in page
exist_captcha = False
user_answer = None
cost = 0
start_time = time.time()
if exist_captcha:
if captcha_sound:
Progress.sound_notify_times(times=1)
print('--> reCAPTCHA solving. It might take some time, please wait...')
key = ''
try:
SITE_KEY = None
try:
# TRY normal captcha box
xpath = '//*[contains(@class,"g-recaptcha")]'
captcha_box = browser.find_element_by_xpath(xpath)
SITE_KEY = captcha_box.get_attribute('data-sitekey')
if not SITE_KEY:
raise Exception
except:
# Normal captcha box COULD NOT BE FOUND. Find site key from new generation of reCAPTCHA
xpath = '//iframe[contains(@role, "presentation")]'
captcha_box = browser.find_element_by_xpath(xpath)
captcha_src = captcha_box.get_attribute('src')
if 'k=' in captcha_src and '&' in captcha_src:
captcha_src_list = captcha_src.split('&')
for i in captcha_src_list:
if i.startswith('k='):
SITE_KEY = i.replace('k=', '')
break
if not SITE_KEY:
raise Exception
user_answer = NoCaptchaTaskProxyless.NoCaptchaTaskProxyless(
anticaptcha_key=ANTICAPTCHA_KEY).captcha_handler(
websiteURL=domain, websiteKey=SITE_KEY)
if 'errorDescription' in user_answer:
raise Exception
key = user_answer['solution']['gRecaptchaResponse']
try:
cost = user_answer['cost']
cost = float(cost)
except:
cost = 0
# Code worked untill here so there is no error.
error_captcha = False
except Exception as e:
error_captcha = True
message = '--> An error occurred while solving reCAPTCHA. Processing is in progress.'
if 'errorDescription' in user_answer:
message_from_system = user_answer['errorDescription']
message = message + '\n' + str(message_from_system)
Progress.exit_app(e=e, message=message, exit_all=False)
if not error_captcha:
if 'endTime' in user_answer and 'createTime' in user_answer:
end_time = user_answer['endTime']
create_time = user_answer['createTime']
pass_time = end_time - create_time
else:
pass_time = time.time() - start_time
print('\nCalculation time: %s' % Progress.time_definition(pass_time))
print('reCAPTCHA solved. Price: $%s' % cost)
if save_cost:
if cost != 0 and isinstance(cost, (int, float)):
read_record = File.read_records_to_list(txt_file=cost_file, file_not_found_error=False, exit_all=False)
try:
balance = float(read_record[0])
except:
balance = 0
balance += cost
File.save_records_list(txt_file=cost_file, records_list=[balance], overwrite=True, exit_all=False)
# ADD SOLUTION TO THE PAGE.
try:
browser.execute_script('document.getElementById("g-recaptcha-response").innerHTML = "%s"' % key)
except:
pass
return exist_captcha
def read_records_data_to_dict(txt_file,
show_progress=True,
file_not_found_error=True,
exit_all=True):
# This def is for reading data with columns like excel but from plain text file
read_dict = dict()
try:
total = 0
file_exist = True
try:
file = open(txt_file, 'r', encoding='utf-8')
for line in file:
total += 1
file.close()
except FileNotFoundError:
file_exist = False
if file_not_found_error:
message = "--> File coulnd't be found in folder. --> '%s'" % txt_file
Progress.exit_app(message=message, exit_all=exit_all)
if file_exist:
count = 0
file = open(txt_file, 'r', encoding='utf-8')
now = time.time()
time.sleep(0.01)
new_line = True
key = 1
for line in file:
if key not in read_dict.keys():
read_dict[key] = list()
line = line[:-1]
if show_progress:
count += 1
Progress.progress(
count=count,
total=total,
now=now,
message='Reading records...',
)
if line == '-' * 40:
key += 1
new_line = True
continue
if line == '-' * 20:
new_line = True
continue
if new_line:
read_dict[key].append(line)
else:
read_dict[key][-1] = read_dict[key][-1] + line
new_line = False
if show_progress:
print()
file.close()
for key in list(read_dict.keys()):
if not len(read_dict[key]):
del read_dict[key]
except Exception as e:
if show_progress:
print()
message = "--> An error occurred while reading file -> '%s'" % txt_file
Progress.exit_app(e=e, message=message, exit_all=exit_all)
return read_dict
def internet_connection(timeout=4,
reload_time=30,
wait_for_network=True,
sound_error=True):
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
header = {"User-Agent": user_agent}
url_list = [
# 'https://api.myip.com/',
# 'https://api.ipify.org/',
'https://www.yahoo.com/',
'https://www.bing.com/',
'https://www.google.com/',
'https://www.amazon.com/',
'https://www.amazon.com.tr/',
'https://www.microsoft.com/',
'https://www.apple.com/',
]
message_pasted = False
length_of_last_message = 0
length_of_last_message_MAX = 0
while True:
try:
url = random.choice(url_list)
network = True
response = requests.get(url, timeout=timeout, headers=header)
if response.status_code != 200:
raise Exception
except:
# There is no internet connection.
network = False
if not wait_for_network and network:
# if there is internet connection OR def overwritten to not wait for network, RETURN
return network
if network:
if message_pasted:
# If there was "False network" and 'count down' printed,
# paste space as much as pasted text before.
# Because after pyinstaller execution, print flush, prints in bad view.
message = 'Connection established.'
length_of_new_message = len(message)
if length_of_last_message - length_of_new_message > 0:
message = message + ' ' * (length_of_last_message_MAX -
length_of_new_message)
print("\r%s" % message, flush=True, end="")
print()
print()
print('-' * 40)
print()
# Continue to run main program (RETURN DEF)
break
else:
if not message_pasted:
print()
print('-' * 10)
print()
if sound_error:
Progress.sound_notify()
message_pasted = True
print(url) # DEBUG
now = time.time()
time.sleep(0.01)
message = ''
while time.time() - now < reload_time:
remaining_time = int(reload_time - (time.time() - now))
net_time_string = Progress.time_definition(remaining_time)
message = '--> Error on internet connection. Trying again in %s.' % net_time_string
print("\r%s" % message, flush=True, end="")
time.sleep(1)
length_of_last_message = len(message)
if length_of_last_message_MAX < length_of_last_message:
length_of_last_message_MAX = length_of_last_message
# In first loop, it will raise Exception and will create Browser first time.
browser.current_url
except Exception as e:
options = webdriver.ChromeOptions()
options.add_argument('user-agent={%s}' % user_agent)
options.add_argument('--blink-settings=imagesEnabled=false'
) # Remove images from pages to open fast
browser = webdriver.Chrome(options=options, executable_path=driver)
count_reflesh = 0
while not login_succesful:
count_reflesh += 1
if count_reflesh > 3:
browser.quit()
message = 'Program shutting down because of errors.'
Progress.exit_app(message=message, exit_all=True)
# Go to the link and check the xpath given if element present on the page.
url = 'https://www.instagram.com/accounts/login/'
xpath = '//div[@id = "react-root"]'
Selenium.check_page(browser, url, xpath, 10)
try:
WebDriverWait(browser, 5).until(
EC.presence_of_element_located((By.NAME, "username")))
except:
message = 'Login form could not be found on page. Will load again.'
Progress.exit_app(message=message, exit_all=False)
continue
element_username = browser.find_element_by_name("username")
def connect_api(https=True,
domain=None,
endpoint='api/external_program/',
code='all',
program='',
inform_user_periodically=False,
show_error=False,
sound_error=False,
exit_all=False,
extra_data={}):
if not domain:
domain = os.getenv("domain")
start = time.time()
time.sleep(0.01)
x = 0
db_settings_dict = {}
if https:
url_first = 'https'
else:
url_first = 'http'
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
while True:
try:
x += 1
url = '%s://%s/%s' % (url_first, domain, endpoint)
# Define, if needed (User-Agent, Accept, Referer etc.)
headers = {
"User-Agent": user_agent,
# 'accept': '*/*',
# 'accept-encoding': 'gzip, deflate, br',
# 'accept-language': 'en-US,en;q=0.9,tr;q=0.8,pl;q=0.7',
}
if endpoint == 'api/external_program/':
data = {
'key': code,
'program': program,
}
data.update(extra_data)
else:
data = {}
response = requests.request("GET",
url,
headers=headers,
data=data,
timeout=10)
response.encoding = 'UTF-8'
response = response.json()
# My API returns a dictionary which have 'ayar' and 'parametre' in keys.
if code == 'all':
if endpoint == 'api/external_program/':
for setting in response:
parameter = setting['parametre']
parameter = String.from_string_to_type(
parameter.lower, 'try_all')
db_settings_dict[setting['ayar']] = parameter
else:
db_settings_dict = response
return db_settings_dict
else:
if len(response) and response:
response = String.from_string_to_type(response, 'try_all')
return response
except Exception as e:
if inform_user_periodically:
if x % 2 == 0:
message = '\nAn error occurred while running, trying again...'
print()
print('-' * 40)
print(message)
print()
if x >= 3:
end = time.time()
passed_time = end - start
message = 'An error occurred while running program. Please try again.\n' \
'(Trying time: %s)' % Progress.time_definition(passed_time)
if sound_error:
Progress.sound_notify()
if show_error:
Progress.exit_app(message=message, exit_all=exit_all)
print()
else:
if exit_all:
Progress.exit_app(exit_all=exit_all)
break
def get_proxy_orbit(selenium=True,
get_random=True,
count_loop=1,
save_false_proxies=True,
error_file='Recorded FALSE Orbit Proxies.txt',
save_ok_proxies=True,
ok_file='Recorded OK Orbit Proxies.txt',
number_of_min_saved_proxies=7,
number_of_save_proxies=15,
run_test=True,
test_header=None,
test_url=None,
test_timeout=1,
sound_error=True,
allow_print=True,
no_proxy=True,
for_https=True,
API_KEY=''):
# You can use this function with whether count_loop or get_random.
# count_loop helps you to run it in while with using count_loop+=1 and you can receive proxies 1 by 1 in lines of proxy file.
# if get_random set True, you get proxy randomly from proxy file without looking count_loop.
if allow_print:
print()
print('--> Proxy scraper is started.')
print()
if get_random:
count_loop = random.randint(1, 101)
if number_of_save_proxies < 2:
number_of_save_proxies = 2 # Proxy Orbit send as list when count is more than 1
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
header = {"User-Agent": user_agent}
url = ''
if run_test:
if not test_header:
test_header = header
if not test_url:
url = 'https://api.myip.com/'
# url = 'https://api.ipify.org/'
else:
url = test_url
if for_https:
if url.lower().startswith('http://'):
url = url.lower().replace('http://', 'https://', 1)
else:
if url.lower().startswith('https://'):
url = url.lower().replace('https://', 'http://', 1)
proxy_decide = ''
again = True
curl = ''
while again:
url_proxy = "http://api.proxyorbit.com/v1/"
url_proxy += '?ssl=%s' % str(for_https).lower()
url_proxy += '&protocols=http'
url_proxy += '&count=%s' % number_of_save_proxies
url_proxy += '&token=%s' % API_KEY
check_internet = True # will use this to check internet connection without proxy only once.
count_loop += 1
again = False # will leave while unless again defined True
if count_loop % 10 == 0 and no_proxy:
# def will return NON-PROXY each 10 times
if allow_print:
print('Default proxy settings setted.')
if selenium:
proxy_decide = '--no-proxy-server'
else:
proxy_decide = {}
else:
# def will return NON-PROXY each 10 times
error_ip_list = File.read_records_to_list(
error_file, file_not_found_error=False, exit_all=False)
ok_ip_list = File.read_records_to_list(ok_file,
file_not_found_error=False,
exit_all=False)
ok_ip_save_list = []
for i in ok_ip_list:
ok_ip_save_list.append(i)
if ((len(ok_ip_list) < number_of_min_saved_proxies)
and save_ok_proxies):
# if number saved proxies to the file less than minimum required number of proxies,
# will crawl more new proxies.
check_internet = False # internet connection checked, so will not check it in next commands.
internet_connection(timeout=4,
reload_time=30,
wait_for_network=True,
sound_error=sound_error)
try:
message = 'Proxies are grabbed.'
logging.log(logging.INFO,
message + ' | URL: %s' % url_proxy)
if allow_print:
print(message)
print()
resp = requests.get(url_proxy)
resp = resp.json()
except:
message = 'Error occurred while crawling new proxies.'
logging.log(logging.ERROR, message)
if allow_print:
print('\n--> ' + message)
again = True
count_loop -= 1
Progress.count_down(30)
# continue to loop until get the new proxies.
continue
curls = []
for pr in resp:
curls.append(pr['curl'])
count_ip = 0
for curl in curls:
if save_false_proxies:
# check if new proxy is not one of the proxies which doesn't work.
if curl not in error_ip_list:
if save_ok_proxies:
if curl not in ok_ip_save_list:
count_ip += 1
ok_ip_save_list.append(curl)
else:
count_ip += 1
ok_ip_save_list.append(curl)
else:
if save_ok_proxies:
# add our new proxy to the list of all proxies to save this in our proxy file in the future.
if curl not in ok_ip_save_list:
count_ip += 1
ok_ip_save_list.append(curl)
if save_ok_proxies:
if len(ok_ip_save_list) > number_of_save_proxies:
ok_ip_save_list = random.sample(
ok_ip_save_list, number_of_save_proxies)
File.save_records_list(ok_file,
ok_ip_save_list,
overwrite=True,
exit_all=False)
if not len(ok_ip_save_list):
again = True
message = "Proxy couldn't get. Trying again..."
Progress.exit_app(message=message, exit_all=False)
continue
if get_random:
curl = random.choice(ok_ip_save_list)
else:
# Remaining calculated to get a proxy from our list, from LAST to FIRST.
remaining = count_loop % len(ok_ip_save_list)
remaining = len(ok_ip_save_list) - remaining
if remaining >= len(ok_ip_save_list):
remaining = 0
curl = ok_ip_save_list[remaining]
curl = curl.replace(' ', '')
curl = curl.replace('\n', '')
proxy_decide = {}
if for_https:
proxy_decide['https'] = curl
else:
proxy_decide['http'] = curl
if save_false_proxies:
if curl in error_ip_list:
File.write_ok_and_false_proxy(curl,
error_file=error_file,
ok_file=ok_file)
again = True
continue
if run_test:
try:
if check_internet:
internet_connection(timeout=test_timeout,
reload_time=30,
wait_for_network=True,
sound_error=sound_error)
response = requests.get(url,
proxies=proxy_decide,
timeout=test_timeout,
stream=True,
headers=test_header)
if test_url:
# if any url overwritten on def, just check the status code.
if response.status_code != 200:
raise Exception
else:
response = response.json()
if response == {}:
raise Exception
if save_ok_proxies:
File.save_records_list(ok_file,
ok_ip_save_list,
overwrite=True,
exit_all=False)
except Exception as e:
message = "Proxy doesn't work. Next proxy is testing...\n" \
"Proxy: %s" % (curl)
if not get_random:
message += '\tProxy Number: %s' % remaining
if allow_print:
print(message)
print()
again = True
if save_false_proxies:
File.write_ok_and_false_proxy(curl,
error_file=error_file,
ok_file=ok_file)
continue
ip_port = curl.split('//')[-1]
if selenium:
proxy_decide = '--proxy-server=%s' % (ip_port)
else:
# proxy_decide defined above.
pass
if allow_print:
if get_random:
print("Proxy activated.\nProxy: %s" % (curl))
else:
print("Proxy activated. Proxy Number: %s.\nProxy: %s" %
(count_loop, curl))
if allow_print:
print()
if get_random:
return proxy_decide, curl
else:
return count_loop, proxy_decide, curl
def get_proxy(selenium=True,
get_random=True,
count_loop=1,
save_false_proxies=True,
error_file='Recorded FALSE Proxies.txt',
save_ok_proxies=True,
ok_file='Recorded OK Proxies.txt',
number_of_min_saved_proxies=20,
number_of_save_proxies=40,
run_test=True,
test_header=None,
test_url=None,
test_timeout=1,
sound_error=True,
allow_print=True,
no_proxy=True,
for_https=True):
# You can use this function with whether count_loop or get_random.
# count_loop helps you to run it in while with using count_loop+=1 and you can receive proxies 1 by 1 in lines of proxy file.
# if get_random set True, you get proxy randomly from proxy file without looking count_loop.
if get_random:
count_loop = random.randint(1, 101)
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
header = {"User-Agent": user_agent}
if run_test:
if not test_header:
test_header = header
if not test_url:
url = 'https://api.myip.com/'
# url = 'https://api.ipify.org/'
else:
url = test_url
if for_https:
if url.lower().startswith('http://'):
url = url.lower().replace('http://', 'https://', 1)
else:
if url.lower().startswith('https://'):
url = url.lower().replace('https://', 'http://', 1)
proxy_decide = ''
url_proxies = [
'https://hidemy.name/tr/proxy-list/?type=s#list',
'https://www.us-proxy.org/',
'https://www.sslproxies.org/',
]
again = True
force_scrap = False
while again:
random_proxy = random.randint(0, len(url_proxies) - 1)
url_proxy = url_proxies[random_proxy]
check_internet = True # will use this to check internet connection without proxy only once.
count_loop += 1
again = False # will leave while unless again defined True
if count_loop % 10 == 0 and no_proxy:
# def will return NON-PROXY each 10 times
if allow_print:
print('Default proxy settings setted.')
if selenium:
proxy_decide = '--no-proxy-server'
else:
proxy_decide = {}
record_ip_type = ''
else:
# def will return NON-PROXY each 10 times
error_ip_list = File.read_records_to_list(
error_file, file_not_found_error=False, exit_all=False)
ok_ip_list = File.read_records_to_list(ok_file,
file_not_found_error=False,
exit_all=False)
ok_ip_save_list = []
for i in ok_ip_list:
ok_ip_save_list.append(i)
if ((len(ok_ip_list) < number_of_min_saved_proxies)
and save_ok_proxies) or force_scrap:
# if number saved proxies to the file less than minimum required number of proxies,
# will crawl more new proxies.
check_internet = False # internet connection checked, so will not check it in next commands.
internet_connection(timeout=4,
reload_time=30,
wait_for_network=True,
sound_error=sound_error)
try:
print('Proxies are grabbed:')
print(url_proxy)
page = requests.get(
url_proxy,
headers=header,
timeout=4,
)
except:
message = 'Error occurred while crawling new proxies.'
logging.log(logging.ERROR, message)
if allow_print:
print('\n--> ' + message)
again = True
count_loop -= 1
# continue to loop until get the new proxies.
continue
tree = html.fromstring(page.content)
if 'hidemy.name' in url_proxy:
ips = tree.xpath(
'//div[@class = "table_block"]/table//tbody/tr/td[1]'
) # list of all ips
ports = tree.xpath(
'//div[@class = "table_block"]/table//tbody/tr/td[2]'
) # list of all ports
types = tree.xpath(
'//div[@class = "table_block"]/table//tbody/tr/td[5]'
) # list of all types
elif 'us-proxy' in url_proxy:
ips = tree.xpath(
'//div[contains(@class, "fpl-list")]//table//tr/td[1]'
) # list of all ips
ports = tree.xpath(
'//div[contains(@class, "fpl-list")]//table//tr/td[2]'
) # list of all ports
types = tree.xpath(
'//div[contains(@class, "fpl-list")]//table//tr/td[7]'
) # list of all types
elif 'sslproxies' in url_proxy:
ips = tree.xpath(
'//div[contains(@class, "fpl-list")]//table//tr/td[1]'
) # list of all ips
ports = tree.xpath(
'//div[contains(@class, "fpl-list")]//table//tr/td[2]'
) # list of all ports
types = tree.xpath(
'//div[contains(@class, "fpl-list")]//table//tr/td[7]'
) # list of all types
count_ip = 0
if len(ips) == len(ports) == len(types):
pass
else:
again = True
count_loop -= 1
# continue to loop untill get the new proxies.
continue
for ip, port, type in zip(ips, ports, types):
# if ip.text and port.text and type.text:
# pass
# else:
# continue
add_type = ''
if 'hidemy.name' in url_proxy:
if 'http' in type.text.lower():
if add_type:
add_type += ','
add_type += 'HTTP'
if 'https' in type.text.lower():
if add_type:
add_type += ','
add_type += 'HTTPS'
elif 'us-proxy' in url_proxy:
add_type += 'HTTP'
if 'yes' in type.text.lower():
add_type += ',HTTPS'
elif 'sslproxies' in url_proxy:
add_type += 'HTTP'
if 'yes' in type.text.lower():
add_type += ',HTTPS'
if add_type:
add_type = ',' + add_type
else:
continue # NO HTTP OR HTTPS PROXY (Such as Socks4, Socks5 proxy)
ip_from_page = ip.text.replace(' ', '')
add_ip_type = '%s:%s%s' % (ip_from_page, port.text,
add_type)
try:
ipaddress.ip_address(ip_from_page)
except:
continue
if save_false_proxies:
# check if new proxy is not one of the proxies which doesn't work.
if add_ip_type not in error_ip_list:
if save_ok_proxies:
if add_ip_type not in ok_ip_save_list:
count_ip += 1
ok_ip_save_list.append(add_ip_type)
else:
count_ip += 1
ok_ip_save_list.append(add_ip_type)
else:
if save_ok_proxies:
# add our new proxy to the list of all proxies to save this in our proxy file in the future.
if add_ip_type not in ok_ip_save_list:
count_ip += 1
ok_ip_save_list.append(add_ip_type)
if save_ok_proxies:
if len(ok_ip_save_list) > number_of_save_proxies:
ok_ip_save_list_new = random.sample(
ok_ip_save_list, number_of_save_proxies)
for elem in ok_ip_save_list:
elem_types = elem.split(',')[1:]
if 'HTTPS' in elem_types:
if elem not in ok_ip_save_list_new:
ok_ip_save_list_new.append(elem)
ok_ip_save_list = ok_ip_save_list_new
File.save_records_list(ok_file,
ok_ip_save_list,
overwrite=True,
exit_all=False)
http_count = 0
https_count = 0
for elem in ok_ip_save_list:
elem_types = elem.split(',')[1:]
if 'HTTP' in elem_types:
http_count += 1
if 'HTTPS' in elem_types:
https_count += 1
if https_count <= 3 or http_count <= 3:
again = True
force_scrap = True
count_loop -= 1
continue
else:
force_scrap = False
if not len(ok_ip_save_list):
again = True
message = "Proxy couldn't get. Trying again..."
Progress.exit_app(message=message, exit_all=False)
continue
if get_random:
record_ip_type = random.choice(ok_ip_save_list)
else:
# Remaining calculated to get a proxy from our list, from LAST to FIRST.
remaining = count_loop % len(ok_ip_save_list)
remaining = len(ok_ip_save_list) - remaining
if remaining >= len(ok_ip_save_list):
remaining = 0
record_ip_type = ok_ip_save_list[remaining]
record_ip_type = record_ip_type.replace(' ', '')
record_ip_type = record_ip_type.replace('\n', '')
record_ip = record_ip_type.split(',', 1)[0]
record_types = record_ip_type.split(',')[1:]
record_ip_list = record_ip.split(':')
if len(record_ip_list) != 2:
message = "Proxy doesn't work. Next proxy is testing...\n" \
"IP-Port: %s" % record_ip
if not get_random:
message += "\tProxy Number: %s" % (remaining)
if allow_print:
print(message)
print()
again = True
if save_false_proxies:
File.write_ok_and_false_proxy(record_ip_type,
error_file=error_file,
ok_file=ok_file)
continue
if for_https:
if 'HTTPS' not in record_types:
again = True
continue
else:
if 'HTTP' not in record_types:
again = True
continue
ip = record_ip_list[0]
port = record_ip_list[1]
proxy_decide = {}
for type in record_types:
proxy_decide[type.lower()] = "http://%s" % record_ip
if save_false_proxies:
if record_ip_type in error_ip_list:
File.write_ok_and_false_proxy(record_ip_type,
error_file=error_file,
ok_file=ok_file)
again = True
continue
if run_test:
try:
if check_internet:
internet_connection(timeout=test_timeout,
reload_time=30,
wait_for_network=True,
sound_error=sound_error)
response = requests.get(url,
proxies=proxy_decide,
timeout=test_timeout,
stream=True,
headers=test_header)
if test_url:
# if any url overwritten on def, just check the status code.
if response.status_code != 200:
raise Exception
else:
response = response.json()
if response == {}:
raise Exception
if save_ok_proxies:
File.save_records_list(ok_file,
ok_ip_save_list,
overwrite=True,
exit_all=False)
except Exception as e:
message = "Proxy doesn't work. Next proxy is testing...\n" \
"IP: %s\tPort: %s" % (ip, port)
if not get_random:
message += '\tProxy Number: %s' % remaining
if allow_print:
print(message)
print()
again = True
if save_false_proxies:
File.write_ok_and_false_proxy(record_ip_type,
error_file=error_file,
ok_file=ok_file)
continue
if selenium:
proxy_decide = '--proxy-server=%s:%s' % (ip, port)
else:
# proxy_decide defined above.
pass
if allow_print:
if get_random:
print("Proxy activated.\nIP: %s\tPort: %s" % (ip, port))
else:
print(
"Proxy activated. Proxy Number: %s.\nIP: %s\tPort: %s"
% (count_loop, ip, port))
if allow_print:
print()
if get_random:
return proxy_decide, record_ip_type
else:
return count_loop, proxy_decide, record_ip_type
def send_email(message,
subject,
recipients,
attach_file_name=None,
attach_file_text=None,
login_mail=None,
pwd=None,
sender='Email Sender',
sound_error=True,
show_error=True,
exit_all=False,
debug_mode=0):
if not login_mail:
login_mail = os.getenv('login_mail')
if not pwd:
pwd = os.getenv('pwd')
try:
msg = MIMEMultipart()
msg['Subject'] = subject
msg['From'] = sender
recipient = ", ".join(recipients)
msg['To'] = recipient
msg.attach(MIMEText(message))
if attach_file_name and attach_file_text:
f = StringIO()
# write some content to 'f'
f.write(attach_file_text)
f.seek(0)
attach = MIMEBase('application', "octet-stream")
attach.set_payload(f.read())
encoders.encode_base64(attach)
attach.add_header('Content-Disposition',
'attachment',
filename=attach_file_name)
msg.attach(attach)
server = smtplib.SMTP('smtp.gmail.com', 587)
server.set_debuglevel(debug_mode) # Prints all process if debug == 1
server.ehlo()
server.starttls()
server.ehlo()
server.login(login_mail, pwd)
# Send the email
server.sendmail(sender, recipients, msg.as_string())
server.close()
return True
except Exception as e:
if sound_error:
Progress.sound_notify()
if show_error:
message = '--> An error occurred while sending email.'
Progress.exit_app(e=e, message=message, exit_all=exit_all)
else:
Progress.exit_app(e=e, exit_all=exit_all)
return False
def excel_read_to_dict(excel, number_of_sheet=0, exit_all=False):
all_data = dict()
headers = dict()
try:
# Check and add xlsx or xls if there is not at the end.
file_name, file_extension = os.path.splitext(excel)
if file_extension != '.xlsx' or file_extension != '.xls':
excel = file_name + '.xlsx'
# check all versions of the file name if it is exist in directory.
# (Checking with all lower and capital characters for excel name if it is equal any file.)
excel = find_file(excel)
if not os.path.exists(excel):
# So given file name could not be found in directory with any combinations of capital and lower characters.
excel2 = None
# switch between xlsx and xls
if file_extension != '.xlsx':
excel2 = file_name + '.xls'
elif file_extension != '.xls':
excel2 = file_name + '.xlsx'
if excel2:
# if given file name is xlsx, it switched to xls in "excel2"
# if given file name is xls, it switched to xlsx in "excel2"
# and checking again...
excel2 = find_file(excel2)
if not os.path.exists(excel2):
message = "! ! File couldn't be found in folder. --> '%s' or '%s'" % (
excel, excel2)
Progress.exit_app(message=message, exit_all=exit_all)
return all_data, headers
else:
excel = excel2
else:
message = "! ! File couldn't be found in folder. --> '%s'" % (
excel)
Progress.exit_app(message=message, exit_all=exit_all)
return all_data, headers
workbook = xlrd.open_workbook(excel) # sheet
sheet = workbook.sheet_by_index(number_of_sheet) # page
number_of_column = sheet.ncols
number_of_row = len(sheet.col(0))
count = 0
total = number_of_row
now = time.time()
message = 'Reading excel...'
time.sleep(0.01)
number_of_data = 0
number_of_header = 0
for y in range(number_of_row):
key = sheet.cell_value(rowx=y, colx=0)
try:
key = int(key)
except:
pass
# I only get integer keys which means excel rows which has integer at first cell.
# This is for not getting header rows in my dictionary.
# and I design my excels with ID column at first column.
if isinstance(key, int):
number_of_data += 1
all_data[number_of_data] = list()
for x in range(number_of_column):
val = sheet.cell_value(rowx=y, colx=x)
val = String.float_to_integer(val, force_number=False)
all_data[number_of_data].append(val)
else:
number_of_header += 1
headers[number_of_header] = list()
for x in range(number_of_column):
val = sheet.cell_value(rowx=y, colx=x)
val = String.float_to_integer(val, force_number=False)
headers[number_of_header].append(val)
count += 1
Progress.progress(
count=count,
total=total,
now=now,
message=message,
)
except PermissionError:
message = "--> '%s' can't access to this file.\nIt is probably because the file is open. If this excel is open, please close it and re-run program." % excel
Progress.exit_app(message=message, exit_all=exit_all)
except Exception as e:
message = "--> An error occurred while reading file... '%s'" % excel
Progress.exit_app(e=e, message=message, exit_all=exit_all)
print('\nNumber of item: %s' % len(all_data))
# it returns a dictionary from 3 rows excel file as:
# all_data = {
# 1: ['1st Column Value', '2nd Column Value', '3rd Column Value', '4th Column Value', '5th Column Value', ],
# 2: ['1st Column Value', '2nd Column Value', '3rd Column Value', '4th Column Value', '5th Column Value', ],
# 3: ['1st Column Value', '2nd Column Value', '3rd Column Value', '4th Column Value', '5th Column Value', ],
# }
return all_data, headers
def excel_create(
excel,
all_data,
headers=None,
sizes=None,
locations=None,
page_name='Page1',
exit_all=False,
):
if not headers:
headers = list()
# Check and add xlsx or xls if there is not at the end.
file_name, file_extension = os.path.splitext(excel)
if file_extension != '.xlsx' or file_extension != '.xls':
excel = file_name + '.xlsx'
try:
message = "'%s' --> Creating..." % excel
total = len(all_data)
print(message)
if not total:
message = '\n--> No data.'
print(message)
return
if len(all_data):
length_max = 0
for val in all_data.values():
try:
if length_max < len(val):
# Find the row which has maximum length
if isinstance(val[-1], dict):
length_max = len(val) - 1
else:
length_max = len(val)
except:
pass
i = 0
while len(headers) < length_max:
# if maximum length of any row larger than HEADERS, add "Header %i" rest of the headers
i += 1
headers.append('Header %s' % i)
for key in list(all_data.keys()):
# if length of Headers larger than any row, add empty cell end of the row
while len(headers) > len(all_data[key]):
all_data[key].append('')
if sizes:
while len(headers) > len(sizes):
sizes.append(20)
else:
sizes = list()
for head in headers:
sizes.append(25)
if locations:
while len(headers) > len(locations):
locations.append('left')
else:
locations = list()
for head in headers:
locations.append('left')
attrs_loc = dict()
for val in all_data.values():
for elem in val:
if isinstance(elem, dict):
for name, attr in elem.items():
if name not in attrs_loc.keys():
headers.append(name)
sizes.append(20)
locations.append('left')
attrs_loc[name] = len(headers)
workbook = xlsxwriter.Workbook(excel)
worksheet = workbook.add_worksheet(page_name)
worksheet.freeze_panes(1, 0)
cell_format_header = workbook.add_format({'border': 1})
cell_format_header.set_pattern(1)
cell_format_header.set_bg_color('orange')
cell_format_header.set_align('center')
cell_format_header.set_align('vcenter')
cell_format_header.set_bold()
cell_format_center_regular = workbook.add_format({'border': 1})
cell_format_center_regular.set_align('center')
cell_format_center_regular.set_align('vcenter')
cell_format_regular = workbook.add_format({'border': 1})
cell_format_regular.set_align('left')
cell_format_regular.set_align('vcenter')
cell_format_right_regular = workbook.add_format({'border': 1})
cell_format_right_regular.set_align('right')
cell_format_right_regular.set_align('vcenter')
cell_format_copyr = workbook.add_format({'border': 1})
cell_format_copyr.set_pattern(1)
cell_format_copyr.set_bg_color('FABF8F')
cell_format_copyr.set_align('center')
cell_format_copyr.set_align('vcenter')
cell_format_copyr.set_bold()
row = 0
col = 0
set_say = 0
worksheet.write(row, col, 'ID', cell_format_header)
worksheet.set_column(set_say, set_say, 8)
set_say += 1
col += 1
for head, size in zip(headers, sizes):
worksheet.write(row, col, head, cell_format_header)
worksheet.set_column(set_say, set_say, size)
set_say += 1
col += 1
worksheet.write(row, col, 'Automated by BerkayMizrak.com',
cell_format_copyr)
worksheet.set_column(set_say, set_say, 34)
row += 1
count = 0
now = time.time()
time.sleep(0.01)
id_count = 0
for val in all_data.values():
id_count += 1
col = 0
worksheet.write(row, col, id_count, cell_format_center_regular)
for elem in val:
if isinstance(elem, dict):
continue
col += 1
if col > len(locations):
go_left = True
else:
go_left = False
if locations[col - 1] == 'center':
worksheet.write(row, col, elem,
cell_format_center_regular)
elif locations[col - 1] == 'right':
worksheet.write(row, col, elem,
cell_format_right_regular)
else:
go_left = True
if go_left:
try:
elem = int(elem)
worksheet.write(row, col, elem,
cell_format_center_regular)
except:
worksheet.write(row, col, elem, cell_format_regular)
for elem in val:
if isinstance(elem, dict):
for name, attr in elem.items():
worksheet.write(row, attrs_loc[name], attr,
cell_format_regular)
row += 1
count += 1
Progress.progress(
count=count,
total=total,
now=now,
)
print()
workbook.close()
message = "'%s' Data Saved to Excel -->> '%s'" % (count, excel)
print(message)
except PermissionError:
message = "--> '%s' can't access to this file.\nIt is probably because the file is open. If this excel is open, please close it and re-run program." % excel
Progress.exit_app(message=message, exit_all=exit_all)
except Exception as e:
message = "--> An error occurred while creating file... '%s'" % excel
Progress.exit_app(e=e, message=message, exit_all=exit_all)
def create_word(word, my_rows):
try:
# Check and add docx if there is not at the end.
file_name, file_extension = os.path.splitext(word)
if file_extension != '.docx':
word = file_name + '.xlsx'
message = "'%s' --> Creating..." % word
total = len(my_rows)
print(message)
if not total:
message = '\n--> No data.'
print(message)
return
document = Document()
"""
EXTRA DETAILS FOR DESIGN:
document.add_heading('Document Title', 0)
p = document.add_paragraph('A plain paragraph having some ')
p.add_run('bold').bold = True
p.add_run(' and some ')
p.add_run('italic.').italic = True
document.add_heading('Heading, level 1', level=1)
document.add_picture('monty-truth.png', width=Inches(1.25))
records = (
(3, '101', 'Spam'),
(7, '422', 'Eggs'),
(4, '631', 'Spam, spam, eggs, and spam')
)
document.add_page_break()
"""
styles = document.styles
style = document.styles['Normal']
font = style.font
font.name = 'Arial'
font.size = Pt(12)
style = styles.add_style('MyHeader1', WD_STYLE_TYPE.PARAGRAPH)
font = style.font
font.bold = True
font.name = 'Arial'
font.size = Pt(14)
style = styles.add_style('MyHeader2', WD_STYLE_TYPE.PARAGRAPH)
font = style.font
font.name = 'Arial'
font.size = Pt(13)
for row in my_rows:
table = row.get('table', False)
if not table:
text = row.get('text', '')
style_name = row.get('style', None)
location = row.get('location', 0)
bold = row.get('bold', False)
italic = row.get('italic', False)
underline = row.get('underline', False)
size = row.get('size', 12)
paragraph = document.add_paragraph()
run = paragraph.add_run(text)
if style_name:
style = document.styles[style_name]
paragraph.style = style
else:
run.bold = bold
run.italic = italic
run.underline = underline
font = style.font
font.size = Pt(size)
paragraph.alignment = location # 0: left, 1: center, 2: right, 3: justify
else:
data = row.get('data', [])
border = row.get('border', False)
if len(data):
table_obj = document.add_table(
rows=0,
cols=len(data[0]),
)
if border:
table_obj.style = 'TableGrid'
for count_row, table_row in enumerate(data):
row_cells = table_obj.add_row().cells
for enum, cell in enumerate(table_row):
row_cells[enum].text = str(cell)
if count_row == 0:
for count_cell in range(len(table_row)):
row_cells[count_cell].paragraphs[0].runs[
0].font.bold = True
row_cells[count_cell].paragraphs[
0].alignment = 1
print()
document.save(word)
message = "Word Created -->> '%s'" % (word)
print(message)
except PermissionError:
message = "--> '%s' can't access to this file.\nIt is probably because the file is open. If this word is open, please close it and re-run program." % word
Progress.exit_app(message=message, exit_all=False)
except Exception as e:
message = "--> An error occurred while creating file... '%s'" % word
Progress.exit_app(e=e, message=message, exit_all=False)
