directory=directory_manager.root_metadata_directory,
)
p_r.api_type = api_type
result: list[api_table] = database_session.query(api_table_).all()
metadata = getattr(subscription.temp_scraped, api_type)
await fix_directories(
result,
subscription,
database_session,
api_type,
)
database_session.close()
return metadata
if __name__ == "__main__":
# WORK IN PROGRESS
from classes.make_settings import Config
from apis.onlyfans import onlyfans as OnlyFans
import helpers.main_helper as main_helper
config_path = Path(".settings", "config.json")
config, _updated = main_helper.get_config(config_path)
api_ = OnlyFans.start(
config=config,
)
subscription = ""
input("WIP")
exit()
def start_datascraper(json_config: dict, site_name_lower: str, api: Optional[OnlyFans.start] = None, webhooks=True):
json_settings = json_config["settings"]
json_webhooks = json_settings["webhooks"]
json_sites = json_config["supported"]
domain = json_settings["auto_site_choice"]
main_helper.assign_vars(json_config)
json_site_settings = json_sites[site_name_lower]["settings"]
auto_model_choice = json_site_settings["auto_model_choice"]
if isinstance(auto_model_choice, str):
temp_identifiers = auto_model_choice.split(",")
identifiers = [x for x in temp_identifiers if x]
else:
identifiers = []
auto_profile_choice = json_site_settings["auto_profile_choice"]
subscription_array = []
original_sessions = []
original_sessions = api_helper.create_session(
settings=json_settings)
original_sessions = [x for x in original_sessions if x]
if not original_sessions:
print("Unable to create session")
return False
archive_time = timeit.default_timer()
if site_name_lower == "onlyfans":
site_name = "OnlyFans"
module = m_onlyfans
if not api:
api = OnlyFans.start()
api = main_helper.process_profiles(
json_settings, original_sessions, site_name, api)
print
subscription_array = []
auth_count = 0
jobs = json_site_settings["jobs"]
subscription_list = module.format_options(
api.auths, "users")
if not auto_profile_choice:
print("Choose Profile")
auths = choose_option(
subscription_list, auto_profile_choice, True)
api.auths = [x.pop(0) for x in auths]
for auth in api.auths:
if not auth.auth_details:
continue
module.assign_vars(auth.auth_details, json_config,
json_site_settings, site_name)
setup = False
setup, subscriptions = module.account_setup(
auth, identifiers, jobs, auth_count)
if not setup:
if webhooks:
x = main_helper.process_webhooks(
api, "auth_webhook", "failed")
auth_details = {}
auth_details["auth"] = auth.auth_details.__dict__
profile_directory = auth.profile_directory
if profile_directory:
user_auth_filepath = os.path.join(
auth.profile_directory, "auth.json")
main_helper.export_data(
auth_details, user_auth_filepath)
continue
auth_count += 1
subscription_array += subscriptions
x = main_helper.process_webhooks(
api, "auth_webhook", "succeeded")
subscription_list = module.format_options(
subscription_array, "usernames")
if jobs["scrape_paid_content"]:
print("Scraping Paid Content")
paid_content = module.paid_content_scraper(api, identifiers)
if jobs["scrape_names"]:
print("Scraping Subscriptions")
names = main_helper.process_names(
module, subscription_list, auto_model_choice, api, json_config, site_name_lower, site_name)
x = main_helper.process_downloads(api, module)
if webhooks:
x = main_helper.process_webhooks(
api, "download_webhook", "succeeded")
elif site_name_lower == "starsavn":
pass
# site_name = "StarsAVN"
# original_api = StarsAVN
# module = m_starsavn
# apis = main_helper.process_profiles(
# json_settings, original_sessions, site_name, original_api)
# auto_profile_choice = json_site_settings["auto_profile_choice"]
# subscription_array = []
# auth_count = -1
# jobs = json_site_settings["jobs"]
# subscription_list = module.format_options(
# apis, "users")
# apis = choose_option(
# subscription_list, auto_profile_choice)
# apis = [x.pop(0) for x in apis]
# for api in apis:
# module.assign_vars(api.auth.auth_details, json_config,
# json_site_settings, site_name)
# identifier = ""
# setup = False
# setup = module.account_setup(api, identifier=identifier)
# if not setup:
# auth_details = api.auth.auth_details.__dict__
# user_auth_filepath = os.path.join(
# api.auth.profile_directory, "auth.json")
# main_helper.export_data(
# auth_details, user_auth_filepath)
# continue
# if jobs["scrape_names"]:
# array = module.manage_subscriptions(
# api, auth_count, identifier=identifier)
# subscription_array += array
# subscription_list = module.format_options(
# subscription_array, "usernames")
# if jobs["scrape_paid_content"]:
# print("Scraping Paid Content")
# paid_content = module.paid_content_scraper(apis)
# if jobs["scrape_names"]:
# print("Scraping Subscriptions")
# names = main_helper.process_names(
# module, subscription_list, auto_model_choice, apis, json_config, site_name_lower, site_name)
# x = main_helper.process_downloads(apis, module)
stop_time = str(
int(timeit.default_timer() - archive_time) / 60)[:4]
print('Archive Completed in ' + stop_time + ' Minutes')
return api
def start_datascraper():
parser = ArgumentParser()
parser.add_argument("-m",
"--metadata",
action='store_true',
help="only exports metadata")
args = parser.parse_args()
if args.metadata:
print("Exporting Metadata Only")
log_error = main_helper.setup_logger('errors', 'errors.log')
console = logging.StreamHandler()
console.setLevel(logging.DEBUG)
formatter = logging.Formatter(
'%(asctime)s %(levelname)s %(name)s %(message)s')
console.setFormatter(formatter)
logging.getLogger("").addHandler(console)
# root = os.getcwd()
config_path = os.path.join('.settings', 'config.json')
json_config, json_config2 = main_helper.get_config(config_path)
json_settings = json_config["settings"]
json_sites = json_config["supported"]
infinite_loop = json_settings["infinite_loop"]
global_user_agent = json_settings['global_user_agent']
domain = json_settings["auto_site_choice"]
path = os.path.join('.settings', 'extra_auth.json')
# extra_auth_config, extra_auth_config2 = main_helper.get_config(path)
extra_auth_config = {}
exit_on_completion = json_settings['exit_on_completion']
loop_timeout = json_settings['loop_timeout']
main_helper.assign_vars(json_config)
string, site_names = module_chooser(domain, json_sites)
try:
while True:
if domain:
if site_names:
site_name = domain
else:
print(string)
continue
else:
print(string)
x = input()
if x == "x":
break
x = int(x)
site_name = site_names[x]
site_name_lower = site_name.lower()
json_auth_array = [json_sites[site_name_lower]["auth"]]
json_site_settings = json_sites[site_name_lower]["settings"]
auto_scrape_names = json_site_settings["auto_scrape_names"]
extra_auth_settings = json_sites[site_name_lower][
"extra_auth_settings"] if "extra_auth_settings" in json_sites[
site_name_lower] else {
"extra_auth": False
}
extra_auth = extra_auth_settings["extra_auth"]
if extra_auth:
choose_auth = extra_auth_settings["choose_auth"]
merge_auth = extra_auth_settings["merge_auth"]
json_auth_array += extra_auth_config["supported"][
site_name_lower]["auths"]
if choose_auth:
json_auth_array = main_helper.choose_auth(json_auth_array)
apis = []
module = m_onlyfans
subscription_array = []
legacy = True
original_sessions = api_helper.create_session(
settings=json_settings)
if not original_sessions:
print("Unable to create session")
continue
archive_time = timeit.default_timer()
if site_name_lower == "onlyfans":
site_name = "OnlyFans"
subscription_array = []
auth_count = -1
jobs = json_site_settings["jobs"]
for json_auth in json_auth_array:
api = OnlyFans.start(original_sessions)
auth_count += 1
user_agent = global_user_agent if not json_auth[
'user_agent'] else json_auth['user_agent']
module = m_onlyfans
module.assign_vars(json_auth, json_config,
json_site_settings, site_name)
api.set_auth_details(**json_auth,
global_user_agent=user_agent)
identifier = ""
setup = module.account_setup(api, identifier=identifier)
if not setup:
continue
if jobs["scrape_names"]:
array = module.manage_subscriptions(
api, auth_count, identifier=identifier)
subscription_array += array
apis.append(api)
subscription_list = module.format_options(
subscription_array, "usernames")
if jobs["scrape_paid_content"]:
print("Scraping Paid Content")
paid_content = module.paid_content_scraper(apis)
if jobs["scrape_names"]:
print("Scraping Subscriptions")
x = main_helper.process_names(module, subscription_list,
auto_scrape_names,
json_auth_array, apis,
json_config, site_name_lower,
site_name)
x = main_helper.process_downloads(apis, module)
print
elif site_name_lower == "starsavn":
site_name = "StarsAVN"
subscription_array = []
auth_count = -1
for json_auth in json_auth_array:
sessions = api_helper.copy_sessions(original_sessions)
api = StarsAVN.start(sessions)
auth_count += 1
user_agent = global_user_agent if not json_auth[
'user_agent'] else json_auth['user_agent']
module = m_starsavn
module.assign_vars(json_auth, json_config,
json_site_settings, site_name)
api.set_auth_details(**json_auth,
global_user_agent=user_agent)
setup = module.account_setup(api)
if not setup:
continue
jobs = json_site_settings["jobs"]
if jobs["scrape_names"]:
array = module.manage_subscriptions(api, auth_count)
subscription_array += array
if jobs["scrape_paid_content"]:
paid_contents = api.get_paid_content()
paid_content = module.paid_content_scraper(api)
apis.append(api)
subscription_array = module.format_options(
subscription_array, "usernames")
stop_time = str(int(timeit.default_timer() - archive_time) /
60)[:4]
print('Archive Completed in ' + stop_time + ' Minutes')
if exit_on_completion:
print("Now exiting.")
exit(0)
elif not infinite_loop:
print("Input anything to continue")
input()
elif loop_timeout:
print('Pausing scraper for ' + loop_timeout + ' seconds.')
time.sleep(int(loop_timeout))
except Exception as e:
log_error.exception(e)
input()
async def start_datascraper(
config: Config,
site_name: str,
api_: Optional[OnlyFans.start | Fansly.start | StarsAVN.start] = None,
webhooks: bool = True,
):
global_settings = config.settings
proxies: list[str] = await api_helper.test_proxies(global_settings.proxies)
if global_settings.proxies and not proxies:
print("Unable to create session")
return None
async def default(
datascraper: Optional[m_onlyfans.OnlyFansDataScraper]
| Optional[m_fansly.FanslyDataScraper]
| Optional[m_starsavn.StarsAVNDataScraper],
):
if not datascraper:
return
api = datascraper.api
global_settings = api.get_global_settings()
site_settings = api.get_site_settings()
if not (global_settings and site_settings):
return
await main_helper.process_profiles(api, global_settings)
subscription_array: list[user_types] = []
auth_count = 0
profile_options = OptionsFormat(
api.auths, "profiles", site_settings.auto_profile_choice
)
api.auths = profile_options.final_choices
identifiers = []
if site_settings.auto_model_choice:
subscription_options = OptionsFormat(
subscription_array, "subscriptions", site_settings.auto_model_choice
)
if not subscription_options.scrape_all():
identifiers = subscription_options.choice_list
for auth in api.auths:
auth: auth_types = auth
if not auth.auth_details:
continue
setup = False
setup, subscriptions = await account_setup(
auth, datascraper, site_settings, identifiers
)
if not setup:
if webhooks:
await main_helper.process_webhooks(
api, "auth_webhook", "failed", global_settings
)
auth_details: dict[str, Any] = {}
auth_details["auth"] = auth.auth_details.export()
profile_directory = api.base_directory_manager.profile.root_directory
user_auth_filepath = profile_directory.joinpath(
api.site_name, auth.auth_details.username, "auth.json"
)
main_helper.export_json(auth_details, user_auth_filepath)
continue
auth_count += 1
subscription_array.extend(subscriptions)
await main_helper.process_webhooks(
api, "auth_webhook", "succeeded", global_settings
)
# Do stuff with authed user
subscription_options = OptionsFormat(
subscription_array, "subscriptions", site_settings.auto_model_choice
)
datascraper.subscription_options = subscription_options
subscription_list = subscription_options.final_choices
await main_helper.process_jobs(datascraper, subscription_list, site_settings)
await main_helper.process_downloads(api, datascraper, global_settings)
if webhooks:
await main_helper.process_webhooks(
api, "download_webhook", "succeeded", global_settings
)
archive_time = timeit.default_timer()
datascraper = None
match site_name:
case "OnlyFans":
if not isinstance(api_, OnlyFans.start):
api_ = OnlyFans.start(
config=config,
)
datascraper = m_onlyfans.OnlyFansDataScraper(api_)
case "Fansly":
if not isinstance(api_, Fansly.start):
api_ = Fansly.start(
config=config,
)
datascraper = m_fansly.FanslyDataScraper(api_)
case "StarsAVN":
if not isinstance(api_, StarsAVN.start):
api_ = StarsAVN.start(
config=config,
)
datascraper = m_starsavn.StarsAVNDataScraper(api_)
case _:
pass
await default(datascraper)
stop_time = str(int(timeit.default_timer() - archive_time) / 60)[:4]
print("Archive Completed in " + stop_time + " Minutes")
return api_
async def start_datascraper(
json_config: dict[Any,Any],
site_name_lower: str,
api: Optional[OnlyFans.start| Fansly.start] = None,
webhooks:bool=True,
) -> Optional[OnlyFans.start]:
json_settings = json_config["settings"]
json_webhooks = json_settings["webhooks"]
json_sites = json_config["supported"]
domain = json_settings["auto_site_choice"]
main_helper.assign_vars(json_config)
json_site_settings = json_sites[site_name_lower]["settings"]
auto_model_choice = json_site_settings["auto_model_choice"]
if isinstance(auto_model_choice, str):
temp_identifiers = auto_model_choice.split(",")
identifiers = [x for x in temp_identifiers if x]
else:
identifiers = []
auto_profile_choice = json_site_settings["auto_profile_choice"]
subscription_array = []
proxies:list[str] = await api_helper.test_proxies(json_settings["proxies"])
if json_settings["proxies"] and not proxies:
print("Unable to create session")
return None
archive_time = timeit.default_timer()
match site_name_lower:
case "onlyfans":
site_name = "OnlyFans"
module = m_onlyfans
if not api:
api = OnlyFans.start(max_threads=json_settings["max_threads"])
api.settings = json_config
api = main_helper.process_profiles(json_settings, proxies, site_name, api)
print
subscription_array = []
auth_count = 0
jobs = json_site_settings["jobs"]
subscription_list = module.format_options(api.auths, "users")
if not auto_profile_choice:
print("Choose Profile")
auths = choose_option(subscription_list, auto_profile_choice, True)
api.auths = [x.pop(0) for x in auths]
for auth in api.auths:
if not auth.auth_details:
continue
module.assign_vars(
auth.auth_details, json_config, json_site_settings, site_name
)
setup = False
setup, subscriptions = await module.account_setup(
auth, identifiers, jobs, auth_count
)
if not setup:
if webhooks:
await main_helper.process_webhooks(api, "auth_webhook", "failed")
auth_details = {}
auth_details["auth"] = auth.auth_details.export()
profile_directory = auth.profile_directory
if profile_directory:
user_auth_filepath = os.path.join(
auth.profile_directory, "auth.json"
)
main_helper.export_data(auth_details, user_auth_filepath)
continue
auth_count += 1
subscription_array += subscriptions
await main_helper.process_webhooks(api, "auth_webhook", "succeeded")
# Do stuff with authed user
subscription_list = module.format_options(
subscription_array, "usernames", api.auths
)
if jobs["scrape_paid_content"] and api.has_active_auths():
print("Scraping Paid Content")
await module.paid_content_scraper(api, identifiers)
if jobs["scrape_names"] and api.has_active_auths():
print("Scraping Subscriptions")
await main_helper.process_names(
module,
subscription_list,
auto_model_choice,
api,
json_config,
site_name_lower,
site_name,
)
await main_helper.process_downloads(api, module)
if webhooks:
await main_helper.process_webhooks(api, "download_webhook", "succeeded")
case "fansly":
site_name = "Fansly"
module = m_fansly
if not api:
api = Fansly.start(max_threads=json_settings["max_threads"])
api.settings = json_config
api = main_helper.process_profiles(json_settings, proxies, site_name, api)
subscription_array = []
auth_count = 0
jobs = json_site_settings["jobs"]
subscription_list = module.format_options(api.auths, "users")
if not auto_profile_choice:
print("Choose Profile")
auths = choose_option(subscription_list, auto_profile_choice, True)
api.auths = [x.pop(0) for x in auths]
for auth in api.auths:
if not auth.auth_details:
continue
module.assign_vars(
auth.auth_details, json_config, json_site_settings, site_name
)
setup = False
setup, subscriptions = await module.account_setup(
auth, identifiers, jobs, auth_count
)
if not setup:
if webhooks:
await main_helper.process_webhooks(api, "auth_webhook", "failed")
auth_details = {}
auth_details["auth"] = auth.auth_details.export()
profile_directory = auth.profile_directory
if profile_directory:
user_auth_filepath = os.path.join(
auth.profile_directory, "auth.json"
)
main_helper.export_data(auth_details, user_auth_filepath)
continue
auth_count += 1
subscription_array += subscriptions
await main_helper.process_webhooks(api, "auth_webhook", "succeeded")
# Do stuff with authed user
subscription_list = module.format_options(
subscription_array, "usernames", api.auths
)
if jobs["scrape_paid_content"] and api.has_active_auths():
print("Scraping Paid Content")
await module.paid_content_scraper(api, identifiers)
if jobs["scrape_names"] and api.has_active_auths():
print("Scraping Subscriptions")
await main_helper.process_names(
module,
subscription_list,
auto_model_choice,
api,
json_config,
site_name_lower,
site_name,
)
await main_helper.process_downloads(api, module)
if webhooks:
await main_helper.process_webhooks(api, "download_webhook", "succeeded")
case "starsavn":
pass
# site_name = "StarsAVN"
# original_api = StarsAVN
# module = m_starsavn
# apis = main_helper.process_profiles(
# json_settings, original_sessions, site_name, original_api)
# auto_profile_choice = json_site_settings["auto_profile_choice"]
# subscription_array = []
# auth_count = -1
# jobs = json_site_settings["jobs"]
# subscription_list = module.format_options(
# apis, "users")
# apis = choose_option(
# subscription_list, auto_profile_choice)
# apis = [x.pop(0) for x in apis]
# for api in apis:
# module.assign_vars(api.auth.auth_details, json_config,
# json_site_settings, site_name)
# identifier = ""
# setup = False
# setup = module.account_setup(api, identifier=identifier)
# if not setup:
# auth_details = api.auth.auth_details.__dict__
# user_auth_filepath = os.path.join(
# api.auth.profile_directory, "auth.json")
# main_helper.export_data(
# auth_details, user_auth_filepath)
# continue
# if jobs["scrape_names"]:
# array = module.manage_subscriptions(
# api, auth_count, identifier=identifier)
# subscription_array += array
# subscription_list = module.format_options(
# subscription_array, "usernames")
# if jobs["scrape_paid_content"]:
# print("Scraping Paid Content")
# paid_content = module.paid_content_scraper(apis)
# if jobs["scrape_names"]:
# print("Scraping Subscriptions")
# names = main_helper.process_names(
# module, subscription_list, auto_model_choice, apis, json_config, site_name_lower, site_name)
# x = main_helper.process_downloads(apis, module)
stop_time = str(int(timeit.default_timer() - archive_time) / 60)[:4]
print("Archive Completed in " + stop_time + " Minutes")
return api
