AIL/ail-framework
7
0
Fork 0
mirror of https://github.com/ail-project/ail-framework.git synced 2024-11-27 00:07:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chg: [crawler] add auto crawler functions

Browse source
This commit is contained in:
Terrtia 2021-10-14 14:23:11 +02:00
parent 57a69fa1f4
commit 57fbacc49c
No known key found for this signature in database
GPG key ID: 1E1B1F50D84613D0
1 changed files with 46 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
bin/lib/crawlers.py
View file

@ -479,6 +479,15 @@ def is_crawler_activated():
def get_crawler_all_types(): def get_crawler_all_types():
return ['onion', 'regular'] return ['onion', 'regular']
def sanitize_crawler_types(l_crawler_types):
all_crawler_types = get_crawler_all_types()
if not l_crawler_types:
return all_crawler_types
for crawler_type in l_crawler_types:
if crawler_type not in all_crawler_types:
return all_crawler_types
return l_crawler_types
def get_all_spash_crawler_status(): def get_all_spash_crawler_status():
crawler_metadata = [] crawler_metadata = []
all_crawlers = r_cache.smembers('all_splash_crawlers') all_crawlers = r_cache.smembers('all_splash_crawlers')
@ -600,9 +609,40 @@ def api_set_nb_crawlers_to_launch(dict_splash_name):
else: else:
return ({'error':'invalid input'}, 400) return ({'error':'invalid input'}, 400)
##-- CRAWLER GLOBAL --## ##-- CRAWLER GLOBAL --##
#### AUTOMATIC CRAWLER ####
def get_auto_crawler_all_domain(l_crawler_types=[]):
l_crawler_types = sanitize_crawler_types(l_crawler_types)
if len(l_crawler_types) == 1:
return r_serv_onion.smembers(f'auto_crawler_url:{crawler_type[0]}')
else:
l_keys_name = []
for crawler_type in l_crawler_types:
l_keys_name.append(f'auto_crawler_url:{crawler_type}')
return r_serv_onion.sunion(l_keys_name[0], *l_keys_name[1:])
def add_auto_crawler_in_queue(domain, domain_type, port, epoch, delta, message):
r_serv_onion.zadd('crawler_auto_queue', int(time.time() + delta) , f'{message};{domain_type}')
# update list, last auto crawled domains
r_serv_onion.lpush('last_auto_crawled', f'{domain}:{port};{epoch}')
r_serv_onion.ltrim('last_auto_crawled', 0, 9)
def update_auto_crawler_queue():
current_epoch = int(time.time())
current_epoch = 1631096842
# check if current_epoch > domain_next_epoch
l_queue = r_serv_onion.zrangebyscore('crawler_auto_queue', 0, current_epoch)
for elem in l_queue:
mess, domain_type = elem.rsplit(';', 1)
print(domain_type)
print(mess)
r_serv_onion.sadd(f'{domain_type}_crawler_priority_queue', mess)
##-- AUTOMATIC CRAWLER --##
#### CRAWLER TASK #### #### CRAWLER TASK ####
def create_crawler_task(url, screenshot=True, har=True, depth_limit=1, max_pages=100, auto_crawler=False, crawler_delta=3600, crawler_type=None, cookiejar_uuid=None, user_agent=None): def create_crawler_task(url, screenshot=True, har=True, depth_limit=1, max_pages=100, auto_crawler=False, crawler_delta=3600, crawler_type=None, cookiejar_uuid=None, user_agent=None):
@ -1448,10 +1488,14 @@ def test_ail_crawlers():
#### ---- #### #### ---- ####
#if __name__ == '__main__': if __name__ == '__main__':
# res = get_splash_manager_version() # res = get_splash_manager_version()
# res = test_ail_crawlers() # res = test_ail_crawlers()
# res = is_test_ail_crawlers_successful() # res = is_test_ail_crawlers_successful()
# print(res) # print(res)
# print(get_test_ail_crawlers_message()) # print(get_test_ail_crawlers_message())
#print(get_all_queues_stats()) #print(get_all_queues_stats())
#res = get_auto_crawler_all_domain()
res = update_auto_crawler_queue()
print(res)