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

fix: [Crawler] retry when splash is not available

Browse source
This commit is contained in:
Terrtia 2018-12-17 16:04:12 +01:00
parent 4e08aaa80f
commit f842194c57
No known key found for this signature in database
GPG key ID: 1E1B1F50D84613D0
1 changed files with 20 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

30
bin/Crawler.py
View file

@ -27,17 +27,27 @@ def crawl_onion(url, domain, date, date_month, message):
if super_father is None:
super_father=paste
try:
r = requests.get(splash_url , timeout=30.0)
except Exception:
# TODO: relaunch docker or send error message
retry = True
nb_retry = 0
while retry:
try:
r = requests.get(splash_url , timeout=30.0)
retry = False
except Exception:
# TODO: relaunch docker or send error message
nb_retry += 1
on_error_send_message_back_in_queue(type_hidden_service, domain, message)
publisher.error('{} SPASH DOWN'.format(splash_url))
print('--------------------------------------')
print(' \033[91m DOCKER SPLASH DOWN\033[0m')
print(' {} DOWN'.format(splash_url))
exit(1)
if nb_retry == 30:
on_error_send_message_back_in_queue(type_hidden_service, domain, message)
publisher.error('{} SPASH DOWN'.format(splash_url))
print('--------------------------------------')
print(' \033[91m DOCKER SPLASH DOWN\033[0m')
print(' {} DOWN'.format(splash_url))
exit(1)
print(' \033[91m DOCKER SPLASH NOT AVAILABLE\033[0m')
print(' Retry({}) in 10 seconds'.format(nb_retry))
time.sleep(10)
if r.status_code == 200:
process = subprocess.Popen(["python", './torcrawler/tor_crawler.py', splash_url, type_hidden_service, url, domain, paste, super_father],