itsulu/FediFetcher
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Cache robots.txt for 24 hours on disk to reduce load on servers

Browse source
This commit is contained in:
nanos 2024-06-26 16:41:51 +01:00
parent 3651d028a6
commit 7e8ca17640
1 changed files with 33 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
find_posts.py
View file

@ -1014,6 +1014,14 @@ def can_fetch(user_agent, url):
return ROBOTS_TXT[robots]
else:
robotsTxt = ROBOTS_TXT[robots]
else:
robotsCachePath = os.path.join(arguments.state_dir, f'robots-{parsed_uri.netloc}')
if os.path.exists(robotsCachePath):
with open(robotsCachePath, "r", encoding="utf-8") as f:
logger.debug(f"Getting robots.text file from cache {file_name}")
robotsTxt = f.read()
ROBOTS_TXT[robots] = robotsTxt
else:
try:
# We are getting the robots.txt manually from here, because otherwise we can't change the User Agent
@ -1026,6 +1034,10 @@ def can_fetch(user_agent, url):
return True
robotsTxt = robotsTxt.text
ROBOTS_TXT[robots] = robotsTxt
with open(robotsCachePath, "w", encoding="utf-8") as f:
f.write(robotsTxt)
except Exception as ex:
return True
@ -1467,6 +1479,15 @@ if __name__ == "__main__":
else:
seen_hosts = ServerList({})
# Delete any old robots.txt files so we can re-download them
for file_name in os.listdir(arguments.state_dir):
file_path = os.path.join(arguments.state_dir,file_name)
if file_name.startswith('robots-') and os.path.isfile(file_path):
if os.path.getmtime(file_path) < time.time() - 60 * 60 * 24:
logger.debug(f"Removing cached robots.text file {file_name}")
os.remove(file_path)
if(isinstance(arguments.access_token, str)):
setattr(arguments, 'access_token', [arguments.access_token])