Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-07 17:33:05 +01:00
Code Issues Projects Releases Wiki Activity

More direct way for /../ in Get Story URLs from web page, previous broke other sites. #1160

Browse source
This commit is contained in:
Jim Miller 2025-02-23 20:37:16 -06:00
parent 9b8eb547fc
commit 8e55d1e6f4
1 changed files with 9 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
fanficfare/geturls.py
View file

@ -23,7 +23,7 @@ import re
# unicode in py2, str in py3 # unicode in py2, str in py3
from .six.moves.urllib.request import urlopen from .six.moves.urllib.request import urlopen
from .six.moves.urllib.parse import (urlparse, urlunparse, urljoin) from .six.moves.urllib.parse import (urlparse, urlunparse)
from .six import text_type as unicode from .six import text_type as unicode
from .six import ensure_str from .six import ensure_str
@ -137,7 +137,7 @@ def form_url(parenturl,url):
returl = urlunparse( returl = urlunparse(
(parsedUrl.scheme, (parsedUrl.scheme,
parsedUrl.netloc, parsedUrl.netloc,
urljoin(url,'.'), url,
'','','')) '','',''))
else: else:
toppath="" toppath=""
@ -148,7 +148,7 @@ def form_url(parenturl,url):
returl = urlunparse( returl = urlunparse(
(parsedUrl.scheme, (parsedUrl.scheme,
parsedUrl.netloc, parsedUrl.netloc,
urljoin(toppath + '/' + url,'.'), toppath + '/' + url,
'','','')) '','',''))
return returl return returl
@ -181,6 +181,12 @@ def cleanup_url(href,configuration,foremail=False):
href = href.replace('&index=1','') href = href.replace('&index=1','')
except Exception as e: except Exception as e:
logger.warning("Skipping royalroad email URL %s, got HTTP error %s"%(href,e)) logger.warning("Skipping royalroad email URL %s, got HTTP error %s"%(href,e))
if '/../' in href:
## For mcstories.com, see #1160 All my attempts to use
## urljoin() got uncomfortably complex in the face of
## javascript links and parameter URLs. And normpath() will
## give \ on windows.
href = re.sub(r'([^/]+/../)',r'',href)
return href return href
def get_urls_from_imap(srv,user,passwd,folder,markread=True,normalize_urls=False): def get_urls_from_imap(srv,user,passwd,folder,markread=True,normalize_urls=False):