Forks/open-source-search-engine
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix iswww directive

Browse Source
This commit is contained in:
mwells 2015-03-18 09:24:50 -06:00
parent 6a1875b619
commit d0be9f68a7
1 changed files with 3 additions and 5 deletions

8
Spider.cpp

@ -11771,10 +11771,9 @@ int32_t getUrlFilterNum2 ( SpiderRequest *sreq ,
}
// iswww, means url is like www.xyz.com/...
if ( strncmp(p,"iswww", 5) == 0 ) {
// now this is a bit
if ( (bool)sreq->m_isWWWSubdomain == (bool)val )
continue;
/*
// now this is a bit - doesn't seem to be working yet
//if ( (bool)sreq->m_isWWWSubdomain == (bool)val )
// continue;
// skip "iswww"
p += 5;
// skip over http:// or https://
@ -11788,7 +11787,6 @@ int32_t getUrlFilterNum2 ( SpiderRequest *sreq ,
u[2] == 'w' ) isWWW = 1;
// skip if no match
if ( isWWW == val ) continue;
*/
// TODO: fix www.knightstown.skepter.com
// maybe just have a bit in the spider request
// another rule?