Index: head/www/crawl/Makefile =================================================================== --- head/www/crawl/Makefile (revision 457210) +++ head/www/crawl/Makefile (revision 457211) @@ -1,33 +1,33 @@ # Created by: Pete Fritchman # $FreeBSD$ PORTNAME= crawl PORTVERSION= 0.4 PORTREVISION= 13 CATEGORIES= www MASTER_SITES= http://www.monkey.org/~provos/ MAINTAINER= ports@FreeBSD.org COMMENT= Small, efficient web crawler with advanced features LICENSE= BSD4CLAUSE LIB_DEPENDS= libevent.so:devel/libevent USES= bdb pkgconfig GNU_CONFIGURE= yes CONFIGURE_ARGS= --with-libevent --program-transform-name='' CONFIGURE_ENV= EVENTINC="`pkgconf --cflags libevent`" EVENTLIB="`pkgconf --libs libevent`" OPTIONS_DEFINE= EXAMPLES post-patch: @${REINPLACE_CMD} -e 's,/usr/include/db2,${BDB_INCLUDE_DIR},g' \ -e 's,db2,${BDB_LIB_NAME},g' ${WRKSRC}/configure.in -post-install: +post-install-EXAMPLES-on: @${MKDIR} ${STAGEDIR}${EXAMPLESDIR} ${INSTALL_DATA} ${WRKSRC}/crawl.conf ${STAGEDIR}${EXAMPLESDIR} .include Index: head/www/crawl/files/patch-Makefile.in =================================================================== --- head/www/crawl/files/patch-Makefile.in (revision 457210) +++ head/www/crawl/files/patch-Makefile.in (revision 457211) @@ -1,10 +1,10 @@ ---- Makefile.in.orig Sat May 17 20:50:51 2003 -+++ Makefile.in Sun Dec 21 12:19:52 2003 -@@ -159,7 +154,6 @@ +--- Makefile.in.orig 2003-05-18 01:50:51 UTC ++++ Makefile.in +@@ -159,7 +159,6 @@ $(srcdir)/config.h.in: $(srcdir)/stamp-h $(MAKE) $(srcdir)/stamp-h.in; \ else :; fi $(srcdir)/stamp-h.in: $(top_srcdir)/configure.in $(ACLOCAL_M4) acconfig.h - cd $(top_srcdir) && $(AUTOHEADER) @echo timestamp > $(srcdir)/stamp-h.in 2> /dev/null mostlyclean-hdr: Index: head/www/crawl/files/patch-compat__gai-errnos.h =================================================================== --- head/www/crawl/files/patch-compat__gai-errnos.h (revision 457210) +++ head/www/crawl/files/patch-compat__gai-errnos.h (revision 457211) @@ -1,10 +1,10 @@ ---- compat/gai-errnos.h.orig Fri Mar 12 07:29:36 2004 -+++ compat/gai-errnos.h Fri Mar 12 07:29:52 2004 +--- compat/gai-errnos.h.orig 2003-05-17 16:39:02 UTC ++++ compat/gai-errnos.h @@ -10,5 +10,7 @@ /* for old netdb.h */ #ifndef EAI_NODATA #define EAI_NODATA 1 +#endif +#ifndef EAI_MEMORY #define EAI_MEMORY 2 #endif Index: head/www/crawl/files/patch-configure =================================================================== --- head/www/crawl/files/patch-configure (revision 457210) +++ head/www/crawl/files/patch-configure (revision 457211) @@ -1,17 +1,17 @@ ---- configure.orig Sun Dec 21 12:18:11 2003 -+++ configure Sun Dec 21 12:18:28 2003 -@@ -2545,11 +2545,11 @@ +--- configure.orig 2003-05-18 01:50:55 UTC ++++ configure +@@ -2545,11 +2545,11 @@ echo "${ECHO_T}no" >&6 *) echo "$as_me:$LINENO: result: $withval" >&5 echo "${ECHO_T}$withval" >&6 - if test -f $withval/event.h -a -f $withval/libevent.a; then + if test -f $withval/include/event.h -a -f $withval/lib/libevent.a; then owd=`pwd` if cd $withval; then withval=`pwd`; cd $owd; fi - EVENTINC="-I$withval" - EVENTLIB="-L$withval -levent" + EVENTINC="-I$withval/include" + EVENTLIB="-L$withval/lib -levent" else { { echo "$as_me:$LINENO: error: event.h or libevent.a not found in $withval" >&5 echo "$as_me: error: event.h or libevent.a not found in $withval" >&2;} Index: head/www/crawl/files/patch-dns.c =================================================================== --- head/www/crawl/files/patch-dns.c (revision 457210) +++ head/www/crawl/files/patch-dns.c (revision 457211) @@ -1,16 +1,16 @@ ---- dns.c.orig Sun May 18 10:21:33 2003 -+++ dns.c Mon May 30 16:20:14 2005 -@@ -562,8 +562,13 @@ +--- dns.c.orig 2003-05-18 01:21:33 UTC ++++ dns.c +@@ -562,8 +562,13 @@ dns_resolve(char *ip, struct addrinfo ** if (res != 0) { fprintf(stderr, "%s: getaddrinfo(%s): %s\n", __func__, ip, gai_strerror(res)); +#ifdef EAI_NODATA if (res != EAI_NODATA) return (-1); +#else + if (res != EAI_NONAME) + return (-1); +#endif /* Negative caching */ ai = NULL; Index: head/www/crawl/pkg-descr =================================================================== --- head/www/crawl/pkg-descr (revision 457210) +++ head/www/crawl/pkg-descr (revision 457211) @@ -1,20 +1,20 @@ The crawl utility starts a depth-first traversal of the web at the specified URLs. It stores all JPEG images that match the configured constraints. Crawl is fairly fast and allows for graceful termination. After terminating crawl, it is possible to restart it at exactly the same spot where it was terminated. Crawl keeps a persistent database that allows multiple crawls without revisiting sites. The main reason for writing crawl was the lack of simple open source web crawlers. Crawl is only a few thousand lines of code and fairly easy to debug and customize. Some of the main features: - Saves encountered JPEG images - Image selection based on regular expressions and size contrainsts - Resume previous crawl after graceful termination - Persistent database of visited URLs - Very small and efficient code - Supports robots.txt -WWW: http://www.monkey.org/~provos/crawl/ +WWW: https://www.monkey.org/~provos/crawl/