32047739fe
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 features of crawl are: * Saves encountered images or other media types * Media selection based on regular expressions and size contraints * Resume previous crawl after graceful termination * Persistent database of visited URLs * Very small and efficient code * Asynchronous DNS lookups * Supports robots.txt
30 lines
880 B
Makefile
30 lines
880 B
Makefile
# $NetBSD: Makefile,v 1.1.1.1 2005/01/18 17:46:31 peter Exp $
|
|
|
|
DISTNAME= crawl-0.4
|
|
CATEGORIES= www
|
|
MASTER_SITES= http://monkey.org/~provos/
|
|
|
|
MAINTAINER= peter@pointless.nl
|
|
HOMEPAGE= http://monkey.org/~provos/crawl/
|
|
COMMENT= Small and efficient HTTP crawler
|
|
|
|
GNU_CONFIGURE= yes
|
|
USE_PKGINSTALL= yes
|
|
USE_BUILDLINK3= yes
|
|
USE_DB185= yes
|
|
|
|
CONF_FILES= ${PREFIX}/share/examples/${PKGBASE}/crawl.conf ${PKG_SYSCONFDIR}/crawl.conf
|
|
|
|
post-install:
|
|
${INSTALL_DATA_DIR} ${PREFIX}/share/examples/${PKGBASE}
|
|
${INSTALL_DATA} ${WRKSRC}/crawl.conf ${PREFIX}/share/examples/${PKGBASE}/crawl.conf
|
|
|
|
SUBST_CLASSES= path
|
|
SUBST_STAGE.path= post-patch
|
|
SUBST_FILES.path= cfg.h
|
|
SUBST_SED.path= -e 's,crawl.conf,${PKG_SYSCONFDIR}/crawl.conf,g'
|
|
SUBST_MESSAGE.path= "Fixing hardcoded path."
|
|
|
|
.include "../../devel/libevent/buildlink3.mk"
|
|
.include "../../mk/bdb.buildlink3.mk"
|
|
.include "../../mk/bsd.pkg.mk"
|