summaryrefslogtreecommitdiff
path: root/www/crawl
diff options
context:
space:
mode:
authorpeter <peter@pkgsrc.org>2005-01-18 17:46:31 +0000
committerpeter <peter@pkgsrc.org>2005-01-18 17:46:31 +0000
commit32047739fe7311f437c2ad717d6f2d729968f297 (patch)
tree567d63160e9c0a97b1563f6dbf544c6d13ba52aa /www/crawl
parentcc4a074fe91572d1fcf28f6d084e9e14b4c3b71d (diff)
downloadpkgsrc-32047739fe7311f437c2ad717d6f2d729968f297.tar.gz
Initial import of crawl-0.4 into the NetBSD Packages Collection.
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
Diffstat (limited to 'www/crawl')
-rw-r--r--www/crawl/DESCR16
-rw-r--r--www/crawl/Makefile30
-rw-r--r--www/crawl/PLIST5
-rw-r--r--www/crawl/distinfo7
-rw-r--r--www/crawl/patches/patch-aa19
-rw-r--r--www/crawl/patches/patch-ab14
-rw-r--r--www/crawl/patches/patch-ac13
7 files changed, 104 insertions, 0 deletions
diff --git a/www/crawl/DESCR b/www/crawl/DESCR
new file mode 100644
index 00000000000..854815c3ab0
--- /dev/null
+++ b/www/crawl/DESCR
@@ -0,0 +1,16 @@
+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
diff --git a/www/crawl/Makefile b/www/crawl/Makefile
new file mode 100644
index 00000000000..17166b1a98e
--- /dev/null
+++ b/www/crawl/Makefile
@@ -0,0 +1,30 @@
+# $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"
diff --git a/www/crawl/PLIST b/www/crawl/PLIST
new file mode 100644
index 00000000000..af0eb30128f
--- /dev/null
+++ b/www/crawl/PLIST
@@ -0,0 +1,5 @@
+@comment $NetBSD: PLIST,v 1.1.1.1 2005/01/18 17:46:31 peter Exp $
+bin/crawl
+man/man1/crawl.1
+share/examples/${PKGBASE}/crawl.conf
+@dirrm share/examples/${PKGBASE}
diff --git a/www/crawl/distinfo b/www/crawl/distinfo
new file mode 100644
index 00000000000..a5fd8ee0979
--- /dev/null
+++ b/www/crawl/distinfo
@@ -0,0 +1,7 @@
+$NetBSD: distinfo,v 1.1.1.1 2005/01/18 17:46:31 peter Exp $
+
+SHA1 (crawl-0.4.tar.gz) = b53be27b572ba6a88ab80243b177873aed0b314b
+Size (crawl-0.4.tar.gz) = 111084 bytes
+SHA1 (patch-aa) = 874cb3b73cbc56e320c58039ecc9fd98ab258a0b
+SHA1 (patch-ab) = 9c934c5c7f03e4acbd02222a30267aded4d01e26
+SHA1 (patch-ac) = 079c792e55fa3e60dead7ff9c1c46132d01a00d4
diff --git a/www/crawl/patches/patch-aa b/www/crawl/patches/patch-aa
new file mode 100644
index 00000000000..01fbfe2b1bf
--- /dev/null
+++ b/www/crawl/patches/patch-aa
@@ -0,0 +1,19 @@
+$NetBSD: patch-aa,v 1.1.1.1 2005/01/18 17:46:31 peter Exp $
+
+--- configure.orig 2003-05-18 03:50:55.000000000 +0200
++++ configure 2004-06-11 23:51:00.000000000 +0200
+@@ -2669,6 +2669,14 @@
+ DBINC="-I/usr/include/db2"
+ DBLIB="-ldb2"
+ have_db=yes
++ elif test -f /usr/include/db1/db.h; then
++
++cat >>confdefs.h <<\_ACEOF
++#define HAVE_DB1_H 1
++_ACEOF
++
++ DBLIB="-ldb"
++ have_db=yes
+ elif test -f /usr/include/db_185.h; then
+
+ cat >>confdefs.h <<\_ACEOF
diff --git a/www/crawl/patches/patch-ab b/www/crawl/patches/patch-ab
new file mode 100644
index 00000000000..c3ba1e7ce79
--- /dev/null
+++ b/www/crawl/patches/patch-ab
@@ -0,0 +1,14 @@
+$NetBSD: patch-ab,v 1.1.1.1 2005/01/18 17:46:31 peter Exp $
+
+--- config.h.in.orig 2003-05-18 02:54:45.000000000 +0200
++++ config.h.in 2004-06-12 00:06:58.000000000 +0200
+@@ -42,6 +42,9 @@
+ /* Define if your system has libdb */
+ #undef HAVE_DB_H
+
++/* Define if your system has libdb */
++#undef HAVE_DB1_H
++
+ /* Define to 1 if you have the `dirname' function. */
+ #undef HAVE_DIRNAME
+
diff --git a/www/crawl/patches/patch-ac b/www/crawl/patches/patch-ac
new file mode 100644
index 00000000000..6812a77a969
--- /dev/null
+++ b/www/crawl/patches/patch-ac
@@ -0,0 +1,13 @@
+$NetBSD: patch-ac,v 1.1.1.1 2005/01/18 17:46:31 peter Exp $
+
+--- crawldb.c.orig 2003-05-17 18:59:51.000000000 +0200
++++ crawldb.c 2004-06-11 23:56:47.000000000 +0200
+@@ -44,6 +44,8 @@
+ #include <db_185.h>
+ #elif HAVE_DB_H
+ #include <db.h>
++#elif HAVE_DB1_H
++#include <db1/db.h>
+ #endif
+ #include <compat/md5.h>
+