From d829c4820adbe7a7634f1c1d825d0d206512e6e7 Mon Sep 17 00:00:00 2001
From: fiddlosopher <fiddlosopher@788f1e2b-df1e-0410-8736-df70ead52e1b>
Date: Fri, 22 Dec 2006 20:16:03 +0000
Subject: Merged changes from branches/wrappers since r177. Summary of main
 changes: + Added -o/--output and -d/--debug options to pandoc. + Modified
 pandoc to behave differently depending on the name   of the program.  For
 example, if the program name is 'html2latex',   the default reader will be
 html and the default writer latex. + Removed most of the old wrappers,
 replacing them with symlinks   to pandoc. + Rewrote markdown2pdf and created
 a new wrapper web2markdown,   with the functionality of the old html2markdown
 script.  These   new scripts exploit pandoc's -d option to avoid having to do
   complex command-line parsing. + Revised man pages and documentation
 appropriately.

git-svn-id: https://pandoc.googlecode.com/svn/trunk@279 788f1e2b-df1e-0410-8736-df70ead52e1b
---
 src/wrappers/web2markdown.in | 173 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 173 insertions(+)
 create mode 100644 src/wrappers/web2markdown.in

(limited to 'src/wrappers/web2markdown.in')

diff --git a/src/wrappers/web2markdown.in b/src/wrappers/web2markdown.in
new file mode 100644
index 000000000..64ff3db9b
--- /dev/null
+++ b/src/wrappers/web2markdown.in
@@ -0,0 +1,173 @@
+#!/bin/sh -e
+# converts HTML from a URL, file, or stdin to markdown
+# uses an available program to fetch URL and tidy to normalize it first
+
+REQUIRED="tidy html2markdown"
+
+### common.sh
+
+grab_url_with () {
+    url="${1:?internal error: grab_url_with: url required}"
+
+    shift
+    cmdline="$@"
+
+    prog=
+    prog_opts=
+    if [ -n "$cmdline" ]; then
+	eval "set -- $cmdline"
+	prog=$1
+	shift
+	prog_opts="$@"
+    fi
+
+    if [ -z "$prog" ]; then
+	# Locate a sensible web grabber (note the order).
+	for p in wget lynx w3m curl links w3c; do
+		if pathfind $p; then
+		    prog=$p
+		    break
+		fi
+	done
+
+	[ -n "$prog" ] || {
+            errn "$THIS:  Couldn't find a program to fetch the file from URL "
+	    err "(e.g. wget, w3m, lynx, w3c, or curl)."
+	    return 1
+	}
+    else
+	pathfind "$prog" || {
+	    err "$THIS:  No such web grabber '$prog' found; aborting."
+	    return 1
+	}
+    fi
+
+    # Setup proper base options for known grabbers.
+    base_opts=
+    case "$prog" in
+    wget)  base_opts="-O-" ;;
+    lynx)  base_opts="-source" ;;
+    w3m)   base_opts="-dump_source" ;;
+    curl)  base_opts="" ;;
+    links) base_opts="-source" ;;
+    w3c)   base_opts="-n -get" ;;
+    *)     err "$THIS:  unhandled web grabber '$prog'; hope it succeeds."
+    esac
+
+    err "$THIS: invoking '$prog $base_opts $prog_opts $url'..."
+    eval "set -- $base_opts $prog_opts"
+    $prog "$@" "$url"
+}
+
+add_option () {
+    options="$options$NEWLINE$1"
+}
+
+options=
+argument=
+encoding=
+grabber=
+
+# Parse command-line arguments
+while [ $# -gt 0 ]; do
+    case "$1" in
+        -h|--help)
+            html2markdown -h 2>&1 | sed -e 's/html2markdown/web2markdown/' 1>&2 
+            err "  -e ENCODING, --encoding=ENCODING"
+            err "        Specify character encoding of input"
+            err "  -g COMMAND, --grabber=COMMAND"
+            err "        Specify command to be used to grab contents of URL"
+            exit 0 ;;
+        -v|--version) 
+            html2markdown -v
+            exit 0 ;;
+        -e)
+            shift
+            encoding=$1 ;; 
+        --encoding=*)
+            wholeopt=$1
+            # extract encoding from after =
+            encoding=${wholeopt#*=} ;;
+        -g)
+            shift
+            grabber=$1 ;; 
+        --grabber=*)
+            wholeopt=$1
+            # extract encoding from after =
+            grabber=${wholeopt#*=} ;;
+        -o|--output|-b|--tab-stop|-H|--include-in-header| \
+        -A|--include-after-body|-C|-B|--include-before-body| \
+        -C|--custom-header|-T|--title-prefix) 
+            add_option $1
+            shift
+            add_option $1 ;;
+        -*) add_option $1 ;;
+        *) 
+            if [ -z "$argument" ]; then
+                argument=$1
+            else
+                err "Warning: extra argument '$1' will be ignored."
+            fi ;;            
+    esac
+    shift
+done
+
+# Unpack options.  Now "$@" will hold the html2markdown options.
+oldifs="$IFS"; IFS="$NEWLINE"; set -- $options; IFS="$oldifs"
+
+inurl=
+if [ -n "$argument" ] && ! [ -f "$argument" ]; then
+    # Treat given argument as an URL.
+    inurl="$argument"
+fi
+
+if [ -n "$inurl" ]; then
+    err "Attempting to fetch file from '$inurl'..."
+
+    ### tempdir.sh
+
+    grabber_out=$THIS_TEMPDIR/grabber.out
+    grabber_log=$THIS_TEMPDIR/grabber.log
+    if ! grab_url_with "$inurl" "$grabber" 1>$grabber_out 2>$grabber_log; then
+        errn "grab_url_with failed"
+        if [ -f $grabber_log ]; then
+            err " with the following error log."
+            err
+            cat >&2 $grabber_log
+        else
+            err .
+        fi
+        exit 1
+    fi
+
+    argument="$grabber_out"
+fi
+
+if [ -z "$encoding" ] && [ "x$argument" != "x" ]; then
+    # Try to determine character encoding if not specified
+    # and input is not STDIN.
+    encoding=$(
+        head "$argument" |
+        LC_ALL=C tr 'A-Z' 'a-z' |
+        sed -ne '/<meta .*content-type.*charset=/ {
+            s/.*charset=["'\'']*\([-a-zA-Z0-9]*\).*["'\'']*/\1/p
+        }'
+    )
+fi
+
+if [ -n "$encoding" ] && pathfind iconv; then
+    alias to_utf8='iconv -f "$encoding" -t utf-8'
+else # assume UTF-8
+    alias to_utf8='cat'
+fi 
+
+if [ -z "$argument" ]; then
+    tidy -utf8 2>/dev/null | html2markdown "$@"
+else
+    if [ -f "$argument" ]; then
+        to_utf8 "$argument" | tidy -utf8 2>/dev/null | html2markdown "$@"
+    else
+        err "File '$argument' not found."
+        exit 1
+    fi
+fi
-- 
cgit v1.2.3