blob: 53ea05c08c8803e00e458601abca46afe3d15f1b (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
|
#!/bin/sh -e
# converts html to markdown
# uses an available program to fetch URL and tidy to normalize it first
pathfind () { # portable which(1), code taken from Debian Developer's Reference
OLDIFS="$IFS"
IFS=:
for _p in $PATH; do
if [ -x "$_p/$*" ]; then
IFS="$OLDIFS"
return 0
fi
done
IFS="$OLDIFS"
return 1
}
for p in pandoc tidy; do
pathfind $p || {
echo >&2 "You need '$p' to use this program!"
exit 1
}
done
ALL="$*"
ARGS=${ALL%% -- *} # only the part before ' -- ' delimiters is relevant
set -- $ARGS
REST=${ALL#$ARGS}; REST=${REST# -- }
PANDOC_OPTS=${REST:-$PANDOC_OPTS}
infile=$1
if [ $# -gt 1 ]; then
shift
echo >&2 "Warning: extra arguments '$@' will be ignored!"
fi
if [ -z "$infile" ] || [ -f $infile ]; then
tidy -utf8 $infile 2>/dev/null | \
pandoc $PANDOC_OPTS -r html -w markdown -s | \
iconv -f utf-8
else
# Treat given argument as an URL. Locate a
# sensible text based browser (note the order).
for p in wget lynx w3m curl links w3c; do
if pathfind $p; then
DUMPER=$p
break
fi
done
# Setup proper options.
case "$DUMPER" in
wget) OPT="-O-" ;;
lynx) OPT="-source" ;;
w3m) OPT="-dump_source" ;;
curl) OPT="" ;;
links) OPT="-source" ;;
w3c) OPT="-n -get" ;;
"") printf "Needs a program to fetch the URL " >&2
printf "(e.g. wget, w3m, lynx, w3c, or curl)." >&2
exit 1 ;;
esac
# Fetch and feed to pandoc.
$DUMPER $OPT $infile 2>/dev/null | \
tidy -utf8 2>/dev/null | \
pandoc $PANDOC_OPTS -r html -w markdown -s | \
iconv -f utf-8
fi
|
