blob: 8bae3a3bf10a0bf861798b2480708305cb9a41b3 (
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
|
#!/bin/sh -e
# converts html to markdown
# uses an available program to fetch URL and tidy to normalize it first
[ -n "$(which pandoc)" ] || {
echo >&2 "You need 'pandoc' to use this program!"
exit 1
}
[ -n "$(which tidy)" ] || {
echo >&2 "You need 'tidy' to use this program!"
exit 1
}
if [ -z "$1" ] || [ -f $1 ]; then
tidy -utf8 $1 2>/dev/null | pandoc -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 which $p >/dev/null; then
DUMPER=$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" ;;
"") echo -n >&2 "Needs a program to fetch the URL "
echo -n >&2 "(e.g. wget, w3m, lynx, w3c, or curl)."
exit 1 ;;
esac
# Fetch and feed to pandoc.
$DUMPER $OPT $1 2>/dev/null | tidy -utf8 2>/dev/null | pandoc -r html -w markdown -s | iconv -f utf-8
fi
|
