blob: 0fece3ccdb3dbadecdd583d4fdd1156abe35e307 (
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
|
#!/bin/sh -e
# converts html to markdown
# uses an available program to fetch URL and tidy to normalize it first
REQUIRED=tidy
### 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"
}
encoding=
grabber=
nograb=
while getopts e:g:nh opt; do
case $opt in
e) encoding="$OPTARG" ;;
g) grabber="$OPTARG" ;;
n) nograb=1 ;;
h|?)
usage "[-e encoding] [-g grabber_command] [-n] [-h] [input_file|url]"
exit 2 ;;
esac
done
shift $(($OPTIND - 1))
### postopts.sh
### singlearg.sh
inurl=
if [ -n "$1" ] && ! [ -f "$1" ]; then
if [ -n "$nograb" ]; then
err "'$1' not found; refusing to treat input as URL."
exit 1
fi
# Treat given argument as an URL.
inurl="$1"
fi
if [ -n "$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
set -- $grabber_out
fi
if [ -z "$encoding" ] && [ "x$@" != "x" ]; then
# Try to determine character encoding unless not specified
# and input is STDIN.
encoding=$(
head "$@" |
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 "$encoding" ] && [ -n "$HAVE_ICONV" ]; then
alias to_utf8='iconv -f "$encoding" -t utf-8'
elif [ -n "$inurl" ]; then # assume web pages are UTF-8
alias to_utf8='cat'
fi # else just use local encoding
to_utf8 "$@" | tidy -utf8 2>/dev/null |
runpandoc -r html -w markdown -s | from_utf8
|
