blob: cc0f83ce9732df0d3f084f2f3fc3fc95d0617506 (
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
|
#!/bin/bash
# v0.1 : basic title extract
# v0.2 : added help arguments
# v0.3 : added version arguments
# v0.3.1: change !title to title in version info
# v0.4 : added case insensitive matching
# v0.5 : ignore SSL certificate errors
# v0.6 : switch to curl, add maximum filesize and time limits
# v0.7 : follow HTTP redirects, was broken since switch to curl
# v0.7.1: pretend to be Firefox, some broken websites reject cURL
# v0.8 : strip newlines and leading whitespace from "broken" titles
# : update user agent string
# v0.8.1: change name in version string to "blatitle"
# v0.9 : add support for gzip compression
# v0.9.1: fix support for servers that don't support HTTP HEAD
# v0.9.2: tidy up temporary files afterwards
# v0.9.3: advertise text/html acceptance as some servers require it
# v0.9.4: switch to a cleaner awk script to detect titles
# v1.0 : if Content-Type is text/plain, just use the first line as the title
# v1.1 : decode HTML in the title using recode (adds recode as a dependency)
# v1.2 : deal with some cURL exit codes
OPTS='--location --insecure --silent --max-filesize 1048576 --max-time 10 -A "Mozilla/5.0 (X11; Linux x86_64; rv:36.0) Gecko/20100101 Firefox/36.0" -H "Accept-Encoding: gzip" -H "Accept: text/html"'
read url
TIME=$(date +%s%N)
if [ -z "$TIME" ]
then
echo "Timestamp error"
exit 1
fi
if [ "$url" == "-h" ] || [ "$url" == "--help" ]
then
echo "Usage: '!title <url>' where <url> is an http:// or https:// URL"
elif [ "$url" == "-v" ] || [ "$url" == "--version" ]
then
echo "blatitle version 1.2"
else
eval curl $OPTS -D /tmp/$TIME.header '$url' -o /tmp/$TIME.body.gz
ret=$?
if [ "$ret" -eq 28 ]
then
echo "Connection to host timed out!"
exit
elif [ "$ret" -ne 0 ]
then
echo "cURL error $ret when fetching the page."
exit
fi
grep -q "Content-Encoding: gzip" /tmp/$TIME.header && gunzip /tmp/$TIME.body.gz || mv /tmp/$TIME.body.gz /tmp/$TIME.body
grep -q "Content-Type: text/plain" /tmp/$TIME.header && TYPE="text/plain"
if [ "$TYPE" == "text/plain" ]
then
head -n1 /tmp/$TIME.body
else
awk -vRS="</title>" '/<title>/{gsub(/.*<title>|\n+/,"");print;exit}' IGNORECASE=1 /tmp/$TIME.body | sed ':a;N;$!ba;s/\n//g' | sed -e 's/^[ \t]*//' | recode html..ascii
fi
rm /tmp/$TIME.header /tmp/$TIME.body
fi
|
