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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
// URLs implements a breadth-first search webcrawler based on the
// example given in section 8.6 of The Go Programming Language.
package main
import (
"context"
"errors"
"fmt"
"log"
"net/url"
"os"
"runtime/pprof"
"strings"
"time"
"github.com/urfave/cli/v3"
)
const shortcodeFilename = "urls.csv"
func main() {
if os.Getenv("GOEXPERIMENT") != "goroutineleakprofile" {
log.Fatal("Missing GOEXPERIMENT=goroutineleakprofile environment setting")
}
// Setting shorfile helps especially for when we log errors
// without returning them.
log.SetFlags(log.LstdFlags | log.Lshortfile)
cmd := &cli.Command{
Usage: "A configurable web crawler",
Commands: []*cli.Command{
{
Name: "get",
Usage: "Crawl the target",
MutuallyExclusiveFlags: []cli.MutuallyExclusiveFlags{
{
Required: true,
Flags: [][]cli.Flag{
{
&cli.StringFlag{
Name: "shortcode",
Usage: "Specify target using a shortcode",
},
},
{
&cli.StringFlag{
Name: "url",
Usage: "Specify target using a URL",
},
},
},
},
},
Flags: []cli.Flag{
&cli.IntFlag{
Name: "concurrency",
Aliases: []string{"c"},
Usage: "Allowable number of concurrent URL fetches",
// Default concurrency setting is 1.
Value: 1,
},
&cli.IntFlag{
Name: "maxurls",
Aliases: []string{"m"},
Usage: "Maximum number of URLs to collect",
DefaultText: "no limit",
},
&cli.IntFlag{
Name: "depth",
Aliases: []string{"d"},
Usage: "Maximum URL depth",
DefaultText: "no limit",
},
},
Action: func(ctx context.Context, cmd *cli.Command) error {
if shortcode := cmd.String("shortcode"); shortcode != "" {
rawURL, err := getURLFromShortcode(shortcodeFilename, shortcode)
if err != nil {
return err
}
u, err := convertToURL(rawURL)
if err != nil {
return err
}
classic(u, cmd.Int("concurrency"), cmd.Int("maxurls"), cmd.Int("depth"))
return nil
}
if rawURL := cmd.String("url"); rawURL != "" {
u, err := convertToURL(rawURL)
if err != nil {
return err
}
classic(u, cmd.Int("concurrency"), cmd.Int("maxurls"), cmd.Int("depth"))
return nil
}
// We shouldn't reach this
// code, but let's at least
// document our intentions.
return errors.New("url and shortcode arguments should be mutually exclusive")
},
},
{
Name: "shortcode",
Usage: "Configure shortcodes",
Action: func(ctx context.Context, cmd *cli.Command) error {
fmt.Println("shortcode!")
return nil
},
},
},
}
if err := cmd.Run(context.Background(), os.Args); err != nil {
fmt.Printf("\n%v\n", err)
os.Exit(1)
}
}
// convertToURL parses the given rawURL into a [url.URL]. If the
// rawURL is missing a scheme, "https://" is prepended before parsing.
//
// Return the parsed URL, along with any error.
func convertToURL(rawURL string) (url.URL, error) {
if !strings.HasPrefix(rawURL, "http://") && !strings.HasPrefix(rawURL, "https://") {
rawURL = "https://" + rawURL
fmt.Printf("start url: %s\n", rawURL)
}
u, err := url.Parse(rawURL)
if err != nil {
return url.URL{}, fmt.Errorf("can't parse %s: %w", rawURL, err)
}
return *u, nil
}
// getLeakProfile runs a leaky program snippet, extracts the goroutine leak profile,
// and writes it to stdout.
func getLeakProfile(leakySnippet func()) {
prof := pprof.Lookup("goroutineleak")
defer func() {
time.Sleep(2 * time.Second)
var content strings.Builder
prof.WriteTo(&content, 2)
// Ignore non leaked goroutines
leaks := strings.SplitSeq(content.String(), "\n\n")
for leak := range leaks {
if strings.Contains(leak, "(leaked)") {
fmt.Println(leak + "\n")
}
}
}()
leakySnippet()
}
|
