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
|
package main
import "os"
import "fmt"
import "log"
import "time"
import "sync"
import "strconv"
import "strings"
import "net/url"
import "github.com/PuerkitoBio/goquery"
type link struct {
u *url.URL
depth int
}
var mutex *sync.Mutex
var Prev map[string]bool
var tFile *os.File
var base string
func validLink(s string) bool {
return true
//return (strings.HasSuffix(s, ".html") || strings.HasSuffix(s, "/") || strings.HasSuffix(s, "\\"))
}
func addLinks(doc *goquery.Document, jobs chan link, current link, depth int, worker_id int) {
doc.Find("body a").Each(func(index int, item *goquery.Selection) {
link_s, _ := item.Attr("href")
d := depth + 1
u, err := url.Parse(link_s)
if err != nil {
panic(err)
}
if !u.IsAbs() {
u = current.u.ResolveReference(u)
}
if strings.Contains(u.String(), base) && validLink(u.String()) {
mutex.Lock()
if !Prev[u.String()] {
jobs <- link{u, d}
Prev[u.String()] = true
}
mutex.Unlock()
} else {
fmt.Printf("%s Failed: contains: %v 2: %v\n", u.String(), strings.Contains(u.String(), base), validLink(u.String()))
}
})
}
func consume(doc *goquery.Document, worker_id int) {
var title string
doc.Find("title").Each(func(index int, item *goquery.Selection) {
title = item.Text()
})
fmt.Println(title)
}
func worker(done chan bool, jobs chan link, depth int, id int) {
for {
fmt.Printf("%d Waiting... buffered: %d\n", id, len(jobs))
select {
case j := <-jobs:
if j.depth < depth {
doc, err := goquery.NewDocument(j.u.String())
if err != nil {
log.Print("Error Reading Document: " + j.u.String() + err.Error())
break
}
fmt.Printf("worker %d Working on %s depth: %d...\n", id, j.u.String(), j.depth)
consume(doc, id)
fmt.Println("Adding Links")
addLinks(doc, jobs, j, j.depth, id)
fmt.Println("Done Adding Links")
}
case <-time.After(time.Second * 10):
fmt.Printf("Worker %d done\n", id)
done <- true
return
}
}
}
func init() {
mutex = &sync.Mutex{}
Prev = make(map[string]bool)
var err error
tFile, err = os.Create("./test.txt")
if err != nil {
panic(err)
}
}
func main() {
var d, w int
if len(os.Args) < 3 {
fmt.Printf("usage: crawler url depth [workers]\n")
panic("test")
}
base = strings.TrimPrefix(os.Args[1], "http://www.")
base = strings.TrimPrefix(base, "https://www.")
if base == os.Args[1] {
panic(base)
}
fmt.Println(base)
d, _ = strconv.Atoi(os.Args[2])
if len(os.Args) == 4 {
w, _ = strconv.Atoi(os.Args[3])
} else {
w = 4
}
jobs := make(chan link, 1024*1024)
done := make(chan bool)
u, err := url.Parse(os.Args[1])
if err != nil {
panic(err)
}
if !u.IsAbs() {
panic("Cannot start with relative url")
}
fmt.Println(u)
fmt.Println(u.RawPath)
fmt.Println(u.String())
fmt.Println("jobs")
jobs <- link{u, 0}
//send first job
for i := 0; i < w; i++ {
go worker(done, jobs, d, i)
}
for i := 0; i < w; {
select {
case <-done:
fmt.Printf("%d done\n", i)
i++
case <-time.After(1 * time.Second):
if len(jobs) == (1024 * 1024) {
i = w
}
}
}
tFile.Close()
close(done)
fmt.Println(len(jobs))
close(jobs)
}
|
