/
wikicrawl.go
205 lines (179 loc) · 4.57 KB
/
wikicrawl.go
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
package main
import (
"http"
"flag"
"git.78762.de/go/error"
"container/list"
"regexp"
"strings"
"bufio"
"bytes"
"io"
"runtime"
)
var (
lang string
rUnneededTags *regexp.Regexp
rAllTags *regexp.Regexp
rATags *regexp.Regexp
rAlphaNum *regexp.Regexp
visitedLinks map[string]bool
)
type WikiArticle struct {
url string
depth int
content string
}
func InitGlobals() {
rUnneededTags = regexp.MustCompile("<[^a][^>]*>")
rAllTags = regexp.MustCompile("<[^>]+>")
rATags = regexp.MustCompile("<a[^>]*href=\"(/wiki/[^?\"]+)\"[^>]*>")
rAlphaNum = regexp.MustCompile("[a-zA-Z0-9,.\\-]+")
visitedLinks = make(map[string]bool)
}
func main() {
error.SetPrefix("WikiCrawl")
error.PrintBacktrace(true)
defer error.ErrorHandler()
InitGlobals()
startpage := flag.String("s", "/wiki/Special:Random", "Page to start crawling at")
flag.StringVar(&lang, "l", "en", "Language of the wiki pages")
numlinks := flag.Int("n", 500, "Number of links to investigate")
flag.Parse()
queue := list.New()
queue.PushBack(&WikiArticle{url: "http://" + lang + ".wikipedia.org" + *startpage, depth: 0})
lines := Crawl(queue, *numlinks)
words := Wordify(lines)
_ = words
for _ = range words { }
//wordlist := CreateWordlist(lines)
}
func Crawl(queue *list.List, limit int) chan string {
articles := Fetcher(queue, limit)
lines, links := ContentExtractor(articles)
PushLinks(queue, links)
return lines
}
func Fetcher(queue *list.List, limit int) chan *WikiArticle {
articles := make(chan *WikiArticle)
go func() {
for i := 0; i < limit; i++ {
for queue.Front() == nil {
runtime.Gosched()
}
// url := q.PopFront()
article := queue.Front().Value.(*WikiArticle)
queue.Remove(queue.Front())
r, url, e := http.Get(article.url)
if e != nil {
println("Failed:", article.url)
continue
}
println("Fetched:", article.depth, url)
buf := bytes.NewBufferString("")
io.Copy(buf, r.Body)
article.content = buf.String()
r.Body.Close()
articles <- article
}
close(articles)
}()
return articles
}
func ContentExtractor(articles chan *WikiArticle) (chan string, chan *WikiArticle) {
text := make(chan string)
linkedArticles := make(chan *WikiArticle)
go func() {
for article := range articles {
article.content = truncateToBodyContent(article.content)
article.content = removeUnneededTags(article.content)
text <- extractText(article.content)
extractLinkedArticles(linkedArticles, article)
}
close(text)
close(linkedArticles)
}()
return text, linkedArticles
}
func PushLinks(queue *list.List, linkedArticles chan *WikiArticle) {
go func() {
for article := range linkedArticles {
article.url = "http://" + lang + ".wikipedia.org" + article.url
queue.PushBack(article)
}
}()
}
func truncateToBodyContent(content string) string {
s := ""
br := bufio.NewReader(strings.NewReader(content))
line, e := br.ReadString('\n')
foundStartSignal := false
for e == nil {
if !foundStartSignal {
foundStartSignal = containsStartSignal(line)
} else if !containsStopSignal(line) {
s += line
} else {
break
}
line, e = br.ReadString('\n')
}
return s
}
func containsStartSignal(line string) bool {
return strings.Contains(line, "<!-- bodyContent -->")
}
func containsStopSignal(line string) bool {
return strings.Contains(line, "<!-- /bodyContent -->")
}
func removeUnneededTags(s string) (r string) {
return rUnneededTags.ReplaceAllString(s, "")
}
func extractText(s string) string {
return rAllTags.ReplaceAllString(s, "")
}
func extractLinkedArticles(linkedArticles chan *WikiArticle, article *WikiArticle) {
matches := rATags.FindAllStringSubmatchIndex(article.content, -1)
if matches == nil {
return
}
for _, match := range matches {
rawmatch := article.content[match[2]:match[3]]
if isUnwantedPage(rawmatch) {
continue
}
_, ok := visitedLinks[rawmatch]
if ok {
continue
}
visitedLinks[rawmatch] = true
linkedArticles <- &WikiArticle{url: rawmatch, depth: article.depth + 1}
}
return
}
func Wordify(lines chan string) chan string {
words := make(chan string)
go func() {
for line := range lines {
br := bufio.NewReader(strings.NewReader(line))
w, e := br.ReadString(' ')
for e == nil {
if rAlphaNum.MatchString(w) {
words <- strings.TrimSpace(w)
}
w, e = br.ReadString(' ')
}
}
close(words)
}()
return words
}
func isUnwantedPage(path string) bool {
prefixes := []string{"File", "Special", "Wikipedia", "Template", "Talk", "Help"}
for _, prefix := range prefixes {
if strings.HasPrefix(path, "/wiki/"+prefix+":") {
return true
}
}
return false
}