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
|
package flyscrape
import (
"log"
"strings"
"sync"
"github.com/PuerkitoBio/goquery"
"github.com/cornelk/hashmap"
"github.com/nlnwa/whatwg-url/url"
)
type ScrapeParams struct {
HTML string
URL string
}
type ScrapeOptions struct {
URL string `json:"url"`
AllowedDomains []string `json:"allowed_domains"`
Depth int `json:"depth"`
}
type ScrapeResult struct {
URL string `json:"url"`
Data any `json:"data,omitempty"`
Links []string `json:"-"`
Error error `json:"error,omitempty"`
}
type (
ScrapeFunc func(ScrapeParams) (any, error)
FetchFunc func(url string) (string, error)
)
type Scraper struct {
ScrapeOptions ScrapeOptions
ScrapeFunc ScrapeFunc
FetchFunc FetchFunc
Concurrency int
visited *hashmap.Map[string, struct{}]
wg *sync.WaitGroup
}
type target struct {
url string
depth int
}
type result struct {
url string
data any
links []string
err error
}
func (s *Scraper) Scrape() <-chan ScrapeResult {
if s.Concurrency == 0 {
s.Concurrency = 1
}
jobs := make(chan target, 1024)
results := make(chan result)
scraperesults := make(chan ScrapeResult)
s.visited = hashmap.New[string, struct{}]()
s.wg = &sync.WaitGroup{}
for i := 0; i < s.Concurrency; i++ {
go s.worker(i, jobs, results)
}
s.wg.Add(1)
jobs <- target{url: s.ScrapeOptions.URL, depth: s.ScrapeOptions.Depth}
go func() {
s.wg.Wait()
close(jobs)
close(results)
}()
go func() {
for res := range results {
scraperesults <- ScrapeResult{
URL: res.url,
Data: res.data,
Links: res.links,
Error: res.err,
}
}
close(scraperesults)
}()
return scraperesults
}
func (s *Scraper) worker(id int, jobs chan target, results chan<- result) {
for j := range jobs {
res := s.process(j)
if j.depth > 0 {
for _, l := range res.links {
if _, ok := s.visited.Get(l); ok {
continue
}
s.wg.Add(1)
select {
case jobs <- target{url: l, depth: j.depth - 1}:
s.visited.Set(l, struct{}{})
default:
log.Println("queue is full, can't add url:", l)
s.wg.Done()
}
}
}
results <- res
s.wg.Done()
}
}
func (s *Scraper) process(job target) result {
html, err := s.FetchFunc(job.url)
if err != nil {
return result{url: job.url, err: err}
}
links := Links(html, job.url)
data, err := s.ScrapeFunc(ScrapeParams{HTML: html, URL: job.url})
if err != nil {
return result{url: job.url, links: links, err: err}
}
return result{url: job.url, data: data, links: links}
}
func Links(html string, origin string) []string {
var links []string
doc, err := goquery.NewDocumentFromReader(strings.NewReader(html))
if err != nil {
return nil
}
urlParser := url.NewParser(url.WithPercentEncodeSinglePercentSign())
uniqueLinks := make(map[string]bool)
doc.Find("a").Each(func(i int, s *goquery.Selection) {
link, _ := s.Attr("href")
parsedLink, err := urlParser.ParseRef(origin, link)
if err != nil || !isValidLink(parsedLink) {
return
}
absLink := parsedLink.Href(true)
if !uniqueLinks[absLink] {
links = append(links, absLink)
uniqueLinks[absLink] = true
}
})
return links
}
func isValidLink(link *url.Url) bool {
if link.Scheme() != "" && link.Scheme() != "http" && link.Scheme() != "https" {
return false
}
if strings.HasPrefix(link.String(), "javascript:") {
return false
}
return true
}
|