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
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
|
// This Source Code Form is subject to the terms of the Mozilla Public
// License, v. 2.0. If a copy of the MPL was not distributed with this
// file, You can obtain one at http://mozilla.org/MPL/2.0/.
package flyscrape
import (
"fmt"
"io"
"log"
"net/http"
"net/http/cookiejar"
"sync"
"github.com/cornelk/hashmap"
)
type Context interface {
ScriptName() string
Visit(url string)
MarkVisited(url string)
MarkUnvisited(url string)
}
type Request struct {
Method string
URL string
Headers http.Header
Cookies http.CookieJar
Depth int
}
type Response struct {
StatusCode int
Headers http.Header
Body []byte
Data any
Error error
Request *Request
Visit func(url string)
}
type target struct {
url string
depth int
}
func NewScraper() *Scraper {
return &Scraper{}
}
type Scraper struct {
ScrapeFunc ScrapeFunc
SetupFunc func()
Script string
Modules []Module
Client *http.Client
wg sync.WaitGroup
jobs chan target
visited *hashmap.Map[string, struct{}]
}
func (s *Scraper) Visit(url string) {
s.enqueueJob(url, 0)
}
func (s *Scraper) MarkVisited(url string) {
s.visited.Insert(url, struct{}{})
}
func (s *Scraper) MarkUnvisited(url string) {
s.visited.Del(url)
}
func (s *Scraper) ScriptName() string {
return s.Script
}
func (s *Scraper) Run() {
s.jobs = make(chan target, 1<<20)
s.visited = hashmap.New[string, struct{}]()
s.initClient()
for _, mod := range s.Modules {
if v, ok := mod.(Provisioner); ok {
v.Provision(s)
}
}
for _, mod := range s.Modules {
if v, ok := mod.(TransportAdapter); ok {
s.Client.Transport = v.AdaptTransport(s.Client.Transport)
}
}
if s.SetupFunc != nil {
s.SetupFunc()
}
go s.scrape()
s.wg.Wait()
close(s.jobs)
for _, mod := range s.Modules {
if v, ok := mod.(Finalizer); ok {
v.Finalize()
}
}
}
func (s *Scraper) initClient() {
if s.Client == nil {
s.Client = &http.Client{}
}
if s.Client.Jar == nil {
s.Client.Jar, _ = cookiejar.New(nil)
}
if s.Client.Transport == nil {
s.Client.Transport = http.DefaultTransport
}
}
func (s *Scraper) scrape() {
for i := 0; i < 500; i++ {
go func() {
for job := range s.jobs {
job := job
s.process(job.url, job.depth)
s.wg.Done()
}
}()
}
}
func (s *Scraper) process(url string, depth int) {
request := &Request{
Method: http.MethodGet,
URL: url,
Headers: defaultHeaders(),
Cookies: s.Client.Jar,
Depth: depth,
}
response := &Response{
Request: request,
Visit: func(url string) {
s.enqueueJob(url, depth+1)
},
}
for _, mod := range s.Modules {
if v, ok := mod.(RequestBuilder); ok {
v.BuildRequest(request)
}
}
req, err := http.NewRequest(request.Method, request.URL, nil)
if err != nil {
response.Error = err
return
}
req.Header = request.Headers
for _, mod := range s.Modules {
if v, ok := mod.(RequestValidator); ok {
if !v.ValidateRequest(request) {
return
}
}
}
defer func() {
for _, mod := range s.Modules {
if v, ok := mod.(ResponseReceiver); ok {
v.ReceiveResponse(response)
}
}
}()
resp, err := s.Client.Do(req)
if err != nil {
response.Error = err
return
}
defer resp.Body.Close()
response.StatusCode = resp.StatusCode
response.Headers = resp.Header
if response.StatusCode < 200 || response.StatusCode >= 300 {
response.Error = fmt.Errorf("%d %s", response.StatusCode, http.StatusText(response.StatusCode))
}
response.Body, err = io.ReadAll(resp.Body)
if err != nil {
response.Error = err
return
}
if s.ScrapeFunc != nil {
response.Data, err = s.ScrapeFunc(ScrapeParams{HTML: string(response.Body), URL: request.URL})
if err != nil {
response.Error = err
return
}
}
}
func (s *Scraper) enqueueJob(url string, depth int) {
if _, ok := s.visited.Get(url); ok {
return
}
s.wg.Add(1)
select {
case s.jobs <- target{url: url, depth: depth}:
s.MarkVisited(url)
default:
log.Println("queue is full, can't add url:", url)
s.wg.Done()
}
}
func defaultHeaders() http.Header {
h := http.Header{}
h.Set("User-Agent", "flyscrape/0.1")
return h
}
|