go语言渐入佳境[55]-爬虫-并发爬虫引擎

go语言实现并发版爬虫,拥有良好的拓展性。效率是单任务的数十倍。

并发版爬虫

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
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419

package main

import (
"io/ioutil"
"golang.org/x/net/html/charset"
"golang.org/x/text/encoding"
"bufio"
"golang.org/x/text/transform"
"golang.org/x/text/encoding/unicode"
"log"
"regexp"
"strconv"
"net/http"
"fmt"
"time"
)


var rateLimiter = time.Tick(100 * time.Millisecond)
/* start Fetch.go*/
func Fetch(url string)([]byte ,error){
//resp,err:= http.Get(url)
//
//if err!=nil{
// return nil,err
//}
//
//defer resp.Body.Close()
//if resp.StatusCode != http.StatusOK{
// return nil,fmt.Errorf("Error: status code:%d",resp.StatusCode)
//}

client := &http.Client{}
req, err := http.NewRequest("GET", url, nil)
if err != nil {
log.Fatalln(err)
}
req.Header.Set("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36")

resp, err := client.Do(req)
if err != nil {
log.Fatalln(err)
}

defer resp.Body.Close()

bodyReader:= bufio.NewReader(resp.Body)
e:= determineEncoding(bodyReader)
utf8reader:= transform.NewReader(bodyReader,e.NewDecoder())

return ioutil.ReadAll(utf8reader)
}


func determineEncoding(r *bufio.Reader) encoding.Encoding{

bytes,err := bufio.NewReader(r).Peek(1024)
if err !=nil{
log.Printf("Fetcher error:%v",err)
return unicode.UTF8
}
e,_,_:= charset.DetermineEncoding(bytes,"")
return e
}
/* end Fetch.go*/
/* start Type.go*/
type Request struct{
Url string
ParserFunc func([]byte) ParseResult
}

type ParseResult struct{
Requests []Request
Items []interface{}
}

func NilParser([]byte) ParseResult{
return ParseResult{}
}

/* end Type.go*/


/* start parser/city.go 爬取城市下每一个用户和网址*/


const cityRe = `<a href="(http://album.zhenai.com/u/[\d]+)" target="_blank">([^<]+)</a>`
func ParseCity(contents []byte) ParseResult{
re:= regexp.MustCompile(cityRe)
matches:= re.FindAllSubmatch(contents,-1)

result := ParseResult{}
for _,m:= range matches{
name:=string(m[2])
println(string(m[1]))
result.Items = append(result.Items,"User:"+string(m[2]))
result.Requests = append(result.Requests,Request{
Url:string(m[1]),
ParserFunc:func(c []byte) ParseResult{
return PaesrProfile(
c,name)
},
})
}

return result

}



/* end parser/city.go */

/* start parser/citylist.go */

const cityListRe = `(http://www.zhenai.com/zhenghun/[0-9a-z]+)"[^>]*>([^<]+)</a>`
func ParseCityList(contents []byte) ParseResult{
re:=regexp.MustCompile(cityListRe)

matches:= re.FindAllSubmatch(contents,-1)
result:=ParseResult{}

for _,m :=range matches{
result.Items = append(result.Items,string(m[2]))
result.Requests = append(
result.Requests,Request{
Url:string(m[1]),
ParserFunc:ParseCity,
})


}

return result
}

/* end parser/citylist.go */

/* start profile.go */
type Profile struct {
Name string
Age int
Marry string
Constellation string
Height int
Weight int
Salary string
}


func (p Profile) String() string{
return p.Name +" " + p.Marry + strconv.Itoa(p.Age) +"olds "+ strconv.Itoa(p.Age) + "cm " + strconv.Itoa(p.Weight)+ "kg "
}
/* end profile.go */

/* start parser/profile.go */


var ageRe = regexp.MustCompile(`<div class="m-btn purple" data-v-bff6f798>([\d]+)岁</div>`)
var marry = regexp.MustCompile(`<div class="m-btn purple" data-v-bff6f798>(已婚)</div>`)
var constellation = regexp.MustCompile(`<div class="m-btn purple" data-v-bff6f798>(.*)座</div>`)
var height =regexp.MustCompile(`160cm`)
var weight =regexp.MustCompile(`<div class="m-btn purple" data-v-bff6f798>([\d]+)kg</div>`)
var salary = regexp.MustCompile(`<div class="m-btn purple" data-v-bff6f798>月收入:([^<]+)</div>`)



//解析器 解析用户
//name为上一级传递过来的
func PaesrProfile(contents []byte,name string) ParseResult{

//ioutil.WriteFile("test.html",contents,0x777)
//用户结构体
profile:=Profile{}
profile.Name = name

//年龄 string转换为int
age,err:= strconv.Atoi(extractString(contents,ageRe))
if err==nil{
profile.Age = age
}
//身高
height,err:= strconv.Atoi(extractString(contents,height))
if err==nil{
profile.Height = height
}
//体重
weight,err:= strconv.Atoi(extractString(contents,weight))
if err==nil{
profile.Weight = weight
}

//薪水
profile.Salary = extractString(contents,salary)

//星座
profile.Constellation = extractString(contents,constellation)
if extractString(contents,marry)== ""{
profile.Marry ="未婚"
}else{
profile.Marry ="已婚"
}


result:=ParseResult{
Items:[]interface{}{profile},
}

return result
}

//封装 正则表达式匹配
func extractString(contents []byte,re *regexp.Regexp) string{
match:=re.FindSubmatch(contents)

if len(match)>=2{

return string(match[1])
}else{
return ""
}
}

/* end parser/profile.go */

/* start engine.go 单任务版引擎*/
func Run(seeds ...Request){
var requests []Request

for _,r := range seeds{
requests = append(requests,r)
}

for len(requests) >0{
r:=requests[0]

requests = requests[1:]
fmt.Printf("Fetching %s",r.Url)
body,err:= Fetch(r.Url)

if err!=nil{
log.Printf("Fetcher:error "+ "fetching url %s, : %v",r.Url,err)
continue
}

parseResult:= r.ParserFunc(body)

requests = append(requests,parseResult.Requests...)

for _,item:= range parseResult.Items{
fmt.Printf("Got item %s\n",item)
}
}
}


//具体的工作 传递一个request,通过解析器对url进行解析
func worker(r Request)(ParseResult,error){
fmt.Printf("Fetching %s\n",r.Url)
body,err:= Fetch(r.Url)

if err!=nil{
log.Printf("Fetcher:error "+ "fetching url %s, : %v",r.Url,err)
return ParseResult{},err
}
return r.ParserFunc(body),nil
}

// 并发版爬虫引擎 包含了调度器 与 工人数
type ConcurrentEngine struct{
Scheduler Scheduler
WorkerCount int
}

//调度器是一个接口,扩展性
type Scheduler interface {

//提交Request进行执行
Submit(Request)
//配置通道
ConfigureMasterWorkChan(chan Request)
}


//并发版爬虫引擎
func (e *ConcurrentEngine) Run(seeds ...Request){


in:=make(chan Request)
out:= make(chan ParseResult)
//配置调度器通道
e.Scheduler.ConfigureMasterWorkChan(in)

//开启WorkerCount个工作
for i:=0;i<e.WorkerCount;i++{
createWorker(in,out)
}
//种子首先运行
for _,r:=range seeds{
e.Scheduler.Submit(r)
}
itemsCount:=0
for{
//out等待接受ParseResult
result:=<-out

//打印出接收到的数据,以及个数。
for _,item:= range result.Items{
fmt.Printf("Got item: #%d: %v\n",itemsCount,item)
itemsCount++
}

//每一个request都通过调度器发送给in通道,由于在调度器中使用了协程的方式,不会卡死在这里陷入死锁。
for _,request:= range result.Requests{
e.Scheduler.Submit(request)
}
}
}

//工作函数,逻辑是 in通道接收到request,即会调用worker函数爬每一个request中的网址,用对应的解析器。 解析完成后,将ParseResult返回给通道out
func createWorker(in chan Request, out chan ParseResult) {
go func(){
for{
request := <-in
result,err:= worker(request)
if err!=nil{
continue
}
out <-result
}
}()
}



/* end engine.go */

/* start scheduler.go 简单版调度器,用于分配工作任务 */
type SimpleScheduler struct{
//通道
workerChan chan Request
}

func ( s *SimpleScheduler) Submit( r Request) {
//为了防止死锁,在调度器中建立go的协程 分配任务到通道中。
go func(){s.workerChan <- r}()
}

func (s *SimpleScheduler) ConfigureMasterWorkChan(c chan Request) {
//in通道
s.workerChan = c
}

/* end scheduler.go */



func main(){


//并发版爬虫
e:= ConcurrentEngine{
Scheduler:&SimpleScheduler{},
WorkerCount:100,
}

e.Run(Request{
Url:"http://www.zhenai.com/zhenghun",
ParserFunc:ParseCityList,
})

//单任务版爬虫
//Run(Request{
// Url:"http://www.zhenai.com/zhenghun",
// ParserFunc:ParseCityList,
//})
//paseTest()
}



//测试
func paseTest(){

contents,_:= ioutil.ReadFile("test.html")


profile:=Profile{}
age,err:= strconv.Atoi(extractString(contents,ageRe))

if err!=nil{

profile.Age = age
}

height,err:= strconv.Atoi(extractString(contents,height))
if err!=nil{
profile.Height = height
}

weight,err:= strconv.Atoi(extractString(contents,weight))
if err!=nil{
profile.Weight = weight
}


profile.Salary = extractString(contents,salary)

profile.Constellation = extractString(contents,constellation)
if extractString(contents,marry)== ""{
profile.Marry ="未婚"
}else{
profile.Marry ="已婚"
}

fmt.Printf("%s",profile)

}