fbcrawl-colly 0.2.0 → 0.2.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 22ec88aaf52a44344fc32ab22f6914f264b49ea10912c527c030ffd97ac12d36
4
- data.tar.gz: d007e4326b15c64e725009548c8e9dac00e263da888d736876b6093a4fba5108
3
+ metadata.gz: 64e7674aa28cfc9c5c6817afef3c3b4ed7106d1620e6da97c3fc7362ac76dc1e
4
+ data.tar.gz: 440cb83ecb7bcb9c461b4c5f9d9e5b3de0f6300384074adee9c08f3be1a68e8b
5
5
  SHA512:
6
- metadata.gz: 448bbb6b045d3b4baa3c0eae23bad85f0daf93159f514ff77e0f9383350b1c52aa3ab5360646099e56ccc19eea0bc8300ba42e67a26262e1e1f3141be61515c0
7
- data.tar.gz: 5d326d26fb0354ea78236849be7328ce49f919435c7c373130f19439c2447f9026ce31f88bc64d5cc72581fadc618a0891cd777f885e438f01217295b58309e5
6
+ metadata.gz: 1fa921c01c8b0381cf85ce4b1544d59912e1997f47fab12f8e29636de10305f410fff12a2137f7370a9749cfd2f28cd2a3ef5953de703056bf63a49770af3daf
7
+ data.tar.gz: 5696f7fe083b55ed24a5cd128dc71a8c7ebe0a7c7a0dda8811fe2e5796a023635c44d3712584b2c98937bfc1a170e7639b6af250c287bca7cbee36211f10669a
@@ -1,7 +1,7 @@
1
1
  PATH
2
2
  remote: .
3
3
  specs:
4
- fbcrawl-colly (0.1.1)
4
+ fbcrawl-colly (0.2.5)
5
5
  ffi
6
6
  google-protobuf
7
7
 
@@ -9,7 +9,7 @@ GEM
9
9
  remote: https://rubygems.org/
10
10
  specs:
11
11
  ffi (1.13.1)
12
- google-protobuf (3.12.4-universal-darwin)
12
+ google-protobuf (3.13.0)
13
13
  minitest (5.14.1)
14
14
  rake (12.3.3)
15
15
  rake-compiler (1.1.1)
@@ -6,9 +6,10 @@ import (
6
6
  "errors"
7
7
  "fmt"
8
8
  "github.com/PuerkitoBio/goquery"
9
- "github.com/gocolly/colly"
10
- "github.com/gocolly/colly/extensions"
11
- "github.com/gocolly/colly/storage"
9
+ "github.com/gocolly/colly/v2"
10
+ "github.com/gocolly/colly/v2/debug"
11
+ "github.com/gocolly/colly/v2/extensions"
12
+ "github.com/gocolly/colly/v2/storage"
12
13
  "github.com/google/logger"
13
14
  "github.com/olebedev/when"
14
15
  "github.com/olebedev/when/rules/common"
@@ -42,7 +43,7 @@ type FbDataFt struct {
42
43
  }
43
44
 
44
45
  func sharedOnRequest(request *colly.Request) {
45
- logger.Info("OnRequest")
46
+ logger.Info("OnRequest ", request.URL)
46
47
  //request.Headers.Set("Host", "facebook.com")
47
48
  request.Headers.Set("Accept-Language", "en-US,en;q=0.9")
48
49
  request.Headers.Set("accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9")
@@ -62,9 +63,10 @@ func sharedOnRequest(request *colly.Request) {
62
63
  func setupSharedCollector(collector *colly.Collector) error {
63
64
  var err error
64
65
  extensions.Referer(collector)
65
-
66
+ collector.AllowURLRevisit = true
66
67
  collector.OnRequest(sharedOnRequest)
67
68
  collector.OnResponse(sharedOnResponse)
69
+ collector.SetDebugger(&debug.LogDebugger{})
68
70
  collector.OnError(func(resp *colly.Response, errHttp error) {
69
71
  err = errHttp
70
72
  logger.Error("OnError", err)
@@ -112,20 +114,23 @@ func (f *Fbcolly) Login(email string, password string, otp string) (string, erro
112
114
 
113
115
  logger.Info("Login using email", email)
114
116
  loggedIn := false
115
-
117
+ firstLogin := true
116
118
  collector.OnHTML("#login_form", func(element *colly.HTMLElement) {
117
- logger.Info("OnHTML login_form")
118
- loginURL, err, reqMap := getForm(element, err)
119
- if err != nil {
120
- logger.Error(err)
121
- return
122
- }
123
- reqMap["email"] = email
124
- reqMap["pass"] = password
125
- logger.Info("req map:", reqMap)
126
- err = collector.Post(loginURL, reqMap)
127
- if err != nil {
128
- logger.Error("post err:", err)
119
+ if firstLogin {
120
+ firstLogin = false
121
+ logger.Info("OnHTML login_form")
122
+ loginURL, err, reqMap := getForm(element, err)
123
+ if err != nil {
124
+ logger.Error(err)
125
+ return
126
+ }
127
+ reqMap["email"] = email
128
+ reqMap["pass"] = password
129
+ logger.Info("req map:", reqMap)
130
+ err = collector.Post(loginURL, reqMap)
131
+ if err != nil {
132
+ logger.Error("post err:", err)
133
+ }
129
134
  }
130
135
  })
131
136
 
@@ -201,16 +206,52 @@ func (f *Fbcolly) FetchGroupFeed(groupId int64) (error, *fbcrawl.FacebookPostLis
201
206
  err = collector.Visit("http://mbasic.facebook.com" + element.Attr("href"))
202
207
  }
203
208
  })
209
+ collector.OnHTML("div[role=\"article\"]", func(element *colly.HTMLElement) {
210
+ dataElement := element
211
+ post := &fbcrawl.FacebookPost{}
212
+ var fbDataFt FbDataFt
213
+ jsonData := dataElement.Attr("data-ft")
214
+
215
+ logger.Info(jsonData)
216
+ err = json.Unmarshal([]byte(jsonData), &fbDataFt)
217
+ if err != nil {
218
+ logger.Error(err)
219
+ return
220
+ }
221
+ logger.Info("Post ", fbDataFt)
222
+ post.Id = fbDataFt.TopLevelPostId
223
+ post.Group = &fbcrawl.FacebookGroup{Id: fbDataFt.PageId, Name: dataElement.DOM.Find("h3 strong:nth-child(2) a").Text()}
224
+ post.User = &fbcrawl.FacebookUser{
225
+ Id: fbDataFt.ContentOwnerIdNew,
226
+ Name: dataElement.DOM.Find("h3 strong:nth-child(1) a").Text(),
227
+ }
228
+ post.CreatedAt = fbDataFt.PageInsights[strconv.FormatInt(fbDataFt.PageId, 10)].PublishTime
229
+ //Content
204
230
 
205
- collector.OnXML("//a[text()=\"Full Story\"]", func(element *colly.XMLElement) {
206
- logger.Info("Post found at", element.Attr("href"))
207
- u, _ := url.Parse("http://mbasic.facebook.com" + element.Attr("href"))
208
- postId, _ := strconv.ParseInt(u.Query().Get("id"), 10, 64)
209
- result = append(result, &fbcrawl.FacebookPost{
210
- Id: postId,
211
- Group: &fbcrawl.FacebookGroup{Id: groupId},
212
- })
213
- //f.detailCollector.Visit(url)
231
+ //NO BACKGROUND TEXT ONLY
232
+ post.Content = strings.Join(dataElement.DOM.Find("p").Map(func(i int, selection *goquery.Selection) string {
233
+ return selection.Text()
234
+ }), "\n")
235
+
236
+ if len(post.Content) == 0 {
237
+ // TEXT WITH BACKGROUND
238
+ post.Content = dataElement.DOM.Find("div[style*=\"background-image:url\"]").Text()
239
+ }
240
+
241
+ post.ContentLink = getUrlFromRedirectHref(dataElement.DOM.Find("a[href*=\"https://lm.facebook.com/l.php\"]").AttrOr("href", ""))
242
+ post.ReactionCount = getNumberFromText(element.DOM.Find("span[id*=\"like_\"]").Text())
243
+ post.CommentCount = getNumberFromText(element.DOM.Find("span[id*=\"like_\"] ~ a").Text())
244
+ post.ContentImages = (funk.Map(fbDataFt.PhotoAttachmentsList, func(id string) *fbcrawl.FacebookImage {
245
+ i, _ := strconv.ParseInt(id, 10, 64)
246
+ return &fbcrawl.FacebookImage{
247
+ Id: i,
248
+ }
249
+ })).([]*fbcrawl.FacebookImage)
250
+
251
+ if fbDataFt.PhotoId > 0 {
252
+ post.ContentImage = &fbcrawl.FacebookImage{Id: fbDataFt.PhotoId}
253
+ }
254
+ result = append(result, post)
214
255
  })
215
256
 
216
257
  err = collector.Visit(fmt.Sprintf("https://mbasic.facebook.com/groups/%d", groupId))
@@ -220,6 +261,26 @@ func (f *Fbcolly) FetchGroupFeed(groupId int64) (error, *fbcrawl.FacebookPostLis
220
261
  return err, &fbcrawl.FacebookPostList{Posts: result}
221
262
  }
222
263
 
264
+ func (f *Fbcolly) FetchGroupInfo(groupIdOrUsername string) (error, *fbcrawl.FacebookGroup) {
265
+ collector := f.collector.Clone()
266
+ err := setupSharedCollector(collector)
267
+ result := &fbcrawl.FacebookGroup{}
268
+
269
+ collector.OnHTML("a[href=\"#groupMenuBottom\"] h1", func(element *colly.HTMLElement) {
270
+ result.Name = element.Text
271
+ })
272
+ collector.OnHTML("a[href*=\"view=member\"]", func(element *colly.HTMLElement) {
273
+ result.Id = getNumberFromText(element.Attr("href"))
274
+ result.MemberCount, _ = strconv.ParseInt(element.DOM.Closest("tr").Find("td:last-child").Text(), 10, 64)
275
+ })
276
+
277
+ err = collector.Visit(fmt.Sprintf("https://mbasic.facebook.com/groups/%s?view=info", groupIdOrUsername))
278
+ if err != nil {
279
+ logger.Error("crawl by colly err:", err)
280
+ }
281
+ return err, result
282
+ }
283
+
223
284
  func (f *Fbcolly) FetchContentImages(postId int64) (error, *fbcrawl.FacebookImageList) {
224
285
  collector := f.collector.Clone()
225
286
  err := setupSharedCollector(collector)
@@ -300,7 +361,7 @@ func (f *Fbcolly) FetchPost(groupId int64, postId int64) (error, *fbcrawl.Facebo
300
361
  }
301
362
 
302
363
  post.ContentLink = getUrlFromRedirectHref(dataElement.Find("a[href*=\"https://lm.facebook.com/l.php\"]").AttrOr("href", ""))
303
-
364
+ post.ReactionCount = getNumberFromText(element.DOM.Find("div[id*=\"sentence_\"]").Text())
304
365
  post.ContentImages = (funk.Map(result.PhotoAttachmentsList, func(id string) *fbcrawl.FacebookImage {
305
366
  i, _ := strconv.ParseInt(id, 10, 64)
306
367
  return &fbcrawl.FacebookImage{
@@ -311,10 +372,6 @@ func (f *Fbcolly) FetchPost(groupId int64, postId int64) (error, *fbcrawl.Facebo
311
372
  if result.PhotoId > 0 {
312
373
  post.ContentImage = &fbcrawl.FacebookImage{Id: result.PhotoId}
313
374
  }
314
-
315
- logger.Info("content", strings.Join(dataElement.Find("p").Map(func(i int, selection *goquery.Selection) string {
316
- return selection.Text()
317
- }), "\n"))
318
375
  }
319
376
 
320
377
  //Comment
@@ -374,3 +431,21 @@ func getImageIdFromHref(href string) int64 {
374
431
  i, _ := strconv.ParseInt(u.Query().Get("fbid"), 10, 64)
375
432
  return i
376
433
  }
434
+
435
+ func getNumberFromText(text string) int64 {
436
+ logger.Error("reaction", text)
437
+ if len(text) > 0 {
438
+ match := regexp.MustCompile("(\\d+)\\s?([km]?)").FindStringSubmatch(text)
439
+ if len(match) > 0 {
440
+ count, _ := strconv.ParseInt(match[1], 10, 64)
441
+ switch match[2] {
442
+ case "k":
443
+ count *= 1000
444
+ case "m":
445
+ count *= 1000000
446
+ }
447
+ return count
448
+ }
449
+ }
450
+ return 0
451
+ }
@@ -7,6 +7,7 @@ option go_package = "./fbcrawl;fbcrawl";
7
7
  message FacebookGroup {
8
8
  int64 id = 1;
9
9
  string name = 2;
10
+ int64 member_count = 3;
10
11
  }
11
12
 
12
13
  message FacebookUser {
@@ -24,6 +25,8 @@ message FacebookPost {
24
25
  repeated FacebookImage content_images = 7;
25
26
  repeated FacebookComment comments = 5;
26
27
  int64 created_at = 9;
28
+ int64 reaction_count = 10;
29
+ int64 comment_count = 11;
27
30
  }
28
31
 
29
32
  message FacebookImage {
data/go.mod CHANGED
@@ -5,20 +5,11 @@ go 1.14
5
5
  require (
6
6
  github.com/PuerkitoBio/goquery v1.5.1
7
7
  github.com/andybalholm/cascadia v1.2.0 // indirect
8
- github.com/antchfx/htmlquery v1.2.3 // indirect
9
- github.com/antchfx/xmlquery v1.2.4 // indirect
10
- github.com/antchfx/xpath v1.1.9 // indirect
11
- github.com/gobwas/glob v0.2.3 // indirect
12
- github.com/gocolly/colly v1.2.0
8
+ github.com/gocolly/colly/v2 v2.1.0
13
9
  github.com/golang/protobuf v1.4.2
14
10
  github.com/google/logger v1.1.0
15
- github.com/kennygrant/sanitize v1.2.4 // indirect
16
11
  github.com/olebedev/when v0.0.0-20190311101825-c3b538a97254
17
- github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
18
- github.com/temoto/robotstxt v1.1.1 // indirect
19
12
  github.com/thoas/go-funk v0.7.0
20
13
  golang.org/x/net v0.0.0-20200707034311-ab3426394381 // indirect
21
- golang.org/x/text v0.3.3 // indirect
22
- google.golang.org/appengine v1.6.6 // indirect
23
14
  google.golang.org/protobuf v1.25.0
24
15
  )
data/go.sum CHANGED
@@ -4,7 +4,6 @@ github.com/AlekSi/pointer v1.0.0/go.mod h1:1kjywbfcPFCmncIxtk6fIEub6LKrfMz3gc5QK
4
4
  github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
5
5
  github.com/PuerkitoBio/goquery v1.5.1 h1:PSPBGne8NIUWw+/7vFBV+kG2J/5MOjbzc7154OaKCSE=
6
6
  github.com/PuerkitoBio/goquery v1.5.1/go.mod h1:GsLWisAFVj4WgDibEWF4pvYnkVQBpKBKeU+7zCJoLcc=
7
- github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo=
8
7
  github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
9
8
  github.com/andybalholm/cascadia v1.2.0 h1:vuRCkM5Ozh/BfmsaTm26kbjm0mIOM3yS5Ek/F5h18aE=
10
9
  github.com/andybalholm/cascadia v1.2.0/go.mod h1:YCyR8vOZT9aZ1CHEd8ap0gMVm2aFgxBp0T0eFw1RUQY=
@@ -12,14 +11,13 @@ github.com/antchfx/htmlquery v1.2.3 h1:sP3NFDneHx2stfNXCKbhHFo8XgNjCACnU/4AO5gWz
12
11
  github.com/antchfx/htmlquery v1.2.3/go.mod h1:B0ABL+F5irhhMWg54ymEZinzMSi0Kt3I2if0BLYa3V0=
13
12
  github.com/antchfx/xmlquery v1.2.4 h1:T/SH1bYdzdjTMoz2RgsfVKbM5uWh3gjDYYepFqQmFv4=
14
13
  github.com/antchfx/xmlquery v1.2.4/go.mod h1:KQQuESaxSlqugE2ZBcM/qn+ebIpt+d+4Xx7YcSGAIrM=
15
- github.com/antchfx/xpath v1.1.6 h1:6sVh6hB5T6phw1pFpHRQ+C4bd8sNI+O58flqtg7h0R0=
16
14
  github.com/antchfx/xpath v1.1.6/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
17
- github.com/antchfx/xpath v1.1.9 h1:s3QDSTRoZMK6EqLajCUt/BJMUATPHvzwlRqKqg12yjU=
18
- github.com/antchfx/xpath v1.1.9/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
15
+ github.com/antchfx/xpath v1.1.8 h1:PcL6bIX42Px5usSx6xRYw/wjB3wYGkj0MJ9MBzEKVgk=
16
+ github.com/antchfx/xpath v1.1.8/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
19
17
  github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
20
18
  github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
21
- github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
22
19
  github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
20
+ github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
23
21
  github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
24
22
  github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
25
23
  github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
@@ -27,12 +25,13 @@ github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
27
25
  github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
28
26
  github.com/gocolly/colly v1.2.0 h1:qRz9YAn8FIH0qzgNUw+HT9UN7wm1oF9OBAilwEWpyrI=
29
27
  github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA=
28
+ github.com/gocolly/colly/v2 v2.1.0 h1:k0DuZkDoCsx51bKpRJNEmcxcp+W5N8ziuwGaSDuFoGs=
29
+ github.com/gocolly/colly/v2 v2.1.0/go.mod h1:I2MuhsLjQ+Ex+IzK3afNS8/1qP3AedHOusRPcRdC5o0=
30
30
  github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
31
31
  github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e h1:1r7pUrabqp18hOBcwBwiTsbnFeTZHV9eER/QT5JVZxY=
32
32
  github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
33
33
  github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
34
34
  github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
35
- github.com/golang/protobuf v1.3.1 h1:YF8+flBXS5eO826T4nzqPrxfhQThhXl0YzfuUPu4SBg=
36
35
  github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
37
36
  github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
38
37
  github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
@@ -51,6 +50,7 @@ github.com/google/go-cmp v0.5.0 h1:/QaMHBdZ26BB3SSst0Iwl10Epc+xhTquomWX0oZEB6w=
51
50
  github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
52
51
  github.com/google/logger v1.1.0 h1:saB74Etb4EAJNH3z74CVbCKk75hld/8T0CsXKetWCwM=
53
52
  github.com/google/logger v1.1.0/go.mod h1:w7O8nrRr0xufejBlQMI83MXqRusvREoJdaAxV+CoAB4=
53
+ github.com/jawher/mow.cli v1.1.0/go.mod h1:aNaQlc7ozF3vw6IJ2dHjp2ZFiA4ozMIYY6PyuRJwlUg=
54
54
  github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o=
55
55
  github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak=
56
56
  github.com/olebedev/when v0.0.0-20190311101825-c3b538a97254 h1:JYoQR67E1vv1WGoeW8DkdFs7vrIEe/5wP+qJItd5tUE=
@@ -63,7 +63,7 @@ github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:
63
63
  github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca h1:NugYot0LIVPxTvN8n+Kvkn6TrbMyxQiuvKdEwFdR9vI=
64
64
  github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca/go.mod h1:uugorj2VCxiV1x+LzaIdVa9b4S4qGAcH6cbhh4qVxOU=
65
65
  github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
66
- github.com/stretchr/testify v1.3.0 h1:TivCn/peBQ7UY8ooIcPgZFpTNSz0Q2U6UrFlUfqbe0Q=
66
+ github.com/stretchr/objx v0.2.0/go.mod h1:qt09Ya8vawLte6SNmTgCsAVtYtaKzEcn8ATUoHMkEqE=
67
67
  github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
68
68
  github.com/stretchr/testify v1.4.0 h1:2E4SXV/wtOkTonXsotYi4li6zVWxYlZuYNCXe9XRJyk=
69
69
  github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
@@ -72,6 +72,7 @@ github.com/temoto/robotstxt v1.1.1/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr
72
72
  github.com/thoas/go-funk v0.7.0 h1:GmirKrs6j6zJbhJIficOsz2aAI7700KsU/5YrdHRM1Y=
73
73
  github.com/thoas/go-funk v0.7.0/go.mod h1:+IWnUfUmFO1+WVYQWQtIJHeRRdaIyyYglZN7xzUPe4Q=
74
74
  golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
75
+ golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
75
76
  golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
76
77
  golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
77
78
  golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
@@ -86,6 +87,7 @@ golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn
86
87
  golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
87
88
  golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
88
89
  golang.org/x/net v0.0.0-20200421231249-e086a090c8fd/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
90
+ golang.org/x/net v0.0.0-20200602114024-627f9648deb9/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
89
91
  golang.org/x/net v0.0.0-20200707034311-ab3426394381 h1:VXak5I6aEWmAXeQjA+QSZzlgNrpq9mjcfDemuexIKsU=
90
92
  golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
91
93
  golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
@@ -100,13 +102,12 @@ golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7w
100
102
  golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
101
103
  golang.org/x/text v0.3.2 h1:tW2bmiBqwgJj/UpqtC8EpXEZVYOwU0yG4iWbprSVAcs=
102
104
  golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
103
- golang.org/x/text v0.3.3 h1:cokOdA+Jmi5PJGXLlLllQSgYigAEfHXJAERHVMaCc2k=
104
- golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
105
105
  golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
106
106
  golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
107
107
  golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
108
108
  golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
109
109
  golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
110
+ golang.org/x/tools v0.0.0-20190606124116-d0a3d012864b/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
110
111
  golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
111
112
  golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
112
113
  google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
@@ -125,9 +126,9 @@ google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQ
125
126
  google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
126
127
  google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
127
128
  google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
128
- google.golang.org/protobuf v1.23.0 h1:4MY060fB1DLGMB/7MBTLnwQUY6+F09GEiz6SsrNqyzM=
129
129
  google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
130
130
  google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
131
+ google.golang.org/protobuf v1.24.0/go.mod h1:r/3tXBNzIEhYS9I1OUVjXDlt8tc493IdKGjtUeSXeh4=
131
132
  google.golang.org/protobuf v1.25.0 h1:Ejskq+SyPohKW+1uil0JJMtmHCgJPJ/qWTxr8qp+R4c=
132
133
  google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
133
134
  gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
@@ -19,6 +19,13 @@ module FbcrawlColly
19
19
  FbcrawlColly::FFI.LoginWithCookies(@colly, cookies)
20
20
  end
21
21
 
22
+ def fetch_group_info(group_id_or_username)
23
+ s, ptr = FbcrawlColly::FFI.FetchGroupInfo(@colly, group_id_or_username.to_s)
24
+ list = FbcrawlColly::FacebookGroup.decode(s)
25
+ FbcrawlColly::FFI.free(ptr)
26
+ list
27
+ end
28
+
22
29
  def fetch_group_feed(group_id)
23
30
  s, ptr = FbcrawlColly::FFI.FetchGroupFeed(@colly, group_id)
24
31
  list = FbcrawlColly::FacebookPostList.decode(s)
@@ -9,6 +9,7 @@ module FbcrawlColly::FFI
9
9
  attach_function :FreeColly, [:pointer], :pointer
10
10
  attach_function :Login, [:pointer, :string, :string], :strptr
11
11
  attach_function :LoginWithCookies, [:pointer, :string], :void
12
+ attach_function :FetchGroupInfo, [:pointer, :string], :strptr
12
13
  attach_function :FetchGroupFeed, [:pointer, :int64], :strptr
13
14
  attach_function :FetchPost, [:pointer, :int64, :int64], :strptr
14
15
  attach_function :FetchContentImages, [:pointer, :int64], :strptr
@@ -1,3 +1,3 @@
1
1
  module FbcrawlColly
2
- VERSION = "0.2.0"
2
+ VERSION = "0.2.6"
3
3
  end
data/main.go CHANGED
@@ -58,6 +58,14 @@ func LoginWithCookies(pointer unsafe.Pointer, cookies *C.char) {
58
58
  p.LoginWithCookies(C.GoString(cookies))
59
59
  }
60
60
 
61
+ //export FetchGroupInfo
62
+ func FetchGroupInfo(pointer unsafe.Pointer, groupIdOrUsername *C.char) unsafe.Pointer {
63
+ p := (*fbcolly.Fbcolly)(pointer)
64
+ _, groupInfo := p.FetchGroupInfo(C.GoString(groupIdOrUsername))
65
+ marshaled, _ := proto.Marshal(groupInfo)
66
+ return C.CBytes(append(marshaled, 0))
67
+ }
68
+
61
69
  //export FetchGroupFeed
62
70
  func FetchGroupFeed(pointer unsafe.Pointer, groupId int64) unsafe.Pointer {
63
71
  p := (*fbcolly.Fbcolly)(pointer)
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: fbcrawl-colly
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.2.0
4
+ version: 0.2.6
5
5
  platform: ruby
6
6
  authors:
7
7
  - Duy Le
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2020-08-13 00:00:00.000000000 Z
11
+ date: 2020-08-15 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: ffi