fbcrawl-colly 0.1.0
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 +7 -0
- data/.gitignore +16 -0
- data/.travis.yml +6 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +7 -0
- data/LICENSE.txt +21 -0
- data/README.md +47 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/ext/fbcrawl_colly/.gitignore +2 -0
- data/ext/fbcrawl_colly/Makefile +6 -0
- data/ext/fbcrawl_colly/extconf.rb +5 -0
- data/fbcolly/fbcolly.go +234 -0
- data/fbcrawl-colly.gemspec +35 -0
- data/fbcrawl.proto +33 -0
- data/go.mod +23 -0
- data/go.sum +131 -0
- data/lib/fbcrawl-colly.rb +16 -0
- data/lib/fbcrawl-colly/version.rb +3 -0
- data/main.go +77 -0
- metadata +95 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 96d233862f21d1dff4a447d57f0f4a4ee6311506d7b5cf1990d75bf92043defa
|
4
|
+
data.tar.gz: a238ee4a34eac5f33fa90bba0d5bdb22169bd0b54034682f8fbb25c1ca4de039
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 36d58d4ef38bf94164f94fe0a841171cc5bdd12a4f2503e818858d77cae029e1fc79cddd3213b2bb9e130e70833703df97ad18700d92c2cc3e31401b8e1f1443
|
7
|
+
data.tar.gz: 5c56a623910f87369812c0d74908e618490b4aeead9d22b055f8076ca040ba9fe5fff0bb380c44e7e435e0d83a13823b259b0f6c57233d7fb3ec38ff83de0832
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/CODE_OF_CONDUCT.md
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
# Contributor Covenant Code of Conduct
|
2
|
+
|
3
|
+
## Our Pledge
|
4
|
+
|
5
|
+
In the interest of fostering an open and welcoming environment, we as
|
6
|
+
contributors and maintainers pledge to making participation in our project and
|
7
|
+
our community a harassment-free experience for everyone, regardless of age, body
|
8
|
+
size, disability, ethnicity, gender identity and expression, level of experience,
|
9
|
+
nationality, personal appearance, race, religion, or sexual identity and
|
10
|
+
orientation.
|
11
|
+
|
12
|
+
## Our Standards
|
13
|
+
|
14
|
+
Examples of behavior that contributes to creating a positive environment
|
15
|
+
include:
|
16
|
+
|
17
|
+
* Using welcoming and inclusive language
|
18
|
+
* Being respectful of differing viewpoints and experiences
|
19
|
+
* Gracefully accepting constructive criticism
|
20
|
+
* Focusing on what is best for the community
|
21
|
+
* Showing empathy towards other community members
|
22
|
+
|
23
|
+
Examples of unacceptable behavior by participants include:
|
24
|
+
|
25
|
+
* The use of sexualized language or imagery and unwelcome sexual attention or
|
26
|
+
advances
|
27
|
+
* Trolling, insulting/derogatory comments, and personal or political attacks
|
28
|
+
* Public or private harassment
|
29
|
+
* Publishing others' private information, such as a physical or electronic
|
30
|
+
address, without explicit permission
|
31
|
+
* Other conduct which could reasonably be considered inappropriate in a
|
32
|
+
professional setting
|
33
|
+
|
34
|
+
## Our Responsibilities
|
35
|
+
|
36
|
+
Project maintainers are responsible for clarifying the standards of acceptable
|
37
|
+
behavior and are expected to take appropriate and fair corrective action in
|
38
|
+
response to any instances of unacceptable behavior.
|
39
|
+
|
40
|
+
Project maintainers have the right and responsibility to remove, edit, or
|
41
|
+
reject comments, commits, code, wiki edits, issues, and other contributions
|
42
|
+
that are not aligned to this Code of Conduct, or to ban temporarily or
|
43
|
+
permanently any contributor for other behaviors that they deem inappropriate,
|
44
|
+
threatening, offensive, or harmful.
|
45
|
+
|
46
|
+
## Scope
|
47
|
+
|
48
|
+
This Code of Conduct applies both within project spaces and in public spaces
|
49
|
+
when an individual is representing the project or its community. Examples of
|
50
|
+
representing a project or community include using an official project e-mail
|
51
|
+
address, posting via an official social media account, or acting as an appointed
|
52
|
+
representative at an online or offline event. Representation of a project may be
|
53
|
+
further defined and clarified by project maintainers.
|
54
|
+
|
55
|
+
## Enforcement
|
56
|
+
|
57
|
+
Instances of abusive, harassing, or otherwise unacceptable behavior may be
|
58
|
+
reported by contacting the project team at duyleekun@gmail.com. All
|
59
|
+
complaints will be reviewed and investigated and will result in a response that
|
60
|
+
is deemed necessary and appropriate to the circumstances. The project team is
|
61
|
+
obligated to maintain confidentiality with regard to the reporter of an incident.
|
62
|
+
Further details of specific enforcement policies may be posted separately.
|
63
|
+
|
64
|
+
Project maintainers who do not follow or enforce the Code of Conduct in good
|
65
|
+
faith may face temporary or permanent repercussions as determined by other
|
66
|
+
members of the project's leadership.
|
67
|
+
|
68
|
+
## Attribution
|
69
|
+
|
70
|
+
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
|
71
|
+
available at [https://contributor-covenant.org/version/1/4][version]
|
72
|
+
|
73
|
+
[homepage]: https://contributor-covenant.org
|
74
|
+
[version]: https://contributor-covenant.org/version/1/4/
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2020 Duy Le
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,47 @@
|
|
1
|
+
# FbcrawlColly
|
2
|
+
|
3
|
+
This project is to crawl mbasic.facebook.com using GO Colly.
|
4
|
+
|
5
|
+
Ruby gem will available to use
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'fbcrawl-colly'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle install
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install fbcrawl-colly
|
22
|
+
|
23
|
+
<!---
|
24
|
+
## Usage
|
25
|
+
|
26
|
+
TODO: Write usage instructions here
|
27
|
+
|
28
|
+
## Development
|
29
|
+
|
30
|
+
|
31
|
+
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
32
|
+
|
33
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
34
|
+
-->
|
35
|
+
|
36
|
+
## Contributing
|
37
|
+
|
38
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/fbcrawl-colly. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/[USERNAME]/fbcrawl-colly/blob/master/CODE_OF_CONDUCT.md).
|
39
|
+
|
40
|
+
|
41
|
+
## License
|
42
|
+
|
43
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
44
|
+
|
45
|
+
## Code of Conduct
|
46
|
+
|
47
|
+
Everyone interacting in the FbcrawlColly project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/fbcrawl-colly/blob/master/CODE_OF_CONDUCT.md).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "fbcrawl-colly"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/fbcolly/fbcolly.go
ADDED
@@ -0,0 +1,234 @@
|
|
1
|
+
package fbcolly
|
2
|
+
|
3
|
+
import "C"
|
4
|
+
import (
|
5
|
+
"encoding/json"
|
6
|
+
"errors"
|
7
|
+
"fmt"
|
8
|
+
"github.com/PuerkitoBio/goquery"
|
9
|
+
"github.com/gocolly/colly"
|
10
|
+
"github.com/gocolly/colly/extensions"
|
11
|
+
"github.com/gocolly/colly/storage"
|
12
|
+
"github.com/google/logger"
|
13
|
+
"net/url"
|
14
|
+
"qnetwork.net/fbcrawl/fbcrawl"
|
15
|
+
"regexp"
|
16
|
+
"strings"
|
17
|
+
)
|
18
|
+
|
19
|
+
type Fbcolly struct {
|
20
|
+
collector *colly.Collector
|
21
|
+
}
|
22
|
+
|
23
|
+
func sharedOnRequest(request *colly.Request) {
|
24
|
+
logger.Info("OnRequest")
|
25
|
+
//request.Headers.Set("Host", "facebook.com")
|
26
|
+
request.Headers.Set("Accept-Language", "en-US,en;q=0.9")
|
27
|
+
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")
|
28
|
+
request.Headers.Set("origin", "https://mbasic.facebook.com")
|
29
|
+
|
30
|
+
//logger.Info("Saved referrer is", request.Ctx.Get("_referer"))
|
31
|
+
request.Headers.Set("referer", "https://mbasic.facebook.com/checkpoint/?_rdr")
|
32
|
+
request.Headers.Set("cache-control", "max-age=0")
|
33
|
+
request.Headers.Set("upgrade-insecure-requests", "1")
|
34
|
+
//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
|
35
|
+
//origin: https://mbasic.facebook.com
|
36
|
+
//referer: https://mbasic.facebook.com/checkpoint/?_rdr
|
37
|
+
request.Headers.Set("User-Agent", "Mozilla/5.0 (Linux; Android 6.0.1; Moto G (4)) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Mobile Safari/537.36")
|
38
|
+
request.ResponseCharacterEncoding = "utf-8"
|
39
|
+
}
|
40
|
+
|
41
|
+
func setupSharedCollector(collector *colly.Collector) error {
|
42
|
+
var err error
|
43
|
+
extensions.Referer(collector)
|
44
|
+
|
45
|
+
collector.OnRequest(sharedOnRequest)
|
46
|
+
collector.OnResponse(sharedOnResponse)
|
47
|
+
collector.OnError(func(resp *colly.Response, errHttp error) {
|
48
|
+
err = errHttp
|
49
|
+
logger.Error("OnError", err)
|
50
|
+
})
|
51
|
+
return err
|
52
|
+
}
|
53
|
+
|
54
|
+
func sharedOnResponse(response *colly.Response) {
|
55
|
+
logger.Info("OnResponse ./last.html")
|
56
|
+
_ = response.Save("./last.html")
|
57
|
+
//logger.Info(string(resp.Body))
|
58
|
+
}
|
59
|
+
|
60
|
+
func getForm(element *colly.HTMLElement, err error) (string, error, map[string]string) {
|
61
|
+
submitUrl, exists := element.DOM.Attr("action")
|
62
|
+
if !exists {
|
63
|
+
err = errors.New("doesn't have action label")
|
64
|
+
return "", nil, nil
|
65
|
+
}
|
66
|
+
submitUrl = fmt.Sprintf("https://mbasic.facebook.com%s", submitUrl)
|
67
|
+
logger.Info("form url is:", submitUrl)
|
68
|
+
reqMap := make(map[string]string)
|
69
|
+
element.DOM.Find("input").Each(func(i int, s *goquery.Selection) {
|
70
|
+
name, _ := s.Attr("name")
|
71
|
+
value, _ := s.Attr("value")
|
72
|
+
if name != "" && name != "sign_up" && name != "submit[logout-button-with-confirm]" {
|
73
|
+
reqMap[name] = value
|
74
|
+
}
|
75
|
+
})
|
76
|
+
return submitUrl, err, reqMap
|
77
|
+
}
|
78
|
+
|
79
|
+
func New() *Fbcolly {
|
80
|
+
f := Fbcolly{}
|
81
|
+
f.collector = colly.NewCollector()
|
82
|
+
return &f
|
83
|
+
}
|
84
|
+
|
85
|
+
func (f *Fbcolly) Login(email string, password string, otp string) error {
|
86
|
+
collector := f.collector.Clone()
|
87
|
+
setupSharedCollector(collector)
|
88
|
+
|
89
|
+
logger.Info("Login using email", email)
|
90
|
+
|
91
|
+
var err error
|
92
|
+
collector.OnHTML("#login_form", func(element *colly.HTMLElement) {
|
93
|
+
logger.Info("OnHTML login_form")
|
94
|
+
loginURL, err, reqMap := getForm(element, err)
|
95
|
+
if err != nil {
|
96
|
+
logger.Error(err)
|
97
|
+
return
|
98
|
+
}
|
99
|
+
reqMap["email"] = email
|
100
|
+
reqMap["pass"] = password
|
101
|
+
logger.Info("req map:", reqMap)
|
102
|
+
err = collector.Post(loginURL, reqMap)
|
103
|
+
if err != nil {
|
104
|
+
logger.Error("post err:", err)
|
105
|
+
}
|
106
|
+
})
|
107
|
+
|
108
|
+
collector.OnHTML("a[href=\"/login/save-device/cancel/?flow=interstitial_nux&nux_source=regular_login\"]", func(element *colly.HTMLElement) {
|
109
|
+
collector.Visit("http://mbasic.facebook.com" + element.Attr("href"))
|
110
|
+
})
|
111
|
+
|
112
|
+
collector.OnHTML("form[action=\"/login/checkpoint/\"]", func(element *colly.HTMLElement) {
|
113
|
+
|
114
|
+
checkpointUrl, err, reqMap := getForm(element, err)
|
115
|
+
if err != nil {
|
116
|
+
logger.Error(err)
|
117
|
+
return
|
118
|
+
}
|
119
|
+
|
120
|
+
if element.DOM.Find("input[name=\"name_action_selected\"]").Length() > 0 {
|
121
|
+
//Save Device
|
122
|
+
logger.Info("OnHTML Save Device checkpoint")
|
123
|
+
reqMap["name_action_selected"] = "dont_save"
|
124
|
+
} else if element.DOM.Find("input[name=\"approvals_code\"]").Length() > 0 {
|
125
|
+
logger.Info("OnHTML OTP checkpoint")
|
126
|
+
//logger.Info("Please input OTP")
|
127
|
+
//reader := bufio.NewReader(os.Stdin)
|
128
|
+
//code, _ := reader.ReadString('\n')
|
129
|
+
code := otp[0:6]
|
130
|
+
reqMap["approvals_code"] = code
|
131
|
+
} else {
|
132
|
+
logger.Info("OnHTML Only Continue checkpoint")
|
133
|
+
}
|
134
|
+
logger.Info("req map:", reqMap)
|
135
|
+
err = collector.Post(checkpointUrl, reqMap)
|
136
|
+
if err != nil {
|
137
|
+
logger.Error("post err:", err)
|
138
|
+
}
|
139
|
+
})
|
140
|
+
|
141
|
+
collector.OnHTML("form[action=\"/search/\"]", func(element *colly.HTMLElement) {
|
142
|
+
//We're in home
|
143
|
+
logger.Info("I'm IN HOME, navigate to page now")
|
144
|
+
})
|
145
|
+
|
146
|
+
err = collector.Visit("https://mbasic.facebook.com/")
|
147
|
+
if err != nil {
|
148
|
+
logger.Error("crawl by colly err:", err)
|
149
|
+
}
|
150
|
+
logger.Info(storage.StringifyCookies(collector.Cookies("https://mbasic.facebook.com/")))
|
151
|
+
//return err, storage.StringifyCookies(collector.Cookies("https://mbasic.facebook.com/"))
|
152
|
+
//return err, collector.getS.Cookies("https://mbasic.facebook.com/")
|
153
|
+
return err
|
154
|
+
}
|
155
|
+
|
156
|
+
func (f *Fbcolly) FetchGroupFeed(groupId string) (error, *fbcrawl.FacebookPostList) {
|
157
|
+
collector := f.collector.Clone()
|
158
|
+
err := setupSharedCollector(collector)
|
159
|
+
currentPage := 1
|
160
|
+
var result []*fbcrawl.FacebookPost
|
161
|
+
|
162
|
+
collector.OnHTML("#m_group_stories_container > :last-child a", func(element *colly.HTMLElement) {
|
163
|
+
currentPage++
|
164
|
+
if currentPage < 3 {
|
165
|
+
logger.Info("Will fetch page", currentPage)
|
166
|
+
collector.Visit("http://mbasic.facebook.com" + element.Attr("href"))
|
167
|
+
}
|
168
|
+
})
|
169
|
+
|
170
|
+
//TODO: May not need this
|
171
|
+
collector.OnXML("//a[text()=\"Full Story\"]", func(element *colly.XMLElement) {
|
172
|
+
u, _ := url.Parse("http://mbasic.facebook.com" + element.Attr("href"))
|
173
|
+
|
174
|
+
result = append(result, &fbcrawl.FacebookPost{
|
175
|
+
Id: u.Query().Get("id"),
|
176
|
+
Group: &fbcrawl.FacebookGroup{Id: groupId},
|
177
|
+
})
|
178
|
+
//f.detailCollector.Visit(url)
|
179
|
+
})
|
180
|
+
|
181
|
+
err = collector.Visit("https://mbasic.facebook.com/groups/" + groupId)
|
182
|
+
if err != nil {
|
183
|
+
logger.Error("crawl by colly err:", err)
|
184
|
+
}
|
185
|
+
return err, &fbcrawl.FacebookPostList{Posts: result}
|
186
|
+
}
|
187
|
+
|
188
|
+
func (f *Fbcolly) FetchPost(groupId string, postId string) (error, *fbcrawl.FacebookPost) {
|
189
|
+
collector := f.collector.Clone()
|
190
|
+
err := setupSharedCollector(collector)
|
191
|
+
post := &fbcrawl.FacebookPost{}
|
192
|
+
collector.OnHTML("#m_story_permalink_view", func(element *colly.HTMLElement) {
|
193
|
+
dataElement := element.DOM.Find("div[data-ft]")
|
194
|
+
if dataElement.Length() > 0 {
|
195
|
+
var result map[string]string
|
196
|
+
jsonData, isExist := dataElement.Attr("data-ft")
|
197
|
+
if isExist {
|
198
|
+
json.Unmarshal([]byte(jsonData), &result)
|
199
|
+
logger.Info("Post ", result)
|
200
|
+
post.Id = result["top_level_post_id"]
|
201
|
+
post.Group = &fbcrawl.FacebookGroup{Id: result["page_id"], Name: dataElement.Find("h3 strong:last-child a").Text()}
|
202
|
+
post.User = &fbcrawl.FacebookUser{Id: result["content_owner_id_new"], Name: dataElement.Find("h3 strong:first-child a").Text()}
|
203
|
+
//Content
|
204
|
+
post.Content = strings.Join(dataElement.Find("p").Map(func(i int, selection *goquery.Selection) string {
|
205
|
+
return selection.Text()
|
206
|
+
}), "\n")
|
207
|
+
|
208
|
+
logger.Info("content", strings.Join(dataElement.Find("p").Map(func(i int, selection *goquery.Selection) string {
|
209
|
+
return selection.Text()
|
210
|
+
}), "\n"))
|
211
|
+
}
|
212
|
+
post.Comments = []*fbcrawl.FacebookComment{}
|
213
|
+
//Comment
|
214
|
+
element.DOM.Find("h3 + div + div + div").Parent().Parent().Each(func(i int, selection *goquery.Selection) {
|
215
|
+
//author
|
216
|
+
commentId := selection.AttrOr("id", "")
|
217
|
+
logger.Info("comment", commentId)
|
218
|
+
//idRegex, _ := regexp.Compile("")
|
219
|
+
//idRegex.FindString()
|
220
|
+
post.Comments = append(post.Comments, &fbcrawl.FacebookComment{
|
221
|
+
Id: commentId,
|
222
|
+
Post: &fbcrawl.FacebookPost{Id: post.Id},
|
223
|
+
User: &fbcrawl.FacebookUser{
|
224
|
+
Id: regexp.MustCompile("/([\\d\\w.]+)").FindStringSubmatch(selection.Find("h3 > a").AttrOr("href", ""))[1],
|
225
|
+
Name: selection.Find("h3 > a").Text(),
|
226
|
+
},
|
227
|
+
Content: selection.Find("h3 + div").Text(),
|
228
|
+
})
|
229
|
+
})
|
230
|
+
}
|
231
|
+
})
|
232
|
+
collector.Visit(fmt.Sprintf("http://mbasic.facebook.com/groups/%s?view=permalink&id=%s&_rdr", groupId, postId))
|
233
|
+
return err, post
|
234
|
+
}
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require_relative 'lib/fbcrawl-colly/version'
|
2
|
+
|
3
|
+
Gem::Specification.new do |spec|
|
4
|
+
spec.name = "fbcrawl-colly"
|
5
|
+
spec.version = FbcrawlColly::VERSION
|
6
|
+
spec.authors = ["Duy Le"]
|
7
|
+
spec.email = ["duyleekun@gmail.com"]
|
8
|
+
|
9
|
+
spec.summary = %q{Crawl mbasic.facebook.com using GO Colly}
|
10
|
+
spec.description = %q{Crawl mbasic.facebook.com using GO Colly}
|
11
|
+
spec.homepage = "http://github.com/duyleekun/fbcrawl-colly"
|
12
|
+
spec.license = "MIT"
|
13
|
+
spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
|
14
|
+
|
15
|
+
# spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
|
16
|
+
|
17
|
+
spec.metadata["homepage_uri"] = spec.homepage
|
18
|
+
spec.metadata["source_code_uri"] = "http://github.com/duyleekun/fbcrawl-colly"
|
19
|
+
spec.metadata["changelog_uri"] = "http://github.com/duyleekun/fbcrawl-colly"
|
20
|
+
|
21
|
+
# Specify which files should be added to the gem when it is released.
|
22
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
23
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
24
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
25
|
+
end
|
26
|
+
# spec.bindir = "exe"
|
27
|
+
# spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
28
|
+
spec.extensions = [
|
29
|
+
'ext/fbcrawl_colly/extconf.rb'
|
30
|
+
]
|
31
|
+
spec.require_paths = ["lib"]
|
32
|
+
|
33
|
+
spec.add_runtime_dependency 'ffi'
|
34
|
+
spec.add_runtime_dependency 'google-protobuf'
|
35
|
+
end
|
data/fbcrawl.proto
ADDED
@@ -0,0 +1,33 @@
|
|
1
|
+
syntax = "proto3";
|
2
|
+
|
3
|
+
option go_package = "./fbcrawl;fbcrawl";
|
4
|
+
|
5
|
+
// The request message containing the user's name.
|
6
|
+
message FacebookGroup {
|
7
|
+
string id = 1;
|
8
|
+
string name = 2;
|
9
|
+
}
|
10
|
+
|
11
|
+
message FacebookUser {
|
12
|
+
string id = 1;
|
13
|
+
string name = 2;
|
14
|
+
}
|
15
|
+
|
16
|
+
message FacebookPost {
|
17
|
+
string id = 1;
|
18
|
+
FacebookGroup group = 2;
|
19
|
+
FacebookUser user = 3;
|
20
|
+
string content = 4;
|
21
|
+
repeated FacebookComment comments = 5;
|
22
|
+
}
|
23
|
+
|
24
|
+
message FacebookComment {
|
25
|
+
string id = 1;
|
26
|
+
FacebookPost post = 2;
|
27
|
+
FacebookUser user = 3;
|
28
|
+
string content = 4;
|
29
|
+
}
|
30
|
+
|
31
|
+
message FacebookPostList {
|
32
|
+
repeated FacebookPost posts = 1;
|
33
|
+
}
|
data/go.mod
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
module qnetwork.net/fbcrawl
|
2
|
+
|
3
|
+
go 1.14
|
4
|
+
|
5
|
+
require (
|
6
|
+
github.com/PuerkitoBio/goquery v1.5.1
|
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
|
13
|
+
github.com/golang/protobuf v1.4.2
|
14
|
+
github.com/google/logger v1.1.0
|
15
|
+
github.com/kennygrant/sanitize v1.2.4 // indirect
|
16
|
+
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
|
17
|
+
github.com/temoto/robotstxt v1.1.1 // indirect
|
18
|
+
github.com/thoas/go-funk v0.7.0
|
19
|
+
golang.org/x/net v0.0.0-20200707034311-ab3426394381 // indirect
|
20
|
+
golang.org/x/text v0.3.3 // indirect
|
21
|
+
google.golang.org/appengine v1.6.6 // indirect
|
22
|
+
google.golang.org/protobuf v1.25.0
|
23
|
+
)
|
data/go.sum
ADDED
@@ -0,0 +1,131 @@
|
|
1
|
+
cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
|
2
|
+
github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
|
3
|
+
github.com/PuerkitoBio/goquery v1.5.1 h1:PSPBGne8NIUWw+/7vFBV+kG2J/5MOjbzc7154OaKCSE=
|
4
|
+
github.com/PuerkitoBio/goquery v1.5.1/go.mod h1:GsLWisAFVj4WgDibEWF4pvYnkVQBpKBKeU+7zCJoLcc=
|
5
|
+
github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo=
|
6
|
+
github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
|
7
|
+
github.com/andybalholm/cascadia v1.2.0 h1:vuRCkM5Ozh/BfmsaTm26kbjm0mIOM3yS5Ek/F5h18aE=
|
8
|
+
github.com/andybalholm/cascadia v1.2.0/go.mod h1:YCyR8vOZT9aZ1CHEd8ap0gMVm2aFgxBp0T0eFw1RUQY=
|
9
|
+
github.com/antchfx/htmlquery v1.2.3 h1:sP3NFDneHx2stfNXCKbhHFo8XgNjCACnU/4AO5gWz6M=
|
10
|
+
github.com/antchfx/htmlquery v1.2.3/go.mod h1:B0ABL+F5irhhMWg54ymEZinzMSi0Kt3I2if0BLYa3V0=
|
11
|
+
github.com/antchfx/xmlquery v1.2.4 h1:T/SH1bYdzdjTMoz2RgsfVKbM5uWh3gjDYYepFqQmFv4=
|
12
|
+
github.com/antchfx/xmlquery v1.2.4/go.mod h1:KQQuESaxSlqugE2ZBcM/qn+ebIpt+d+4Xx7YcSGAIrM=
|
13
|
+
github.com/antchfx/xpath v1.1.6 h1:6sVh6hB5T6phw1pFpHRQ+C4bd8sNI+O58flqtg7h0R0=
|
14
|
+
github.com/antchfx/xpath v1.1.6/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
|
15
|
+
github.com/antchfx/xpath v1.1.9 h1:s3QDSTRoZMK6EqLajCUt/BJMUATPHvzwlRqKqg12yjU=
|
16
|
+
github.com/antchfx/xpath v1.1.9/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
|
17
|
+
github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
|
18
|
+
github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
|
19
|
+
github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
|
20
|
+
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
21
|
+
github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
|
22
|
+
github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
|
23
|
+
github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
|
24
|
+
github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
|
25
|
+
github.com/gocolly/colly v1.2.0 h1:qRz9YAn8FIH0qzgNUw+HT9UN7wm1oF9OBAilwEWpyrI=
|
26
|
+
github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA=
|
27
|
+
github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
|
28
|
+
github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e h1:1r7pUrabqp18hOBcwBwiTsbnFeTZHV9eER/QT5JVZxY=
|
29
|
+
github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
|
30
|
+
github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
|
31
|
+
github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
|
32
|
+
github.com/golang/protobuf v1.3.1 h1:YF8+flBXS5eO826T4nzqPrxfhQThhXl0YzfuUPu4SBg=
|
33
|
+
github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
|
34
|
+
github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
|
35
|
+
github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
|
36
|
+
github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
|
37
|
+
github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
|
38
|
+
github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
|
39
|
+
github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
|
40
|
+
github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8=
|
41
|
+
github.com/golang/protobuf v1.4.2 h1:+Z5KGCizgyZCbGh1KZqA0fcLLkwbsjIzS4aV2v7wJX0=
|
42
|
+
github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
|
43
|
+
github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
|
44
|
+
github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
|
45
|
+
github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
|
46
|
+
github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
|
47
|
+
github.com/google/go-cmp v0.5.0 h1:/QaMHBdZ26BB3SSst0Iwl10Epc+xhTquomWX0oZEB6w=
|
48
|
+
github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
|
49
|
+
github.com/google/logger v1.1.0 h1:saB74Etb4EAJNH3z74CVbCKk75hld/8T0CsXKetWCwM=
|
50
|
+
github.com/google/logger v1.1.0/go.mod h1:w7O8nrRr0xufejBlQMI83MXqRusvREoJdaAxV+CoAB4=
|
51
|
+
github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o=
|
52
|
+
github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak=
|
53
|
+
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
|
54
|
+
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
|
55
|
+
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
|
56
|
+
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca h1:NugYot0LIVPxTvN8n+Kvkn6TrbMyxQiuvKdEwFdR9vI=
|
57
|
+
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca/go.mod h1:uugorj2VCxiV1x+LzaIdVa9b4S4qGAcH6cbhh4qVxOU=
|
58
|
+
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
|
59
|
+
github.com/stretchr/testify v1.3.0 h1:TivCn/peBQ7UY8ooIcPgZFpTNSz0Q2U6UrFlUfqbe0Q=
|
60
|
+
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
|
61
|
+
github.com/stretchr/testify v1.4.0 h1:2E4SXV/wtOkTonXsotYi4li6zVWxYlZuYNCXe9XRJyk=
|
62
|
+
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
|
63
|
+
github.com/temoto/robotstxt v1.1.1 h1:Gh8RCs8ouX3hRSxxK7B1mO5RFByQ4CmJZDwgom++JaA=
|
64
|
+
github.com/temoto/robotstxt v1.1.1/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo=
|
65
|
+
github.com/thoas/go-funk v0.7.0 h1:GmirKrs6j6zJbhJIficOsz2aAI7700KsU/5YrdHRM1Y=
|
66
|
+
github.com/thoas/go-funk v0.7.0/go.mod h1:+IWnUfUmFO1+WVYQWQtIJHeRRdaIyyYglZN7xzUPe4Q=
|
67
|
+
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
|
68
|
+
golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
|
69
|
+
golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
|
70
|
+
golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
|
71
|
+
golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
|
72
|
+
golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
|
73
|
+
golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
74
|
+
golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
75
|
+
golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
76
|
+
golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
77
|
+
golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
|
78
|
+
golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
|
79
|
+
golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
|
80
|
+
golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
|
81
|
+
golang.org/x/net v0.0.0-20200421231249-e086a090c8fd/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
|
82
|
+
golang.org/x/net v0.0.0-20200707034311-ab3426394381 h1:VXak5I6aEWmAXeQjA+QSZzlgNrpq9mjcfDemuexIKsU=
|
83
|
+
golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
|
84
|
+
golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
|
85
|
+
golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
86
|
+
golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
87
|
+
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
88
|
+
golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
89
|
+
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
90
|
+
golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
91
|
+
golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd h1:xhmwyvizuTgC2qz7ZlMluP20uW+C3Rm0FD/WLDX8884=
|
92
|
+
golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
93
|
+
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
94
|
+
golang.org/x/text v0.3.2 h1:tW2bmiBqwgJj/UpqtC8EpXEZVYOwU0yG4iWbprSVAcs=
|
95
|
+
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
|
96
|
+
golang.org/x/text v0.3.3 h1:cokOdA+Jmi5PJGXLlLllQSgYigAEfHXJAERHVMaCc2k=
|
97
|
+
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
98
|
+
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
99
|
+
golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
100
|
+
golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
|
101
|
+
golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
|
102
|
+
golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
|
103
|
+
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
|
104
|
+
golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
105
|
+
google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
|
106
|
+
google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
|
107
|
+
google.golang.org/appengine v1.6.6 h1:lMO5rYAqUxkmaj76jAkRUvt5JZgFymx/+Q5Mzfivuhc=
|
108
|
+
google.golang.org/appengine v1.6.6/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
|
109
|
+
google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
|
110
|
+
google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
|
111
|
+
google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
|
112
|
+
google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
|
113
|
+
google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
|
114
|
+
google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
|
115
|
+
google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
|
116
|
+
google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
|
117
|
+
google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
|
118
|
+
google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
|
119
|
+
google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
|
120
|
+
google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
|
121
|
+
google.golang.org/protobuf v1.23.0 h1:4MY060fB1DLGMB/7MBTLnwQUY6+F09GEiz6SsrNqyzM=
|
122
|
+
google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
|
123
|
+
google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
|
124
|
+
google.golang.org/protobuf v1.25.0 h1:Ejskq+SyPohKW+1uil0JJMtmHCgJPJ/qWTxr8qp+R4c=
|
125
|
+
google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
|
126
|
+
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
|
127
|
+
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
|
128
|
+
gopkg.in/yaml.v2 v2.2.2 h1:ZCJp+EgiOT7lHqUV2J862kp8Qj64Jo6az82+3Td9dZw=
|
129
|
+
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
|
130
|
+
honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
|
131
|
+
honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require 'ffi'
|
2
|
+
require 'fbcrawl_pb'
|
3
|
+
module FbcrawlColly
|
4
|
+
extend FFI::Library
|
5
|
+
|
6
|
+
ffi_lib File.expand_path("../ext/fbcrawl_colly/fbcolly.so", File.dirname(__FILE__))
|
7
|
+
attach_function :free, [ :pointer ], :void
|
8
|
+
|
9
|
+
attach_function :Init, [], :pointer
|
10
|
+
attach_function :Login, [:pointer, :string, :string], :void
|
11
|
+
attach_function :FetchGroupFeed, [:pointer, :string], :string
|
12
|
+
attach_function :FetchPost, [:pointer, :string, :string], :string
|
13
|
+
# attach_function :FetchGroup, [:pointer, :string], :pointer
|
14
|
+
# attach_function :Login, [:pointer, :string, :string, :string], :void
|
15
|
+
# attach_function :FreePointer, [:pointer], :void
|
16
|
+
end
|
data/main.go
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
package main
|
2
|
+
|
3
|
+
/*
|
4
|
+
#include <stdio.h>
|
5
|
+
#include <stdlib.h>
|
6
|
+
|
7
|
+
static void myprint(char* s) {
|
8
|
+
printf("%s\n", s);
|
9
|
+
}
|
10
|
+
|
11
|
+
|
12
|
+
*/
|
13
|
+
import "C"
|
14
|
+
|
15
|
+
import (
|
16
|
+
"flag"
|
17
|
+
"github.com/golang/protobuf/proto"
|
18
|
+
"qnetwork.net/fbcrawl/fbcolly"
|
19
|
+
"unsafe"
|
20
|
+
)
|
21
|
+
|
22
|
+
const logPath = "parse.log"
|
23
|
+
|
24
|
+
var verbose = flag.Bool("verbose", true, "print info level logs to stdout")
|
25
|
+
var email = flag.String("email", "change_me@gmail.com", "facebook email")
|
26
|
+
var password = flag.String("password", "change_me", "facebook password")
|
27
|
+
var otp = flag.String("otp", "123456", "facebook otp")
|
28
|
+
var groupId = flag.String("groupId", "334294967318328", "facebook group id, default is 334294967318328")
|
29
|
+
|
30
|
+
var tmp = fbcolly.New()
|
31
|
+
|
32
|
+
//export Init
|
33
|
+
func Init() uintptr {
|
34
|
+
return (uintptr)(unsafe.Pointer(tmp))
|
35
|
+
}
|
36
|
+
|
37
|
+
//export Login
|
38
|
+
func Login(pointer unsafe.Pointer, email *C.char, password *C.char) {
|
39
|
+
p := (*fbcolly.Fbcolly)(pointer)
|
40
|
+
//print(p.E)
|
41
|
+
p.Login(C.GoString(email), C.GoString(password), "")
|
42
|
+
}
|
43
|
+
|
44
|
+
//export FetchGroupFeed
|
45
|
+
func FetchGroupFeed(pointer unsafe.Pointer, groupId *C.char) unsafe.Pointer {
|
46
|
+
p := (*fbcolly.Fbcolly)(pointer)
|
47
|
+
_, postsList := p.FetchGroupFeed(C.GoString(groupId))
|
48
|
+
marshaledPostsList, _ := proto.Marshal(postsList)
|
49
|
+
return C.CBytes(append(marshaledPostsList, 0))
|
50
|
+
}
|
51
|
+
|
52
|
+
//export FetchPost
|
53
|
+
func FetchPost(pointer unsafe.Pointer, groupId *C.char, postId *C.char) unsafe.Pointer {
|
54
|
+
p := (*fbcolly.Fbcolly)(pointer)
|
55
|
+
_, post := p.FetchPost(C.GoString(groupId), C.GoString(postId))
|
56
|
+
marshaledPost, _ := proto.Marshal(post)
|
57
|
+
return C.CBytes(append(marshaledPost, 0))
|
58
|
+
}
|
59
|
+
|
60
|
+
func main() {
|
61
|
+
//r := regexp.MustCompile("/([\\d\\w.]+)").FindStringSubmatch()[1]
|
62
|
+
//print(r.FindStringSubmatch("/liem.phamthanh.161?refid=18&__tn__=R")[1])
|
63
|
+
//flag.Parse()
|
64
|
+
//
|
65
|
+
////post := fbcrawl.FacebookPost{}
|
66
|
+
////bPost, err := proto.Marshal(&post)
|
67
|
+
//
|
68
|
+
//lf, err := os.OpenFile(logPath, os.O_CREATE|os.O_WRONLY|os.O_APPEND, 0660)
|
69
|
+
//if err != nil {
|
70
|
+
// logger.Fatalf("Failed to open log file: %v", err)
|
71
|
+
//}
|
72
|
+
//defer lf.Close()
|
73
|
+
//defer logger.Init("fb-colly", *verbose, false, lf).Close()
|
74
|
+
//f := fbcolly.New()
|
75
|
+
//err = f.Login(*email, *password, *otp)
|
76
|
+
//f.FetchGroupFeed(*groupId)
|
77
|
+
}
|
metadata
ADDED
@@ -0,0 +1,95 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: fbcrawl-colly
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Duy Le
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2020-08-05 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: ffi
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: google-protobuf
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
description: Crawl mbasic.facebook.com using GO Colly
|
42
|
+
email:
|
43
|
+
- duyleekun@gmail.com
|
44
|
+
executables: []
|
45
|
+
extensions:
|
46
|
+
- ext/fbcrawl_colly/extconf.rb
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- ".gitignore"
|
50
|
+
- ".travis.yml"
|
51
|
+
- CODE_OF_CONDUCT.md
|
52
|
+
- Gemfile
|
53
|
+
- LICENSE.txt
|
54
|
+
- README.md
|
55
|
+
- Rakefile
|
56
|
+
- bin/console
|
57
|
+
- bin/setup
|
58
|
+
- ext/fbcrawl_colly/.gitignore
|
59
|
+
- ext/fbcrawl_colly/Makefile
|
60
|
+
- ext/fbcrawl_colly/extconf.rb
|
61
|
+
- fbcolly/fbcolly.go
|
62
|
+
- fbcrawl-colly.gemspec
|
63
|
+
- fbcrawl.proto
|
64
|
+
- go.mod
|
65
|
+
- go.sum
|
66
|
+
- lib/fbcrawl-colly.rb
|
67
|
+
- lib/fbcrawl-colly/version.rb
|
68
|
+
- main.go
|
69
|
+
homepage: http://github.com/duyleekun/fbcrawl-colly
|
70
|
+
licenses:
|
71
|
+
- MIT
|
72
|
+
metadata:
|
73
|
+
homepage_uri: http://github.com/duyleekun/fbcrawl-colly
|
74
|
+
source_code_uri: http://github.com/duyleekun/fbcrawl-colly
|
75
|
+
changelog_uri: http://github.com/duyleekun/fbcrawl-colly
|
76
|
+
post_install_message:
|
77
|
+
rdoc_options: []
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: 2.3.0
|
85
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
requirements: []
|
91
|
+
rubygems_version: 3.1.2
|
92
|
+
signing_key:
|
93
|
+
specification_version: 4
|
94
|
+
summary: Crawl mbasic.facebook.com using GO Colly
|
95
|
+
test_files: []
|