ids_please 2.1.2 → 2.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +1 -0
- data/lib/ids_please/grabbers/base.rb +4 -1
- data/lib/ids_please/grabbers/facebook.rb +25 -9
- data/lib/ids_please/grabbers/google_plus.rb +25 -0
- data/lib/ids_please/grabbers/instagram.rb +13 -17
- data/lib/ids_please/grabbers/mailru.rb +7 -7
- data/lib/ids_please/grabbers/twitter.rb +15 -9
- data/lib/ids_please/grabbers/vkontakte.rb +8 -8
- data/lib/ids_please/grabbers.rb +2 -0
- data/lib/ids_please/version.rb +1 -1
- data/spec/ids_please/basic_spec.rb +1 -1
- metadata +3 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: cbbb7fdc96da69f11a60cfbda149c1efc18cf3ec
|
|
4
|
+
data.tar.gz: a32ec832041c194f72d78aae0f410688edbd3239
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e903c0a4695122ade18201fe6f33035644c2193cd13e1f950426da6ba98de85ccb4953f6aab4069288652b202441ed4992b09cd51e13ea34d544e8afe5060ed8
|
|
7
|
+
data.tar.gz: 94ef374b9075560bad7f53dd829d98a499f3b84d923de4392df9f77a07afeb628a723ef8e977b9fcde2323c94084da47d726e14791c08f3d81997d64905475da
|
data/README.md
CHANGED
|
@@ -8,7 +8,7 @@ class IdsPlease
|
|
|
8
8
|
links.map { |l| self.new(l).grab_link }
|
|
9
9
|
end
|
|
10
10
|
|
|
11
|
-
attr_reader :avatar, :display_name, :username, :link, :page_source, :network_id, :data
|
|
11
|
+
attr_reader :avatar, :display_name, :username, :link, :page_source, :network_id, :data, :counts
|
|
12
12
|
|
|
13
13
|
def initialize(link)
|
|
14
14
|
@link = link
|
|
@@ -45,6 +45,9 @@ class IdsPlease
|
|
|
45
45
|
to_s
|
|
46
46
|
end
|
|
47
47
|
|
|
48
|
+
def page_source
|
|
49
|
+
@page_source ||= open(link).read
|
|
50
|
+
end
|
|
48
51
|
end
|
|
49
52
|
end
|
|
50
53
|
end
|
|
@@ -3,27 +3,43 @@ class IdsPlease
|
|
|
3
3
|
class Facebook < IdsPlease::Grabbers::Base
|
|
4
4
|
|
|
5
5
|
def grab_link
|
|
6
|
-
@page_source
|
|
7
|
-
@
|
|
8
|
-
@
|
|
9
|
-
@
|
|
10
|
-
@
|
|
11
|
-
@avatar = CGI.unescapeHTML(@avatar.encode('utf-8')) if @avatar
|
|
6
|
+
@network_id = page_source.scan(/entity_id":"(\d+)"/).flatten.first
|
|
7
|
+
@avatar = page_source.scan(/og:image" content="([^"]+)"/).flatten.first
|
|
8
|
+
@display_name = page_source.scan(/og:title" content="([^"]+)"/).flatten.first
|
|
9
|
+
@username = page_source.scan(/og:url" content="[^"]+\/([^\/"]+)"/).flatten.first
|
|
10
|
+
@avatar = CGI.unescapeHTML(@avatar.encode('utf-8')) if @avatar
|
|
12
11
|
@display_name = CGI.unescapeHTML(@display_name.encode('utf-8')) if @display_name
|
|
13
12
|
@data = {}
|
|
14
13
|
{
|
|
15
|
-
type:
|
|
16
|
-
description:
|
|
14
|
+
type: page_source.scan(/og:type" content="([^"]+)"/).flatten.first.to_s.encode('utf-8'),
|
|
15
|
+
description: page_source.scan(/og:description" content="([^"]+)"/).flatten.first.to_s.encode('utf-8'),
|
|
17
16
|
}.each do |k, v|
|
|
18
17
|
next if v.nil? || v == ''
|
|
19
|
-
@data[k] = CGI.unescapeHTML(v)
|
|
18
|
+
@data[k] = CGI.unescapeHTML(v).strip
|
|
20
19
|
end
|
|
20
|
+
@counts = {
|
|
21
|
+
likes: likes,
|
|
22
|
+
visits: visits,
|
|
23
|
+
}.delete_if {|k,v| v.nil? }
|
|
21
24
|
self
|
|
22
25
|
rescue => e
|
|
23
26
|
p e
|
|
24
27
|
return self
|
|
25
28
|
end
|
|
26
29
|
|
|
30
|
+
def likes
|
|
31
|
+
page_source.scan(/>([^"]+) <span class=".+">likes/).flatten.first.to_s.tr(',','').to_i
|
|
32
|
+
rescue => e
|
|
33
|
+
p e
|
|
34
|
+
return nil
|
|
35
|
+
end
|
|
36
|
+
|
|
37
|
+
def visits
|
|
38
|
+
page_source.scan(/likes.+>([^"]+)<\/span> <span class=".+">visits/).flatten.first.to_s.tr(',','').to_i
|
|
39
|
+
rescue => e
|
|
40
|
+
p e
|
|
41
|
+
return nil
|
|
42
|
+
end
|
|
27
43
|
end
|
|
28
44
|
end
|
|
29
45
|
end
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
class IdsPlease
|
|
2
|
+
module Grabbers
|
|
3
|
+
class GooglePlus < IdsPlease::Grabbers::Base
|
|
4
|
+
|
|
5
|
+
def grab_link
|
|
6
|
+
@network_id = page_source.scan(/data-oid="(\d+)"/).flatten.first
|
|
7
|
+
@avatar = 'https:' + page_source.scan(/guidedhelpid="profile_photo"><img src="([^"]+)"/).flatten.first
|
|
8
|
+
@display_name = page_source.scan(/og:title" content="([^"]+)"/).flatten.first.gsub(' - Google+','')
|
|
9
|
+
@username = '+' + page_source.scan(/"https:\/\/plus.google.com\/\+(.+?)"/).flatten.first
|
|
10
|
+
@data = {
|
|
11
|
+
description: page_source.scan(/name="Description" content="([^"]+)">/).flatten.first.to_s.encode('utf-8')
|
|
12
|
+
}
|
|
13
|
+
@counts = {
|
|
14
|
+
followers: page_source.scan(/">([^"]+)<\/span> followers</).flatten.first.to_s.tr(',','').to_i,
|
|
15
|
+
views: page_source.scan(/">([^"]+)<\/span> views</).flatten.first.to_s.tr(',','').to_i,
|
|
16
|
+
}
|
|
17
|
+
self
|
|
18
|
+
rescue => e
|
|
19
|
+
p e
|
|
20
|
+
return self
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
end
|
|
24
|
+
end
|
|
25
|
+
end
|
|
@@ -5,29 +5,25 @@ class IdsPlease
|
|
|
5
5
|
class Instagram < IdsPlease::Grabbers::Base
|
|
6
6
|
|
|
7
7
|
def grab_link
|
|
8
|
-
@page_source
|
|
9
|
-
@
|
|
10
|
-
@
|
|
11
|
-
@
|
|
12
|
-
@
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
{
|
|
17
|
-
|
|
18
|
-
|
|
19
|
-
|
|
20
|
-
}
|
|
21
|
-
next if v.nil? || v == '' || !v.is_a?(String)
|
|
22
|
-
@data[k] = v.gsub(/\\u([\da-fA-F]{4})/) {|m| [$1].pack("H*").unpack("n*").pack("U*")}
|
|
23
|
-
end
|
|
8
|
+
@network_id = page_source.scan(/"user":{.+"id":"(\d+)"/).flatten.first
|
|
9
|
+
@avatar = page_source.scan(/"user":{.+"profile_pic_url":"([^"]+)"/).flatten.first.gsub('\\', '')
|
|
10
|
+
@display_name = page_source.scan(/"user":{.+"full_name":"([^"]+)"/).flatten.first
|
|
11
|
+
@username = page_source.scan(/"user":{"username":"([^"]+)"/).flatten.first.gsub('\\', '')
|
|
12
|
+
@data = {
|
|
13
|
+
bio: page_source.scan(/"biography":"([^"]+)"/).flatten.first,
|
|
14
|
+
website: page_source.scan(/"user":{.+"external_url":"([^"]+)"/).flatten.first.gsub('\\', ''),
|
|
15
|
+
}
|
|
16
|
+
@counts = {
|
|
17
|
+
media: page_source.scan(/"media":{"count":(\d+)/).flatten.first.to_i,
|
|
18
|
+
followed_by: page_source.scan(/"followed_by":{"count":(\d+)/).flatten.first.to_i,
|
|
19
|
+
follows: page_source.scan(/"follows":{"count":(\d+)/).flatten.first.to_i,
|
|
20
|
+
}
|
|
24
21
|
@display_name = @display_name.gsub(/\\u([\da-fA-F]{4})/) {|m| [$1].pack("H*").unpack("n*").pack("U*")}
|
|
25
22
|
self
|
|
26
23
|
rescue => e
|
|
27
24
|
p e
|
|
28
25
|
return self
|
|
29
26
|
end
|
|
30
|
-
|
|
31
27
|
end
|
|
32
28
|
end
|
|
33
29
|
end
|
|
@@ -5,16 +5,16 @@ class IdsPlease
|
|
|
5
5
|
class Mailru < IdsPlease::Grabbers::Base
|
|
6
6
|
|
|
7
7
|
def grab_link
|
|
8
|
-
@page_source
|
|
9
|
-
uid_url
|
|
10
|
-
@network_id
|
|
8
|
+
@page_source ||= open(link).read.encode('utf-8')
|
|
9
|
+
uid_url = "http://appsmail.ru/platform/#{link.split('/')[-2..-1].join('/')}"
|
|
10
|
+
@network_id = JSON.parse(open(uid_url).read)['uid']
|
|
11
11
|
@username, type = get_name_and_type(link)
|
|
12
|
-
@avatar
|
|
13
|
-
@display_name
|
|
14
|
-
@display_name
|
|
12
|
+
@avatar = page_source.scan(/profile__avatar" src="([^"]+)/).flatten.first
|
|
13
|
+
@display_name = page_source.scan(/h1.+title="([^"]+)/).flatten.first
|
|
14
|
+
@display_name = CGI.unescapeHTML(@display_name) if @display_name
|
|
15
15
|
@data = {
|
|
16
16
|
type: type,
|
|
17
|
-
description:
|
|
17
|
+
description: page_source.scan(/profile__content_mainInfo" title="([^"]+)/).flatten.first
|
|
18
18
|
}
|
|
19
19
|
@data[:description] = CGI.unescapeHTML(@data[:description]) if @data[:description]
|
|
20
20
|
self
|
|
@@ -3,20 +3,26 @@ class IdsPlease
|
|
|
3
3
|
class Twitter < IdsPlease::Grabbers::Base
|
|
4
4
|
|
|
5
5
|
def grab_link
|
|
6
|
-
@page_source
|
|
7
|
-
@
|
|
8
|
-
@
|
|
9
|
-
@
|
|
10
|
-
@username = @page_source.scan(/<title>[^\(]+\(@([^\)]+)\)/).flatten.first
|
|
6
|
+
@network_id = page_source.scan(/data-user-id="(\d+)"/).flatten.first
|
|
7
|
+
@avatar = page_source.scan(/ProfileAvatar-image " src="([^"]+)"/).flatten.first
|
|
8
|
+
@display_name = page_source.scan(/ProfileHeaderCard-nameLink[^>]+>([^<]+)</).flatten.first
|
|
9
|
+
@username = page_source.scan(/<title>[^\(]+\(@([^\)]+)\)/).flatten.first
|
|
11
10
|
@data = {}
|
|
12
11
|
{
|
|
13
|
-
description:
|
|
14
|
-
location:
|
|
15
|
-
join_date:
|
|
12
|
+
description: page_source.scan(/ProfileHeaderCard-bio[^>]+>([^<]+)</).flatten.first.to_s.encode('utf-8'),
|
|
13
|
+
location: page_source.scan(/ProfileHeaderCard-locationText[^>]+>([^<]+)</).flatten.first.to_s.encode('utf-8'),
|
|
14
|
+
join_date: page_source.scan(/ProfileHeaderCard-joinDateText[^>]+>([^<]+)</).flatten.first.to_s.encode('utf-8'),
|
|
16
15
|
}.each do |k, v|
|
|
17
16
|
next if v.nil? || v == ''
|
|
18
|
-
@data[k] = CGI.unescapeHTML(v)
|
|
17
|
+
@data[k] = CGI.unescapeHTML(v).strip
|
|
19
18
|
end
|
|
19
|
+
@counts = {
|
|
20
|
+
tweets: page_source.scan(/statuses_count":(\d+),"/).flatten.first.to_i,
|
|
21
|
+
following: page_source.scan(/friends_count":(\d+),"/).flatten.first.to_i,
|
|
22
|
+
followers: page_source.scan(/followers_count":(\d+),"/).flatten.first.to_i,
|
|
23
|
+
favorites: page_source.scan(/favourites_count":(\d+),"/).flatten.first.to_i,
|
|
24
|
+
lists: page_source.scan(/listed_count":(\d+),"/).flatten.first.to_i,
|
|
25
|
+
}
|
|
20
26
|
self
|
|
21
27
|
rescue => e
|
|
22
28
|
p e
|
|
@@ -3,16 +3,16 @@ class IdsPlease
|
|
|
3
3
|
class Vkontakte < IdsPlease::Grabbers::Base
|
|
4
4
|
|
|
5
5
|
def grab_link
|
|
6
|
-
agent
|
|
6
|
+
agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36'
|
|
7
7
|
@page_source ||= open(link, 'User-Agent' => agent).read.encode('utf-8')
|
|
8
|
-
@network_id
|
|
9
|
-
@username
|
|
10
|
-
@avatar
|
|
11
|
-
@avatar
|
|
12
|
-
@display_name
|
|
13
|
-
@display_name
|
|
8
|
+
@network_id = page_source.scan(/href="\/wall(-\d+)_/).flatten.first
|
|
9
|
+
@username = @link.to_s.split('vk.com/').last.gsub('/', '')
|
|
10
|
+
@avatar = page_source.scan(/page_avatar.+\n.+src="([^"]+)/).flatten.first
|
|
11
|
+
@avatar = CGI.unescapeHTML(@avatar) if @avatar
|
|
12
|
+
@display_name = page_source.scan(/page_name">([^<]+)/).flatten.first
|
|
13
|
+
@display_name = CGI.unescapeHTML(@display_name) if @display_name
|
|
14
14
|
@data = {
|
|
15
|
-
description:
|
|
15
|
+
description: page_source.scan(/description" content="([^"]+)/).flatten.first
|
|
16
16
|
}
|
|
17
17
|
@data[:description] = CGI.unescapeHTML(@data[:description]) if @data[:description]
|
|
18
18
|
self
|
data/lib/ids_please/grabbers.rb
CHANGED
|
@@ -4,6 +4,7 @@ require_relative 'grabbers/vkontakte'
|
|
|
4
4
|
require_relative 'grabbers/instagram'
|
|
5
5
|
require_relative 'grabbers/twitter'
|
|
6
6
|
require_relative 'grabbers/mailru'
|
|
7
|
+
require_relative 'grabbers/google_plus'
|
|
7
8
|
|
|
8
9
|
class IdsPlease
|
|
9
10
|
module Grabbers
|
|
@@ -14,6 +15,7 @@ class IdsPlease
|
|
|
14
15
|
twitter: IdsPlease::Grabbers::Twitter,
|
|
15
16
|
instagram: IdsPlease::Grabbers::Instagram,
|
|
16
17
|
mailru: IdsPlease::Grabbers::Mailru,
|
|
18
|
+
google_plus: IdsPlease::Grabbers::GooglePlus,
|
|
17
19
|
}
|
|
18
20
|
|
|
19
21
|
def self.each
|
data/lib/ids_please/version.rb
CHANGED
|
@@ -4,7 +4,7 @@ describe IdsPlease do
|
|
|
4
4
|
|
|
5
5
|
recognazible_links = %w(
|
|
6
6
|
https://www.facebook.com/fb_acc
|
|
7
|
-
https://
|
|
7
|
+
https://facebook.com/fb_acc2<U+200>
|
|
8
8
|
http://instagram.com/inst_acc
|
|
9
9
|
http://hi5.com/hi5_acc
|
|
10
10
|
http://www.hi5.com/profile.html?uid=12341234
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: ids_please
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 2.
|
|
4
|
+
version: 2.2.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- gazay
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2015-08-
|
|
11
|
+
date: 2015-08-17 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rake
|
|
@@ -56,6 +56,7 @@ files:
|
|
|
56
56
|
- lib/ids_please/grabbers.rb
|
|
57
57
|
- lib/ids_please/grabbers/base.rb
|
|
58
58
|
- lib/ids_please/grabbers/facebook.rb
|
|
59
|
+
- lib/ids_please/grabbers/google_plus.rb
|
|
59
60
|
- lib/ids_please/grabbers/instagram.rb
|
|
60
61
|
- lib/ids_please/grabbers/mailru.rb
|
|
61
62
|
- lib/ids_please/grabbers/twitter.rb
|