instagram_scraper 0.1.1 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/instagram_scraper.rb +38 -13
- metadata +31 -3
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 3671326d193735c6a72b39b2841b64815f39f9a2
|
|
4
|
+
data.tar.gz: c07bf5cdc92b101f5e1b812b990b9bba36b335a8
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 78870b7b1527b31f3ea55a7324a6fe875621e63cf33fc877c937dca38c2160cf511cc5fd4dd711130a93f9047947990c5235145486395d341ddabe136924ec62
|
|
7
|
+
data.tar.gz: b2387a74534ddf063311960fc9a28182431aba445ec56c32b0391d33ec87cd611bfa1611002b8c129ed3b604e372d2ce91770c6708caf816ee4013f3e296464a
|
data/lib/instagram_scraper.rb
CHANGED
|
@@ -1,21 +1,12 @@
|
|
|
1
1
|
class InstagramScraper
|
|
2
2
|
#code
|
|
3
|
-
def self.get_user_basic_json(name)
|
|
4
|
-
info_json = load_json("https://www.instagram.com/web/search/topsearch/?query=#{name}")
|
|
5
|
-
info_json['users'].find { |e| e['user']['username'] == name }['user']
|
|
6
|
-
end
|
|
7
|
-
|
|
8
|
-
def self.load_json(url)
|
|
9
|
-
#code
|
|
10
|
-
JSON.load(open(url))
|
|
11
|
-
end
|
|
12
3
|
|
|
13
|
-
def
|
|
14
|
-
|
|
15
|
-
|
|
4
|
+
def initialize(username, password)
|
|
5
|
+
@username = username
|
|
6
|
+
@password = password
|
|
16
7
|
end
|
|
17
8
|
|
|
18
|
-
def
|
|
9
|
+
def get(name)
|
|
19
10
|
basic_json = get_user_basic_json name
|
|
20
11
|
media_json = load_media_json name
|
|
21
12
|
@user = InstagramUser.new
|
|
@@ -26,7 +17,41 @@ class InstagramScraper
|
|
|
26
17
|
@user.media_json = media_json
|
|
27
18
|
@user
|
|
28
19
|
end
|
|
20
|
+
|
|
21
|
+
private
|
|
22
|
+
def load_media_json(name)
|
|
23
|
+
url = "https://www.instagram.com/#{name}/media"
|
|
24
|
+
b = login_instagram @username, @password
|
|
25
|
+
b.goto url
|
|
26
|
+
html_doc = Nokogiri::HTML(b.html)
|
|
27
|
+
json = html_doc.css('pre').first.content
|
|
28
|
+
JSON.load(json)
|
|
29
|
+
end
|
|
30
|
+
|
|
31
|
+
def login_instagram(username, password)
|
|
32
|
+
browser = Watir::Browser.new
|
|
33
|
+
browser.goto "https://www.instagram.com/accounts/login/"
|
|
34
|
+
browser.text_field(css: 'div._ccek6:nth-child(1) > input:nth-child(1)').when_present.set(username)
|
|
35
|
+
browser.text_field(css: 'div._ccek6:nth-child(2) > input:nth-child(1)').when_present.set(password)
|
|
36
|
+
browser.button(css: '._rz1lq').click
|
|
37
|
+
browser.div(css: '._l09h7').wait_until_present
|
|
38
|
+
browser
|
|
39
|
+
end
|
|
40
|
+
|
|
41
|
+
def get_user_basic_json(name)
|
|
42
|
+
info_json = load_json("https://www.instagram.com/web/search/topsearch/?query=#{name}")
|
|
43
|
+
info_json['users'].find { |e| e['user']['username'] == name }['user']
|
|
44
|
+
end
|
|
45
|
+
|
|
46
|
+
def load_json(url)
|
|
47
|
+
#code
|
|
48
|
+
# JSON.load(open(url))
|
|
49
|
+
uri = URI.parse(url)
|
|
50
|
+
JSON.load(uri.open)
|
|
51
|
+
end
|
|
29
52
|
end
|
|
30
53
|
|
|
54
|
+
require 'nokogiri'
|
|
55
|
+
require "watir"
|
|
31
56
|
require 'open-uri'
|
|
32
57
|
require "json"
|
metadata
CHANGED
|
@@ -1,15 +1,43 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: instagram_scraper
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.2.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- samwalker
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2016-02-
|
|
12
|
-
dependencies:
|
|
11
|
+
date: 2016-02-05 00:00:00.000000000 Z
|
|
12
|
+
dependencies:
|
|
13
|
+
- !ruby/object:Gem::Dependency
|
|
14
|
+
name: nokogiri
|
|
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: watir
|
|
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'
|
|
13
41
|
description: A instagram scraper to get user instagram data thought public api (search
|
|
14
42
|
and media)
|
|
15
43
|
email: samwalker505@gmail.com
|