medium-scrapper 0.0.2
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/lib/builder/user_builder.rb +17 -0
- data/lib/medium-scrapper.rb +11 -0
- data/lib/model/post.rb +10 -0
- data/lib/model/user.rb +16 -0
- data/lib/parser/url_parser.rb +19 -0
- data/lib/retriever/post_retriever.rb +26 -0
- data/lib/retriever/user_retriever.rb +28 -0
- metadata +51 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 159c9a1de5200ace4fd046cc2730f93d4a91e053
|
4
|
+
data.tar.gz: 1234666074cdde0a5bdbbc2a46eb285c809f4653
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 076802e6c3c210cf301a80e6e2b377fa7b10d17ad93184e45c1a242f3730483f79f37650adbe993b2d96e04b16eff5340103ece74732b07c9df051159cd523e6
|
7
|
+
data.tar.gz: 889135aede45a43ca0e821f057c14585226262420867c3f3e4a6de25ecde3540f21de74ca3dd2746ee18b5f8771e010a5975a23ce590f2add13c0c48e94075a9
|
@@ -0,0 +1,17 @@
|
|
1
|
+
|
2
|
+
require "model/user"
|
3
|
+
|
4
|
+
class UserBuilder
|
5
|
+
def initialize(raw_user)
|
6
|
+
@raw_user = raw_user
|
7
|
+
end
|
8
|
+
|
9
|
+
def build
|
10
|
+
name = @raw_user["name"]
|
11
|
+
username = @raw_user["username"]
|
12
|
+
user_id = @raw_user["userId"]
|
13
|
+
bio = @raw_user["bio"]
|
14
|
+
|
15
|
+
User.new(name, username, user_id, bio)
|
16
|
+
end
|
17
|
+
end
|
data/lib/model/post.rb
ADDED
data/lib/model/user.rb
ADDED
@@ -0,0 +1,16 @@
|
|
1
|
+
|
2
|
+
class User
|
3
|
+
attr_reader :name, :username, :user_id, :bio, :posts
|
4
|
+
|
5
|
+
def initialize(name, username, user_id, bio)
|
6
|
+
@name = name
|
7
|
+
@username = username
|
8
|
+
@user_id = user_id
|
9
|
+
@bio = bio
|
10
|
+
@posts = []
|
11
|
+
end
|
12
|
+
|
13
|
+
def add_post(post)
|
14
|
+
@posts << post
|
15
|
+
end
|
16
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
|
2
|
+
require "open-uri"
|
3
|
+
require "json"
|
4
|
+
|
5
|
+
class UrlParser
|
6
|
+
def initialize(url)
|
7
|
+
@url = url
|
8
|
+
end
|
9
|
+
|
10
|
+
def parse
|
11
|
+
content = ""
|
12
|
+
open(@url) do |file|
|
13
|
+
file.each_line do |line|
|
14
|
+
content << line
|
15
|
+
end
|
16
|
+
end
|
17
|
+
JSON.parse(content[16..-1])["payload"]
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
|
2
|
+
require "model/post"
|
3
|
+
|
4
|
+
class PostRetriever
|
5
|
+
def initialize(parser)
|
6
|
+
@parser = parser
|
7
|
+
end
|
8
|
+
|
9
|
+
def load(user_id, post_id)
|
10
|
+
parsed_url = parse_url(user_id, post_id)
|
11
|
+
|
12
|
+
Post.new(parsed_url["title"], parsed_url["content"]["subtitle"], normalize_content(parsed_url["content"]["bodyModel"]["paragraphs"]))
|
13
|
+
end
|
14
|
+
|
15
|
+
def normalize_content(paragraphs_raw)
|
16
|
+
body = ""
|
17
|
+
paragraphs_raw[1..-1].each do |paragraph|
|
18
|
+
body << paragraph["text"] + "\n\n"
|
19
|
+
end
|
20
|
+
body
|
21
|
+
end
|
22
|
+
|
23
|
+
def parse_url(user_id, post_id)
|
24
|
+
@parser.new("https://www.medium.com/@#{user_id}/#{post_id}?format=json").parse["value"]
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,28 @@
|
|
1
|
+
|
2
|
+
require "builder/user_builder"
|
3
|
+
require "retriever/post_retriever"
|
4
|
+
|
5
|
+
class UserRetriever
|
6
|
+
def initialize(parser)
|
7
|
+
@parser = parser
|
8
|
+
end
|
9
|
+
|
10
|
+
def load(username)
|
11
|
+
parsed_url = parse_url(username)
|
12
|
+
|
13
|
+
user = UserBuilder.new(parsed_url["value"]).build
|
14
|
+
|
15
|
+
posts_raw = parsed_url["latestPosts"]
|
16
|
+
posts_raw.each do |post_raw|
|
17
|
+
user.add_post(PostRetriever.new(@parser).load(user.user_id, post_raw["id"]))
|
18
|
+
end
|
19
|
+
|
20
|
+
user
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
def parse_url(username)
|
26
|
+
@parser.new("https://www.medium.com/@#{username}?format=json").parse
|
27
|
+
end
|
28
|
+
end
|
metadata
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: medium-scrapper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- uesteibar
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-06-21 00:00:00.000000000 Z
|
12
|
+
dependencies: []
|
13
|
+
description: Ruby gem that provides a Medium.com read-only API
|
14
|
+
email: uesteibar@gmail.com
|
15
|
+
executables: []
|
16
|
+
extensions: []
|
17
|
+
extra_rdoc_files: []
|
18
|
+
files:
|
19
|
+
- lib/builder/user_builder.rb
|
20
|
+
- lib/medium-scrapper.rb
|
21
|
+
- lib/model/post.rb
|
22
|
+
- lib/model/user.rb
|
23
|
+
- lib/parser/url_parser.rb
|
24
|
+
- lib/retriever/post_retriever.rb
|
25
|
+
- lib/retriever/user_retriever.rb
|
26
|
+
homepage: https://github.com/uesteibar/medium-gem
|
27
|
+
licenses:
|
28
|
+
- MIT
|
29
|
+
metadata: {}
|
30
|
+
post_install_message:
|
31
|
+
rdoc_options: []
|
32
|
+
require_paths:
|
33
|
+
- lib
|
34
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
35
|
+
requirements:
|
36
|
+
- - ">="
|
37
|
+
- !ruby/object:Gem::Version
|
38
|
+
version: '0'
|
39
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
version: '0'
|
44
|
+
requirements: []
|
45
|
+
rubyforge_project:
|
46
|
+
rubygems_version: 2.4.6
|
47
|
+
signing_key:
|
48
|
+
specification_version: 4
|
49
|
+
summary: medium read-only api
|
50
|
+
test_files: []
|
51
|
+
has_rdoc:
|