makuri 0.2.0 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +11 -1
- data/lib/makuri/browser.rb +35 -25
- data/lib/makuri/browser_builder/ferrum.rb +44 -0
- data/lib/makuri/browser_builder/net_http.rb +8 -1
- data/lib/makuri/spider.rb +29 -9
- data/lib/makuri/version.rb +1 -1
- data/lib/makuri.rb +1 -1
- metadata +16 -30
- data/lib/makuri/browser_builder/chrome.rb +0 -34
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: '08d39eda46b02f5f6894d581eb0d837ac4680f4c2f6239b6f585a4c187ed44d7'
|
4
|
+
data.tar.gz: 433093581b01eb5327e1bb8e6dd6653f0b51fcfdae54276a914339b0bff61b2f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: daaf82155b49cc1efe7da7d092c617fb47e8948758108afbea79a5d484a08757781a2f156d066946d821c0c25b5984693b69dbdde764bf2dd14c07a9997d3112
|
7
|
+
data.tar.gz: e8655c684cfa1087d1046a7cf0447f8a4b52ee8d17c6b25028c78d8f50bfa8df0a076ecd38f0cb504311dc1b55bae53b199fea2bc5982b65bf5b9b9d10221e33
|
data/CHANGELOG.md
CHANGED
@@ -1,10 +1,20 @@
|
|
1
|
+
## 0.4.0 (2024-06-13)
|
2
|
+
- Add Ferrum support
|
3
|
+
- Remove Capybara/chrome support
|
4
|
+
- Bug fixes
|
5
|
+
|
6
|
+
## 0.3.0 (2021-02-07)
|
7
|
+
- Allow scrape from multiple start_urls
|
8
|
+
- Add :engine support to Spider
|
9
|
+
- Add :enable_images support to :chrome engine
|
10
|
+
- Bug fixes and restructure #request_method & #request_body
|
11
|
+
|
1
12
|
## 0.2.0 (2021-01-25)
|
2
13
|
- Add Capybara Support
|
3
14
|
- Add :headless option to Browser object
|
4
15
|
- Bug fixes & restructure Browser #follow, #request methods
|
5
16
|
|
6
17
|
## 0.1.0 (2021-01-05)
|
7
|
-
|
8
18
|
- First Release
|
9
19
|
- Add Basic Browser Builders for crawling web pages
|
10
20
|
- Add Spider Framework to support scraping
|
data/lib/makuri/browser.rb
CHANGED
@@ -1,50 +1,50 @@
|
|
1
1
|
module Makuri
|
2
2
|
class Browser
|
3
|
-
attr_accessor :url, :
|
3
|
+
attr_accessor :url, :engine, :headless, :user_agent, :request_method, :request_body
|
4
4
|
|
5
5
|
def initialize(options = {})
|
6
|
-
@
|
7
|
-
@request_method = options.fetch(:request_method, :get)
|
8
|
-
@request_body = options.fetch(:request_body, {})
|
9
|
-
|
10
|
-
@js = options.fetch(:js, false)
|
6
|
+
@engine = options.fetch(:engine, :net_http)
|
11
7
|
@headless = options.fetch(:headless, true)
|
12
8
|
@user_agent = options.fetch(
|
13
9
|
:user_agent,
|
14
10
|
'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.111 Safari/537.36'
|
15
11
|
)
|
12
|
+
|
13
|
+
# Defaults
|
14
|
+
@request_method = :get
|
15
|
+
@request_body = {}
|
16
16
|
end
|
17
17
|
|
18
18
|
def browser
|
19
19
|
@browser ||= create_browser
|
20
20
|
end
|
21
21
|
|
22
|
-
#
|
23
|
-
def
|
24
|
-
@url =
|
25
|
-
|
22
|
+
# Allow for NetHttp get request
|
23
|
+
def request(url, options = {})
|
24
|
+
@url = url
|
25
|
+
validate_url
|
26
26
|
|
27
|
-
|
27
|
+
return follow if ['Ferrum', 'Chrome'].include? browser_engine
|
28
28
|
|
29
|
-
|
30
|
-
|
29
|
+
@request_method = options.fetch(:method, request_method)
|
30
|
+
@request_body = options.fetch(:body, request_body)
|
31
|
+
browser.visit(@url)
|
31
32
|
end
|
32
33
|
|
33
|
-
|
34
|
-
|
35
|
-
@url = current_url unless current_url.empty?
|
36
|
-
raise 'Invalid URL supplied' if url.empty?
|
37
|
-
|
38
|
-
raise 'Invalid request type for js=true. Use #follow in place of #get' if js
|
39
|
-
|
40
|
-
browser.visit(url).body
|
34
|
+
def quit
|
35
|
+
browser.respond_to?(:quit) ? browser.quit : nil
|
41
36
|
end
|
42
37
|
|
43
38
|
private
|
44
39
|
|
40
|
+
# Only allow for capybara get request
|
41
|
+
def follow
|
42
|
+
browser.visit(@url)
|
43
|
+
browser
|
44
|
+
end
|
45
|
+
|
45
46
|
def create_browser
|
46
|
-
|
47
|
-
builder = Object.const_get "Makuri::BrowserBuilder::#{engine}"
|
47
|
+
builder = Object.const_get "Makuri::BrowserBuilder::#{browser_engine}"
|
48
48
|
builder.new(browser_params).build
|
49
49
|
end
|
50
50
|
|
@@ -57,8 +57,18 @@ module Makuri
|
|
57
57
|
}
|
58
58
|
end
|
59
59
|
|
60
|
-
def
|
61
|
-
|
60
|
+
def validate_url
|
61
|
+
uri = URI.parse(@url)
|
62
|
+
raise 'Invalid URL supplied' unless uri.is_a?(URI::HTTP) && !uri.host.nil?
|
63
|
+
end
|
64
|
+
|
65
|
+
def browser_engine
|
66
|
+
case engine
|
67
|
+
when :ferrum
|
68
|
+
'Ferrum'
|
69
|
+
else
|
70
|
+
'NetHttp'
|
71
|
+
end
|
62
72
|
end
|
63
73
|
end
|
64
74
|
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
require 'ferrum'
|
2
|
+
|
3
|
+
module Makuri::BrowserBuilder
|
4
|
+
class Ferrum < Base
|
5
|
+
attr_accessor :headless, :html
|
6
|
+
|
7
|
+
def initialize(options = {})
|
8
|
+
super
|
9
|
+
@headless = options.fetch(:headless, true)
|
10
|
+
end
|
11
|
+
|
12
|
+
def build
|
13
|
+
headers = { 'User-Agent': user_agent }
|
14
|
+
@ferrum = ::Ferrum::Browser.new(headless: @headless, headers: headers)
|
15
|
+
self
|
16
|
+
end
|
17
|
+
|
18
|
+
def visit(url)
|
19
|
+
@ferrum.go_to url
|
20
|
+
@html = @ferrum.body
|
21
|
+
self
|
22
|
+
end
|
23
|
+
|
24
|
+
def quit
|
25
|
+
@ferrum.quit
|
26
|
+
end
|
27
|
+
|
28
|
+
private
|
29
|
+
|
30
|
+
# TODO:
|
31
|
+
# def browser_options
|
32
|
+
# args = %w[
|
33
|
+
# --disable-gpu
|
34
|
+
# --no-sandbox
|
35
|
+
# --disable-translate
|
36
|
+
# --ignore-certificate-errors
|
37
|
+
# ]
|
38
|
+
# args << '--headless' if headless
|
39
|
+
# args << "--user-agent=#{user_agent}"
|
40
|
+
# args << "--blink-settings=imagesEnabled=#{enable_images}"
|
41
|
+
# Selenium::WebDriver::Chrome::Options.new(args: args)
|
42
|
+
# end
|
43
|
+
end
|
44
|
+
end
|
@@ -2,6 +2,8 @@ require 'net/http'
|
|
2
2
|
|
3
3
|
module Makuri::BrowserBuilder
|
4
4
|
class NetHttp < Base
|
5
|
+
attr_accessor :response
|
6
|
+
|
5
7
|
def build
|
6
8
|
self
|
7
9
|
end
|
@@ -12,9 +14,14 @@ module Makuri::BrowserBuilder
|
|
12
14
|
|
13
15
|
request = send("#{request_method}_request", uri.request_uri, headers)
|
14
16
|
|
15
|
-
Net::HTTP.start(uri.host, uri.port, use_ssl: (uri.scheme == 'https')) do |http|
|
17
|
+
@response = Net::HTTP.start(uri.host, uri.port, use_ssl: (uri.scheme == 'https')) do |http|
|
16
18
|
http.request(request)
|
17
19
|
end
|
20
|
+
self
|
21
|
+
end
|
22
|
+
|
23
|
+
def html
|
24
|
+
@response.body
|
18
25
|
end
|
19
26
|
|
20
27
|
private
|
data/lib/makuri/spider.rb
CHANGED
@@ -18,23 +18,39 @@ module Makuri
|
|
18
18
|
@start_urls = urls
|
19
19
|
end
|
20
20
|
|
21
|
+
def spider_options(**options)
|
22
|
+
@engine = options.fetch(:engine, :net_http)
|
23
|
+
@headless = options.fetch(:headless, true)
|
24
|
+
end
|
25
|
+
|
21
26
|
def run
|
22
27
|
raise "Start URLs not found. Define start_urls for #{self}." unless defined? @start_urls
|
23
28
|
|
24
|
-
|
29
|
+
@engine ||= :net_http
|
30
|
+
@headless = defined?(@headless) ? @headless : true
|
31
|
+
|
32
|
+
@start_urls.each { |start_url| new(start_url: start_url, engine: @engine, headless: @headless).parse }
|
25
33
|
end
|
26
34
|
end
|
27
35
|
|
28
|
-
attr_accessor :
|
36
|
+
attr_accessor :engine, :headless, :response
|
29
37
|
|
30
|
-
def initialize(
|
31
|
-
@
|
38
|
+
def initialize(**config)
|
39
|
+
@start_url = config.fetch(:start_url, nil)
|
40
|
+
@engine = config.fetch(:engine, :net_http)
|
41
|
+
@headless = config.fetch(:headless, true)
|
32
42
|
|
33
|
-
update_response(@
|
43
|
+
update_response(@start_url)
|
44
|
+
browser_quit_wrapper { parse }
|
34
45
|
end
|
35
46
|
|
36
47
|
def browser
|
37
|
-
@browser ||= Makuri::Browser.new
|
48
|
+
@browser ||= Makuri::Browser.new(engine: engine, headless: headless)
|
49
|
+
end
|
50
|
+
|
51
|
+
def browser_quit_wrapper
|
52
|
+
yield
|
53
|
+
browser.quit
|
38
54
|
end
|
39
55
|
|
40
56
|
def parse
|
@@ -55,18 +71,22 @@ module Makuri
|
|
55
71
|
end
|
56
72
|
|
57
73
|
def absolute_url(relative_url)
|
58
|
-
Addressable::URI.join(
|
74
|
+
Addressable::URI.join(base_url, relative_url).to_s
|
59
75
|
end
|
60
76
|
|
61
77
|
private
|
62
78
|
|
79
|
+
def base_url
|
80
|
+
@start_url || browser.url.to_s
|
81
|
+
end
|
82
|
+
|
63
83
|
def valid_url?(url)
|
64
84
|
defined?(url) && !url.to_s.empty?
|
65
85
|
end
|
66
86
|
|
67
87
|
def update_response(url)
|
68
|
-
|
69
|
-
@response = Nokogiri::HTML(
|
88
|
+
res = browser.request(absolute_url(url)).html
|
89
|
+
@response = Nokogiri::HTML(res)
|
70
90
|
end
|
71
91
|
end
|
72
92
|
end
|
data/lib/makuri/version.rb
CHANGED
data/lib/makuri.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: makuri
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Lal Saud
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2024-06-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: addressable
|
@@ -16,84 +16,70 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '2.
|
19
|
+
version: '2.8'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '2.
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: capybara
|
29
|
-
requirement: !ruby/object:Gem::Requirement
|
30
|
-
requirements:
|
31
|
-
- - "~>"
|
32
|
-
- !ruby/object:Gem::Version
|
33
|
-
version: '3.34'
|
34
|
-
type: :runtime
|
35
|
-
prerelease: false
|
36
|
-
version_requirements: !ruby/object:Gem::Requirement
|
37
|
-
requirements:
|
38
|
-
- - "~>"
|
39
|
-
- !ruby/object:Gem::Version
|
40
|
-
version: '3.34'
|
26
|
+
version: '2.8'
|
41
27
|
- !ruby/object:Gem::Dependency
|
42
28
|
name: nokogiri
|
43
29
|
requirement: !ruby/object:Gem::Requirement
|
44
30
|
requirements:
|
45
31
|
- - "~>"
|
46
32
|
- !ruby/object:Gem::Version
|
47
|
-
version: 1.
|
33
|
+
version: 1.15.5
|
48
34
|
type: :runtime
|
49
35
|
prerelease: false
|
50
36
|
version_requirements: !ruby/object:Gem::Requirement
|
51
37
|
requirements:
|
52
38
|
- - "~>"
|
53
39
|
- !ruby/object:Gem::Version
|
54
|
-
version: 1.
|
40
|
+
version: 1.15.5
|
55
41
|
- !ruby/object:Gem::Dependency
|
56
|
-
name:
|
42
|
+
name: ferrum
|
57
43
|
requirement: !ruby/object:Gem::Requirement
|
58
44
|
requirements:
|
59
45
|
- - "~>"
|
60
46
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
47
|
+
version: '0.15'
|
62
48
|
type: :runtime
|
63
49
|
prerelease: false
|
64
50
|
version_requirements: !ruby/object:Gem::Requirement
|
65
51
|
requirements:
|
66
52
|
- - "~>"
|
67
53
|
- !ruby/object:Gem::Version
|
68
|
-
version: '
|
54
|
+
version: '0.15'
|
69
55
|
- !ruby/object:Gem::Dependency
|
70
56
|
name: bundler
|
71
57
|
requirement: !ruby/object:Gem::Requirement
|
72
58
|
requirements:
|
73
59
|
- - "~>"
|
74
60
|
- !ruby/object:Gem::Version
|
75
|
-
version:
|
61
|
+
version: 2.5.0
|
76
62
|
type: :development
|
77
63
|
prerelease: false
|
78
64
|
version_requirements: !ruby/object:Gem::Requirement
|
79
65
|
requirements:
|
80
66
|
- - "~>"
|
81
67
|
- !ruby/object:Gem::Version
|
82
|
-
version:
|
68
|
+
version: 2.5.0
|
83
69
|
- !ruby/object:Gem::Dependency
|
84
70
|
name: webmock
|
85
71
|
requirement: !ruby/object:Gem::Requirement
|
86
72
|
requirements:
|
87
73
|
- - "~>"
|
88
74
|
- !ruby/object:Gem::Version
|
89
|
-
version: '3.
|
75
|
+
version: '3.20'
|
90
76
|
type: :development
|
91
77
|
prerelease: false
|
92
78
|
version_requirements: !ruby/object:Gem::Requirement
|
93
79
|
requirements:
|
94
80
|
- - "~>"
|
95
81
|
- !ruby/object:Gem::Version
|
96
|
-
version: '3.
|
82
|
+
version: '3.20'
|
97
83
|
description:
|
98
84
|
email: lalusaud@gmail.com
|
99
85
|
executables: []
|
@@ -106,7 +92,7 @@ files:
|
|
106
92
|
- lib/makuri.rb
|
107
93
|
- lib/makuri/browser.rb
|
108
94
|
- lib/makuri/browser_builder/base.rb
|
109
|
-
- lib/makuri/browser_builder/
|
95
|
+
- lib/makuri/browser_builder/ferrum.rb
|
110
96
|
- lib/makuri/browser_builder/net_http.rb
|
111
97
|
- lib/makuri/spider.rb
|
112
98
|
- lib/makuri/version.rb
|
@@ -122,14 +108,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
122
108
|
requirements:
|
123
109
|
- - ">="
|
124
110
|
- !ruby/object:Gem::Version
|
125
|
-
version: '2.
|
111
|
+
version: '2.7'
|
126
112
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
127
113
|
requirements:
|
128
114
|
- - ">="
|
129
115
|
- !ruby/object:Gem::Version
|
130
116
|
version: '0'
|
131
117
|
requirements: []
|
132
|
-
rubygems_version: 3.
|
118
|
+
rubygems_version: 3.5.11
|
133
119
|
signing_key:
|
134
120
|
specification_version: 4
|
135
121
|
summary: Web-crawling framework for Ruby
|
@@ -1,34 +0,0 @@
|
|
1
|
-
require 'capybara'
|
2
|
-
require 'selenium-webdriver'
|
3
|
-
|
4
|
-
module Makuri::BrowserBuilder
|
5
|
-
class Chrome < Base
|
6
|
-
def initialize(options = {})
|
7
|
-
super
|
8
|
-
@headless = options.fetch(:headless, true)
|
9
|
-
end
|
10
|
-
|
11
|
-
def build
|
12
|
-
Capybara.register_driver :selenium_chrome do |app|
|
13
|
-
Capybara::Selenium::Driver.new app, browser: :chrome, options: browser_options
|
14
|
-
end
|
15
|
-
Capybara.threadsafe = true
|
16
|
-
Capybara::Session.new :selenium_chrome
|
17
|
-
end
|
18
|
-
|
19
|
-
private
|
20
|
-
|
21
|
-
def browser_options
|
22
|
-
args = %w[
|
23
|
-
--disable-gpu
|
24
|
-
--no-sandbox
|
25
|
-
--disable-translate
|
26
|
-
--blink-settings=imagesEnabled=false
|
27
|
-
--ignore-certificate-errors
|
28
|
-
]
|
29
|
-
args << '--headless' if @headless
|
30
|
-
args << "--user-agent=#{@user_agent}"
|
31
|
-
Selenium::WebDriver::Chrome::Options.new(args: args)
|
32
|
-
end
|
33
|
-
end
|
34
|
-
end
|