web_scraping_helper 0.5.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/Gemfile +4 -0
- data/Guardfile +6 -0
- data/README.md +36 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/web_scraping_helper/version.rb +3 -0
- data/lib/web_scraping_helper.rb +146 -0
- data/web_scraping_helper.gemspec +39 -0
- metadata +179 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 02ab48dc934b462c435c3cc75f1223f10624ce22
|
4
|
+
data.tar.gz: 1a1e020edcecc0ba2af3e2b2a67a7c0cd224e4a1
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: bb4312d25cddd201cfec98a8d24972d8ea96395d99451d0ca28224db0aee1b2be888fb269f7b3bc5dc014fdfbd005de25f19d1fe4d95b8340a73751ddb33f845
|
7
|
+
data.tar.gz: b8895c65fe159fc1c8e0f152807f292e9eaabb53e945c479f5cb74b294ff0d2ac859982f2b0f959900e2f435864916ddb356ecfb7870c0ceee0988684f6e6779
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Guardfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,36 @@
|
|
1
|
+
# WebScrapingHelper
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/web_scraping_helper`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'web_scraping_helper'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install web_scraping_helper
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
30
|
+
|
31
|
+
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).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/web_scraping_helper.
|
36
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "web_scraping_helper"
|
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
|
data/bin/setup
ADDED
@@ -0,0 +1,146 @@
|
|
1
|
+
#-*- encoding: utf-8 -*-
|
2
|
+
require "web_scraping_helper/version"
|
3
|
+
require 'rest-client'
|
4
|
+
require 'fileutils'
|
5
|
+
|
6
|
+
class WebScrapingHelper
|
7
|
+
DEFAULT_USER_AGENT = 'Mozilla/5.0'
|
8
|
+
DEFAULT_WAIT_TIME = 1
|
9
|
+
DEFAULT_ENCODING = Encoding::UTF_8
|
10
|
+
|
11
|
+
def self.reset!
|
12
|
+
@@global_cache_dir = nil
|
13
|
+
@@blocks = []
|
14
|
+
end
|
15
|
+
reset!
|
16
|
+
|
17
|
+
def self.cache_dir
|
18
|
+
@@global_cache_dir
|
19
|
+
end
|
20
|
+
|
21
|
+
def self.cache_dir=(v)
|
22
|
+
@@global_cache_dir = v
|
23
|
+
end
|
24
|
+
|
25
|
+
def self.before(&block)
|
26
|
+
@@blocks << {timing: :before, proc: block}
|
27
|
+
end
|
28
|
+
|
29
|
+
def self.after(&block)
|
30
|
+
@@blocks << {timing: :after, proc: block}
|
31
|
+
end
|
32
|
+
|
33
|
+
def initialize(cookie_filename = nil)
|
34
|
+
@jar = HTTP::CookieJar.new
|
35
|
+
if cookie_filename
|
36
|
+
@jar.load(cookie_filename) if File.exist?(cookie_filename)
|
37
|
+
@cookie_filename = cookie_filename
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
attr_accessor :user_agent, :wait_time, :encoding
|
42
|
+
attr_accessor :cache_dir
|
43
|
+
|
44
|
+
def post(url, opts = {})
|
45
|
+
request_http(:post, url, opts)
|
46
|
+
end
|
47
|
+
alias post_http post # support old method
|
48
|
+
|
49
|
+
def get(url, opts = {})
|
50
|
+
request_http(:get, url, opts)
|
51
|
+
end
|
52
|
+
alias get_http get # support old method
|
53
|
+
|
54
|
+
def exist_cookie?(url)
|
55
|
+
cookie = HTTP::Cookie.cookie_value(@jar.cookies(url))
|
56
|
+
not cookie.empty?
|
57
|
+
end
|
58
|
+
|
59
|
+
private
|
60
|
+
|
61
|
+
def request_http(request_method, url, opts)
|
62
|
+
@@blocks
|
63
|
+
.select{|block| block[:timing] == :before}
|
64
|
+
.each{|block| block[:proc].call(url) }
|
65
|
+
|
66
|
+
if request_method == :get && (res = find_cache(url))
|
67
|
+
return res
|
68
|
+
end
|
69
|
+
wait
|
70
|
+
|
71
|
+
headers = {}
|
72
|
+
opts.each{|k, v| headers[k.downcase] = v if String === k}
|
73
|
+
unless headers.key?("user-agent")
|
74
|
+
headers["user-agent"] = @user_agent || DEFAULT_USER_AGENT
|
75
|
+
end
|
76
|
+
unless headers.key?("cookie")
|
77
|
+
cookie = HTTP::Cookie.cookie_value(@jar.cookies(url))
|
78
|
+
headers["cookie"] = cookie unless cookie.empty?
|
79
|
+
end
|
80
|
+
|
81
|
+
params = {
|
82
|
+
method: request_method,
|
83
|
+
url: url,
|
84
|
+
headers: headers
|
85
|
+
}
|
86
|
+
params[:payload] = opts[:body] if opts[:body]
|
87
|
+
res = RestClient::Request.execute(params)
|
88
|
+
|
89
|
+
encoding = opts[:encoding] || get_encoding(res)
|
90
|
+
if encoding
|
91
|
+
res.force_encoding(encoding)
|
92
|
+
res.encode!(@encoding || DEFAULT_ENCODING)
|
93
|
+
end
|
94
|
+
|
95
|
+
cookies = res.headers[:set_cookie]
|
96
|
+
if cookies
|
97
|
+
cookies.each{|cookie| @jar.parse(cookie, url)}
|
98
|
+
@jar.save(@cookie_filename) if @cookie_filename
|
99
|
+
end
|
100
|
+
|
101
|
+
set_wait_base_time
|
102
|
+
save_cache(url, res)
|
103
|
+
|
104
|
+
@@blocks
|
105
|
+
.select{|block| block[:timing] == :after}
|
106
|
+
.each{|block| block[:proc].call(url, res) }
|
107
|
+
|
108
|
+
res
|
109
|
+
end
|
110
|
+
|
111
|
+
def get_encoding(res)
|
112
|
+
content_type = res.headers[:content_type]
|
113
|
+
return content_type[/;\s*charset=([^;]+)/, 1] if content_type
|
114
|
+
end
|
115
|
+
|
116
|
+
def find_cache(url)
|
117
|
+
cache_file = url_to_cache_path(url)
|
118
|
+
return nil if cache_file.nil? or not File.exist?(cache_file)
|
119
|
+
File.open(cache_file, "r:utf-8"){|f| f.read}
|
120
|
+
end
|
121
|
+
|
122
|
+
def save_cache(url, html)
|
123
|
+
cache_file = url_to_cache_path(url)
|
124
|
+
return if cache_file.nil?
|
125
|
+
FileUtils.mkdir_p(File.dirname(cache_file))
|
126
|
+
File.open(cache_file, "w+:utf-8"){|f| f.print html}
|
127
|
+
end
|
128
|
+
|
129
|
+
def url_to_cache_path(url)
|
130
|
+
cache_dir = @cache_dir || @@global_cache_dir
|
131
|
+
return unless cache_dir
|
132
|
+
File.expand_path(url.gsub(%r{[\\/:\?"<>\|]}, "_"), cache_dir)
|
133
|
+
end
|
134
|
+
|
135
|
+
def wait
|
136
|
+
if not @prev_time.nil?
|
137
|
+
wait_time = @wait_time || DEFAULT_WAIT_TIME
|
138
|
+
wait_time -= (Time.now - @prev_time)
|
139
|
+
sleep wait_time if wait_time > 0
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|
143
|
+
def set_wait_base_time
|
144
|
+
@prev_time = Time.now
|
145
|
+
end
|
146
|
+
end
|
@@ -0,0 +1,39 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'web_scraping_helper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "web_scraping_helper"
|
8
|
+
spec.version = WebScrapingHelper::VERSION
|
9
|
+
spec.authors = ["momo-lab"]
|
10
|
+
spec.email = ["momotaro.n@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = "WebScrapingHelper"
|
13
|
+
spec.description = "WebScrapingHelper"
|
14
|
+
spec.homepage = "https://github.com/momo-lab/web_scraping_helper"
|
15
|
+
|
16
|
+
# # Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
|
17
|
+
# # delete this section to allow pushing this gem to any host.
|
18
|
+
# if spec.respond_to?(:metadata)
|
19
|
+
# spec.metadata['allowed_push_host'] = "TODO: Set to 'http://mygemserver.com'"
|
20
|
+
# else
|
21
|
+
# raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
|
22
|
+
# end
|
23
|
+
|
24
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
25
|
+
spec.bindir = "exe"
|
26
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
27
|
+
spec.require_paths = ["lib"]
|
28
|
+
|
29
|
+
spec.add_dependency "rest-client"
|
30
|
+
|
31
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
32
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
33
|
+
spec.add_development_dependency "minitest", "~> 5.0"
|
34
|
+
spec.add_development_dependency "minitest-reporters"
|
35
|
+
spec.add_development_dependency "minitest-power_assert"
|
36
|
+
spec.add_development_dependency "webmock", "~> 2.0"
|
37
|
+
spec.add_development_dependency "guard"
|
38
|
+
spec.add_development_dependency "guard-minitest"
|
39
|
+
end
|
metadata
ADDED
@@ -0,0 +1,179 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: web_scraping_helper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.5.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- momo-lab
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-06-05 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rest-client
|
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: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.11'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.11'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: minitest
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '5.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '5.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: minitest-reporters
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: minitest-power_assert
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: webmock
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '2.0'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '2.0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: guard
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - ">="
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - ">="
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: guard-minitest
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
139
|
+
description: WebScrapingHelper
|
140
|
+
email:
|
141
|
+
- momotaro.n@gmail.com
|
142
|
+
executables: []
|
143
|
+
extensions: []
|
144
|
+
extra_rdoc_files: []
|
145
|
+
files:
|
146
|
+
- ".gitignore"
|
147
|
+
- Gemfile
|
148
|
+
- Guardfile
|
149
|
+
- README.md
|
150
|
+
- Rakefile
|
151
|
+
- bin/console
|
152
|
+
- bin/setup
|
153
|
+
- lib/web_scraping_helper.rb
|
154
|
+
- lib/web_scraping_helper/version.rb
|
155
|
+
- web_scraping_helper.gemspec
|
156
|
+
homepage: https://github.com/momo-lab/web_scraping_helper
|
157
|
+
licenses: []
|
158
|
+
metadata: {}
|
159
|
+
post_install_message:
|
160
|
+
rdoc_options: []
|
161
|
+
require_paths:
|
162
|
+
- lib
|
163
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
164
|
+
requirements:
|
165
|
+
- - ">="
|
166
|
+
- !ruby/object:Gem::Version
|
167
|
+
version: '0'
|
168
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
169
|
+
requirements:
|
170
|
+
- - ">="
|
171
|
+
- !ruby/object:Gem::Version
|
172
|
+
version: '0'
|
173
|
+
requirements: []
|
174
|
+
rubyforge_project:
|
175
|
+
rubygems_version: 2.5.1
|
176
|
+
signing_key:
|
177
|
+
specification_version: 4
|
178
|
+
summary: WebScrapingHelper
|
179
|
+
test_files: []
|