Class: Cyberweb::ScrapeThisUrl

Inherits:
Kimurai::Base
  • Object
show all
Defined in:
lib/cyberweb/web_scraper/scrape_this_url.rb

Overview

Cyberweb::ScrapeThisUrl

Constant Summary collapse

BASE_URL =
#

BASE_URL

#
'https://www.ncbi.nlm.nih.gov/protein/NP_417539.1?report=fasta'

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(optional_arguments = ARGV) ⇒ ScrapeThisUrl

#

initialize

#


81
82
83
84
85
86
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 81

def initialize(
    optional_arguments = ARGV
  )
  super()
  reset
end

Class Method Details

.add_this_url(i) ⇒ Object

#

Cyberweb::ScrapeThisUrl.add_this_url

#


72
73
74
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 72

def self.add_this_url(i)
  @start_urls = [i]
end

.into?Boolean

#

Cyberweb::ScrapeThisUrl.into?

#

Returns:

  • (Boolean)


47
48
49
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 47

def self.into?
  @into
end

.set_start_urls(i = ARGV) ⇒ Object

#

Cyberweb::ScrapeThisUrl.set_start_urls

#


64
65
66
67
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 64

def self.set_start_urls(i = ARGV)
  i = [i].flatten.compact
  @start_urls = i
end

.set_store_into(i) ⇒ Object

#

Cyberweb::ScrapeThisUrl.set_store_into

#


40
41
42
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 40

def self.set_store_into(i)
  @into = i
end

Instance Method Details

#e(i = '') ⇒ Object

#

e

#


135
136
137
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 135

def e(i = '')
  puts i
end

#opnnObject

#

opnn

#


145
146
147
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 145

def opnn
  Opn.opn(NAMESPACE)
end

#parse(response, url:, data: {}) ⇒ Object

#

parse

The variable url will point to the remote URL.

#


108
109
110
111
112
113
114
115
116
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 108

def parse(
    response,
    url: ,
    data: {}
  )
  @remote_url = url
  @result = response
  store_result_into_a_webpage
end

#remote_url?Boolean

#

remote_url?

#

Returns:

  • (Boolean)


152
153
154
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 152

def remote_url?
  ::Cyberweb::ScrapeThisUrl.into?
end

#resetObject

#

reset

#


91
92
93
94
95
96
97
98
99
100
101
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 91

def reset
  infer_the_namespace
  # ======================================================================= #
  # === @result
  # ======================================================================= #
  @result     = nil # Will be set when it is running.
  # ======================================================================= #
  # === @remote_url
  # ======================================================================= #
  @remote_url = nil
end

#result?Boolean

#

result?

#

Returns:

  • (Boolean)


121
122
123
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 121

def result?
  @result
end

#show_resultObject

#

show_result

#


128
129
130
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 128

def show_result
  e @result
end

#store_result_into_a_webpage(into = ScrapeThisUrl.into?) ⇒ Object

#

store_result_into_a_webpage

This method can be used to store the result into a .html file. The only argument that should be supplied is the location to that .html file, which can be given through the variable ‘into`.

The dataset has already been stored in the variable @result.

#


165
166
167
168
169
170
171
# File 'lib/cyberweb/web_scraper/scrape_this_url.rb', line 165

def store_result_into_a_webpage(
    into = ScrapeThisUrl.into?
  )
  what = @result
  opnn; e 'Now storing the resulting dataset into the local file `'+into+'`.'
  ::Cyberweb.write_what_into(what, into)
end