Class: DaimonSkycrawlers::Filter::UpdateChecker

Inherits:
Base
  • Object
show all
Defined in:
lib/daimon_skycrawlers/filter/update_checker.rb

Overview

This filter provides update checker for given URL.

Skip processing URLs that is latest (not updated since previous access).

Instance Method Summary collapse

Methods inherited from Base

#storage

Methods included from LoggerMixin

included

Constructor Details

#initialize(storage: nil, base_url: nil) ⇒ UpdateChecker

Returns a new instance of UpdateChecker.



13
14
15
16
17
 
# File 'lib/daimon_skycrawlers/filter/update_checker.rb', line 13

def initialize(storage: nil, base_url: nil)
  super(storage: storage)
  @base_url = nil
  @base_url = URI(base_url) if base_url
end

Instance Method Details

#call(message, connection: nil) ⇒ true|false Also known as: updated?

Return true when need update, otherwise return false

Parameters:

  • message (Hash)
  • connection (Faraday) (defaults to: nil)

Returns:

  • (true|false) —

    Return true when need update, otherwise return false



24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
 
# File 'lib/daimon_skycrawlers/filter/update_checker.rb', line 24

def call(message, connection: nil)
  url = normalize_url(message[:url])
  page = storage.find(url)
  return true unless page
  if connection
    response = connection.head(url)
  else
    response = Faraday.head(url)
  end
  headers = response.headers
  case
  when headers.key?("etag") && page.etag
    headers["etag"] != page.etag
  when headers.key?("last-modified") && page.last_modified_at
    if headers["last-modified"] < page.last_modified_at
      log.warn("#{url} returns old contents. #{headers["last-modified"]} < #{page.last_modified_at}")
    end
    headers["last-modified"] > page.last_modified_at
  else
    true
  end
end