Class: WebhookProcessors::OxylabsProcessor

Inherits:
Object
  • Object
show all
Defined in:
app/services/webhook_processors/oxylabs_processor.rb

Overview

Processor for Oxylabs webhook callbacks
Handles price check results from Oxylabs Web Scraper API

Examples:

WebhookProcessors::OxylabsProcessor.call(webhook_log)

See Also:

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(webhook_log) ⇒ OxylabsProcessor

Returns a new instance of OxylabsProcessor.



17
18
19
20
 
# File 'app/services/webhook_processors/oxylabs_processor.rb', line 17

def initialize(webhook_log)
  @webhook_log = webhook_log
  @data = webhook_log.data
end

Class Method Details

.call(webhook_log) ⇒ Object 



13
14
15
 
# File 'app/services/webhook_processors/oxylabs_processor.rb', line 13

def self.call(webhook_log)
  new(webhook_log).call
end

Instance Method Details

#call ⇒ Object 



22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
 
# File 'app/services/webhook_processors/oxylabs_processor.rb', line 22

def call
  job_id = @data['id']
  status = @data['status']
  catalog_item_id = @webhook_log.resource_id
  url_used = @data['url']

  Rails.logger.info "[OxylabsProcessor] Processing job #{job_id} for CatalogItem #{catalog_item_id}"

  # Find catalog item first - needed for creating probe records
  catalog_item = CatalogItem.find_by(id: catalog_item_id)

  unless catalog_item
    Rails.logger.warn "[OxylabsProcessor] CatalogItem #{catalog_item_id} not found"
    return { status: 'error', reason: 'CatalogItem not found' }
  end

  # Handle non-done statuses by creating a failed probe record
  unless status == 'done'
    Rails.logger.warn "[OxylabsProcessor] Job #{job_id} not done (status: #{status})"

    # Create a probe record documenting the failed attempt
    probe = CatalogItemRetailerProbe.create!(
      catalog_item_id: catalog_item_id,
      status: 'failed',
      url: url_used,
      error_message: "Oxylabs job #{status}: #{extract_error_reason}",
      page_accessible: false,
      geo_location: @data['geo_location']
    )

    return {
      status: 'failed',
      reason: "Job status is #{status}, not done",
      probe_id: probe.id,
      oxylabs_status: status,
      url_used: url_used,
      catalog_item_id: catalog_item_id,
      catalog_item_sku: catalog_item.sku
    }
  end

  # Fetch results from Oxylabs API using job_id
  api = Retailer::OxylabsApi.new
  api_result = api.job_results(job_id)

  unless api_result.success?
    Rails.logger.error "[OxylabsProcessor] Failed to fetch results for job #{job_id}: #{api_result.error}"

    # Create probe record for API fetch failure
    probe = create_failed_probe(catalog_item_id, url_used, "API fetch failed: #{api_result.error}")

    return {
      status: 'api_error',
      job_id: job_id,
      probe_id: probe.id,
      error: api_result.error,
      url_used: url_used,
      catalog_item_id: catalog_item_id,
      catalog_item_sku: catalog_item.sku
    }
  end

  results = api_result.data
  if results.blank?
    Rails.logger.warn "[OxylabsProcessor] Job #{job_id} returned empty results"

    # Create probe record for empty results
    probe = create_failed_probe(catalog_item_id, url_used, 'Oxylabs returned empty results')

    return {
      status: 'empty_results',
      job_id: job_id,
      probe_id: probe.id,
      url_used: url_used,
      catalog_item_id: catalog_item_id,
      catalog_item_sku: catalog_item.sku
    }
  end

  # Delegate to the existing processor for extraction
  processor = Retailer::WebhookResultProcessor.new
  result = processor.process(@data.merge('_catalog_item_id' => catalog_item_id))

  Rails.logger.info "[OxylabsProcessor] Completed processing job #{job_id}"

  # Capture content size from API response for troubleshooting
  api_content_size = results.first&.dig('content').to_s.size

  # Return detailed result hash for WebhookLog#response_data
  if result.is_a?(CatalogItemRetailerProbe)
    {
      status: result.status,
      probe_id: result.id,
      price: result.price&.to_f,
      currency: result.currency,
      page_accessible: result.page_accessible,
      product_available: result.product_available,
      url: result.url&.truncate(200),
      error_message: result.error_message,
      content_size_bytes: result.content_size_bytes || api_content_size,
      response_time_ms: result.response_time_ms,
      catalog_item_id: catalog_item_id,
      catalog_item_sku: catalog_item.sku
    }.compact
  else
    {
      status: 'processing_failed',
      job_id: job_id,
      content_size_bytes: api_content_size,
      catalog_item_id: catalog_item_id,
      catalog_item_sku: catalog_item.sku
    }
  end
end