Class: LigaMagicScraper::GlobalScraper

Inherits:
BaseScraper show all
Defined in:
lib/ligamagic_scraper/scrapers/global_scraper.rb

Constant Summary collapse

BASE_URL =
'https://www.ligamagic.com.br/?view=cards%2Fsearch&tipo=1'
MAX_CLICKS =
50

Instance Attribute Summary collapse

Attributes inherited from BaseScraper

#alert_system, #browser_mode

Attributes included from Loggable

#logs

Instance Method Summary collapse

Methods inherited from BaseScraper

#close_browser, #configure_browser, #find_previous_scrape, #generate_slug, #parse_price, #save_to_json

Methods included from Loggable

#clear_logs, #formatted_logs, #initialize_logs, #log, #log_debug, #log_error, #log_info, #log_warning

Constructor Details

#initialize(search_term:, browser_mode: 'headed', alert_config: nil) ⇒ GlobalScraper

Returns a new instance of GlobalScraper.



13
14
15
16
17
18
19
20
21
22
# File 'lib/ligamagic_scraper/scrapers/global_scraper.rb', line 13

def initialize(search_term:, browser_mode: 'headed', alert_config: nil)
  @search_term = search_term
  @product_html_snapshots = []
  @timings = {}
  super(browser_mode:, alert_config:)
  
  log_info("🚀 Starting Liga Magic global search scraper...")
  log_info("🔍 Search term: #{search_term}")
  log_info("🖥️  Browser mode: #{browser_mode}")
end

Instance Attribute Details

#search_termObject (readonly)

Returns the value of attribute search_term.



11
12
13
# File 'lib/ligamagic_scraper/scrapers/global_scraper.rb', line 11

def search_term
  @search_term
end

Instance Method Details

#build_json_data(products) ⇒ Object



94
95
96
97
98
99
100
101
102
# File 'lib/ligamagic_scraper/scrapers/global_scraper.rb', line 94

def build_json_data(products)
  {
    search_term:,
    search_type: 'global',
    scraped_at: Time.now.iso8601,
    total_products: products.count,
    products:
  }
end

#generate_filenameObject



88
89
90
91
92
# File 'lib/ligamagic_scraper/scrapers/global_scraper.rb', line 88

def generate_filename
  datetime_str = Time.now.strftime('%Y%m%d_%H%M%S')
  slug = search_term.downcase.gsub(/[^a-z0-9]+/, '_').gsub(/^_|_$/, '')
  "scrapped/global/#{datetime_str}__#{slug}.json"
end

#scrapeObject



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
# File 'lib/ligamagic_scraper/scrapers/global_scraper.rb', line 28

def scrape
  start_time = Time.now
  
  visit url
  log_info("📄 Loaded initial page")
  
  # Phase 1: Load all pages (browser open, no capturing)
  load_time = Benchmark.measure do
    load_all_products
  end
  @timings[:loading] = load_time.real
  log_info("⏱️  Phase 1 (Loading): #{format('%.2f', load_time.real)}s")
  
  # Phase 2: Capture all products at once (browser still open)
  capture_time = Benchmark.measure do
    capture_all_products
  end
  @timings[:capture] = capture_time.real
  log_info("⏱️  Phase 2 (Capture): #{format('%.2f', capture_time.real)}s")
  
  # Close browser ASAP
  close_time = Benchmark.measure do
    close_browser
  end
  @timings[:browser_close] = close_time.real
  log_info("✅ Browser closed in #{format('%.2f', close_time.real)}s")
  
  # Phase 3: Extract products from memory (browser closed)
  log_info("🔍 Extracting products from memory...")
  products = nil
  extraction_time = Benchmark.measure do
    products = extract_products
  end
  @timings[:extraction] = extraction_time.real
  log_info("⏱️  Phase 3 (Extraction): #{format('%.2f', extraction_time.real)}s")
  
  total_time = Time.now - start_time
  @timings[:total] = total_time
  
  log_info("=" * 60)
  log_info("📊 PERFORMANCE SUMMARY")
  log_info("=" * 60)
  log_info("⏱️  Loading (browser open):           #{format('%.2f', @timings[:loading])}s")
  log_info("⏱️  Capture (browser open):           #{format('%.2f', @timings[:capture])}s")
  log_info("⏱️  Browser Close:                    #{format('%.2f', @timings[:browser_close])}s")
  log_info("⏱️  Extraction (browser closed):      #{format('%.2f', @timings[:extraction])}s")
  log_info("⏱️  Total Time:                       #{format('%.2f', @timings[:total])}s")
  log_info("📦 Products captured:                 #{@product_html_snapshots.count}")
  log_info("✅ Valid products extracted:          #{products.count}")
  log_info("=" * 60)
  
  products
rescue => e
  log_error("❌ Error during scraping: #{e.message}")
  log_debug(e.backtrace.first(5).join("\n"))
  []
ensure
  close_browser if @driver
end

#urlObject



24
25
26
# File 'lib/ligamagic_scraper/scrapers/global_scraper.rb', line 24

def url
  "#{BASE_URL}&card=#{CGI.escape(search_term)}"
end