Module: Instaview

Defined in:
lib/instaview.rb,
lib/instaview/version.rb

Defined Under Namespace

Classes: Error

Constant Summary collapse

VERSION = 
"0.2.0"

Class Method Summary collapse

Class Method Details

.cache_dir ⇒ Object

— Cache helpers —



110
111
112
 
# File 'lib/instaview.rb', line 110

def self.cache_dir
  ENV['INSTAVIEW_CACHE_DIR'] || File.join(Dir.home, ".cache", "instaview")
end

.cache_file_for(username) ⇒ Object 



122
123
124
125
 
# File 'lib/instaview.rb', line 122

def self.cache_file_for(username)
  sanitized = username.to_s.gsub(/[^a-zA-Z0-9_\-.]/, '_')
  File.join(cache_dir, "#{sanitized}.json")
end

.fetch_data_async(username, method: :selenium) ⇒ Object

Raises:

  • (ArgumentError) 


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
 
# File 'lib/instaview.rb', line 41

def self.fetch_data_async(username, method: :selenium)
  raise ArgumentError, "username is required" if username.nil? || username.to_s.strip.empty?

  Thread.new do
    result = case method
             when :selenium
               scrape_instagram_stories(username)
             when :simple_http
               scrape_with_simple_http(username)
             else
               scrape_instagram_stories(username)
             end

    # Persist to cache on success
    if data_found?(result)
      begin
        write_to_cache(username, result)
      rescue StandardError
        # Ignore cache write failures to avoid affecting callers
      end
    end

    result
  end
end

.get_from_cache_or_async(username, max_age_hours: 12, method: :selenium) ⇒ Object 



77
78
79
80
81
82
83
84
 
# File 'lib/instaview.rb', line 77

def self.get_from_cache_or_async(username, max_age_hours: 12, method: :selenium)
  max_age_seconds = (max_age_hours.to_i * 3600)
  cached = read_from_cache(username, max_age_seconds: max_age_seconds)
  return cached if cached

  t = fetch_data_async(username, method: method)
  t.value # join and return result
end

.getData(username = nil) ⇒ Object

Raises:

  • (ArgumentError) 


25
26
27
28
29
 
# File 'lib/instaview.rb', line 25

def self.getData(username = nil)
  # Default data accessor: try cache first (12h TTL), otherwise fetch asynchronously and return result
  raise ArgumentError, "username is required" if username.nil? || username.to_s.strip.empty?
  get_from_cache_or_async(username, max_age_hours: 12)
end

.load_from_cache_only(username, max_age_hours: 12) ⇒ Object

Raises:

  • (ArgumentError) 


95
96
97
98
99
 
# File 'lib/instaview.rb', line 95

def self.load_from_cache_only(username, max_age_hours: 12)
  raise ArgumentError, "username is required" if username.nil? || username.to_s.strip.empty?
  max_age_seconds = (max_age_hours.to_i * 3600)
  read_from_cache(username, max_age_seconds: max_age_seconds)
end

.parseData ⇒ Object 



460
461
462
463
464
465
466
467
468
469
470
471
 
# File 'lib/instaview.rb', line 460

def self.parseData
  # Using a third-party web app, to get Instagram data.
  # Afterwards, we use Nokogiri to parse the HTML.
  require "nokogiri"
  require "open-uri"

  url = "https://www.instaview.me/"
  html = URI.open(url)
  doc = Nokogiri::HTML(html)

  doc.xpath("//profile-media-list__item").map(&:text)
end

.read_from_cache(username, max_age_seconds: 43_200) ⇒ Object 



136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
 
# File 'lib/instaview.rb', line 136

def self.read_from_cache(username, max_age_seconds: 43_200)
  path = cache_file_for(username)
  return nil unless File.exist?(path)

  age = Time.now - File.mtime(path)
  return nil if age > max_age_seconds

  content = File.read(path)
  data = JSON.parse(content, symbolize_names: true)
  return nil unless data_found?(data)
  # annotate so callers can tell it came from cache
  if data.is_a?(Hash)
    data[:cached] = true
  end
  data
rescue JSON::ParserError
  nil
end

.scrape_instagram_stories(username = nil) ⇒ Object 



201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
 
# File 'lib/instaview.rb', line 201

def self.scrape_instagram_stories(username = nil)
  target_username = username || ARGV[0] # pass username as argument

  driver = nil
  begin
    # Setup Selenium WebDriver with headless Chrome
    options = Selenium::WebDriver::Chrome::Options.new
    options.add_argument('--headless=new')
    options.add_argument('--no-sandbox')
    options.add_argument('--disable-dev-shm-usage')
    options.add_argument('--disable-gpu')
    options.add_argument('--disable-extensions')
    options.add_argument('--disable-background-timer-throttling')
    options.add_argument('--disable-backgrounding-occluded-windows')
    options.add_argument('--disable-renderer-backgrounding')
    options.add_argument('--window-size=1920,1080')
    options.add_argument('--remote-debugging-port=9222')
    options.add_argument('--user-data-dir=/tmp/chrome-user-data')

    # Try different Chrome/Chromium binaries
    chrome_paths = [
      "/snap/bin/chromium",
      "/usr/bin/chromium",
      "/usr/bin/chromium-browser",
      "/usr/bin/google-chrome"
    ]

    chrome_binary = chrome_paths.find { |path| File.exist?(path) }
    options.binary = chrome_binary if chrome_binary

    driver = Selenium::WebDriver.for :chrome, options: options

    # 1) Go to StoriesIG homepage
    driver.navigate.to "https://storiesig.info/"
    sleep 2

    # 2) Find the specific search input for StoriesIG
    wait = Selenium::WebDriver::Wait.new(timeout: 10)

    input_element = begin
      wait.until do
        element = driver.find_element(:css, 'input.search.search-form__input[placeholder*="username"]')
        element if element.displayed?
      end
    rescue Selenium::WebDriver::Error::TimeoutError
      raise Instaview::Error, "Search input not found with selector: input.search.search-form__input"
    end

    input_element.clear
    input_element.send_keys(target_username)

    # 3) Click the specific search button
    begin
      button_element = driver.find_element(:css, 'button.search-form__button')
      button_element.click
    rescue Selenium::WebDriver::Error::NoSuchElementError
      input_element.send_keys(:return)
    end

    # 4) Wait for results to load and check different possible outcomes
    sleep 3

    # Check for various possible page states
    page_state = "unknown"
    error_message = nil

    # Check if media items loaded
    media_items = driver.find_elements(:css, 'li.profile-media-list__item')
    if media_items.length > 0
      page_state = "media_found"
    else
      # Check for error messages or other states
      sleep 2  # Give it more time
      media_items = driver.find_elements(:css, 'li.profile-media-list__item')

      if media_items.length > 0
        page_state = "media_found_delayed"
      else
        # Look for common error indicators
        error_selectors = [
          '.error', '.alert', '.warning',
          '[class*="error"]', '[class*="not-found"]',
          'p:contains("not found")', 'div:contains("error")'
        ]

        error_found = false
        error_selectors.each do |selector|
          begin
            error_elements = driver.find_elements(:css, selector)
            if error_elements.any?
              error_message = error_elements.first.text
              error_found = true
              break
            end
          rescue StandardError
            # Continue checking other selectors
          end
        end

        page_state = error_found ? "error_found" : "no_media"
      end
    end

    # 5) Extract media content from the specific structure
    html = driver.page_source
    doc = Nokogiri::HTML(html)

    # Extract specific media items using the provided selector
    media_list_items = doc.css('li.profile-media-list__item')

    extracted_media = []
    media_list_items.each do |item|
      media_data = {}

      # Extract image source
      img_element = item.css('.media-content__image').first
      if img_element
        media_data[:image_url] = img_element['src']
        media_data[:alt_text] = img_element['alt']
      end

      # Extract caption
      caption_element = item.css('.media-content__caption').first
      media_data[:caption] = caption_element&.text&.strip

      # Extract download link
      download_element = item.css('a.button.button--filled.button__download').first
      media_data[:download_url] = download_element['href'] if download_element

      # Extract metadata
      like_element = item.css('.media-content__meta-like').first
      media_data[:likes] = like_element&.text&.strip

      time_element = item.css('.media-content__meta-time').first
      media_data[:time] = time_element&.text&.strip
      media_data[:time_title] = time_element['title'] if time_element

      extracted_media << media_data unless media_data.empty?
    end

    # Also extract any general images and links
    all_images = doc.css('img').map { |img| img['src'] }.compact.uniq.reject(&:empty?)
    all_links = doc.css('a').map { |link| link['href'] }.compact.uniq.reject(&:empty?)
    download_links = doc.css('a.button__download').map { |link| link['href'] }.compact.uniq

    result = {
      username: target_username,
      method: "selenium_storiesig",
      page_state: page_state,
      media_items_found: extracted_media.length,
      media_items: extracted_media,
      all_images: all_images.select { |img| img.start_with?('http') }.first(10), # Limit output
      download_links: download_links,
      error_message: error_message,
      success: extracted_media.length > 0,
      debug_info: {
        total_images: all_images.length,
        total_links: all_links.length,
      }
    }

    # Save screenshot for debugging if needed
    if ENV['INSTAVIEW_DEBUG']
      screenshot_path = "/tmp/instaview_debug_#{Time.now.to_i}.png"
      driver.save_screenshot(screenshot_path)
      result[:debug_info][:screenshot_path] = screenshot_path
    end

    result
  rescue Instaview::Error
    raise
  rescue => e
    raise Instaview::Error, "Selenium scraping failed: #{e.message}"
  ensure
    driver&.quit
  end
end

.scrape_with_simple_http(username = nil) ⇒ Object

Raises:

  • (ArgumentError) 


388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
 
# File 'lib/instaview.rb', line 388

def self.scrape_with_simple_http(username = nil)
  target_username = username
  raise ArgumentError, "Username is required for simple HTTP method" if target_username.nil? || target_username.empty?

  begin
    # Simple HTTP approach using curl
    curl_command = "curl -s -L -H 'User-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' 'https://storiesig.info/'"

    html_content = `#{curl_command}`

    unless $?.success? && !html_content.empty?
      raise Instaview::Error, "Curl command failed or returned empty content"
    end

    doc = Nokogiri::HTML(html_content)

    # Extract basic page information
    forms = doc.css('form')
    inputs = doc.css('input[type="text"], input[name*="user"]')

    # Look for any existing media or links
    images = doc.css('img').map { |img| img['src'] }.compact.select { |src| src.start_with?('http') }

    {
      username: target_username,
      method: "simple_http_curl",
      forms_found: forms.length,
      inputs_found: inputs.length,
      sample_images: images.first(3),
      message: "Simple HTTP method using curl - shows page structure. For full automation use selenium method."
    }
  rescue Instaview::Error
    raise
  rescue => e
    raise Instaview::Error, "HTTP scraping failed: #{e.message}"
  end
end

.test_connectivity ⇒ Object 



434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
 
# File 'lib/instaview.rb', line 434

def self.test_connectivity
  # Simple test method to verify the gem works
  {
    gem_name: "Instaview",
    version: Instaview::VERSION,
    methods_available: [
      "scrape_instagram_stories",
      "scrape_with_simple_http",
      "fetch_data_async",
      "get_from_cache_or_async",
      "load_from_cache_only",
      "getData",
      "test_connectivity"
    ],
    status: "OK"
  }
end

.write_to_cache(username, data) ⇒ Object 



164
165
166
167
168
 
# File 'lib/instaview.rb', line 164

def self.write_to_cache(username, data)
  FileUtils.mkdir_p(cache_dir)
  File.write(cache_file_for(username), JSON.pretty_generate(data))
  true
end