Class: XapiScraper::Articles

Inherits:
Object
  • Object
show all
Extended by:
T::Sig
Defined in:
lib/xapi_scraper/articles.rb

Instance Method Summary collapse

Constructor Details

#initialize(sdk_config) ⇒ Articles

Returns a new instance of Articles.



21
22
23
 
# File 'lib/xapi_scraper/articles.rb', line 21

def initialize(sdk_config)
  @sdk_configuration = sdk_config
end

Instance Method Details

#fetch(request:, retries: nil, timeout_ms: nil, http_headers: nil) ⇒ Object

Raises:

  • (StandardError) 


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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
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
 
# File 'lib/xapi_scraper/articles.rb', line 49

def fetch(request:, retries: nil, timeout_ms: nil, http_headers: nil)
  # fetch - Batch Fetch X Articles
  # Retrieves detailed article content for a specified list of X (Twitter) IDs. Use this endpoint to fetch full text, metadata, and media links for multiple posts in a single request. The maximum input quantity is limited by your plan's QPS. To pass larger input quantity limits, upgrade your plan to get higher QPS.
  url, params = @sdk_configuration.get_server_details
  base_url = Utils.template_url(url, params)
  url = "#{base_url}/x/article"
  headers = {}
  headers = T.cast(headers, T::Hash[String, String])
  req_content_type, data, form = Utils.serialize_request_body(request, false, false, :request, :json)
  headers["content-type"] = req_content_type
  raise StandardError, "request body is required" if data.nil? && form.nil?

  if form && !form.empty?
    body = Utils.encode_form(form)
  elsif Utils.match_content_type(req_content_type, "application/x-www-form-urlencoded")
    body = URI.encode_www_form(T.cast(data, T::Hash[Symbol, Object]))
  else
    body = data
  end

  headers["Accept"] = "application/json"
  headers["user-agent"] = @sdk_configuration.user_agent
  retries ||= @sdk_configuration.retry_config
  retries ||= Utils::RetryConfig.new(
    backoff: Utils::BackoffStrategy.new(
      exponent: 1.5,
      initial_interval: 500,
      max_elapsed_time: 3_600_000,
      max_interval: 60_000
    ),
    retry_connection_errors: true,
    strategy: "backoff"
  )
  retry_options = retries.to_faraday_retry_options(initial_time: Time.now)
  retry_options[:retry_statuses] = [408, 409, 429, 500, 501, 502, 503, 504, 505]

  security = @sdk_configuration.security_source&.call

  timeout = (timeout_ms.to_f / 1000) unless timeout_ms.nil?
  timeout ||= @sdk_configuration.timeout

  connection = @sdk_configuration.client.dup
  connection.use(Utils::RetryMiddleware, retry_options)

  hook_ctx = SDKHooks::HookContext.new(
    config: @sdk_configuration,
    base_url: base_url,
    oauth2_scopes: nil,
    operation_id: "articlesFetch",
    security_source: @sdk_configuration.security_source
  )

  error = T.let(nil, T.nilable(StandardError))
  http_response = T.let(nil, T.nilable(Faraday::Response))

  begin
    http_response = T.must(connection).post(url) do |req|
      req.body = body
      req.headers.merge!(headers)
      req.options.timeout = timeout unless timeout.nil?
      Utils.configure_request_security(req, security)
      http_headers&.each do |key, value|
        req.headers[key.to_s] = value
      end

      @sdk_configuration.hooks.before_request(
        hook_ctx: SDKHooks::BeforeRequestHookContext.new(
          hook_ctx: hook_ctx
        ),
        request: req
      )
    end

  rescue StandardError => e
    error = e
  ensure
    if http_response.nil? || Utils.error_status?(http_response.status)
      http_response = @sdk_configuration.hooks.after_error(
        error: error,
        hook_ctx: SDKHooks::AfterErrorHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
    else
      http_response = @sdk_configuration.hooks.after_success(
        hook_ctx: SDKHooks::AfterSuccessHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
    end

    if http_response.nil?
      raise error if !error.nil?
      raise "no response"
    end
  end

  content_type = http_response.headers.fetch("Content-Type", "application/octet-stream")
  if Utils.match_status_code(http_response.status, ["200"])
    if Utils.match_content_type(content_type, "application/json")
      http_response = @sdk_configuration.hooks.after_success(
        hook_ctx: SDKHooks::AfterSuccessHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
      response_data = http_response.env.response_body
      obj = Crystalline.unmarshal_json(JSON.parse(response_data), Models::Components::XArticleResponse)
      response = Models::Operations::ArticlesFetchResponse.new(
        status_code: http_response.status,
        content_type: content_type,
        raw_response: http_response,
        x_article_response: T.unsafe(obj)
      )

      return response
    else
      raise(
        ::XapiScraper::Models::Errors::APIError.new(
          status_code: http_response.status,
          body: http_response.env.response_body,
          raw_response: http_response
        ),
        "Unknown content type received"
      )
    end
  elsif Utils.match_status_code(http_response.status, ["422"])
    if Utils.match_content_type(content_type, "application/json")
      http_response = @sdk_configuration.hooks.after_success(
        hook_ctx: SDKHooks::AfterSuccessHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
      response_data = http_response.env.response_body
      obj = Crystalline.unmarshal_json(JSON.parse(response_data), Models::Errors::HTTPValidationError)
      obj.raw_response = http_response
      raise obj
    else
      raise(
        ::XapiScraper::Models::Errors::APIError.new(
          status_code: http_response.status,
          body: http_response.env.response_body,
          raw_response: http_response
        ),
        "Unknown content type received"
      )
    end
  elsif Utils.match_status_code(http_response.status, ["4XX"])
    raise(
      ::XapiScraper::Models::Errors::APIError.new(
        status_code: http_response.status,
        body: http_response.env.response_body,
        raw_response: http_response
      ),
      "API error occurred"
    )
  elsif Utils.match_status_code(http_response.status, ["5XX"])
    raise(
      ::XapiScraper::Models::Errors::APIError.new(
        status_code: http_response.status,
        body: http_response.env.response_body,
        raw_response: http_response
      ),
      "API error occurred"
    )
  else
    raise(
      ::XapiScraper::Models::Errors::APIError.new(
        status_code: http_response.status,
        body: http_response.env.response_body,
        raw_response: http_response
      ),
      "Unknown status code received"
    )

  end
end

#get_url(base_url:, url_variables: nil) ⇒ Object 



26
27
28
29
30
31
32
33
34
35
36
37
38
 
# File 'lib/xapi_scraper/articles.rb', line 26

def get_url(base_url:, url_variables: nil)
  sd_base_url, sd_options = @sdk_configuration.get_server_details

  if base_url.nil?
    base_url = sd_base_url
  end

  if url_variables.nil?
    url_variables = sd_options
  end

  return Utils.template_url(base_url, url_variables)
end

#markdown(request:, retries: nil, timeout_ms: nil, http_headers: nil) ⇒ Object 



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
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
 
# File 'lib/xapi_scraper/articles.rb', line 239

def markdown(request:, retries: nil, timeout_ms: nil, http_headers: nil)
  # markdown - Fetch Article as Markdown
  # Retrieves the content of an X (Twitter) article formatted as **clean, valid Markdown**. The response body is delivered as a raw UTF-8 string, optimized for direct import into static site generators, Obsidian, Notion, or any standard Markdown editor.
  url, params = @sdk_configuration.get_server_details
  base_url = Utils.template_url(url, params)
  url = Utils.generate_url(
    Models::Operations::ArticlesMarkdownRequest,
    base_url,
    "/x/article/{tweet_id}/markdown",
    request
  )
  headers = {}
  headers = T.cast(headers, T::Hash[String, String])
  headers["Accept"] = "text/plain"
  headers["user-agent"] = @sdk_configuration.user_agent
  retries ||= @sdk_configuration.retry_config
  retries ||= Utils::RetryConfig.new(
    backoff: Utils::BackoffStrategy.new(
      exponent: 1.5,
      initial_interval: 500,
      max_elapsed_time: 3_600_000,
      max_interval: 60_000
    ),
    retry_connection_errors: true,
    strategy: "backoff"
  )
  retry_options = retries.to_faraday_retry_options(initial_time: Time.now)
  retry_options[:retry_statuses] = [408, 409, 429, 500, 501, 502, 503, 504, 505]

  security = @sdk_configuration.security_source&.call

  timeout = (timeout_ms.to_f / 1000) unless timeout_ms.nil?
  timeout ||= @sdk_configuration.timeout

  connection = @sdk_configuration.client.dup
  connection.use(Utils::RetryMiddleware, retry_options)

  hook_ctx = SDKHooks::HookContext.new(
    config: @sdk_configuration,
    base_url: base_url,
    oauth2_scopes: nil,
    operation_id: "articlesMarkdown",
    security_source: @sdk_configuration.security_source
  )

  error = T.let(nil, T.nilable(StandardError))
  http_response = T.let(nil, T.nilable(Faraday::Response))

  begin
    http_response = T.must(connection).get(url) do |req|
      req.headers.merge!(headers)
      req.options.timeout = timeout unless timeout.nil?
      Utils.configure_request_security(req, security)
      http_headers&.each do |key, value|
        req.headers[key.to_s] = value
      end

      @sdk_configuration.hooks.before_request(
        hook_ctx: SDKHooks::BeforeRequestHookContext.new(
          hook_ctx: hook_ctx
        ),
        request: req
      )
    end

  rescue StandardError => e
    error = e
  ensure
    if http_response.nil? || Utils.error_status?(http_response.status)
      http_response = @sdk_configuration.hooks.after_error(
        error: error,
        hook_ctx: SDKHooks::AfterErrorHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
    else
      http_response = @sdk_configuration.hooks.after_success(
        hook_ctx: SDKHooks::AfterSuccessHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
    end

    if http_response.nil?
      raise error if !error.nil?
      raise "no response"
    end
  end

  content_type = http_response.headers.fetch("Content-Type", "application/octet-stream")
  if Utils.match_status_code(http_response.status, ["200"])
    if Utils.match_content_type(content_type, "text/plain")
      http_response = @sdk_configuration.hooks.after_success(
        hook_ctx: SDKHooks::AfterSuccessHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
      obj = http_response.env.body.force_encoding("UTF-8")

      return Models::Operations::ArticlesMarkdownResponse.new(
        status_code: http_response.status,
        content_type: content_type,
        raw_response: http_response,
        res: T.unsafe(obj)
      )
    else
      raise(
        ::XapiScraper::Models::Errors::APIError.new(
          status_code: http_response.status,
          body: http_response.env.response_body,
          raw_response: http_response
        ),
        "Unknown content type received"
      )
    end
  elsif Utils.match_status_code(http_response.status, ["422"])
    if Utils.match_content_type(content_type, "application/json")
      http_response = @sdk_configuration.hooks.after_success(
        hook_ctx: SDKHooks::AfterSuccessHookContext.new(
          hook_ctx: hook_ctx
        ),
        response: http_response
      )
      response_data = http_response.env.response_body
      obj = Crystalline.unmarshal_json(JSON.parse(response_data), Models::Errors::HTTPValidationError)
      obj.raw_response = http_response
      raise obj
    else
      raise(
        ::XapiScraper::Models::Errors::APIError.new(
          status_code: http_response.status,
          body: http_response.env.response_body,
          raw_response: http_response
        ),
        "Unknown content type received"
      )
    end
  elsif Utils.match_status_code(http_response.status, ["4XX"])
    raise(
      ::XapiScraper::Models::Errors::APIError.new(
        status_code: http_response.status,
        body: http_response.env.response_body,
        raw_response: http_response
      ),
      "API error occurred"
    )
  elsif Utils.match_status_code(http_response.status, ["5XX"])
    raise(
      ::XapiScraper::Models::Errors::APIError.new(
        status_code: http_response.status,
        body: http_response.env.response_body,
        raw_response: http_response
      ),
      "API error occurred"
    )
  else
    raise(
      ::XapiScraper::Models::Errors::APIError.new(
        status_code: http_response.status,
        body: http_response.env.response_body,
        raw_response: http_response
      ),
      "Unknown status code received"
    )

  end
end