Class: Elephrame::Bots::EbooksBot

Inherits:
GenerativeBot show all
Defined in:
lib/elephrame/mix/bots.rb

Overview

A basic Ebooks bot template

Constant Summary collapse

PrivacyLevels = 
['public', 'unlisted', 'private', 'direct']
APILimit = 
280
RetryTime = 
'6m'

Constants inherited from GenerativeBot

GenerativeBot::SavedFileName, GenerativeBot::SavedFilterFileName

Constants inherited from BaseBot

BaseBot::FNGabLink, BaseBot::NoBotRegex

Instance Attribute Summary collapse

Attributes inherited from GenerativeBot

#char_limit, #cw, #filter, #filter_by, #filter_filename, #filter_words, #following, #model, #model_filename, #model_hash, #retry_limit, #visibility

Attributes included from Command

#cmd_hash, #cmd_regex, #commands, #not_found, #prefix

Attributes included from Reply

#on_reply

Attributes included from Scheduler

#schedule, #scheduler

Attributes included from Streaming

#streamer

Attributes inherited from BaseBot

#client, #failed, #max_retries, #strip_html, #username

Instance Method Summary collapse

Methods inherited from GenerativeBot

#add_filter_word, #add_privileged_command, #filter_and_post, #load_file, #save_file

Methods included from Command

#add_command, #if_not_found, #run_commands, #set_help, #set_prefix, #setup_command

Methods included from Reply

#reply, #reply_with_mentions, #run_reply

Methods included from Scheduler

#run_scheduled, #setup_scheduler

Methods included from Streaming

#setup_streaming

Methods inherited from BaseBot

backup_method, #fetch_account_id, #fetch_list_id, #find_ancestor, #no_bot?, #post

Constructor Details

#initialize(interval, opts = {}) ⇒ EbooksBot

Creates a new Ebooks bot

Parameters:

  • interval (String) —

    how often should the bot post on it’s own

  • opts (Hash) (defaults to: {}) —

    options for the bot

  • opt (Hash) —

    a customizable set of options



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
 
# File 'lib/elephrame/mix/bots.rb', line 124

def initialize(interval, opts = {})
  super

  # add our manual update command
  add_privileged_command 'update' do
    fetch_new_posts
  end

  # set some defaults for our internal vars
  level = PrivacyLevels.index(opts[:scrape_privacy]) || 0
  @scrape_filter = /(#{PrivacyLevels[0..level].join('|')})/
  @update_interval = opts[:update_interval] || '2d'

  # if we don't have what a newest post id then we fetch them
  #  for each account
  if @model_hash[:last_id].empty?
    @old_id = {}
    
    @following.each do ||
      # get the newest post from this account and save the id
      newest_id = @client.statuses(,
                                   exclude_reblogs: true,
                                   limit: 1).first.id
      @model_hash[:last_id][] = newest_id
      @old_id[] = newest_id
    end
  end

  # if our model's token are empty that means we have an empty model
  fetch_old_posts if @model_hash[:model].tokens.empty?
end

Instance Attribute Details

#old_id ⇒ Object (readonly)

Returns the value of attribute old_id.



98
99
100
 
# File 'lib/elephrame/mix/bots.rb', line 98

def old_id
  @old_id
end

#scrape_filter ⇒ Object (readonly)

Returns the value of attribute scrape_filter.



98
99
100
 
# File 'lib/elephrame/mix/bots.rb', line 98

def scrape_filter
  @scrape_filter
end

#update_interval ⇒ Object (readonly)

Returns the value of attribute update_interval.



98
99
100
 
# File 'lib/elephrame/mix/bots.rb', line 98

def update_interval
  @update_interval
end

Instance Method Details

#default_help ⇒ Object

overloads the super’s help method



303
304
305
306
307
308
 
# File 'lib/elephrame/mix/bots.rb', line 303

def default_help
  txt = []
  txt << '!update -- tells the bot to manually fetch new posts'
  txt << super
  txt.join '\n'
end

#fetch_new_posts ⇒ Object

Fetch posts from the accounts the bot follows



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
 
# File 'lib/elephrame/mix/bots.rb', line 224

def fetch_new_posts
  begin
    # set up some vars for tracking our progress
    added_posts = { statuses: [],
                    mentions: [] }
    api_calls = 1
    errored = false

    # for each account we're following
    @following.each do ||
      # get 40 posts at a time, where we left off
      posts = @client.statuses(,
                               exclude_reblogs: true,
                               limit: 40,
                               since_id: @model_hash[:last_id][])

      # while we have posts to process and we haven't
      #  gotten near the api limit
      while not posts.size.zero? and api_calls < APILimit
        posts.reverse_each do |post|
          # save our post id for next loop
          @model_hash[:last_id][] = post.id

          # if the post matches our set visibility we add it to our hash
          if post.visibility =~ @scrape_filter
            added_posts = add_post_to_hash post, added_posts
          end
        end

        # fetch more posts
        posts = @client.statuses(,
                                 exclude_reblogs: true,
                                 limit: 40,
                                 since_id: @model_hash[:last_id][])
        api_calls += 1
      end

      # in case we hit our api limit between calls
      break if api_calls >= APILimit
    end
    
  rescue 
    # if we've hit here then we've errored out
    errored = true
    
  ensure
    # consume our new posts, and add them to our original hash
    @model_hash[:model].consume! added_posts
    
    if api_calls >= APILimit or errored
      @scheduler.in RetryTime do
        fetch_new_posts
      end
    end
    
    # then we save 
    save_file(@model_filename,
              @model_hash.collect {|key, value| value.to_hash }.to_yaml)
  end
end

#fetch_old_posts ⇒ Object

Method to go and fetch all posts

should be ran first



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
 
# File 'lib/elephrame/mix/bots.rb', line 160

def fetch_old_posts
  begin
    # init some vars to keep track of where we are
    api_calls = 1
    errored = false
    new_posts = { statuses: [],
                  mentions: [] }

    # for each account we're following
    @following.each do ||
      # okay so
      #  we keep track of how many get requests we're doing and before
      #  the limit (300) we schedule for 5min and go on, saving what we got
      posts = @client.statuses(,
                               exclude_reblogs: true,
                               limit: 40,
                               max_id: @old_id[])
      
      # while we still have posts and haven't gotten near the api limit
      while not posts.size.zero? and api_calls < APILimit
        posts.each do |post|
          
          # add the new post to our hash
          if post.visibility =~ @scrape_filter
            new_posts = add_post_to_hash post, new_posts
          end
          
          # set our cached id to the latest post id
          @old_id[] = post.id
        end
        
        # fetch more posts
        posts = @client.statuses(,
                                 exclude_reblogs: true,
                                 limit: 40,
                                 max_id: @old_id[])
        api_calls += 1
      end
      
      break if api_calls >= APILimit
    end
    
  rescue 
    errored = true
    
  ensure
    # consume our posts, and then save our model
    @model_hash[:model].consume! new_posts
    save_file(@model_filename,
              @model_hash.collect {|key, value| value.to_hash }.to_yaml)

    # if we have more than our limit of api calls
    #  or we errored out that means we need to check again
    if api_calls >= APILimit or errored 
      @scheduler.in RetryTime do
        fetch_old_posts
      end
    end
  end
end

#run ⇒ Object

Run the Ebooks bot



288
289
290
291
292
293
294
295
296
 
# File 'lib/elephrame/mix/bots.rb', line 288

def run
  # set up our scheduler to scrape posts
  @scheduler.repeat @update_interval do
    fetch_new_posts
  end

  # call generativebot's run method
  super
end