Class: Downloader

Inherits:
Object
  • Object
show all
Defined in:
lib/downloader.rb

Overview

小説サイトからのダウンロード

Constant Summary collapse

NOVEL_SITE_SETTING_DIR =
"webnovel/"
SECTION_SAVE_DIR_NAME =

本文を保存するディレクトリ名

"本文"
CACHE_SAVE_DIR_NAME =

差分用キャッシュ保存用ディレクトリ名

"cache"
RAW_DATA_DIR_NAME =

本文の生データを保存するディレクトリ名

"raw"
TOC_FILE_NAME =
"toc.yaml"
STEPS_WAIT_TIME =

数話ごとにかかるwaitの秒数

5
WAITING_TIME_FOR_503 =

503 のときに待機する秒数

20
RETRY_MAX_FOR_503 =

503 のときに何回再試行するか

5
NOVEL_TYPE_SERIES =

連載

1
NOVEL_TYPE_SS =

短編

2
DISPLAY_LIMIT_DIGITS =

indexの表示桁数限界

4
@@settings =
load_settings
@@database =
Database.instance

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(site_setting, force = false, from_download = false) ⇒ Downloader

コンストラクタ



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
# File 'lib/downloader.rb', line 282

def initialize(site_setting, force = false, from_download = false)
  @title = nil
  @file_title = nil
  @setting = site_setting
  @force = force
  @from_download = from_download
  @cache_dir = nil
  @new_arrivals = false
  @novel_data_dir = nil
  @novel_status = nil
  @id = @@database.get_id("toc_url", @setting["toc_url"]) || @@database.get_new_id
  @section_download_cache = {}

  # ウェイト管理関係初期化
  @@__run_once ||= true
  if @@__run_once
    @@__run_once = false
    @@__wait_counter = 0
    @@__last_download_time = Time.now - 20
    @@interval_sleep_time = Inventory.load("local_setting", :local)["download.interval"] || 0
    @@interval_sleep_time = 0 if @@interval_sleep_time < 0
    @@max_steps_wait_time = [STEPS_WAIT_TIME, @@interval_sleep_time].max
  end
  @download_wait_steps = Inventory.load("local_setting", :local)["download.wait-steps"] || 0
  if @setting["is_narou"] && (@download_wait_steps > 10 || @download_wait_steps == 0)
    @download_wait_steps = 10
  end
end

Instance Attribute Details

#idObject (readonly)

Returns the value of attribute id.



34
35
36
# File 'lib/downloader.rb', line 34

def id
  @id
end

Class Method Details

.get_cache_list(target) ⇒ Object

差分用キャッシュのディレクトリ一覧取得



266
267
268
269
270
271
272
# File 'lib/downloader.rb', line 266

def self.get_cache_list(target)
  dir = get_cache_root_dir(target)
  if dir
    return Dir.glob("#{dir}/*")
  end
  nil
end

.get_cache_root_dir(target) ⇒ Object

差分用キャッシュの保存ディレクトリ取得



255
256
257
258
259
260
261
# File 'lib/downloader.rb', line 255

def self.get_cache_root_dir(target)
  dir = get_novel_data_dir_by_target(target)
  if dir
    return File.join(dir, SECTION_SAVE_DIR_NAME, CACHE_SAVE_DIR_NAME)
  end
  nil
end

.get_data_by_target(target) ⇒ Object

target からデータベースのデータを取得



158
159
160
161
162
# File 'lib/downloader.rb', line 158

def self.get_data_by_target(target)
  target = Narou.alias_to_id(target)
  toc_url = get_toc_url(target) or return nil
  @@database.get_data("toc_url", toc_url)
end

.get_id_by_target(target) ⇒ Object

target のIDを取得



149
150
151
152
153
# File 'lib/downloader.rb', line 149

def self.get_id_by_target(target)
  target = Narou.alias_to_id(target)
  toc_url = get_toc_url(target) or return nil
  @@database.get_id("toc_url", toc_url)
end

.get_novel_data_dir_by_target(target) ⇒ Object

指定されたIDとかから小説の保存ディレクトリを取得



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
# File 'lib/downloader.rb', line 117

def self.get_novel_data_dir_by_target(target)
  target = Narou.alias_to_id(target)
  type = get_target_type(target)
  data = nil
  id = nil
  case type
  when :url, :ncode
    toc_url = get_toc_url(target)
    data = @@database.get_data("toc_url", toc_url)
  when :other
    data = @@database.get_data("title", target)
  when :id
    data = @@database[target.to_i]
  end
  return nil unless data
  id = data["id"]
  file_title = data["file_title"] || data["title"]   # 互換性維持のための処理
  path = File.join(Database.archive_root_path, data["sitename"], file_title)
  if File.exists?(path)
    return path
  else
    @@database.delete(id)
    @@database.save_database
    error "#{path} が見つかりません。"
    warn "保存フォルダが消去されていたため、データベースのインデックスを削除しました。"
    return nil
  end
end

.get_novel_section_save_dir(archive_path) ⇒ Object

本文格納用ディレクトリを取得



91
92
93
# File 'lib/downloader.rb', line 91

def self.get_novel_section_save_dir(archive_path)
  File.join(archive_path, SECTION_SAVE_DIR_NAME)
end

.get_sitesetting_by_sitename(sitename) ⇒ Object



221
222
223
224
225
226
# File 'lib/downloader.rb', line 221

def self.get_sitesetting_by_sitename(sitename)
  setting = @@settings.find { |s| s["name"] == sitename }
  return setting if setting
  error "#{sitename} の設定ファイルが見つかりません"
  exit 1
end

.get_sitesetting_by_target(target) ⇒ Object

小説サイト設定を取得する



79
80
81
82
83
84
85
86
# File 'lib/downloader.rb', line 79

def self.get_sitesetting_by_target(target)
  toc_url = get_toc_url(target)
  setting = nil
  if toc_url
    setting = @@settings.find { |s| s.multi_match(toc_url, "url") }
  end
  setting
end

.get_target_type(target) ⇒ Object

target の種別を判別する

ncodeの場合、targetを破壊的に変更する



100
101
102
103
104
105
106
107
108
109
110
111
112
# File 'lib/downloader.rb', line 100

def self.get_target_type(target)
  case target
  when URI.regexp
    :url
  when /^n\d+[a-z]+$/i
    target.downcase!
    :ncode
  when /^\d+$/, Fixnum
    :id
  else
    :other
  end
end

.get_toc_data(archive_path) ⇒ Object

toc 読込



167
168
169
# File 'lib/downloader.rb', line 167

def self.get_toc_data(archive_path)
  YAML.load_file(File.join(archive_path, TOC_FILE_NAME))
end

.get_toc_url(target) ⇒ Object

指定の小説の目次ページのURLを取得する

targetがURLかNコードの場合、実際には小説が存在しないURLが返ってくることがあるのを留意する



176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
# File 'lib/downloader.rb', line 176

def self.get_toc_url(target)
  target = Narou.alias_to_id(target)
  case get_target_type(target)
  when :url
    setting = @@settings.find { |s| s.multi_match(target, "url") }
    return setting["toc_url"] if setting
  when :ncode
    @@database.each do |_, data|
      if data["toc_url"] =~ %r!#{target}/$!
        return data["toc_url"]
      end
    end
    return "#{@@narou["top_url"]}/#{target}/"
  when :id
    data = @@database[target.to_i]
    return data["toc_url"] if data
  when :other
    data = @@database.get_data("title", target)
    return data["toc_url"] if data
  end
  nil
end

.load_settingsObject

小説サイトの定義ファイルを全部読み込む



231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
# File 'lib/downloader.rb', line 231

def self.load_settings
  settings = @@__settings_cache ||= []
  return settings unless settings.empty?
  Dir.glob(File.join(Narou.get_script_dir, NOVEL_SITE_SETTING_DIR, "*.yaml")) do |path|
    setting = SiteSetting.load_file(path)
    if setting["name"] == "小説家になろう"
      @@narou = setting
    end
    settings << setting
  end
  if settings.empty?
    error "小説サイトの定義ファイルがひとつもありません"
    exit 1
  end
  unless @@narou
    error "小説家になろうの定義ファイルが見つかりませんでした"
    exit 1
  end
  settings
end

.novel_exists?(target) ⇒ Boolean

Returns:

  • (Boolean)


199
200
201
202
203
# File 'lib/downloader.rb', line 199

def self.novel_exists?(target)
  target = Narou.alias_to_id(target)
  id = get_id_by_target(target) or return nil
  @@database.novel_exists?(id)
end

.remove_novel(target, with_file = false) ⇒ Object



205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
# File 'lib/downloader.rb', line 205

def self.remove_novel(target, with_file = false)
  target = Narou.alias_to_id(target)
  data = get_data_by_target(target) or return nil
  data_dir = get_novel_data_dir_by_target(target)
  if with_file
    FileUtils.remove_entry_secure(data_dir, true)
    puts "#{data_dir} を完全に削除しました"
  else
    # TOCは消しておかないと再DL時に古いデータがあると誤認する
    File.delete(File.join(data_dir, TOC_FILE_NAME))
  end
  @@database.delete(data["id"])
  @@database.save_database
  data["title"]
end

.start(target, force = false, from_download = false) ⇒ Object

ターゲット(ID、URL、Nコード、小説名)を指定して小説データのダウンロードを開始する

force が true なら全話強制ダウンロード



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

def self.start(target, force = false, from_download = false)
  setting = nil
  target = Narou.alias_to_id(target)
  fail_status = OpenStruct.new(:id => nil, :new_arrivals => nil,
                               :status => false).freeze
  case type = get_target_type(target)
  when :url, :ncode
    setting = get_sitesetting_by_target(target)
    unless setting
      error "対応外の#{type}です(#{target})"
      return fail_status
    end
  when :id
    data = @@database[target.to_i]
    unless data
      error "指定のID(#{target})は存在しません"
      return fail_status
    end
    setting = get_sitesetting_by_sitename(data["sitename"])
    setting.multi_match(data["toc_url"], "url")
  when :other
    data = @@database.get_data("title", target)
    if data
      setting = get_sitesetting_by_sitename(data["sitename"])
      setting.multi_match(data["toc_url"], "url")
    else
      error "指定の小説(#{target})は存在しません"
      return fail_status
    end
  end
  downloader = Downloader.new(setting, force, from_download)
  result = downloader.start_download
  result
end

Instance Method Details

#__search_index_in_subtitles(subtitles, index) ⇒ Object



651
652
653
654
655
# File 'lib/downloader.rb', line 651

def __search_index_in_subtitles(subtitles, index)
  subtitles.index { |item|
    item["index"] == index
  }
end

#__strdate_to_ymd(date) ⇒ Object



657
658
659
# File 'lib/downloader.rb', line 657

def __strdate_to_ymd(date)
  Date.parse(date.to_s.tr("年月日時分秒", "///:::")).strftime("%Y%m%d")
end

#a_section_download(subtitle_info) ⇒ Object

指定された話数の本文をダウンロード



877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
# File 'lib/downloader.rb', line 877

def a_section_download(subtitle_info)
  index = subtitle_info["index"]
  return @section_download_cache[index] if @section_download_cache[index]
  sleep_for_download
  href = subtitle_info["href"]
  if @setting["is_narou"]
    subtitle_url = @setting.replace_group_values("txtdownload_url", subtitle_info)
  elsif href[0] == "/"
    subtitle_url = @setting["top_url"] + href
  else
    subtitle_url = @setting["toc_url"] + href
  end
  raw = download_raw_data(subtitle_url)
  if @setting["is_narou"]
    save_raw_data(raw, subtitle_info)
    element = extract_elements_in_section(raw, subtitle_info["subtitle"])
    element["data_type"] = "text"
  else
    save_raw_data(raw, subtitle_info, ".html")
    @setting.multi_match(raw, "body_pattern", "introduction_pattern", "postscript_pattern")
    element = { "data_type" => "html" }
    %w(introduction body postscript).each { |type|
      element[type] = @setting[type] || ""
    }
  end
  subtitle_info["download_time"] = Time.now
  @section_download_cache[index] = element
  element
end

#confirm_over18?Boolean

18歳以上か確認する

Returns:

  • (Boolean)


314
315
316
317
318
319
320
321
322
323
324
325
326
# File 'lib/downloader.rb', line 314

def confirm_over18?
  global_setting = Inventory.load("global_setting", :global)
  if global_setting.include?("over18")
    return global_setting["over18"]
  end
  if Helper.confirm("年齢認証:あなたは18歳以上ですか")
    global_setting["over18"] = true
    global_setting.save
    return true
  else
    return false
  end
end

#create_cache_dirObject

差分用キャッシュ保存ディレクトリ作成



473
474
475
476
477
478
479
# File 'lib/downloader.rb', line 473

def create_cache_dir
  now = Time.now
  name = now.strftime("%Y.%m.%d@%H.%M.%S")
  cache_dir = File.join(get_novel_data_dir, SECTION_SAVE_DIR_NAME, CACHE_SAVE_DIR_NAME, name)
  FileUtils.mkdir_p(cache_dir)
  cache_dir
end

#create_section_file_path(subtitle_info) ⇒ Object

小説本文の保存パスを生成



1017
1018
1019
1020
# File 'lib/downloader.rb', line 1017

def create_section_file_path(subtitle_info)
  filename = "#{subtitle_info["index"]} #{subtitle_info["file_subtitle"]}.yaml"
  File.join(get_novel_data_dir, SECTION_SAVE_DIR_NAME, filename)
end

#create_short_story_subtitles(info) ⇒ Object

短編用の情報を生成



769
770
771
772
773
774
775
776
777
778
779
780
# File 'lib/downloader.rb', line 769

def create_short_story_subtitles(info)
  subtitle = {
    "index" => "1",
    "href" => @setting.replace_group_values("href", "index" => "1"),
    "chapter" => "",
    "subtitle" => @setting["title"],
    "file_subtitle" => Helper.replace_filename_special_chars(@setting["title"]),
    "subdate" => info["general_firstup"],
    "subupdate" => info["novelupdated_at"]
  }
  [subtitle]
end

#different_section?(old_relative_path, new_subtitle_info) ⇒ Boolean

すでに保存されている内容とDLした内容が違うかどうか

Returns:

  • (Boolean)


837
838
839
840
841
842
843
844
# File 'lib/downloader.rb', line 837

def different_section?(old_relative_path, new_subtitle_info)
  path = File.join(get_novel_data_dir, old_relative_path)
  if File.exists?(path)
    return YAML.load_file(path)["element"] != new_subtitle_info["element"]
  else
    return true
  end
end

#digest_output_interface(old_subtitles_count, latest_subtitles_count) ⇒ Object



455
456
457
458
459
460
461
462
463
464
465
466
467
468
# File 'lib/downloader.rb', line 455

def digest_output_interface(old_subtitles_count, latest_subtitles_count)
  STDOUT.puts
  STDOUT.puts "保存済み話数: #{old_subtitles_count}"
  STDOUT.puts "更新後の話数: #{latest_subtitles_count}"
  STDOUT.puts
  STDOUT.puts "1: このまま更新する"
  STDOUT.puts "2: 更新をキャンセル"
  STDOUT.puts "3: 更新をキャンセルして小説を凍結する"
  STDOUT.puts "4: バックアップを作成する"
  STDOUT.puts "5: 最新のあらすじを表示する"
  STDOUT.puts "6: 小説ページをブラウザで開く"
  STDOUT.puts "7: 保存フォルダを開く"
  STDOUT.print "選択する処理の番号を入力: "
end

#download_raw_data(url) ⇒ Object

指定したURLからデータをダウンロード



910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
# File 'lib/downloader.rb', line 910

def download_raw_data(url)
  raw = nil
  retry_count = RETRY_MAX_FOR_503
  begin
    open(url) do |fp|
      raw = Helper.pretreatment_source(fp.read, @setting["encoding"])
    end
  rescue OpenURI::HTTPError => e
    if e.message =~ /^503/
      if retry_count == 0
        error "上限までリトライしましたがファイルがダウンロード出来ませんでした"
        exit 1
      end
      retry_count -= 1
      puts
      warn "server message: #{e.message}"
      warn "リトライ待機中……"
      @@display_hint_once ||= true
      if @@display_hint_once
        warn "ヒント: narou s download.wait-steps=10 とすることで、" \
             "10話ごとにウェイトをいれられます"
        @@display_hint_once = false
      end
      sleep(WAITING_TIME_FOR_503)
      retry
    else
      raise
    end
  end
  raw
end

#extract_elements_in_section(section, subtitle) ⇒ Object

本文を解析して前書き・本文・後書きの要素に分解する

本文に含まれるタイトルは消す



966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
# File 'lib/downloader.rb', line 966

def extract_elements_in_section(section, subtitle)
  lines = section.lstrip.lines.map(&:rstrip)
  introduction = slice_introduction(lines)
  postscript = slice_postscript(lines)
  if lines[0] == subtitle.strip
    if lines[1] == ""
      lines.slice!(0, 2)
    else
      lines.slice!(0, 1)
    end
  end
  {
    "introduction" => introduction,
    "body" => lines.join("\n"),
    "postscript" => postscript
  }
end

#get_file_titleObject

小説を格納するためのディレクトリ名を取得する



559
560
561
562
563
564
565
566
567
568
569
570
571
# File 'lib/downloader.rb', line 559

def get_file_title
  return @file_title if @file_title
  # すでにデータベースに登録されているならそれを引き続き使うようにする
  if @@database[@id] && @@database[@id]["file_title"]
    @file_title = @@database[@id]["file_title"]
    return @file_title
  end
  @file_title = @setting["ncode"]
  if @setting["append_title_to_folder_name"]
    @file_title += " " + Helper.replace_filename_special_chars(get_title, true).strip
  end
  @file_title
end

#get_latest_table_of_contentsObject

目次データを取得する



588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
# File 'lib/downloader.rb', line 588

def get_latest_table_of_contents
  toc_url = @setting["toc_url"]
  return nil unless toc_url
  toc_source = ""
  begin
    open(toc_url) do |toc_fp|
      if toc_fp.base_uri.to_s != toc_url
        # リダイレクトされた場合。
        # ノクターン・ムーンライトのNコードを ncode.syosetu.com に渡すと、novel18.syosetu.com に飛ばされる
        # 目次の定義が微妙に ncode.syosetu.com と違うので、設定を取得し直す
        @setting.clear   # 今まで使っていたのは一旦クリア
        @setting = Downloader.get_sitesetting_by_target(toc_fp.base_uri.to_s)
        toc_url = @setting["toc_url"]
      end
      toc_source = Helper.pretreatment_source(toc_fp.read, @setting["encoding"])
    end
  rescue OpenURI::HTTPError => e
    if e.message =~ /^404/
      error "<bold><red>[404]</red></bold> 小説が削除されている可能性があります".termcolor
      $stdout.silence do
        Command::Tag.execute!([@id, "--add", "404", "--color", "white"])
      end
      Command::Freeze.execute!([@id])
    else
      error "何らかの理由により目次が取得できませんでした(#{e.message})"
    end
    return false
  end
  @setting.multi_match(toc_source, "tcode")
  #if @setting["narou_api_url"]
  if false
    # なろうAPIの出力がおかしいので直るまで使用中止
    info = Narou::API.new(@setting, "t-s-gf-nu-w")
  else
    info = NovelInfo.load(@setting)
  end
  if info
    @setting["title"] = info["title"]
    @setting["author"] = info["writer"]
    @setting["story"] = info["story"]
  else
    # 小説情報ページがないサイトの場合は目次ページから取得する
    @setting.multi_match(toc_source, "title", "author", "story")
    @setting["story"] = HTML.new(@setting["story"]).to_aozora
  end
  @setting["title"] = get_title
  if series_novel?
    # 連載小説
    subtitles = get_subtitles(toc_source)
  else
    # 短編小説
    subtitles = create_short_story_subtitles(info)
  end
  toc_objects = {
    "title" => get_title,
    "author" => @setting["author"],
    "toc_url" => @setting["toc_url"],
    "story" => @setting["story"],
    "subtitles" => subtitles
  }
  toc_objects
end

#get_novel_data_dirObject

小説データの格納ディレクトリパス



1007
1008
1009
1010
1011
1012
# File 'lib/downloader.rb', line 1007

def get_novel_data_dir
  return @novel_data_dir if @novel_data_dir
  raise "小説名がまだ設定されていません" unless get_file_title
  @novel_data_dir = File.join(Database.archive_root_path, @setting["name"], get_file_title)
  @novel_data_dir
end

#get_novel_statusObject



512
513
514
515
516
517
518
519
520
521
522
523
524
525
# File 'lib/downloader.rb', line 512

def get_novel_status
  novel_status = if false # @setting["narou_api_url"]
                   Narou::API.new(@setting, "nt-e")
                 else
                   NovelInfo.load(@setting)
                 end
  unless novel_status
    novel_status = {
      "novel_type" => NOVEL_TYPE_SERIES,
      "end" => false
    }
  end
  novel_status
end

#get_novel_typeObject

小説の種別を取得(連載か短編)



530
531
532
533
534
535
536
# File 'lib/downloader.rb', line 530

def get_novel_type
  if @novel_status
    @novel_status["novel_type"]
  end
  @novel_status ||= get_novel_status
  @novel_status["novel_type"]
end

#get_raw_dirObject



942
943
944
# File 'lib/downloader.rb', line 942

def get_raw_dir
  @raw_dir ||= File.join(get_novel_data_dir, RAW_DATA_DIR_NAME)
end

#get_section_file_timestamp(old_subtitles_info, latest_subtitles_info) ⇒ Object

対象話数のタイムスタンプを取得



733
734
735
736
737
738
739
740
# File 'lib/downloader.rb', line 733

def get_section_file_timestamp(old_subtitles_info, latest_subtitles_info)
  download_time = old_subtitles_info["download_time"]
  unless download_time
    download_time = File.mtime(create_section_file_path(old_subtitles_info))
  end
  latest_subtitles_info["download_time"] = download_time
  download_time
end

#get_subtitles(toc_source) ⇒ Object

各話の情報を取得



745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
# File 'lib/downloader.rb', line 745

def get_subtitles(toc_source)
  subtitles = []
  toc_post = toc_source.dup
  loop do
    match_data = @setting.multi_match(toc_post, "subtitles")
    break unless match_data
    toc_post = match_data.post_match
    @setting["subtitle"] = @setting["subtitle"].gsub("\t", "")
    subtitles << {
      "index" => @setting["index"],
      "href" => @setting["href"],
      "chapter" => @setting["chapter"],
      "subtitle" => @setting["subtitle"].gsub("\n", ""),
      "file_subtitle" => Helper.replace_filename_special_chars(@setting["subtitle"]),
      "subdate" => @setting["subdate"],
      "subupdate" => @setting["subupdate"]
    }
  end
  subtitles
end

#get_titleObject

小説のタイトルを取得する



576
577
578
579
580
581
582
583
# File 'lib/downloader.rb', line 576

def get_title
  return @title if @title
  @title = @setting["title"]
  if @setting["title_strip_pattern"]
    @title = @title.gsub(/#{@setting["title_strip_pattern"]}/, "").gsub(/^[ \s]*(.+?)[ \s]*?$/, "\\1")
  end
  @title
end

#init_novel_dirObject

小説データの格納ディレクトリを初期設定する



1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
# File 'lib/downloader.rb', line 1046

def init_novel_dir
  novel_dir_path = get_novel_data_dir
  file_title = File.basename(novel_dir_path)
  FileUtils.mkdir_p(novel_dir_path) unless File.exists?(novel_dir_path)
  default_settings = NovelSetting::DEFAULT_SETTINGS
  special_preset_dir = File.join(Narou.get_preset_dir, @setting["domain"], @setting["ncode"])
  exists_special_preset_dir = File.exists?(special_preset_dir)
  [NovelSetting::INI_NAME, "converter.rb", NovelSetting::REPLACE_NAME].each do |filename|
    if exists_special_preset_dir
      preset_file_path = File.join(special_preset_dir, filename)
      if File.exists?(preset_file_path)
        unless File.exists?(File.join(novel_dir_path, filename))
          FileUtils.cp(preset_file_path, novel_dir_path)
        end
        next
      end
    end
    Template.write(filename, novel_dir_path, binding)
  end
end

#init_raw_dirObject



946
947
948
949
# File 'lib/downloader.rb', line 946

def init_raw_dir
  path = get_raw_dir
  FileUtils.mkdir_p(path) unless File.exists?(path)
end

#load_novel_data(filename) ⇒ Object

小説データの格納ディレクトリから読み込む



1036
1037
1038
1039
1040
1041
# File 'lib/downloader.rb', line 1036

def load_novel_data(filename)
  dir_path = get_novel_data_dir
  YAML.load_file(File.join(dir_path, filename))
rescue Errno::ENOENT
  nil
end

#move_to_cache_dir(relative_path) ⇒ Object

差分用のキャッシュとして保存



849
850
851
852
853
854
# File 'lib/downloader.rb', line 849

def move_to_cache_dir(relative_path)
  path = File.join(get_novel_data_dir, relative_path)
  if File.exists?(path) && @cache_dir
    FileUtils.mv(path, @cache_dir)
  end
end

#novel_end?Boolean

小説が完結しているか調べる

Returns:

  • (Boolean)


541
542
543
544
545
546
547
# File 'lib/downloader.rb', line 541

def novel_end?
  if @novel_status
    @novel_status["end"]
  end
  @novel_status ||= get_novel_status
  @novel_status["end"]
end

#process_digest(old_toc, latest_toc) ⇒ Object

ダイジェスト化に関する処理

Returns:

  • true = 更新をキャンセル、false = 更新する



415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
# File 'lib/downloader.rb', line 415

def process_digest(old_toc, latest_toc)
  return false unless old_toc["subtitles"]
  latest_subtitles_count = latest_toc["subtitles"].count
  old_subtitles_count = old_toc["subtitles"].count
  if latest_subtitles_count < old_subtitles_count
    STDOUT.puts "#{latest_toc["title"]}"
    STDOUT.puts "更新後の話数が保存されている話数より減少していることを検知しました"
    STDOUT.puts "ダイジェスト化されている可能性があるので、更新に関しての処理を選択して下さい"
    digest_output_interface(old_subtitles_count, latest_subtitles_count)
    unless STDIN.tty?
      puts "2"
      return true
    end
    while input = $stdin.getch
      puts input
      case input
      when "1"
        return false
      when "2"
        return true
      when "3"
        Command::Freeze.execute!([latest_toc["toc_url"]])
        return true
      when "4"
        Command::Backup.execute!([latest_toc["toc_url"]])
      when "5"
        STDOUT.puts "あらすじ"
        STDOUT.puts latest_toc["story"]
      when "6"
        Helper.open_browser(latest_toc["toc_url"])
      when "7"
        Helper.open_directory(Downloader.get_novel_data_dir_by_target(latest_toc["toc_url"]))
      end
      digest_output_interface(old_subtitles_count, latest_subtitles_count)
    end
  else
    return false
  end
end

#remove_cache_dirObject

差分用キャッシュ保存ディレクトリを削除



484
485
486
# File 'lib/downloader.rb', line 484

def remove_cache_dir
  FileUtils.remove_entry_secure(@cache_dir, true) if @cache_dir
end

#run_downloadObject

ダウンロード処理本体



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/downloader.rb', line 344

def run_download
  latest_toc = get_latest_table_of_contents
  unless latest_toc
    error @setting["toc_url"] + " の目次データが取得出来ませんでした"
    return :failed
  end
  if @setting["confirm_over18"]
    unless confirm_over18?
      puts "18歳以上のみ閲覧出来る小説です。ダウンロードを中止しました"
      return :canceled
    end
  end
  old_toc = load_novel_data(TOC_FILE_NAME)
  unless old_toc
    init_novel_dir
    old_toc = {}
    @new_arrivals = true
  end
  init_raw_dir
  if old_toc.empty? || @force
    update_subtitles = latest_toc["subtitles"]
  else
    update_subtitles = update_body_check(old_toc["subtitles"], latest_toc["subtitles"])
  end
  return_status = nil
  if update_subtitles.count > 0
    unless @force
      if process_digest(old_toc, latest_toc)
        return :canceled
      end
    end
    @cache_dir = create_cache_dir if old_toc.length > 0
    begin
      sections_download_and_save(update_subtitles)
      if @cache_dir && Dir.glob(File.join(@cache_dir, "*")).count == 0
        remove_cache_dir
      end
    rescue Interrupt
      remove_cache_dir
      puts "ダウンロードを中断しました"
      exit 1
    end
    update_database
    return_status = :ok
  else
    return_status = :none
  end
  save_novel_data(TOC_FILE_NAME, latest_toc)
  if novel_end?
    if old_toc.empty? || !@@database[@id]["end"]
      $stdout.silence do
        Command::Tag.execute!([@id, "--add", "end", "--color", "white"])
      end
      if old_toc.empty?
        puts "<bold><cyan>ID:#{@id} #{@title} は完結しているようです</cyan></bold>".termcolor
      else
        puts "<bold><cyan>ID:#{@id} #{@title} は完結したようです</cyan></bold>".termcolor
        update_database if update_subtitles.count == 0
      end
    end
  end
  return_status
ensure
  @setting.clear
end

#save_novel_data(filename, object) ⇒ Object

小説データの格納ディレクトリに保存



1025
1026
1027
1028
1029
1030
1031
1032
# File 'lib/downloader.rb', line 1025

def save_novel_data(filename, object)
  path = File.join(get_novel_data_dir, filename)
  dir_path = File.dirname(path)
  unless File.exists?(dir_path)
    FileUtils.mkdir_p(dir_path)
  end
  File.write(path, YAML.dump(object))
end

#save_raw_data(raw_data, subtitle_info, ext = ".txt") ⇒ Object

テキストデータの生データを保存



954
955
956
957
958
959
# File 'lib/downloader.rb', line 954

def save_raw_data(raw_data, subtitle_info, ext = ".txt")
  index = subtitle_info["index"]
  file_subtitle = subtitle_info["file_subtitle"]
  path = File.join(get_raw_dir, "#{index} #{file_subtitle}#{ext}")
  File.write(path, raw_data)
end

#sections_download_and_save(subtitles) ⇒ Object

小説本文をまとめてダウンロードして保存

subtitles にダウンロードしたいものをまとめた subtitle info を渡す



787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
# File 'lib/downloader.rb', line 787

def sections_download_and_save(subtitles)
  max = subtitles.count
  return if max == 0
  puts ("<bold><green>" + TermColor.escape("ID:#{@id} #{get_title} のDL開始") + "</green></bold>").termcolor
  save_least_one = false
  subtitles.each_with_index do |subtitle_info, i|
    index, subtitle, file_subtitle, chapter = %w(index subtitle file_subtitle chapter).map { |k|
                                                subtitle_info[k]
                                              }
    unless chapter.empty?
      puts "#{chapter}"
    end
    if get_novel_type == NOVEL_TYPE_SERIES
      if index.to_s.length <= DISPLAY_LIMIT_DIGITS
        # indexの数字がでかいと見た目がみっともないので特定の桁以内だけ表示する
        print "#{index}部分 "
      end
    else
      print "短編 "
    end
    print "#{subtitle} (#{i+1}/#{max})"
    info = subtitle_info.dup
    info["element"] = a_section_download(subtitle_info)
    section_file_name = "#{info["index"]} #{info["file_subtitle"]}.yaml"
    section_file_relative_path = File.join(SECTION_SAVE_DIR_NAME, section_file_name)
    if File.exists?(File.join(get_novel_data_dir, section_file_relative_path))
      if @force
        if different_section?(section_file_relative_path, info)
          print " (更新あり)"
          move_to_cache_dir(section_file_relative_path)
        end
      else
        move_to_cache_dir(section_file_relative_path)
      end
    else
      if !@from_download || (@from_download && @force)
        print " <bold><magenta>(新着)</magenta></bold>".termcolor
      end
      @new_arrivals = true
    end
    save_novel_data(section_file_relative_path, info)
    save_least_one = true
    puts
  end
  remove_cache_dir unless save_least_one
end

#series_novel?Boolean

連載小説かどうか調べる

Returns:

  • (Boolean)


552
553
554
# File 'lib/downloader.rb', line 552

def series_novel?
  get_novel_type == NOVEL_TYPE_SERIES
end

#sleep_for_downloadObject



856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
# File 'lib/downloader.rb', line 856

def sleep_for_download
  if Time.now - @@__last_download_time > @@max_steps_wait_time
    @@__wait_counter = 0
  end
  if @download_wait_steps > 0 && @@__wait_counter % @download_wait_steps == 0 \
    && @@__wait_counter >= @download_wait_steps
    # MEMO:
    # 小説家になろうは連続DL規制があるため、ウェイトを入れる必要がある。
    # 10話ごとに規制が入るため、10話ごとにウェイトを挟む。
    # 1話ごとに1秒待機を10回繰り返そうと、11回目に規制が入るため、ウェイトは必ず必要。
    sleep(@@max_steps_wait_time)
  else
    sleep(@@interval_sleep_time) if @@__wait_counter > 0
  end
  @@__wait_counter += 1
  @@__last_download_time = Time.now
end

#slice_introduction(lines) ⇒ Object



984
985
986
987
988
989
990
991
992
# File 'lib/downloader.rb', line 984

def slice_introduction(lines)
  lines.each_with_index do |line, lineno|
    if line =~ ConverterBase::AUTHOR_INTRODUCTION_SPLITTER
      lines.slice!(lineno, 1)
      return lines.slice!(0...lineno).join("\n")
    end
  end
  ""
end

#slice_postscript(lines) ⇒ Object



994
995
996
997
998
999
1000
1001
1002
# File 'lib/downloader.rb', line 994

def slice_postscript(lines)
  lines.each_with_index do |line, lineno|
    if line =~ ConverterBase::AUTHOR_POSTSCRIPT_SPLITTER
      lines.slice!(lineno, 1)
      return lines.slice!(lineno..-1).join("\n")
    end
  end
  ""
end

#start_downloadObject

ダウンロードを処理本体を起動



332
333
334
335
336
337
338
339
# File 'lib/downloader.rb', line 332

def start_download
  @status = run_download
  OpenStruct.new(
    :id => @id,
    :new_arrivals => @new_arrivals,
    :status => @status
    ).freeze
end

#update_body_check(old_subtitles, latest_subtitles) ⇒ Object

本文更新チェック

更新された subtitle だけまとまった配列を返す



666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
# File 'lib/downloader.rb', line 666

def update_body_check(old_subtitles, latest_subtitles)
  strong_update = Inventory.load("local_setting", :local)["update.strong"]
  latest_subtitles.select do |latest|
    index = latest["index"]
    index_in_old_toc = __search_index_in_subtitles(old_subtitles, index)
    next true unless index_in_old_toc
    old = old_subtitles[index_in_old_toc]
    # タイトルチェック
    if old["subtitle"] != latest["subtitle"]
      next true
    end
    # 章チェック
    if old["chapter"] != latest["chapter"]
      next true
    end
    # 更新日チェック
    # subdate : 初稿投稿日(Arcadiaでは改稿日)
    # subupdate : 改稿日
    old_subdate = old["subdate"]
    latest_subdate = latest["subdate"]
    old_subupdate = old["subupdate"]
    latest_subupdate = latest["subupdate"]
    # oldにsubupdateがなくても、latestのほうにsubupdateがある場合もある
    old_subupdate = old_subdate if latest_subupdate && !old_subupdate
    different_check = nil
    latest["download_time"] = old["download_time"]
    if strong_update
       = __strdate_to_ymd(get_section_file_timestamp(old, latest))
      section_file_name = "#{index} #{old["file_subtitle"]}.yaml"
      section_file_relative_path = File.join(SECTION_SAVE_DIR_NAME, section_file_name)
      different_check = -> {
        latest_info_dummy = latest.dup
        latest_info_dummy["element"] = a_section_download(latest)
        deffer = different_section?(section_file_relative_path, latest_info_dummy)
        unless deffer
          # 差分がある場合はこのあと保存されて更新されるので、差分がない場合のみ
          # タイムスタンプを更新しておく
          now = Time.now
          File.utime(now, now, File.join(get_novel_data_dir, section_file_relative_path))
        end
        deffer
      }
    end
    if old_subupdate && latest_subupdate
      if old_subupdate == ""
        next latest_subupdate != ""
      end
      if strong_update
        if __strdate_to_ymd(old_subupdate) == 
          next different_check.call
        end
      end
      latest_subupdate > old_subupdate
    else
      if strong_update
        if __strdate_to_ymd(old_subdate) == 
          next different_check.call
        end
      end
      latest_subdate > old_subdate
    end
  end
end

#update_databaseObject

データベース更新



491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
# File 'lib/downloader.rb', line 491

def update_database
  data = {
    "id" => @id,
    "author" => @setting["author"],
    "title" => get_title,
    "file_title" => get_file_title,
    "toc_url" => @setting["toc_url"],
    "sitename" => @setting["name"],
    "novel_type" => get_novel_type,
    "end" => novel_end?,
    "last_update" => Time.now,
    "new_arrivals_date" => (@new_arrivals ? Time.now : @@database[@id]["new_arrivals_date"]),
  }
  if @@database[@id]
    @@database[@id].merge!(data)
  else
    @@database[@id] = data
  end
  @@database.save_database
end