Class: Alexandria::BookProviders::ThaliaProvider

Inherits:
WebsiteBasedProvider show all
Includes:
Logging
Defined in:
lib/alexandria/book_providers/thalia.rb

Constant Summary collapse

SITE = 
'http://www.thalia.de'
BASE_SEARCH_URL =

type,term

"#{SITE}/shop/bde_bu_hg_startseite/suche/?%s=%s"

Instance Attribute Summary

Attributes inherited from AbstractProvider

#fullname, #name, #prefs

Instance Method Summary collapse

Methods included from Logging

included, #log

Methods inherited from WebsiteBasedProvider

#html_to_doc, #text_of

Methods inherited from AbstractProvider

#<=>, abstract?, #abstract?, #action_name, #enabled, #reinitialize, #remove, #toggle_enabled, #transport, unabstract, #variable_name

Constructor Details

#initialize ⇒ ThaliaProvider

Returns a new instance of ThaliaProvider.



39
40
41
42
43
 
# File 'lib/alexandria/book_providers/thalia.rb', line 39

def initialize
  super('Thalia', 'Thalia (Germany)')
  # no preferences for the moment
  prefs.read
end

Instance Method Details

#create_search_uri(search_type, search_term) ⇒ Object 



62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
 
# File 'lib/alexandria/book_providers/thalia.rb', line 62

def create_search_uri(search_type, search_term)
  (search_type_code = {
    SEARCH_BY_ISBN => 'sq',
    SEARCH_BY_AUTHORS => 'sa', # Autor
    SEARCH_BY_TITLE => 'st', # Titel
    SEARCH_BY_KEYWORD => 'ssw' # Schlagwort
  }[search_type]) || ''
  search_type_code = CGI.escape(search_type_code)
  search_term_encoded = if search_type == SEARCH_BY_ISBN
                          # search_term_encoded = search_term.as_isbn_13
                          Library.canonicalise_isbn(search_term) # check this!
                        else
                          CGI.escape(search_term)
                        end
  format(BASE_SEARCH_URL, search_type_code, search_term_encoded)
end

#data_from_label(node, label_text) ⇒ Object 



93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/alexandria/book_providers/thalia.rb', line 93

def data_from_label(node, label_text)
  label_node = node % "strong[text()*='#{label_text}']"
  if (item_node = label_node.parent)
    data = ''
    item_node.children.each do |n|
      data += n.to_html if n.text?
    end
    data.strip
  else
    ''
  end
end

#get_book_from_search_result(result) ⇒ Object 



106
107
108
109
110
 
# File 'lib/alexandria/book_providers/thalia.rb', line 106

def get_book_from_search_result(result)
  log.debug { "Fetching book from #{result[:lookup_url]}" }
  html_data = transport.get_response(URI.parse(result[:lookup_url]))
  parse_result_data(html_data.body, 'noisbn', true)
end

#parse_result_data(html, isbn, recursing = false) ⇒ Object 



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
 
# File 'lib/alexandria/book_providers/thalia.rb', line 112

def parse_result_data(html, isbn, recursing = false)
  doc = html_to_doc(html)

  results_divs = doc / 'div.articlePresentationSearchCH'
  unless results_divs.empty?
    if recursing
      # already recursing, avoid doing so endlessly second time
      # around *should* lead to a book description, not a result
      # list
      return
    end
    # ISBN-lookup results in multiple results (trying to be
    # useful, such as for new editions e.g. 9780974514055
    # "Programming Ruby" )
    results = parse_search_result_data(html)
    isbn10 = Library.canonicalise_isbn(isbn)
    # e.g. .../dave_thomas/ISBN0-9745140-5-5/ID6017044.html
    chosen = results.first # fallback!
    results.each do |rslt|
      if rslt[:lookup_url] =~ /\/ISBN(\d+[\d-]*)\//
        if Regexp.last_match[1].delete('-') == isbn10
          chosen = rslt
          break
        end
      end
    end
    html_data = transport.get_response(URI.parse(chosen[:lookup_url]))
    return parse_result_data(html_data.body, isbn, true)
  end

  begin
    if (div = doc % 'div#contentFull')
      title_img = ((div % :h2) / :img).first
      title = title_img['alt']

      # note, the following img also has alt="von Author, Author..."

      if (author_h = doc % 'h3[text()*="Mehr von"]') # "More from..." links
        authors = []
        author_links = author_h.parent / :a
        author_links.each do |a|
          if a['href'] =~ /BUCH\/sa/
            # 'sa' means search author, there may also be 'ssw' (search keyword) links
            authors << a.inner_text[0..-2].strip
            # NOTE stripping the little >> character here...
          end
        end
      end

      item_details = doc % 'ul.itemDataList'
      isbns = []
      isbns << data_from_label(item_details, 'EAN')
      isbns << data_from_label(item_details, 'ISBN')

      year = nil
      date = data_from_label(item_details, 'Erschienen:')
      year = Regexp.last_match[1].to_i if date =~ /([\d]{4})/

      binding = data_from_label(item_details, 'Einband')

      publisher = data_from_label(item_details, 'Erschienen bei:')

      book = Book.new(title, authors, isbns.first,
                      publisher, year, binding)

      image_url = nil
      if (image_link = doc % 'a[@id=itemPicStart]')
        image_url = image_link['href']
      end

      return [book, image_url]

    end
  rescue => ex
    trace = ex.backtrace.join("\n> ")
    log.warn {
      'Failed parsing search results for Thalia ' \
      "#{ex.message} #{trace}"
    }
    raise NoResultsError
  end
end

#parse_search_result_data(html) ⇒ Object 



79
80
81
82
83
84
85
86
87
88
89
90
91
 
# File 'lib/alexandria/book_providers/thalia.rb', line 79

def parse_search_result_data(html)
  doc = html_to_doc(html)
  book_search_results = []
  results_divs = doc / 'div.articlePresentationSearchCH'
  results_divs.each do |div|
    result = {}
    title_link = div % 'div.articleText/h2/a'
    result[:title] = title_link.inner_html
    result[:lookup_url] = title_link['href']
    book_search_results << result
  end
  book_search_results
end

#search(criterion, type) ⇒ Object 



49
50
51
52
53
54
55
56
57
58
59
60
 
# File 'lib/alexandria/book_providers/thalia.rb', line 49

def search(criterion, type)
  req = create_search_uri(type, criterion)
  puts req if $DEBUG
  html_data = transport.get_response(URI.parse(req))
  if type == SEARCH_BY_ISBN
    parse_result_data(html_data.body, criterion)
  else
    results = parse_search_result_data(html_data.body)
    raise NoResultsError if results.empty?
    results.map { |result| get_book_from_search_result(result) }
  end
end

#url(book) ⇒ Object 



45
46
47
 
# File 'lib/alexandria/book_providers/thalia.rb', line 45

def url(book)
  create_search_uri(SEARCH_BY_ISBN, book.isbn)
end