質問編集履歴
2
コードを追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -200,4 +200,76 @@
|
|
|
200
200
|
|
|
201
201
|
|
|
202
202
|
|
|
203
|
-
|
|
203
|
+
追記：以下にRubyのコードを記載いたします。
|
|
204
|
+
|
|
205
|
+
|
|
206
|
+
|
|
207
|
+
```
|
|
208
|
+
|
|
209
|
+
require 'mechanize'
|
|
210
|
+
|
|
211
|
+
|
|
212
|
+
|
|
213
|
+
class Scraping
|
|
214
|
+
|
|
215
|
+
def self.icecream_urls
|
|
216
|
+
|
|
217
|
+
links = [] # 個別ページのリンクを保存する配列
|
|
218
|
+
|
|
219
|
+
agent = Mechanize.new
|
|
220
|
+
|
|
221
|
+
(1..4).each do |i|
|
|
222
|
+
|
|
223
|
+
current_page = agent.get("http://www.morinaga.co.jp/products/list.php?id=030#{i}")
|
|
224
|
+
|
|
225
|
+
elements = current_page.search('.products__list__item a')
|
|
226
|
+
|
|
227
|
+
elements.each do |ele|
|
|
228
|
+
|
|
229
|
+
links << ele.get_attribute('href')
|
|
230
|
+
|
|
231
|
+
end
|
|
232
|
+
|
|
233
|
+
end
|
|
234
|
+
|
|
235
|
+
|
|
236
|
+
|
|
237
|
+
|
|
238
|
+
|
|
239
|
+
links.each do |link| #get_product に引数（個別ページのURL）を渡す
|
|
240
|
+
|
|
241
|
+
get_product('http://www.morinaga.co.jp/products/' + link)
|
|
242
|
+
|
|
243
|
+
end
|
|
244
|
+
|
|
245
|
+
end
|
|
246
|
+
|
|
247
|
+
|
|
248
|
+
|
|
249
|
+
def self.get_product(link) # 個別ページからアイスの情報を取得する
|
|
250
|
+
|
|
251
|
+
agent = Mechanize.new
|
|
252
|
+
|
|
253
|
+
page = agent.get(link)
|
|
254
|
+
|
|
255
|
+
product_name = page.at('.headingType01__txt').inner_text # 商品名
|
|
256
|
+
|
|
257
|
+
image_url = page.at('.products-mainImg img').get_attribute('src') # 商品画像
|
|
258
|
+
|
|
259
|
+
|
|
260
|
+
|
|
261
|
+
serving_size = page.search('dd:nth-child(13)').inner_text # 内容量
|
|
262
|
+
|
|
263
|
+
|
|
264
|
+
|
|
265
|
+
product = Product.where(name: product_name, image_url: image_url, serving_size: serving_size).first_or_initialize
|
|
266
|
+
|
|
267
|
+
|
|
268
|
+
|
|
269
|
+
product.save
|
|
270
|
+
|
|
271
|
+
end
|
|
272
|
+
|
|
273
|
+
end
|
|
274
|
+
|
|
275
|
+
```
|
1
コードの追加
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -172,9 +172,23 @@
|
|
|
172
172
|
|
|
173
173
|
```
|
|
174
174
|
|
|
175
|
-
page.at('.products-detailBox__list dt:nth-child(2) dd').inner_text
|
|
175
|
+
serving_size = page.at('.products-detailBox__list dt:nth-child(2) dd').inner_text
|
|
176
|
-
|
|
176
|
+
|
|
177
|
-
```
|
|
177
|
+
```
|
|
178
|
+
|
|
179
|
+
|
|
180
|
+
|
|
181
|
+
追記：以下のコードもだめでした。
|
|
182
|
+
|
|
183
|
+
|
|
184
|
+
|
|
185
|
+
```
|
|
186
|
+
|
|
187
|
+
serving_size = page.at('dl dt:nth-child(2) dd').inner_text
|
|
188
|
+
|
|
189
|
+
```
|
|
190
|
+
|
|
191
|
+
|
|
178
192
|
|
|
179
193
|
|
|
180
194
|
|