質問編集履歴
1
vbaコードを更新しました。 divタグ内にあるdata-asinの値の抽出方法を教えてください。宜しくお願い致します。
title
CHANGED
File without changes
|
body
CHANGED
@@ -4,7 +4,7 @@
|
|
4
4
|
一通りググってみましたが、わからず行き詰っております。
|
5
5
|
よろしくお願いします。
|
6
6
|
|
7
|
-
vba
|
7
|
+
vbaスクレイピングで、
|
8
8
|
amazon検索一覧URLから、商品のASINだけを抽出したい。ページおくりで、検索の最後まで、一気に抽出したい。
|
9
9
|
(参考:https://www.amazon.co.jp/s?bbn=170092011&rh=n%3A52374051%2Cn%3A%2152391051%2Cn%3A5267100051%2Cn%3A170040011%2Cn%3A170092011%2Cp_76%3A2227292051&dc&fst=as%3Aoff&qid=1586994278&rnid=2227291051&ref=lp_170092011_nr_p_76_0
|
10
10
|
|
@@ -14,36 +14,61 @@
|
|
14
14
|
参考https://excel-ubara.com/excelvba4/EXCEL_VBA_401.html#にして、
|
15
15
|
下記コードまで記述しました。
|
16
16
|
|
17
|
-
|
18
|
-
Sub
|
17
|
+
Sub testIE()
|
18
|
+
Dim I As Integer
|
19
|
+
Dim objIE As InternetExplorer 'IEオブジェクトを準備
|
20
|
+
Set objIE = CreateObject("Internetexplorer.Application") '新しいIEオブジェクトを作成してセット
|
19
21
|
|
20
|
-
|
21
|
-
Driver.Start "chrome"
|
22
|
-
Driver.Get "https://www.amazon.co.jp/s?bbn=170092011&rh=n%3A52374051%2Cn%3A%2152391051%2Cn%3A5267100051%2Cn%3A170040011%2Cn%3A170092011%2Cp_76%3A2227292051&dc&fst=as%3Aoff&qid=1586994278&rnid=2227291051&ref=lp_170092011_nr_p_76_0"
|
23
|
-
Driver.Get "/"
|
22
|
+
objIE.Visible = True 'IEを表示
|
24
23
|
|
24
|
+
I = 2
|
25
|
+
Do
|
26
|
+
If Range("A" & I) = "" Then Exit Do
|
25
|
-
|
27
|
+
If I > 100 Then Exit Do
|
28
|
+
|
29
|
+
objIE.navigate Range("A" & I) 'IEでURLを開く
|
30
|
+
|
31
|
+
Call WaitResponse(objIE) '読み込み待ち
|
26
32
|
|
27
|
-
Dim txt As String
|
28
|
-
|
33
|
+
Dim objDoc As HTMLElementCollection
|
29
|
-
Debug.Print txt
|
30
|
-
Driver.Close
|
31
|
-
|
34
|
+
Set objDoc = objIE.document
|
32
|
-
|
35
|
+
Dim element As IHTMLElement
|
36
|
+
For Each element In objDoc.getElementsByClassName("sg-col-4-of-24 sg-col-4-of-12 sg-col-4-of-36 s-result-item s-asin sg-col-4-of-28 sg-col-4-of-16 sg-col sg-col-4-of-20 sg-col-4-of-32")
|
37
|
+
Debug.Print element. 'わからない部分!!!!!
|
38
|
+
|
39
|
+
|
40
|
+
|
41
|
+
Next element
|
42
|
+
I = I + 1
|
43
|
+
Loop
|
44
|
+
|
45
|
+
Call WaitResponse(objIE)
|
33
46
|
End Sub
|
34
47
|
|
35
48
|
|
36
49
|
|
37
|
-
肝心のASIN抽出処理部分ですが、HTMLでASINコードが入っているのが href要素かと思い、様々な方法で記述してみましたが、エラーがでます。
|
38
|
-
|
50
|
+
Sub WaitResponse(objIE As Object)
|
51
|
+
Do While objIE.Busy = True Or objIE.readyState < READYSTATE_COMPLETE '読み込み待ち
|
39
|
-
|
52
|
+
DoEvents
|
53
|
+
Loop
|
54
|
+
End Sub
|
40
55
|
|
41
56
|
|
42
|
-
|
57
|
+
|
58
|
+
|
59
|
+
|
60
|
+
肝心のASIN抽出処理部分ですが、HTMLでASINコードが入っているのが
|
61
|
+
下記divタグ内のdata-asin=にあるので、getElementByclassNameで取得をしようとしているのですが、
|
62
|
+
data-asin=””にあるASINコードはどのようにすると抽出できますか??
|
63
|
+
宜しくお願い致します。
|
64
|
+
|
65
|
+
<div ****data-asin="B07HVKS8DM"**** data-index="9" data-uuid="644bd227-abf2-4d00-9fc9-6b8be26f583b" class="sg-col-4-of-24 sg-col-4-of-12 sg-col-4-of-36 s-result-item s-asin sg-col-4-of-28 sg-col-4-of-16 sg-col sg-col-4-of-20 sg-col-4-of-32 __web-inspector-hide-shortcut__" data-cel-widget="search_result_9"><div class="sg-col-inner">
|
43
66
|
|
44
67
|
|
45
68
|
|
69
|
+
|
70
|
+
|
46
|
-
<span cel_widget_id="SEARCH_RESULTS-SEARCH_RESULTS" class="celwidget slot=SEARCH_RESULTS template=SEARCH_RESULTS widgetId=search-results index=
|
71
|
+
<span cel_widget_id="SEARCH_RESULTS-SEARCH_RESULTS" class="celwidget slot=SEARCH_RESULTS template=SEARCH_RESULTS widgetId=search-results index=9" data-cel-widget="SEARCH_RESULTS-SEARCH_RESULTS">
|
47
72
|
|
48
73
|
|
49
74
|
|
@@ -72,16 +97,175 @@
|
|
72
97
|
|
73
98
|
|
74
99
|
|
75
|
-
<span data-component-type="s-product-image" class="rush-component" data-component-id="
|
100
|
+
<span data-component-type="s-product-image" class="rush-component" data-component-id="17">
|
76
101
|
|
77
|
-
<a class="a-link-normal" target="_blank" href="/
|
102
|
+
<a class="a-link-normal" target="_blank" href="/%E6%A9%9F%E5%8B%95%E6%88%A6%E5%A3%AB%E3%82%AC%E3%83%B3%E3%83%80%E3%83%A0-MS-09-MS-09R-%E3%83%AA%E3%83%83%E3%82%AF%E3%83%BB%E3%83%89%E3%83%A0-144%E3%82%B9%E3%82%B1%E3%83%BC%E3%83%AB/dp/B07HVKS8DM/ref=sr_1_10?dchild=1&fst=as%3Aoff&qid=1586877663&refinements=p_n_feature_fifteen_browse-bin%3A3307612051%2Cp_76%3A2227292051&rnid=2227291051&rps=1&s=hobby&sr=1-10">
|
78
103
|
<div class="a-section aok-relative s-image-square-aspect">
|
79
104
|
|
80
105
|
|
81
106
|
|
82
|
-
<img src="https://m.media-amazon.com/images/I/
|
107
|
+
<img src="https://m.media-amazon.com/images/I/61tIVRyF7qL._AC_UL320_ML3_.jpg" class="s-image" alt="HGUC 機動戦士ガンダム MS-09 ドム/MS-09R リック・ドム 1/144スケール プラモデル" srcset="https://m.media-amazon.com/images/I/61tIVRyF7qL._AC_UL320_ML3_.jpg 1x, https://m.media-amazon.com/images/I/61tIVRyF7qL._AC_UL480_FMwebp_QL65_.jpg 1.5x, https://m.media-amazon.com/images/I/61tIVRyF7qL._AC_UL640_FMwebp_QL65_.jpg 2x, https://m.media-amazon.com/images/I/61tIVRyF7qL._AC_UL800_FMwebp_QL65_.jpg 2.5x, https://m.media-amazon.com/images/I/61tIVRyF7qL._AC_UL960_FMwebp_QL65_.jpg 3x" data-image-index="9" data-image-load="" data-image-latency="s-product-image" data-image-source-density="1">
|
83
108
|
|
84
109
|
|
85
110
|
</div>
|
86
111
|
</a>
|
87
|
-
</span>
|
112
|
+
</span>
|
113
|
+
|
114
|
+
|
115
|
+
|
116
|
+
|
117
|
+
|
118
|
+
<div class="a-section a-spacing-none a-spacing-top-small">
|
119
|
+
|
120
|
+
|
121
|
+
|
122
|
+
|
123
|
+
|
124
|
+
<h2 class="a-size-mini a-spacing-none a-color-base s-line-clamp-4">
|
125
|
+
|
126
|
+
|
127
|
+
|
128
|
+
|
129
|
+
|
130
|
+
|
131
|
+
|
132
|
+
<a class="a-link-normal a-text-normal" target="_blank" href="/%E6%A9%9F%E5%8B%95%E6%88%A6%E5%A3%AB%E3%82%AC%E3%83%B3%E3%83%80%E3%83%A0-MS-09-MS-09R-%E3%83%AA%E3%83%83%E3%82%AF%E3%83%BB%E3%83%89%E3%83%A0-144%E3%82%B9%E3%82%B1%E3%83%BC%E3%83%AB/dp/B07HVKS8DM/ref=sr_1_10?dchild=1&fst=as%3Aoff&qid=1586877663&refinements=p_n_feature_fifteen_browse-bin%3A3307612051%2Cp_76%3A2227292051&rnid=2227291051&rps=1&s=hobby&sr=1-10">
|
133
|
+
|
134
|
+
|
135
|
+
|
136
|
+
<span class="a-size-base-plus a-color-base a-text-normal">HGUC 機動戦士ガンダム MS-09 ドム/MS-09R リック・ドム 1/144スケール プラモデル</span>
|
137
|
+
|
138
|
+
|
139
|
+
|
140
|
+
|
141
|
+
</a>
|
142
|
+
|
143
|
+
|
144
|
+
</h2>
|
145
|
+
|
146
|
+
</div>
|
147
|
+
|
148
|
+
<div class="a-section a-spacing-none a-spacing-top-micro">
|
149
|
+
<div class="a-row a-size-small">
|
150
|
+
|
151
|
+
|
152
|
+
<span aria-label="5つ星のうち4.5">
|
153
|
+
|
154
|
+
|
155
|
+
|
156
|
+
|
157
|
+
|
158
|
+
|
159
|
+
|
160
|
+
|
161
|
+
<span class="a-declarative" data-action="a-popover" data-a-popover="{"max-width":"700","closeButton":false,"position":"triggerBottom","url":"/review/widgets/average-customer-review/popover/ref=acr_search__popover?ie=UTF8&asin=B07HVKS8DM&ref=acr_search__popover&contextId=search"}">
|
162
|
+
|
163
|
+
<a href="javascript:void(0)" class="a-popover-trigger a-declarative"><i class="a-icon a-icon-star-small a-star-small-4-5 aok-align-bottom"><span class="a-icon-alt">5つ星のうち4.5</span></i><i class="a-icon a-icon-popover"></i></a>
|
164
|
+
</span>
|
165
|
+
|
166
|
+
|
167
|
+
|
168
|
+
|
169
|
+
</span>
|
170
|
+
|
171
|
+
|
172
|
+
|
173
|
+
<span aria-label="36">
|
174
|
+
|
175
|
+
|
176
|
+
|
177
|
+
|
178
|
+
|
179
|
+
<a class="a-link-normal" target="_blank" href="/%E6%A9%9F%E5%8B%95%E6%88%A6%E5%A3%AB%E3%82%AC%E3%83%B3%E3%83%80%E3%83%A0-MS-09-MS-09R-%E3%83%AA%E3%83%83%E3%82%AF%E3%83%BB%E3%83%89%E3%83%A0-144%E3%82%B9%E3%82%B1%E3%83%BC%E3%83%AB/dp/B07HVKS8DM/ref=sr_1_10?dchild=1&fst=as%3Aoff&qid=1586877663&refinements=p_n_feature_fifteen_browse-bin%3A3307612051%2Cp_76%3A2227292051&rnid=2227291051&rps=1&s=hobby&sr=1-10#customerReviews">
|
180
|
+
|
181
|
+
|
182
|
+
|
183
|
+
<span class="a-size-base">36</span>
|
184
|
+
|
185
|
+
|
186
|
+
|
187
|
+
|
188
|
+
</a>
|
189
|
+
|
190
|
+
</span>
|
191
|
+
</div>
|
192
|
+
</div>
|
193
|
+
|
194
|
+
|
195
|
+
|
196
|
+
|
197
|
+
<div class="a-section a-spacing-none a-spacing-top-small">
|
198
|
+
<div class="a-row a-size-base a-color-base"><div class="a-row">
|
199
|
+
|
200
|
+
|
201
|
+
|
202
|
+
|
203
|
+
<a class="a-size-base a-link-normal s-no-hover a-text-normal" target="_blank" href="/%E6%A9%9F%E5%8B%95%E6%88%A6%E5%A3%AB%E3%82%AC%E3%83%B3%E3%83%80%E3%83%A0-MS-09-MS-09R-%E3%83%AA%E3%83%83%E3%82%AF%E3%83%BB%E3%83%89%E3%83%A0-144%E3%82%B9%E3%82%B1%E3%83%BC%E3%83%AB/dp/B07HVKS8DM/ref=sr_1_10?dchild=1&fst=as%3Aoff&qid=1586877663&refinements=p_n_feature_fifteen_browse-bin%3A3307612051%2Cp_76%3A2227292051&rnid=2227291051&rps=1&s=hobby&sr=1-10">
|
204
|
+
|
205
|
+
|
206
|
+
|
207
|
+
<span class="a-price" data-a-size="m" data-a-color="price"><span class="a-offscreen">¥2,480</span><span aria-hidden="true"><span class="a-price-symbol"></span><span class="a-price-whole">¥2,480</span></span></span>
|
208
|
+
|
209
|
+
|
210
|
+
|
211
|
+
|
212
|
+
</a>
|
213
|
+
</div></div>
|
214
|
+
</div>
|
215
|
+
|
216
|
+
|
217
|
+
<div class="a-section a-spacing-none a-spacing-top-micro">
|
218
|
+
<div class="a-row a-size-base a-color-secondary s-align-children-center"><div class="a-row s-align-children-center">
|
219
|
+
|
220
|
+
|
221
|
+
|
222
|
+
|
223
|
+
<span class="aok-inline-block s-image-logo-view">
|
224
|
+
<span class="aok-relative s-icon-text-medium s-prime">
|
225
|
+
<i class="a-icon a-icon-prime a-icon-medium" role="img" aria-label="Amazon プライム"></i>
|
226
|
+
</span>
|
227
|
+
<span>
|
228
|
+
|
229
|
+
</span>
|
230
|
+
</span>
|
231
|
+
|
232
|
+
|
233
|
+
|
234
|
+
<span aria-label="明日中4/16に無料配送">
|
235
|
+
<span class="a-text-bold">明日中4/16</span><span>に無料配送</span>
|
236
|
+
</span>
|
237
|
+
</div></div><div class="a-row a-size-base a-color-secondary">
|
238
|
+
|
239
|
+
|
240
|
+
<span aria-label="残り2点 ご注文はお早めに">
|
241
|
+
<span class="a-color-price">残り2点 ご注文はお早めに</span>
|
242
|
+
</span>
|
243
|
+
</div>
|
244
|
+
</div>
|
245
|
+
|
246
|
+
|
247
|
+
|
248
|
+
<div class="a-section a-spacing-none a-spacing-top-mini">
|
249
|
+
<div class="a-row a-size-base a-color-secondary"><span class="a-size-base a-color-secondary">こちらからもご購入いただけます</span><br><span class="a-color-price">¥1,683</span><span class="a-letter-space"></span>
|
250
|
+
|
251
|
+
|
252
|
+
|
253
|
+
|
254
|
+
<a class="a-link-normal" href="/gp/offer-listing/B07HVKS8DM/ref=sr_1_10?rnid=2227291051&s=hobby&rps=1&fst=as%3Aoff&qid=1586877663&refinements=p_n_feature_fifteen_browse-bin%3A3307612051%2Cp_76%3A2227292051&sr=1-10&dchild=1">
|
255
|
+
|
256
|
+
|
257
|
+
|
258
|
+
(10点の新品)
|
259
|
+
|
260
|
+
|
261
|
+
</a>
|
262
|
+
</div>
|
263
|
+
</div>
|
264
|
+
|
265
|
+
|
266
|
+
</div>
|
267
|
+
</div>
|
268
|
+
|
269
|
+
</span>
|
270
|
+
|
271
|
+
</div></div>
|