質問編集履歴
3
追加質問の自己解決
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -62,6 +62,14 @@
|
|
|
62
62
|
|
|
63
63
|
|
|
64
64
|
|
|
65
|
+
⇛
|
|
66
|
+
|
|
67
|
+
「f = open("./static/"+os.path.basename(resource), "wb")」
|
|
68
|
+
|
|
69
|
+
にする事で解決できました
|
|
70
|
+
|
|
71
|
+
|
|
72
|
+
|
|
65
73
|
# web_crawler.py
|
|
66
74
|
|
|
67
75
|
|
2
パス修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -62,14 +62,22 @@
|
|
|
62
62
|
|
|
63
63
|
|
|
64
64
|
|
|
65
|
+
# web_crawler.py
|
|
66
|
+
|
|
67
|
+
|
|
68
|
+
|
|
69
|
+
```
|
|
70
|
+
|
|
65
|
-
|
|
71
|
+
python3 web_crawler.py "https://search.yahoo.co.jp/image/search?ei=UTF-8&fr=sfp_as&aq=-1&oq=&ts=1609&p=%E8%B5%B0%E3%82%8C%EF%BC%81
|
|
66
72
|
|
|
67
73
|
%E3%80%80%E3%82%B3%E3%83%BC%E3%83%89%E5%AD%A6%E5%9C%92&meta=vc%3D" .jpeg,.jpg
|
|
68
74
|
|
|
69
|
-
|
|
70
|
-
|
|
71
75
|
```
|
|
72
76
|
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
```
|
|
80
|
+
|
|
73
81
|
#-*- coding:utf-8 -*-
|
|
74
82
|
|
|
75
83
|
|
1
追加質問の為
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -37,3 +37,323 @@
|
|
|
37
37
|
pip3 freeze | grep beautifulsoup
|
|
38
38
|
|
|
39
39
|
beautifulsoup4==4.5.3
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
【追加質問です。】
|
|
46
|
+
|
|
47
|
+
上記は解決しました。
|
|
48
|
+
|
|
49
|
+
|
|
50
|
+
|
|
51
|
+
下記を実行するとプログラムが置かれたフォルダ直下に保存される為、
|
|
52
|
+
|
|
53
|
+
f = open(os.path.basename("./static/"+resource), "wb")
|
|
54
|
+
|
|
55
|
+
と書き換えれば指定ディレクトリに保存できる考えたのですが
|
|
56
|
+
|
|
57
|
+
うまく行きませんでした。
|
|
58
|
+
|
|
59
|
+
|
|
60
|
+
|
|
61
|
+
アドバイスお願いします
|
|
62
|
+
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
# python3 web_crawler.py "https://search.yahoo.co.jp/image/search?ei=UTF-8&fr=sfp_as&aq=-1&oq=&ts=1609&p=%E8%B5%B0%E3%82%8C%EF%BC%81
|
|
66
|
+
|
|
67
|
+
%E3%80%80%E3%82%B3%E3%83%BC%E3%83%89%E5%AD%A6%E5%9C%92&meta=vc%3D" .jpeg,.jpg
|
|
68
|
+
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
#-*- coding:utf-8 -*-
|
|
74
|
+
|
|
75
|
+
|
|
76
|
+
|
|
77
|
+
import os
|
|
78
|
+
|
|
79
|
+
import sys
|
|
80
|
+
|
|
81
|
+
import time
|
|
82
|
+
|
|
83
|
+
import bs4
|
|
84
|
+
|
|
85
|
+
import urllib.request
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
def crawring(url, extensions):
|
|
90
|
+
|
|
91
|
+
"""
|
|
92
|
+
|
|
93
|
+
Content:
|
|
94
|
+
|
|
95
|
+
クローリング
|
|
96
|
+
|
|
97
|
+
Param:
|
|
98
|
+
|
|
99
|
+
url: クローリングするURL
|
|
100
|
+
|
|
101
|
+
extensions: 取得するリソースの拡張子(list)
|
|
102
|
+
|
|
103
|
+
"""
|
|
104
|
+
|
|
105
|
+
# 指定したURLのHTMLを取得
|
|
106
|
+
|
|
107
|
+
html = get_html_string(url)
|
|
108
|
+
|
|
109
|
+
if len(html) < 1:
|
|
110
|
+
|
|
111
|
+
print("HTMLが取得できませんでした。")
|
|
112
|
+
|
|
113
|
+
print("URLを確認してください。")
|
|
114
|
+
|
|
115
|
+
sys.exit(1)
|
|
116
|
+
|
|
117
|
+
|
|
118
|
+
|
|
119
|
+
# リソース取得
|
|
120
|
+
|
|
121
|
+
get_resource(html, extensions)
|
|
122
|
+
|
|
123
|
+
|
|
124
|
+
|
|
125
|
+
def get_resource(html, extensions):
|
|
126
|
+
|
|
127
|
+
"""
|
|
128
|
+
|
|
129
|
+
Content:
|
|
130
|
+
|
|
131
|
+
リソース取得
|
|
132
|
+
|
|
133
|
+
Param
|
|
134
|
+
|
|
135
|
+
html: HTML
|
|
136
|
+
|
|
137
|
+
extensions 拡張子のリスト
|
|
138
|
+
|
|
139
|
+
"""
|
|
140
|
+
|
|
141
|
+
|
|
142
|
+
|
|
143
|
+
resource_list = []
|
|
144
|
+
|
|
145
|
+
|
|
146
|
+
|
|
147
|
+
soup = bs4.BeautifulSoup(html,'lxml')
|
|
148
|
+
|
|
149
|
+
for a_tag in soup.find_all("a"):
|
|
150
|
+
|
|
151
|
+
href_str = a_tag.get("href")
|
|
152
|
+
|
|
153
|
+
try:
|
|
154
|
+
|
|
155
|
+
(path, ext) = os.path.splitext(href_str)
|
|
156
|
+
|
|
157
|
+
if ext in extensions:
|
|
158
|
+
|
|
159
|
+
resource_list.append(href_str)
|
|
160
|
+
|
|
161
|
+
except:
|
|
162
|
+
|
|
163
|
+
pass
|
|
164
|
+
|
|
165
|
+
|
|
166
|
+
|
|
167
|
+
resource_list = sorted(set(resource_list), key=resource_list.index)
|
|
168
|
+
|
|
169
|
+
for resource in resource_list:
|
|
170
|
+
|
|
171
|
+
try:
|
|
172
|
+
|
|
173
|
+
print("download ---> [%s]" % os.path.basename(resource))
|
|
174
|
+
|
|
175
|
+
request = urllib.request.urlopen(resource)
|
|
176
|
+
|
|
177
|
+
f = open(os.path.basename("./static/"+resource), "wb")
|
|
178
|
+
|
|
179
|
+
f.write(request.read())
|
|
180
|
+
|
|
181
|
+
except Exception as e:
|
|
182
|
+
|
|
183
|
+
print(e)
|
|
184
|
+
|
|
185
|
+
print("download failed ... [%s]" % os.path.basename(resource))
|
|
186
|
+
|
|
187
|
+
finally:
|
|
188
|
+
|
|
189
|
+
time.sleep(3)
|
|
190
|
+
|
|
191
|
+
|
|
192
|
+
|
|
193
|
+
def get_html_string(url):
|
|
194
|
+
|
|
195
|
+
"""
|
|
196
|
+
|
|
197
|
+
Content:
|
|
198
|
+
|
|
199
|
+
HTML取得
|
|
200
|
+
|
|
201
|
+
Param:
|
|
202
|
+
|
|
203
|
+
url HTMLを取得するURL
|
|
204
|
+
|
|
205
|
+
"""
|
|
206
|
+
|
|
207
|
+
decoded_html = ""
|
|
208
|
+
|
|
209
|
+
|
|
210
|
+
|
|
211
|
+
# HTMLを取得
|
|
212
|
+
|
|
213
|
+
try:
|
|
214
|
+
|
|
215
|
+
request = urllib.request.urlopen(url)
|
|
216
|
+
|
|
217
|
+
html = request.read()
|
|
218
|
+
|
|
219
|
+
except:
|
|
220
|
+
|
|
221
|
+
return decoded_html
|
|
222
|
+
|
|
223
|
+
|
|
224
|
+
|
|
225
|
+
# エンコードを取得
|
|
226
|
+
|
|
227
|
+
enc = check_encoding(html)
|
|
228
|
+
|
|
229
|
+
if enc == None:
|
|
230
|
+
|
|
231
|
+
return decoded_html
|
|
232
|
+
|
|
233
|
+
|
|
234
|
+
|
|
235
|
+
# HTMLをデコード
|
|
236
|
+
|
|
237
|
+
decoded_html = html.decode(enc)
|
|
238
|
+
|
|
239
|
+
|
|
240
|
+
|
|
241
|
+
return decoded_html
|
|
242
|
+
|
|
243
|
+
|
|
244
|
+
|
|
245
|
+
def check_encoding(byte_string):
|
|
246
|
+
|
|
247
|
+
"""
|
|
248
|
+
|
|
249
|
+
Content:
|
|
250
|
+
|
|
251
|
+
文字コード確認
|
|
252
|
+
|
|
253
|
+
Param:
|
|
254
|
+
|
|
255
|
+
byte_string: バイト文字列
|
|
256
|
+
|
|
257
|
+
"""
|
|
258
|
+
|
|
259
|
+
encoding_list = ["utf-8", "utf_8", "euc_jp",
|
|
260
|
+
|
|
261
|
+
"euc_jis_2004", "euc_jisx0213", "shift_jis",
|
|
262
|
+
|
|
263
|
+
"shift_jis_2004","shift_jisx0213", "iso2022jp",
|
|
264
|
+
|
|
265
|
+
"iso2022_jp_1", "iso2022_jp_2", "iso2022_jp_3",
|
|
266
|
+
|
|
267
|
+
"iso2022_jp_ext","latin_1", "ascii"]
|
|
268
|
+
|
|
269
|
+
|
|
270
|
+
|
|
271
|
+
for enc in encoding_list:
|
|
272
|
+
|
|
273
|
+
try:
|
|
274
|
+
|
|
275
|
+
byte_string.decode(enc)
|
|
276
|
+
|
|
277
|
+
break
|
|
278
|
+
|
|
279
|
+
except:
|
|
280
|
+
|
|
281
|
+
enc = None
|
|
282
|
+
|
|
283
|
+
|
|
284
|
+
|
|
285
|
+
return enc
|
|
286
|
+
|
|
287
|
+
|
|
288
|
+
|
|
289
|
+
|
|
290
|
+
|
|
291
|
+
def check_args():
|
|
292
|
+
|
|
293
|
+
"""
|
|
294
|
+
|
|
295
|
+
Content:
|
|
296
|
+
|
|
297
|
+
起動引数確認
|
|
298
|
+
|
|
299
|
+
"""
|
|
300
|
+
|
|
301
|
+
if len(sys.argv) == 3:
|
|
302
|
+
|
|
303
|
+
return True
|
|
304
|
+
|
|
305
|
+
else:
|
|
306
|
+
|
|
307
|
+
return False
|
|
308
|
+
|
|
309
|
+
|
|
310
|
+
|
|
311
|
+
def print_usage():
|
|
312
|
+
|
|
313
|
+
print("Usage: %s URL Extensions" % __file__)
|
|
314
|
+
|
|
315
|
+
print("URLにはクロールしたいウェブサイトのアドレスを指定してください。")
|
|
316
|
+
|
|
317
|
+
print("Extensionsにはクロールしたときに取得するファイルの拡張子を指定してください。")
|
|
318
|
+
|
|
319
|
+
print("Extensionsはカンマ区切りで複数指定できます。")
|
|
320
|
+
|
|
321
|
+
|
|
322
|
+
|
|
323
|
+
def main():
|
|
324
|
+
|
|
325
|
+
"""
|
|
326
|
+
|
|
327
|
+
Content:
|
|
328
|
+
|
|
329
|
+
main
|
|
330
|
+
|
|
331
|
+
"""
|
|
332
|
+
|
|
333
|
+
# 引数確認
|
|
334
|
+
|
|
335
|
+
if check_args() is False:
|
|
336
|
+
|
|
337
|
+
print_usage()
|
|
338
|
+
|
|
339
|
+
sys.exit(1)
|
|
340
|
+
|
|
341
|
+
|
|
342
|
+
|
|
343
|
+
url = sys.argv[1]
|
|
344
|
+
|
|
345
|
+
extensions = sys.argv[2].split(",")
|
|
346
|
+
|
|
347
|
+
|
|
348
|
+
|
|
349
|
+
# クロール開始
|
|
350
|
+
|
|
351
|
+
crawring(url, extensions)
|
|
352
|
+
|
|
353
|
+
|
|
354
|
+
|
|
355
|
+
if __name__ == "__main__":
|
|
356
|
+
|
|
357
|
+
main()
|
|
358
|
+
|
|
359
|
+
```
|