質問編集履歴
2
改善
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -143,3 +143,63 @@
|
|
|
143
143
|
|
|
144
144
|
|
|
145
145
|
```
|
|
146
|
+
|
|
147
|
+
|
|
148
|
+
|
|
149
|
+
#成功
|
|
150
|
+
|
|
151
|
+
上記のコードだと`result-cassette__item`に入っている`<li>`を全て取得していたので、数が多くエラーの原因になっていたと思います。
|
|
152
|
+
|
|
153
|
+
クラス名を指定すると欲しいものだけ取得する事ができました。
|
|
154
|
+
|
|
155
|
+
|
|
156
|
+
|
|
157
|
+
もっと簡単な方法があれば教えていただけると幸いです。
|
|
158
|
+
|
|
159
|
+
```python
|
|
160
|
+
|
|
161
|
+
def main():
|
|
162
|
+
|
|
163
|
+
try:
|
|
164
|
+
|
|
165
|
+
options = Options()
|
|
166
|
+
|
|
167
|
+
options.binary_location = '/Applications/Chromium.app/Contents/MacOS/Chromium'
|
|
168
|
+
|
|
169
|
+
options.add_argument('--headless')
|
|
170
|
+
|
|
171
|
+
|
|
172
|
+
|
|
173
|
+
driver = webdriver.Chrome(options=options)
|
|
174
|
+
|
|
175
|
+
driver.get("https://r.gnavi.co.jp/area/hokkaido/rs/")
|
|
176
|
+
|
|
177
|
+
sleep(5)
|
|
178
|
+
|
|
179
|
+
parentElement = driver.find_elements_by_class_name("result-cassette__wrapper")[1].find_elements_by_class_name('result-cassette__item')
|
|
180
|
+
|
|
181
|
+
sleep(5)
|
|
182
|
+
|
|
183
|
+
for i in parentElement:
|
|
184
|
+
|
|
185
|
+
sleep(5)
|
|
186
|
+
|
|
187
|
+
li_links = i.find_element_by_tag_name('a').get_attribute('href')
|
|
188
|
+
|
|
189
|
+
print(li_links)
|
|
190
|
+
|
|
191
|
+
driver.close()
|
|
192
|
+
|
|
193
|
+
except:
|
|
194
|
+
|
|
195
|
+
traceback.print_exc()
|
|
196
|
+
|
|
197
|
+
driver.quit()
|
|
198
|
+
|
|
199
|
+
|
|
200
|
+
|
|
201
|
+
main()
|
|
202
|
+
|
|
203
|
+
|
|
204
|
+
|
|
205
|
+
```
|
1
追記
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -91,3 +91,55 @@
|
|
|
91
91
|
|
|
92
92
|
|
|
93
93
|
```
|
|
94
|
+
|
|
95
|
+
#追記
|
|
96
|
+
|
|
97
|
+
```python
|
|
98
|
+
|
|
99
|
+
def main():
|
|
100
|
+
|
|
101
|
+
try:
|
|
102
|
+
|
|
103
|
+
options = Options()
|
|
104
|
+
|
|
105
|
+
options.binary_location = '/Applications/Chromium.app/Contents/MacOS/Chromium'
|
|
106
|
+
|
|
107
|
+
options.add_argument('--headless')
|
|
108
|
+
|
|
109
|
+
|
|
110
|
+
|
|
111
|
+
driver = webdriver.Chrome(options=options)
|
|
112
|
+
|
|
113
|
+
driver.get("https://r.gnavi.co.jp/area/hokkaido/rs/")
|
|
114
|
+
|
|
115
|
+
sleep(5)
|
|
116
|
+
|
|
117
|
+
parentElement = driver.find_elements_by_class_name("result-cassette__list")[1].find_elements_by_tag_name('li')
|
|
118
|
+
|
|
119
|
+
sleep(5)
|
|
120
|
+
|
|
121
|
+
print(parentElement)
|
|
122
|
+
|
|
123
|
+
for i in parentElement:
|
|
124
|
+
|
|
125
|
+
sleep(5)
|
|
126
|
+
|
|
127
|
+
li_links = i.find_element_by_tag_name('a').get_attribute('href')
|
|
128
|
+
|
|
129
|
+
print(li_links)
|
|
130
|
+
|
|
131
|
+
driver.close()
|
|
132
|
+
|
|
133
|
+
except:
|
|
134
|
+
|
|
135
|
+
traceback.print_exc()
|
|
136
|
+
|
|
137
|
+
driver.quit()
|
|
138
|
+
|
|
139
|
+
|
|
140
|
+
|
|
141
|
+
main()
|
|
142
|
+
|
|
143
|
+
|
|
144
|
+
|
|
145
|
+
```
|