回答編集履歴
1
サンプルコードの貼り付け誤り
test
CHANGED
|
@@ -48,84 +48,46 @@
|
|
|
48
48
|
|
|
49
49
|
|
|
50
50
|
|
|
51
|
+
for link in links:
|
|
52
|
+
|
|
53
|
+
print('-----', link)
|
|
54
|
+
|
|
51
|
-
|
|
55
|
+
r = requests.get(link)
|
|
56
|
+
|
|
57
|
+
soup = BeautifulSoup(r.text,'html.parser')
|
|
58
|
+
|
|
59
|
+
url_list= soup.find_all("a", class_ = "treatment-menu__link")
|
|
60
|
+
|
|
61
|
+
#print(url_list)
|
|
62
|
+
|
|
63
|
+
time.sleep(3)
|
|
52
64
|
|
|
53
65
|
|
|
54
66
|
|
|
55
|
-
for lin
|
|
67
|
+
for i, url in enumerate(url_list):
|
|
68
|
+
|
|
69
|
+
if i > 5:
|
|
70
|
+
|
|
71
|
+
break
|
|
72
|
+
|
|
73
|
+
url = url.get('href')
|
|
74
|
+
|
|
75
|
+
new_url = "https://clinic.beauty.hotpepper.jp" + url
|
|
76
|
+
|
|
77
|
+
print(i, 'new_url', new_url)
|
|
78
|
+
|
|
79
|
+
r = requests.get(new_url)
|
|
80
|
+
|
|
81
|
+
soup = BeautifulSoup(r.text,'html.parser')
|
|
56
82
|
|
|
57
83
|
|
|
58
84
|
|
|
59
|
-
|
|
85
|
+
detail = soup.find(class_ = "l-container")
|
|
60
86
|
|
|
61
|
-
|
|
87
|
+
plan_name = soup.find(class_ = "menu-summary__treatment-menu-name").text
|
|
62
88
|
|
|
63
|
-
|
|
89
|
+
print(plan_name)
|
|
64
90
|
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
url_list= soup.find_all("a", class_ = "treatment-menu__link")
|
|
68
|
-
|
|
69
|
-
print(url_list)
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
#url_listからhref属性だけを取り出す(この時点でリストに入れた片方の詳細URLしかとれてない？)
|
|
74
|
-
|
|
75
|
-
urls = []
|
|
76
|
-
|
|
77
|
-
for url in url_list:
|
|
78
|
-
|
|
79
|
-
try:
|
|
80
|
-
|
|
81
|
-
link_ = url.get('href')
|
|
82
|
-
|
|
83
|
-
urls.append(link_)
|
|
84
|
-
|
|
85
|
-
except:
|
|
86
|
-
|
|
87
|
-
pass
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
#各プランの詳細ページURL生成
|
|
92
|
-
|
|
93
|
-
new_urls = []
|
|
94
|
-
|
|
95
|
-
for url in urls:
|
|
96
|
-
|
|
97
|
-
new_url = "https://clinic.beauty.hotpepper.jp" + url
|
|
98
|
-
|
|
99
|
-
print('new_url', new_url)
|
|
100
|
-
|
|
101
|
-
new_urls.append(new_url)
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
#詳細ページURLのパース
|
|
106
|
-
|
|
107
|
-
for url in new_urls:
|
|
108
|
-
|
|
109
|
-
r = requests.get(url)
|
|
110
|
-
|
|
111
|
-
|
|
91
|
+
time.sleep(3)
|
|
112
|
-
|
|
113
|
-
soup = BeautifulSoup(r.text,'html.parser')
|
|
114
|
-
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
#ここから各プラン詳細ページの情報取得
|
|
118
|
-
|
|
119
|
-
detail = soup.find(class_ = "l-container")
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
plan_name = soup.find(class_ = "menu-summary__treatment-menu-name").text
|
|
124
|
-
|
|
125
|
-
#print(detail)
|
|
126
|
-
|
|
127
|
-
print(plan_name)
|
|
128
|
-
|
|
129
|
-
|
|
130
92
|
|
|
131
93
|
```
|