回答編集履歴
1
文法の修正
answer
CHANGED
|
@@ -8,52 +8,63 @@
|
|
|
8
8
|
from bs4 import BeautifulSoup
|
|
9
9
|
|
|
10
10
|
|
|
11
|
-
def get_href():
|
|
12
|
-
|
|
11
|
+
i = 1
|
|
13
|
-
|
|
12
|
+
num = 2
|
|
14
|
-
|
|
13
|
+
while i < 48:
|
|
15
|
-
|
|
14
|
+
for num in range(1, 300):
|
|
16
|
-
|
|
15
|
+
zero_i = str(i).zfill(2)
|
|
17
|
-
|
|
16
|
+
base = 'https://www.judo-ch.jp/sekkotsuinsrch/{}/list/{}/'
|
|
18
|
-
|
|
17
|
+
url = base.format(zero_i,num)
|
|
19
|
-
|
|
18
|
+
res = requests.get(url)
|
|
20
|
-
|
|
19
|
+
if res.status_code == 200:
|
|
20
|
+
html = requests.get(url)
|
|
21
|
+
soup = BeautifulSoup(html.content,"html.parser")
|
|
22
|
+
for tag in soup.find_all("h3","shisetsu_name_s"):
|
|
23
|
+
link = tag.find("a")
|
|
24
|
+
url = link.get("href")
|
|
21
25
|
html = requests.get(url)
|
|
22
|
-
|
|
26
|
+
get_soup = BeautifulSoup(html.content, "html.parser")
|
|
27
|
+
res_p = get_soup.find("p", "lnk_url")
|
|
28
|
+
if res_p is not None:
|
|
29
|
+
print(res_p.text)
|
|
30
|
+
res_p = get_soup.find("span", "name")
|
|
31
|
+
if res_p is not None:
|
|
32
|
+
print(res_p.text)
|
|
23
|
-
|
|
33
|
+
res_p = get_soup.find("dd", "name")
|
|
24
|
-
|
|
34
|
+
if res_p is not None:
|
|
25
|
-
print(
|
|
35
|
+
print(res_p.text)
|
|
26
|
-
|
|
36
|
+
for s_tag in soup.find_all("h3","shisetsu_name"):
|
|
27
|
-
|
|
37
|
+
s_link = s_tag.find("a")
|
|
28
|
-
|
|
38
|
+
s_url = s_link.get("href")
|
|
39
|
+
html = requests.get(s_url)
|
|
40
|
+
get_soup = BeautifulSoup(html.content, "html.parser")
|
|
41
|
+
res_p = get_soup.find("p", "lnk_url")
|
|
42
|
+
if res_p is not None:
|
|
29
|
-
print(
|
|
43
|
+
print(res_p.text)
|
|
44
|
+
res_p = get_soup.find("span", "name")
|
|
45
|
+
if res_p is not None:
|
|
46
|
+
print(res_p.text)
|
|
47
|
+
res_p = get_soup.find("dd", "name")
|
|
48
|
+
if res_p is not None:
|
|
49
|
+
print(res_p.text)
|
|
30
|
-
|
|
50
|
+
links = soup.find_all("a","fa_name")
|
|
31
|
-
|
|
51
|
+
for link in links:
|
|
52
|
+
i_url = link.get("href")
|
|
53
|
+
html = requests.get(i_url)
|
|
54
|
+
get_soup = BeautifulSoup(html.content, "html.parser")
|
|
55
|
+
res_p = get_soup.find("p", "lnk_url")
|
|
56
|
+
if res_p is not None:
|
|
32
|
-
print(
|
|
57
|
+
print(res_p.text)
|
|
58
|
+
res_p = get_soup.find("span", "name")
|
|
33
|
-
|
|
59
|
+
if res_p is not None:
|
|
34
|
-
break
|
|
35
|
-
|
|
60
|
+
print(res_p.text)
|
|
61
|
+
res_p = get_soup.find("dd", "name")
|
|
62
|
+
if res_p is not None:
|
|
63
|
+
print(res_p.text)
|
|
36
64
|
else:
|
|
37
65
|
break
|
|
66
|
+
num += 1
|
|
67
|
+
else:
|
|
68
|
+
break
|
|
38
|
-
|
|
69
|
+
i += 1
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
def get_soup(url):
|
|
42
|
-
html = requests.get(url)
|
|
43
|
-
return BeautifulSoup(html.content, "html.parser")
|
|
44
|
-
|
|
45
|
-
def scraping_gh():
|
|
46
|
-
|
|
47
|
-
soup = get_soup(get_href())
|
|
48
|
-
|
|
49
|
-
# 整骨院の名称
|
|
50
|
-
res_p = soup.find("span", "name")
|
|
51
|
-
res = res_p.find(text=re.compile(""))
|
|
52
|
-
print(res.string)
|
|
53
|
-
# ホームページのURL
|
|
54
|
-
res_p = soup.find("a", "lnk_url")
|
|
55
|
-
res = res_p.find(text=re.compile(""))
|
|
56
|
-
print(res.string)
|
|
57
|
-
|
|
58
|
-
scraping_gh()
|
|
59
70
|
```
|