Skip to content

Commit a25274d

Browse files
turbouturbou
committed
update.
1 parent 4f20a0a commit a25274d

File tree

4 files changed

+143
-3
lines changed

4 files changed

+143
-3
lines changed

‎feeds/index.html‎

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,8 +3,10 @@ <h2>リリース情報</h2>
33
<hr>
44
<h2>RSS feed</h2>
55
<h3>Contrast</h3>
6-
Contrast Release Note<br />
7-
<a target="_blank" href="https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote.xml">https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote.xml</a>
6+
Contrast Release Note(SaaS)<br />
7+
<a target="_blank" href="https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote_saas.xml">https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote_saas.xml</a>
8+
Contrast Release Note(On-premises)<br />
9+
<a target="_blank" href="https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote_eop.xml">https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote_eop.xml</a>
810
<hr />
911
<h3>.NET Core</h3>
1012
.NET Core Agent Release Note<br />

‎work/contrast_rlsnote.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ def main():
1919
feed = Rss201rev2Feed(
2020
title='Contrast Release Note',
2121
link='https://contrastsecurity.dev/contrast-documentation-rss',
22-
description='Java Agent Release Note',
22+
description='Contrast Release Note',
2323
language='ja',
2424
author_name="Contrast Security Japan G.K.",
2525
feed_url='https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote.xml',

‎work/contrast_rlsnote_eop.py‎

Lines changed: 69 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,69 @@
1+
import urllib.request as req
2+
from bs4 import BeautifulSoup
3+
import xml.dom.minidom
4+
from django.utils.feedgenerator import Rss201rev2Feed
5+
from datetime import datetime
6+
import locale
7+
import re
8+
import html
9+
import hashlib
10+
11+
def main():
12+
url = 'https://docs.contrastsecurity.jp/ja/release-on-premises.html'
13+
res = req.urlopen(url)
14+
soup = BeautifulSoup(res, 'lxml')
15+
elems = soup.select('section.section')
16+
modified_date = soup.select_one('span.formatted-date').text.strip()
17+
#print(modified_date)
18+
19+
feed = Rss201rev2Feed(
20+
title='Contrast Release Note(On-premises)',
21+
link='https://contrastsecurity.dev/contrast-documentation-rss',
22+
description='Contrast Release Note(On-premises)',
23+
language='ja',
24+
author_name="Contrast Security Japan G.K.",
25+
feed_url='https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote_eop.xml',
26+
feed_copyright='Copyright 2023 Contrast Security Japan G.K.'
27+
)
28+
29+
id_ptn = re.compile(r'^[0-9]{1,2}月-[0-9\-]+-$')
30+
title_ptn = re.compile(r'^[0-9]{1,2}月\([0-9\.]+\)$')
31+
32+
for elem in elems:
33+
try:
34+
id_str = elem.get("id").strip()
35+
title = elem.select('h3.title')[0].text.strip()
36+
if not id_ptn.search(id_str) or not title_ptn.search(title):
37+
continue
38+
pubdate_str = elem.get("data-time-modified") # November 6, 2023
39+
pubdate = None
40+
if pubdate_str:
41+
pubdate = datetime.strptime(pubdate_str, '%B %d, %Y')
42+
#print(id_str, pubdate_str, title)
43+
desc_buffer = []
44+
for elem2 in elem.select('section.section'):
45+
id_str2 = elem2.get("id").strip()
46+
#print('- ', elem2.select_one('div.titlepage').text)
47+
desc_buffer.append('<b>%s</b>' % elem2.select_one('div.titlepage').text)
48+
for elem3 in elem2.select('li.listitem'):
49+
#print(' - ', elem3.select_one('p').text)
50+
desc_buffer.append('・%s' % elem3.select_one('p').text)
51+
#print(id_str, elem.get('data-legacy-id'))
52+
#if not title.lower().startswith('java'):
53+
# continue
54+
id_hash = hashlib.md5(id_str.encode()).hexdigest()
55+
url = 'https://docs.contrastsecurity.jp/ja/release-on-premises.html#%s' % id_str
56+
guid = 'https://docs.contrastsecurity.jp/ja/release-on-premises.html#%s' % id_hash
57+
if not '月' in title:
58+
continue
59+
feed.add_item(title=title, link=url, description=''.join(['<p>{0}</p>'.format(s) for s in desc_buffer]), pubdate=pubdate, unique_id=guid)
60+
except IndexError:
61+
continue
62+
str_val = feed.writeString('utf-8')
63+
dom = xml.dom.minidom.parseString(str_val)
64+
with open('/feeds/contrast_rlsnote_eop.xml','w') as fp:
65+
dom.writexml(fp, encoding='utf-8', newl='\n', indent='', addindent=' ')
66+
67+
if __name__ == "__main__":
68+
main()
69+

‎work/contrast_rlsnote_saas.py‎

Lines changed: 69 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,69 @@
1+
import urllib.request as req
2+
from bs4 import BeautifulSoup
3+
import xml.dom.minidom
4+
from django.utils.feedgenerator import Rss201rev2Feed
5+
from datetime import datetime
6+
import locale
7+
import re
8+
import html
9+
import hashlib
10+
11+
def main():
12+
url = 'https://docs.contrastsecurity.jp/ja/release-hosted.html'
13+
res = req.urlopen(url)
14+
soup = BeautifulSoup(res, 'lxml')
15+
elems = soup.select('section.section')
16+
modified_date = soup.select_one('span.formatted-date').text.strip()
17+
#print(modified_date)
18+
19+
feed = Rss201rev2Feed(
20+
title='Contrast Release Note(SaaS)',
21+
link='https://contrastsecurity.dev/contrast-documentation-rss',
22+
description='Contrast Release Note(SaaS)',
23+
language='ja',
24+
author_name="Contrast Security Japan G.K.",
25+
feed_url='https://contrastsecurity.dev/contrast-documentation-rss/contrast_rlsnote_saas.xml',
26+
feed_copyright='Copyright 2023 Contrast Security Japan G.K.'
27+
)
28+
29+
id_ptn = re.compile(r'^20[0-9]{2}年[0-9]{1,2}月$')
30+
title_ptn = re.compile(r'^20[0-9]{2}年[0-9]{1,2}月$')
31+
32+
for elem in elems:
33+
try:
34+
id_str = elem.get("id").strip()
35+
title = elem.select('h3.title')[0].text.strip()
36+
if not id_ptn.search(id_str) or not title_ptn.search(title):
37+
continue
38+
pubdate_str = elem.get("data-time-modified") # November 6, 2023
39+
pubdate = None
40+
if pubdate_str:
41+
pubdate = datetime.strptime(pubdate_str, '%B %d, %Y')
42+
#print(id_str, pubdate_str, title)
43+
desc_buffer = []
44+
for elem2 in elem.select('section.section'):
45+
id_str2 = elem2.get("id").strip()
46+
#print('- ', elem2.select_one('div.titlepage').text)
47+
desc_buffer.append('<b>%s</b>' % elem2.select_one('div.titlepage').text)
48+
for elem3 in elem2.select('li.listitem'):
49+
#print(' - ', elem3.select_one('p').text)
50+
desc_buffer.append('・%s' % elem3.select_one('p').text)
51+
#print(id_str, elem.get('data-legacy-id'))
52+
#if not title.lower().startswith('java'):
53+
# continue
54+
id_hash = hashlib.md5(id_str.encode()).hexdigest()
55+
url = 'https://docs.contrastsecurity.jp/ja/release-hosted.html#%s' % id_str
56+
guid = 'https://docs.contrastsecurity.jp/ja/release-hosted.html#%s' % id_hash
57+
if not '月' in title:
58+
continue
59+
feed.add_item(title=title, link=url, description=''.join(['<p>{0}</p>'.format(s) for s in desc_buffer]), pubdate=pubdate, unique_id=guid)
60+
except IndexError:
61+
continue
62+
str_val = feed.writeString('utf-8')
63+
dom = xml.dom.minidom.parseString(str_val)
64+
with open('/feeds/contrast_rlsnote_saas.xml','w') as fp:
65+
dom.writexml(fp, encoding='utf-8', newl='\n', indent='', addindent=' ')
66+
67+
if __name__ == "__main__":
68+
main()
69+

0 commit comments

Comments
 (0)