df16c98366
공공기관2 작업 중. _temp 몽타주(재생성가능)는 제외. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
41 lines
1.8 KiB
Python
41 lines
1.8 KiB
Python
import sys, io
|
|
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
|
|
import urllib.request, ssl, re
|
|
ctx=ssl.create_default_context(); ctx.check_hostname=False; ctx.verify_mode=ssl.CERT_NONE
|
|
hdr={'User-Agent':'Mozilla/5.0'}
|
|
def fetch(url):
|
|
req=urllib.request.Request(url, headers=hdr)
|
|
with urllib.request.urlopen(req, context=ctx, timeout=25) as r:
|
|
return r.read().decode('utf-8','replace')
|
|
|
|
def content_imgs(html):
|
|
# extract main content area #contents or .contents and find non-decorative imgs
|
|
m=re.search(r'id="contents"(.*?)(?:</main>|<footer|id="footer)', html, re.S) or \
|
|
re.search(r'class="[^"]*contents[^"]*"(.*?)(?:</main>|<footer|id="footer)', html, re.S)
|
|
area=m.group(1) if m else html
|
|
imgs=re.findall(r'<img[^>]*src="([^"]*)"[^>]*>', area)
|
|
deco=re.compile(r'move\.png|no[-_]?img|blank|spacer|icon|btn_|bullet|/common/|opentype', re.I)
|
|
real=[s for s in imgs if not deco.search(s)]
|
|
return imgs, real
|
|
|
|
for pg in range(10):
|
|
url=f'https://www.asan.go.kr/main/cms/?no=55&pg={pg}'
|
|
html=fetch(url)
|
|
t=re.search(r'<h[1-4][^>]*class="[^"]*(?:tit|title)[^"]*"[^>]*>(.*?)</h', html, re.S)
|
|
title=re.sub(r'<[^>]+>','',t.group(1)).strip() if t else ''
|
|
allimg, real = content_imgs(html)
|
|
ot=re.search(r'img_opentype_(\d)', html)
|
|
# detect tables, embeds, video
|
|
has_table='<table' in html
|
|
has_video=bool(re.search(r'<video|youtube|<iframe', html, re.I))
|
|
print(f'pg={pg} title={title!r} opentype={ot.group(1) if ot else None} realimg={len(real)} table={has_table} video={has_video}')
|
|
for s in real[:6]:
|
|
print(' img:', s)
|
|
|
|
print('\n===== no=365 search-list inspect =====')
|
|
html=fetch('https://www.asan.go.kr/main/cms/?no=365')
|
|
m=re.search(r'<[^>]*class="[^"]*search-list[^"]*"[^>]*>(.*?)</(?:ul|div)>', html, re.S)
|
|
if m:
|
|
seg=m.group(1)
|
|
print(re.sub(r'\s+',' ', seg)[:1500])
|