- 공공기관2/3 작업본 + 오늘 제출 17곳 D~J 카테고리 셀병합 정상화 - 한국지역난방공사 옵션2(고아셀 F98 수정)+전행 높이17 - 제출_프리랜서2_2026-06-21.zip 생성(17개 xlsx, 2,468행) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
31 lines
1.8 KiB
Python
31 lines
1.8 KiB
Python
# -*- coding: utf-8 -*-
|
|
import urllib.request, ssl, re, io
|
|
from bs4 import BeautifulSoup
|
|
ctx=ssl.create_default_context(); ctx.check_hostname=False; ctx.verify_mode=ssl.CERT_NONE
|
|
def body(u):
|
|
try:
|
|
req=urllib.request.Request(u,headers={"User-Agent":"Mozilla/5.0"})
|
|
raw=urllib.request.urlopen(req,context=ctx,timeout=20).read()
|
|
soup=BeautifulSoup(raw,"html.parser")
|
|
for sel in ["#content","#contents",".contents",".content"]:
|
|
el=soup.select_one(sel)
|
|
if el and len(el.get_text(strip=True))>30:
|
|
# remove the breadcrumb / share / local-subnav noise by taking text after '프린트'
|
|
txt=re.sub(r'\s+',' ',el.get_text(" ",strip=True))
|
|
core=txt.split("프린트",1)[-1]
|
|
return core.strip()[:260]
|
|
return "(no content div)"
|
|
except Exception as e:
|
|
return "ERR:"+str(e)
|
|
pairs=[
|
|
("연혁(게시판vs페이지)","https://www.kdhc.co.kr/kdhc/bbs/B0000066/list.do?menuNo=200226","https://www.kdhc.co.kr/kdhc/main/contents.do?menuNo=200169"),
|
|
("기본방향(발전배열vs연료전지)","https://www.kdhc.co.kr/kdhc/main/contents.do?menuNo=200598","https://www.kdhc.co.kr/kdhc/main/contents.do?menuNo=200601"),
|
|
("기본요금(발전배열vs연료전지)","https://www.kdhc.co.kr/kdhc/main/contents.do?menuNo=200599","https://www.kdhc.co.kr/kdhc/main/contents.do?menuNo=200602"),
|
|
("사용량요금(발전배열vs연료전지)","https://www.kdhc.co.kr/kdhc/main/contents.do?menuNo=200600","https://www.kdhc.co.kr/kdhc/main/contents.do?menuNo=200603"),
|
|
]
|
|
out=io.open("_cmp3_out.txt","w",encoding="utf-8")
|
|
for nm,a,b in pairs:
|
|
ca=body(a); cb=body(b)
|
|
out.write(f"### {nm} SAME={ca==cb and not ca.startswith('ERR')}\n A: {ca}\n B: {cb}\n\n")
|
|
out.close(); print("done")
|