DB_JOB/작업파일/공공기관3/완료/5.한국임업진흥원/_invest.py
2026-06-26 09:47:44 +09:00

52 lines
2.7 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import requests, io, re
from bs4 import BeautifulSoup
hd={"User-Agent":"Mozilla/5.0"}
BASE="https://www.kofpi.or.kr"
out=io.open("_invest_out.txt","w",encoding="utf-8")
def fetch(u):
r=requests.get(u,headers=hd,timeout=25); r.encoding=r.apparent_encoding
return BeautifulSoup(r.content,"html.parser"), r
# (a) ALL tab widgets on the 주요사업 ambiguous pages
for u in ["/service/introduceInfo_01.do","/service/introduceInfo_47.do","/service/introduceInfo_20.do","/service/certInfo_02.do","/service/edu_01.do"]:
s,_=fetch(BASE+u)
out.write(f"\n=== {u} ALL tab-like UL/DIV ===\n")
for w in s.select("div[class*=tab], ul[class*=tab]"):
cls=w.get("class")
lis=w.find_all("li", recursive=True)
labs=[(li.find('a').get_text(' ',strip=True)[:18] if li.find('a') else li.get_text(' ',strip=True)[:18], (li.find('a').get('href') if li.find('a') else None)) for li in lis][:12]
if labs:
out.write(f" {w.name}.{cls}: {labs}\n")
# (b) board counts: find total/lastpage for paging boards
boards={
"임산물정보":"/info/imupStory/forestStory_01.do","임산물레시피":"/info/imupStory/forestStory_02.do",
"우리목재":"/info/imupStory/wood_02.do",
"공모중인사업":"/info/exportInfo/govSupport_02.do",
"통합자료실(수출)":"/info/exportInfo/exportData_01.do","해외시장보고서":"/info/exportInfo/exportData_02.do",
"연구보고서(수출)":"/info/exportInfo/exportData_03.do","발굴업체홍보":"/info/exportInfo/exportData_05.do","임업기계장비(수출)":"/info/exportInfo/exportData_06.do",
"기술이전현황":"/info/tech/techComm_01_02.do","사업화성공사례":"/info/tech/techComm_01_03.do","보유특허정보":"/info/tech/techComm_01_01.do","기술자료집":"/info/tech_06.do",
}
out.write("\n\n=== BOARD COUNTS ===\n")
for nm,u in boards.items():
s,_=fetch(BASE+u)
txt=s.get_text(" ",strip=True)
tot=None
for pat in [r"\s*([\d,]+)\s*건",r"전체\s*([\d,]+)",r"\s*게시(?:물|글)?\s*[:]?\s*([\d,]+)",r"게시물\s*[:]?\s*([\d,]+)\s*건"]:
m=re.search(pat,txt)
if m: tot=m.group(1); break
# last page number from pagination links
pglinks=[a.get('href','') for a in s.select("[class*=paging] a, [class*=page] a, .pagination a")]
pgnums=[]
for a in s.select("[class*=paging] a, .pagination a, [class*=page] a"):
t=a.get_text(strip=True)
if t.isdigit(): pgnums.append(int(t))
# number column max in list
nums=[]
for td in s.select("table tbody tr td, ul.board_list li, .board_list .num"):
t=td.get_text(strip=True)
if t.isdigit(): nums.append(int(t))
out.write(f" {nm} {u}\n total_text={tot} maxpage={max(pgnums) if pgnums else None} maxnum={max(nums) if nums else None}\n")
out.close()
print("done")