네이버 구찌 검색

crawl.py

import urllib.request
import time
import os

# 네이버 구찌 검색 url
url_base = 'https://search.naver.com/search.naver?date_from=&date_option=0&date_to=&dup_remove=1&nso=&post_blogurl=&post_blogurl_without=&query=%EA%B5%AC%EC%B0%8C&sm=tab_pge&srchby=all&st=sim&where=post&start='
folder_dir = '구찌'

os.makedirs(folder_dir)

N = 100
for page_num in range(N):
  url = url_base + str(page_num * 10 + 1)

  with urllib.request.urlopen(url) as fp:
    mystr = fp.read().decode("utf8")
    with open(os.path.join(folder_dir, '%d.html' % page_num), 'w', encoding='utf8') as fh:
      fh.write(mystr)
      print('page %d saved.' % (page_num + 1))
  time.sleep(1)