https://www.flickr.com/photos/ncsm-sky/albums/page1
この中の16ページまですべての画像を取得したいのですがどういう風にアクセスしたらいいかわかりません。
何か良い方法はありますか??
zipファイルを回収できたらなお良いです。
動きませんが現在のところこんな感じです。
# -*- coding: utf-8 -*- from bs4 import BeautifulSoup from urllib import request from urllib.error import URLError, HTTPError import os.path import os import time #https://www.flickr.com/photos/ncsm-sky/sets/72157681801352463 def download(url): url = url headers = { "User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:47.0) Gecko/20100101 Firefox/47.0", } print(url) req = request.Request(url, None, headers) img = request.urlopen(req) localfile = open(os.path.basename(url), 'wb') localfile.write(img.read()) img.close() localfile.close() def main(): try: url="https://www.flickr.com/photos/ncsm-sky/albums/page1" urlb="https://www.flickr.com" # urlアクセス res = request.urlopen(url) # beautifulsoupでパース soup = BeautifulSoup(res.read(),"html.parser") for link in soup.find_all('a', class_='interaction-view avatar photo-list-album album ginormous'): linka=link.get("href") urlc=urlb+linka res1= request.urlopen(urlc) soup = BeautifulSoup(res1.read(),"html.parser") for src in soup.find_all('img.src'): print(src) # print(urlc)=それぞれのページ # download(urlc) except HTTPError as e: print('Error code: ', e.code) except URLError as e: print('Error code: ', e.code) if __name__ == '__main__': main()