pip install requests
pip install beautifulsoup4

# coding:utf-8
from time import sleep
import time
from bs4 import BeautifulSoup
import sys
import requests, urllib.request, os
from selenium.common.exceptions import TimeoutException

domain="http://blog.nogizaka46.com/"
member="manatsu.akimoto" #メンバーの指定
url=domain+member+"/"

def getImages(soup,cnt,mouthtrue):
    member_path="./"+member
    #画像を保存する関数
    for entry in soup.find_all("div", class_="entrybody"):# 全てのentrybodyを取得
        for img in entry.find_all("img"):# 全てのimgを取得
            cnt +=1
            imgurl=img.attrs["src"]
            imgurlnon=imgurl.replace('https','http')
            if mouthtrue:
                try:
                    urllib.request.urlretrieve(imgurlnon, member_path+ str(year)+'0'+str(mouth) + "-" + str(cnt) + ".jpeg")
                except:
                    print("error",imgurlnon)
            else:
                try:
                    urllib.request.urlretrieve(imgurlnon, member_path + str(year)+str(mouth) + "-" + str(cnt) + ".jpeg")
                except:
                    print("error",imgurlnon)


if(__name__ == "__main__"):
    #保存するブログの始まり
    year=2012
    mouth=12
    #保存するブログの終わり
    endyear=2020
    endmouth=6

    while(True):
        mouthtrue=True
        if mouth<10:
            BlogPageURL=url+"?d="+str(year)+"0"+str(mouth)
        else:
            BlogPageURL=url+"?d="+str(year)+str(mouth)
            mouthtrue=False
        headers = {"User-Agent": "Mozilla/5.0"}
        soup = BeautifulSoup(requests.get(BlogPageURL, headers=headers).content, 'html.parser')#htmlの取得
        print(year,mouth)
        sleep(3)
        cnt = 0
        ht=soup.find_all("div", class_="paginate")
        print("ht",ht)
        getImages(soup,cnt,mouthtrue)#画像保存関数の呼び出し
        if len(ht)>0:#もし同じ月に複数ページあったとき，そのページ分だけ保存
            ht_url=ht[0]
            print(ht_url)
            url_all=ht_url.find_all("a")
            for i,hturl in enumerate(url_all):
                if (i+1)==len(url_all):
                    break
                link = hturl.get("href")
                print("url",url+link)
                soup = BeautifulSoup(requests.get(url+link, headers=headers).content, 'html.parser')
                sleep(3)
                getImages(soup,cnt,mouthtrue)#画像保存関数の呼び出し
        if year==endyear and mouth==endmouth:
            print("Finish")
            sys.exit()#プログラム終了
        if mouth==12:
            mouth=1
            year=year+1
            print("update",year,mouth)
        else:
            mouth=mouth+1
            print("update",year,mouth)