python3 网上图片自动下载 奥数网

http://www.aoshu.com/e/20190719/5d3130b205314.shtml有一些小学的练习题，家里有娃只好自己写个程序下载

#!C:\Python37
# -*- coding:utf-8 -*-
import requests
import os
from bs4 import BeautifulSoup

def downpic(url,unit):
    pageurls = []
    pageurls.append(url)
    (base,ext)= os.path.splitext(url)
    #print(base,ext)
    for i in range(2,11):
        #pass
        pageurls.append(base + '_' + str(i)+ext)
    #print(pageurls)
    page =1
    for pageurl in pageurls:
        #pageurl = 'http://www.aoshu.com/e/20190719/5d3128d7a53bd.shtml'
        try:
            res = requests.get(pageurl)
        except Exception as e:
            print(e)
            pass
        if res.status_code != 200:
            continue

        soup = BeautifulSoup(res.text,'html.parser')
        plists = soup.find_all(name='p')

        for p in plists:
            imglist = p.find_all(name='img')
            if len(imglist) > 0:
                imgurl = imglist[0]['src']
        #print(imgurl)
        (base,filename) = os.path.split(imgurl)
        filename= str(unit)+'_'+str(page)+filename
        savename = os.path.join(os.getcwd(),'math',filename)

        #print(savename)
        try:
            imgres = requests.get(imgurl)
        except  Exception as e:
            print(e)
            continue
        with open(savename,'wb') as fw:
            fw.write(imgres.content)
            print('[+]download '+filename)
        page+=1
    return

def findUnitUrl(url):
    urllists=[]

    try:
        res = requests.get(url)
        #print(res.text)
        soup = BeautifulSoup(res.text,'html.parser')
        tablelists = soup.find_all(name='table')
        #print(tablelists)
        for table in tablelists:
            unitlist = table.find_all(name='a')
            #print(unitlist)
            for list in unitlist:
                urllists.append(list['href'])
        #print(urllists)
        return urllists
    except Exception as e:
        print(e)
        return


def main():
    url ='http://www.aoshu.com/e/20190719/5d3130b205314.shtml'
    uniturl=findUnitUrl(url)
   
    unit =1
    for uniturl in uniturl:
        downpic(uniturl,unit)
        unit+=1

    return

if __name__ == '__main__':
    main()