9ku.py

import re
import os
import urllib
import requests
from bs4 import BeautifulSoup
from multiprocessing import Pool

initurl = 'http://www.03122.com/xinggan/12374/'
baseurl = os.path.split(initurl)[0]

urlpool = []
save_path = os.path.abspath("./tmp/")
if not os.path.exists(save_path):
    os.mkdir(save_path)

headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/602.4.8 (KHTML, like Gecko) Version/10.0.3 Safari/602.4.8'}

inithtml = requests.get(initurl, headers=headers)
initsoup = BeautifulSoup(inithtml.text, 'html.parser')
totalspan = initsoup.find('span', attrs={'class':'page-ch'}).getText()
totalstr = re.findall(r'\d+', totalspan)[0]
totalnum = int(totalstr) + 1
print u"Total %s pages." %totalnum

for i in xrange(1,totalnum):
    tmpstr = baseurl + '/%s.html' %i
    print tmpstr
    tmphl = requests.get(tmpstr, headers=headers)
    tmpsoup = BeautifulSoup(tmphl.text, 'html.parser')
    tmpurl = tmpsoup.find(id='ppPage').img.get('src')
    imgurl = tmpurl.split('?')[0]
    print imgurl
    urlpool.append(imgurl)

def down_img(url):
    localpath = os.path.join(save_path, url.split('/')[7])
    urllib.urlretrieve(url, localpath)
    print 'Download %s done!' %localpath

if len(urlpool) > 0:
    pool = Pool(4)
    pool.map(down_img, urlpool)
    pool.close()
    pool.join()