|

楼主 |
发表于 2016-3-26 13:20:23
|
显示全部楼层
import urllib.request
import urllib.parse
import os
import re
'''
def get_page():
pass
'''
def url_open(url):
req = urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0')
response = urllib.request.urlopen(req)
def find_img(page_url):
html = url_open(page_url).decode('utf-8')
res = re.search(r'http,\.jpg',page_url)
return res.group(1)
def save_img(folder,img_addrs):
for each in img_addrs:
filename=each.split('/')[-1]
with open(filename,'wb') as f:
img = img_addrs(each)
f.write(img)
def download_mm(folder,pages=10):
os.mkdir()
os.chdir()
url="http://www.chunmm.com/"
page_num = pages
for i in range(pages):
page_num-=1
page_url = url+'cosplay/'+'20169-'+str(pages)
img_addrs = find_img(page_url)
save_img(folder,img_addrs)
if __name__=='_main__':
download_mm() |
|