import urllib.request
import os
#to open the url
def url_open(url):
req=urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.3; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0')
response=urllib.request.urlopen(url)
html=response.read()
return html
#to get the num of page like 1,2,3,4...
def get_page(url):
html=url_open(url).decode('utf-8')
a=html.find('current-comment-page')+23 #add the 23 offset th arrive at the [2356]
b=html.find(']',a)
#print(html[a:b])
return html[a:b]
#find the url of imgs and return the url of arr
def find_imgs(url):
html=url_open(url).decode('utf-8')
img_addrs=[]
a=html.find('img src=')
while a!=-1:
b=html.find('.jpg',a,a+255) # if false : return -1
if b!=-1:
img_addrs.append('http:'+html[a+9:b+4])
else:
b=a+9
a=html.find('img src=',b)
#print(img_addrs)
return img_addrs
#print('http:'+each)
#save the imgs
def save_imgs(folder,img_addrs):
for each in img_addrs:
filename=each.split('/')[-1] #get the last member of arr,that is the name
with open(filename,'wb') as f:
img = url_open(each)
f.write(img)
def download_mm(folder='mm',pages=10):
os.mkdir(folder)
os.chdir(folder)
url='http://jandan.net/ooxx/'
page_num=int(get_page(url))
for i in range(pages):
page_num -= i
page_url = url + 'page-' + str(page_num) + '#comments'
img_addrs=find_imgs(page_url)
save_imgs(folder,img_addrs)
if __name__ == '__main__':
download_mm()
