源码:
import urllib.request
import urllib.parse
import os
def url_open(url):
req = urllib.request.urlopen(url)
response = urllib.request.urlopen(url)
html = response.read()
return html
def get_page(url):
html = url_open(url).decode('utf-8')
a = html.find('current-comment-page')+23
b = html.find(']',a)
return html[a:b]
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 b!=-1:
img_addrs.append(html[a+9:b+4])
else:
b = a + 9
a = html.find('img src=',b)
return img_addrs;
def save_imgs(folder,img_addrs):
for each in img_addrs:
filename = each.split('/')[-1]
if os.path.exists(filename):
break
else:
with open(filename,'wb') as f:
img = url_open('http:'+each)
f.write(img)
def download_mm(folder='ooxx',pages=10):
#os.mkdir(folder)
os.chdir(folder)
url = 'https://jandan.net/ooxx/'
page_num = int(get_page(url))
for i in range(page_num):
page_num -= 1
if page_num!=0:
page_url = url + 'page-' + str(page_num) + '#comments'
img_addrs = find_imgs(page_url)
save_imgs(folder,img_addrs)
if __name__ == '__main__':
download_mm()
本人今天试了一下,还不错!
注意: 必须得有Python的运行环境!
在运行的时候,必须 在程序的下面 建一个 ooxx 的文件夹!
