|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
import urllib.request
import os
import re
url = "http://jandan.net/ooxx"
def url_open(url):
req = urllib.request.Request(url)
req.add_header("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36")
response = urllib.request.urlopen(url)
html = response.read().decode('utf-8')
return html
def get_page(url):
a = r'\[\d\d\]'
b = re.findall(a,url_open(url))
c = b[:1]
d = int(c[0].strip('[]'))
return d
def find_imgs(page_url):
img_addrs = []
cc = r'<img src="(.*\.jpg)'
dd = re.findall(cc,url_open(url))
img_addrs = ['http:'+x for x in dd]
return (img_addrs)
def save_image(folder,img_addrs):
for each in img_addrs:
filename = each.split('/')[-1]
with open(filename,'wb') as f:
img = url_open(each)
f.write(img)
def download_mm(folder = 'OOXX',pages = 10):
os.mkdir(folder)
os.chdir(folder)
page_num = int(get_page(url))
把 html = response.read().decode('utf-8') 去掉 .decode('utf-8')
然后加在 b = re.findall(a, url_open(url)) 中,b = re.findall(a, url_open(url).decode('utf-8'))
|
-
|