|
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
def url_open(url):
req = urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.110 Safari/537.36')
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]
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)
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()
出现下面的错误:
Traceback (most recent call last):
File "C:\Users\Fredericlong\Desktop\download_mm.py", line 56, in <module>
download_mm()
File "C:\Users\Fredericlong\Desktop\download_mm.py", line 53, in download_mm
save_imgs(folder, img_addrs)
File "C:\Users\Fredericlong\Desktop\download_mm.py", line 39, in save_imgs
img = url_open(each)
File "C:\Users\Fredericlong\Desktop\download_mm.py", line 5, in url_open
req = urllib.request.Request(url)
File "D:\Python\lib\urllib\request.py", line 329, in __init__
self.full_url = url
File "D:\Python\lib\urllib\request.py", line 355, in full_url
self._parse()
File "D:\Python\lib\urllib\request.py", line 384, in _parse
raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: '//wx1.sinaimg.cn/mw600/661eb95cgy1fe09x3v2gqj20re14awqu.jpg' |
|