|
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
代码执行完提示:
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 642, in http_response
'http', request, response, code, msg, hdrs)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 570, in error
return self._call_chain(*args)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 504, in _call_chain
result = func(*args)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 650, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 404: Not Found
import urllib.request
import os
# 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; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36')
response = urllib.request.urlopen(url)
html = response.read()
print(url)
return html
# y=url_open(url)
# print(y)
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)
for each in img_addrs:
print(each)
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)
print(img_addrs)
def download_mm(folder='o22ox13', pages=2):
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()
|
|