|
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
谁能帮我看一下哪里错了。十分感谢
报错:urllib.error.HTTPError: HTTP Error 404: Not Found
import urllib.request
import random
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/68.0.3440.106 Safari/537.36')
response=urllib.request.urlopen(req)
html=response.read()
return html
def get_page(url):
html=url_open(url).decode('utf-8')
a=html.find('current-comment')+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)
return img_addrs
def save_imgs(file,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(file='新建',num=10):
os.mkdir(file)
os.chdir(file)
url='http://www.jandan.net/ooxx/'
page_num=int(get_page(url))
for i in range(num):
page_num-=i;
page_url=url+'page-'+str(page_num)+'#comments'
img_addrs=find_imgs(page_url)
save_imgs(file,img_addrs)
if __name__=='__main__':
download()
|
|