|
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
file:///C:\Users\lostlove\Documents\Tencent Files\1321348561\Image\C2C\1@0P4X)@FB){90APJJ_ET80.jpgfile:///C:\Users\lostlove\Documents\Tencent Files\1321348561\Image\C2C\1@0P4X)@FB){90APJJ_ET80.jpg
下面是代码和错误 求大神解答哪里写错了
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; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 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(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()
|
-
代码
-
系统提示的爬虫错误
|