|
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 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36')
response=urllib.request.urlopen(url)
html=response.read()
print(url)
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_img(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_img(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_img(page_url)
save_img(folder,img_addrs)
if __name__=='__main__':
download_mm()
结果是:
http://jandan.net/ooxx/
http://jandan.net/ooxx/page-48#comments
Traceback (most recent call last):
File "D:/python/联系代码/11.py", line 52, in <module>
download_mm()
File "D:/python/联系代码/11.py", line 49, in download_mm
img_addrs=find_img(page_url)
File "D:/python/联系代码/11.py", line 25, in find_img
img_addrs.append(html[a+9,b+4])
TypeError: string indices must be integers
这是什么意思啊,不知道怎么改,麻烦帮忙看一下
|
|