|
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
这是跟着打的:(出现的py提示的错误后面)
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/55.0.2883.87 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)
print(html[a:b])
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)
return img_addrs
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',page = 10):
os.mkdir(folder)
os.chdir(folder)
url = "http://jandan.net/ooxx/"
page_num = int(get_page(url))
for i in range(page):
page_num -= i
page_url = url + 'page-' + str(page_num) + '#comments'
img_addrs = find_img(page_url)
save_imgs(folder,img_addrs)
if __name__ == '__main__':
download_mm()
这里是py提供的提示:
Traceback (most recent call last):
File "C:\Users\10757\Desktop\py\download_mm.py", line 61, in <module>
download_mm()
File "C:\Users\10757\Desktop\py\download_mm.py", line 56, in download_mm
img_addrs = find_img(page_url)
File "C:\Users\10757\Desktop\py\download_mm.py", line 30, in find_img
img_addrs.append(int(html[a+9,b+4]))
TypeError: string indices must be integers
求助大腿 告知怎么回事 怎么改???
|
|