|
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 get_page(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/51.0.2704.79 Safari/537.36 Edge/14.14393'
response = urllib.request.urlopen(url)
html = response.read().decode('utf-8')
a = html.find('current-comment-page' + 23
b = html.find(']', a)
print(html[a:b])
def img_addrs(url):
pass
def sava_imgs(folder, img_addrs):
pass
def fownload_mm(floder = 'ooxx', pages = 10):
#创建文件夹
os.mkdir(folder)
#改变目录
os.chdir(folder)
ure = 'http://jandan.net/ooxx'
#获得页面地址
page_num = int(get_page(url))
for i in range(pages):
page_num -= i
page_url = url +'page-' + sty(page_num) + '#comments'
img_addrs = find_imgs(page_url)
sava_imgs(folder, img_addrs)
这里 为什么response会出现语法错误[img][/img]
你看看你的这句
其他没怎么看,但是这句肯定是格式错误
自己好好看看是不是自己本身就写错了
req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.79 Safari/537.36 Edge/14.14393'
|
|