|
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 re
import os
def get_page(url):#查找页面
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36'}
req = urllib.request.Request(url, headers=headers)
response = urllib.request.urlopen(req)
html = response.read().decode('utf-8')
p = r'<span class="current-comment-page">[(\d+?)]</span>'
pages_addrs = re.findall(p, html)
print(pages_addrs)
def find_img(url):
pass
def save_img(img_addrs):
pass
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 rangs(pages):
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()
这一段说缩进中制表符和空格使用不一致 p = r'<span class="current-comment-page">[(\d+?)]</span>'
不明白是哪里出错了
p = r'<span class="current-comment-page">\[(\d+?)\]</span>'这样也不可以
很是疑惑
还望大佬们指教
谢谢 |
|