|
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 requests
from requests.exceptions import RequestException
import os
import re
def get_one_page(url):
try:
response = requests.get(url)
if response.status_code ==200 :
return response.text
return None
except RequestException:
return None
def parse_one_page(html):
pattern = re .compile('<li.*?src="(.*?)".*?</li>')
items = re.findall(pattern, html)
return items
def save_img(folder, items):
for each in items:
file_name = each.split('/')[-1]
with open(file_name, 'wb') as f:
img = get_one_page(each)
f.write(img)
def main(folder= 'jiandan',page = 10):
os.makedirs(folder)
os.chdir(folder)
url = 'http://jandan.net/ooxx/page-' + str(page) + '#comments'
html = get_one_page(url)
items = parse_one_page(html)
save_img(folder, items)
if __name__ == 'main':
for i in range(10):
main(i) |
|