小李飞刀图片:http://www.verycd.com/entries/507389/images/view/778356
# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
def downloadPic(url='http://www.verycd.com/entries/507389/images/view/', index=100903):
# 1 get the pic_url
data = requests.post(url=url+str(index))
print data.status_code
if data.status_code == 200:
soup = BeautifulSoup(data.content, 'html.parser')
img_src = soup.find('img', {'id': 'img_big_url'})
img_url = img_src.get('src')
# 2 start downloading
data2 = requests.get(url=img_url)
img_content = data2.content
fo = open('D:\\images\\{}.png'.format(str(index)), 'wb')
fo.write(img_content)
fo.flush()
fo.close()
return True
else:
return False
def batch_download(index):
flag = downloadPic(index=str(index))
while flag:
index += 1
flag = downloadPic(index=str(index))
batch_download(100903)
batch_download(778321)
python header:
header = {'Connection': 'keep-alive',
'Cache-Control': 'max-age=0',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) AppleWebKit/537.36 (KHTML, like Gecko)',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8',
}