|
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
本帖最后由 石头怪 于 2017-3-31 15:49 编辑
import urllib.request
import os
def open_url(url):
req = urllib.request.Request(url)
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36')
response = urllib.request.urlopen(url)
html = response.read()
return html
def find_url(url):
html = open_url(url).decode('utf-8')
img_url = []
a = html.find('img class="BDE_Image" src=')
while a != -1:
b = html.find('.jpg',a,a+255)
if b != -1:
html = html[a+27:b+4]
img_url.append(html)
else:
b = a + 9
a = html.find('img class="BDE_Image" src=',b)
return img_url
def save_img(img_url):
for each in img_url:
filename = each.split('/')[-1]
with open(filename,'wb')as f:
img = open_url(each)
f.write(img)
def tbdownload(folder='tieba'):
os.mkdir(folder)
os.chdir(folder)
url = 'https://tieba.baidu.com/p/5048269511'
img_url = find_url(url)
save_img(img_url)
if __name__ == '__main__':
tbdownload() |
|