import
re
import
urllib
def
getHtml
(
html
):
page
=
urllib
.
urlopen
(
html
)
Html
=
page
.
read
()
return
Html
def
getImg
(
Html
):
r
=
r'src="(.*?\.jpg)"'
#正则r用来筛选图片的地址
img_re
=
re
.
compile
(
r
)
imgHtml
=
re
.
findall
(
img_re
,
Html
)
x
=
0
for
imght
in
imgHtml
:
urllib
.
urlretrieve
(
imght
,
"
%s
.jpg"
%
x
)
#下载并保存图片
x
+=
1
html
=
getHtml
(
"http://movie.douban.com/"
)
getImg
(
html
)
