Reptile crawling hummingbird in HD Wallpaper
Want to automatically download a website HD wallpaper, not one by one click to download, so with reptiles automatic download. Change the code, a special analysis only for a specific site needs a different site.
First, analyze site
Just click on one, you can find previous, next flip, so you can get after change plans, get the next image address, wireless loop, download wallpaper. In order to achieve this multi-functional, use a regular expression re beautifulsoup and two search mode.
Information required above figure, from top to bottom: change the image download address, the name of the picture, the next picture address.
Second, get the page
|
1
2
3
4
5
6
7
8
|
def
getHtmlurl(url):
# 获取网址
try
:
r
=
requests.get(url)
r.raise_for_status()
r.encoding
=
r.apparent_encoding
return
r.text
except
:
return
""
|
Third, download pictures and get the next picture address
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
|
def
getpic(html):
# 获取图片地址并下载，再返回下一张图片地址
soup
=
BeautifulSoup(html,
'html.parser'
)
#all_img = soup.find('div', class_='imgBig').find_all('img')
all_img
=
soup.find(
'a'
,
class_
=
'downPic'
)
img_url
=
all_img[
'href'
]
reg
=
r
'<h3 class="title overOneTxt">(.*?)</h3>'
# r'<a\sclass=".*?"\starget=".*?"\shref=".*?">(.*)</a>' # 正则表达式
reg_ques
=
re.
compile
(reg)
# 编译一下正则表达式，运行的更快
image_name
=
reg_ques.findall(html)
# 匹配正则表达式
urlNextHtml
=
soup.find(
'a'
,
class_
=
'right btn'
)
urlNext
=
urlHead
+
urlNextHtml[
'href'
]
print
(
'正在下载：'
+
img_url)
root
=
'D:/pic/'
path
=
root
+
image_name[
0
]
+
'.jpg'
try
:
# 创建或判断路径图片是否存在并下载
if
not
os.path.exists(root):
os.mkdir(root)
if
not
os.path.exists(path):
r
=
requests.get(img_url)
with
open
(path,
'wb'
) as f:
f.write(r.content)
f.close()
print
(
"图片下载成功"
)
else
:
print
(
"文件已存在"
)
except
:
print
(
"爬取失败"
)
return
urlNext
|
四、结果
当然，我们也可以下载别的网页上图片，如下图，这就不放大了。
五、源代码
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
from
bs4
import
BeautifulSoup
import
requests
import
os
import
re
urlHead
=
'https://photo.fengniao.com/'
url
=
'https://photo.fengniao.com/pic_43591143.html'
def
getHtmlurl(url):
# 获取网址
try
:
r
=
requests.get(url)
r.raise_for_status()
r.encoding
=
r.apparent_encoding
return
r.text
except
:
return
""
def
getpic(html):
# 获取图片地址并下载，再返回下一张图片地址
soup
=
BeautifulSoup(html,
'html.parser'
)
#all_img = soup.find('div', class_='imgBig').find_all('img')
all_img
=
soup.find(
'a'
,
class_
=
'downPic'
)
img_url
=
all_img[
'href'
]
reg
=
r
'<h3 class="title overOneTxt">(.*?)</h3>'
# r'<a\sclass=".*?"\starget=".*?"\shref=".*?">(.*)</a>' # 正则表达式
reg_ques
=
re.
compile
(reg)
# 编译一下正则表达式，运行的更快
image_name
=
reg_ques.findall(html)
# 匹配正则表达式
urlNextHtml
=
soup.find(
'a'
,
class_
=
'right btn'
)
urlNext
=
urlHead
+
urlNextHtml[
'href'
]
print
(
'正在下载：'
+
img_url)
root
=
'D:/pic/'
path
=
root
+
image_name[
0
]
+
'.jpg'
try
:
# 创建或判断路径图片是否存在并下载
if
not
os.path.exists(root):
os.mkdir(root)
if
not
os.path.exists(path):
r
=
requests.get(img_url)
with
open
(path,
'wb'
) as f:
f.write(r.content)
f.close()
print
(
"图片下载成功"
)
else
:
print
(
"文件已存在"
)
except
:
print
(
"爬取失败"
)
return
urlNext
def
main():
html
=
(getHtmlurl(url))
print
(html)
return
getpic(html)
if
__name__
=
=
'__main__'
:
for
i
in
range
(
1
,
100
):
url
=
main()
|
下一篇应该是，爬某网站的小视频。
有问题，联系微信：GD5626633