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
|
"""
爬虫
爬取 哔哩哔哩中 的领克壁纸
"""
import re
import requests
def main():
url = "https://www.bilibili.com/read/cv8222028"
meizi_html = requests.get(url).text
patt = "data-src=\"//i0.hdslb.com/bfs/article/(.*?.\w\wg)\" width"
src_list = re.findall(patt,meizi_html)
i = 0
for src in src_list:
i+=1
image_url = "http://i0.hdslb.com/bfs/article/"+src
download(image_url,"./lynk/",str(i)+image_url[-4:])
print(src)
def download(image_url,dir_path,file_name):
r = requests.get(image_url)
with open(dir_path+file_name, 'wb') as f:
f.write(r.content)
main()
|
在第一次获取到页面,最好先保存一下HTML,免得被封掉
