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
| import requests
from bs4 import BeautifulSoup
"""
wallhaven.cc
"""
def requestWallHaven(page, root_dir):
"""
壁纸数据爬取
:param page: 页数
:param root_dir: 图片存放地址
:return:
"""
res = requests.get("https://wallhaven.cc/hot?page=" + page).text
soup = BeautifulSoup(res, "html.parser")
for item in soup.find_all("a", "preview"):
print("页面地址: %s" % item.get("href"))
body = requests.get(item.get("href")).text
body_soup = BeautifulSoup(body, "html.parser")
img_url = body_soup.find("img", id="wallpaper").get("src")
print("图片地址: %s" % img_url)
data = img_url.split("/")
file_name = data[len(data) - 1]
print("文件名称: %s " % file_name)
with open(root_dir + file_name, "wb") as f:
f.write(requests.get(img_url).content)
print("Page => %s Success！" % page)
if __name__ == '__main__':
for i in range(32, 130):
requestWallHaven(str(i), "E:\\Wallhaven\\")
print("全部下载完毕！")
|
