如图
代码:
1 import requests
2 import re
3 from lxml import html
4 import _thread
5
6
7 class wallpaper:
8 def __init__(self):
9 '''
10 初始化
11 '''
12 self.url = "http://simpledesktops.com/"
13 self.req_header = {
14 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
15 }
16 self.S = requests.session()
17
18 def home(self, num):
19 '''
20 访问首页
21 '''
22 self.numx = num
23 X = self.S.get(self.url+f"browse/{num}")
24 self.context = X.text
25
26 def url_all(self):
27 '''
28 获取所有子页链接
29 '''
30 tree = html.fromstring(self.context)
31 self.res = tree.xpath('//div[@class="desktop"]/a/@href')
32 print(self.res)
33
34 def Single(self, url):
35 '''
36 访问子页,下载图片
37 '''
38 url = url
39 O = self.S.get(self.url+url)
40 Otree = html.fromstring(O.text)
41 res = Otree.xpath('//div[@class="desktop"]/a/@href')
42 title = Otree.xpath('//h2/a/text()')
43 print(f"第{self.numx}页_标题:"+title[0])
44 cs = self.S.get(self.url+res[0])
45 print("链接:"+self.url+res[0])
46 with open(f'img/{self.numx}_{title[0]}.png', 'wb') as f:
47 f.write(cs.content)
48
49 def dowlod(self):
50 '''
51 下载所有图片
52 '''
53 for i in self.res:
54 self.Single(url=i)
55
56
57 def job(IN, OUT):
58 '''
59 线程函数
60 '''
61 for num in range(IN, OUT):
62 A = wallpaper()
63 A.home(num=num)
64 A.url_all()
65 A.dowlod()
66
67
68 try: # 多线程分段下载
69 _thread.start_new_thread(job, (5, 10, ))
70 _thread.start_new_thread(job, (14, 20, ))
71 _thread.start_new_thread(job, (23, 30, ))
72 _thread.start_new_thread(job, (32, 40, ))
73 _thread.start_new_thread(job, (41, 51, ))
74 except:
75 print("Error: 无法启动线程")
76
77
78 while 1: # 阻塞程序
79 pass
