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
from requests import get
import time

try:
    with open('url.txt', 'r') as f:  # 该文件放入爬取到的图片链接
        urllist = f.read().splitlines()
except:
    urllist = []
print(urllist)


def GetPic():
    api = 'https://api.vvhan.com/api/bing?type=sj'  # 将要爬取的站点
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36'}
    url = get(api, headers=headers, timeout=2).request.url
    if url:
        return url


def init():
    i = 0
    ii = 0
    while i < 30 and ii < 3000:  # 连续30张图都重复或者本次采集到3000张图就停止
        url = GetPic()
        if url not in urllist:
            print(url)
            urllist.append(url)
            with open('url.txt', 'a+') as f:
                f.write(url + '\n')
            ii = ii + 1
            i = 0
        else:
            i = i + 1
            print("重复次数" + str(i) + ",重复的: " + url)
        time.sleep(1)


init()