python打造多线程图片下载工具

Posted on

整理一下以前写的代码, 发现一个小工具, 下载高清桌面图片, 使用的是多线程调用wget方式下载

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
57
import re
import os
import requests
from threading import Thread
 
 
# 请求头
def request_head(site):
    host = site.split("/")[2]
    heads = {
        "Content-Type": "text/html",
        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "en-US,en;q=0.9",
        "Host": host,
        "Referer": site,
        "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36",
    }
    return heads
 
 
# 发起请求
def request_spider(url):
    try:
        res = requests.get(url=url, headers=request_head(url))
        if res.status_code == 200:
            res.encoding = "utf-8"
            # print(url)
            return res.text
    except Exception as e:
        print("发起请求出错：", e)
 
 
def dowload_spider(url):
    file_path = os.path.dirname(os.path.abspath(__file__))
    res = request_spider(url)
    img_list = re.findall(r'data-progressive="(.*?)"', res)
    if os.path.exists(f'{file_path}/images'):
        os.chdir(f'{file_path}/images')
    else:
        os.mkdir(f'{file_path}/images')
        os.chdir(f'{file_path}/images')
    for item in img_list:
        if not os.path.exists(item.rsplit('/')[-1]):
            os.system(f'wget {item}')
 
 
if __name__ == '__main__':
    works = []
    url = 'https://bing.ioliu.cn/?p={}'
    for page in range(1, 102):
        thread = Thread(target=dowload_spider, args=(url.format(page),))
        thread.start()
        works.append(thread)
    for work in works:
        work.join()
    print("程序完成!")
Post Views: 77