python多线程下载文件-无忧网

从文件中读取图片url和名称，将url中的文件下载下来。文件中每一行包含一个url和文件名，用制表符隔开。

1、使用requests请求url并下载文件

            def
             download(img_url, img_name):
    with closing(requests.get(img_url, stream=True)) as r:
        with open(os.path.join(out_dir, img_name), ‘wb‘) as f:
            for data in r.iter_content(1024):
                f.write(data)

2、从文件中读取url，考虑文件较大，使用生成器的方式读取。

            def
             get_imgurl_generate():
    with open(
            ‘
            ./example.txt
            ‘, ‘r‘) as f:
        for line in f:
            line = line.strip()
            yield imgs

3、使用多线程进行下载

lock = threading.Lock()
def loop(imgs):
    while True:
        try:
            with lock:
                img_url, img_name = next(imgs)
        except StopIteration:
            break
        download_pic(img_url, img_name)

img_gen = imgurl_generate()

for i in range(0, thread_num):
    t = threading.Thread(target=loop, args=(img_gen,))
    t.start()

完整代码，加入异常处理

                 1
                #
                 -*- coding: utf-8 -*-
                 2
                import
                 os

                 3
                from contextlib import closing
 4import threading
 5import requests
 6import time
 7 8 9 headers = {
10‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36‘11}
1213#输出文件夹14 out_dir = ‘./output‘15#线程数16 thread_num = 20
17#http请求超时设置18 timeout = 5
1920ifnot os.path.exists(out_dir):
21    os.mkdir(out_dir)
22232425def download(img_url, img_name):
26if os.path.isfile(os.path.join(out_dir, img_name)):
27return28     with closing(requests.get(img_url, stream=True, headers=headers, timeout=timeout)) as r:
29         rc = r.status_code
30if 299 < rc or rc < 200:
31print‘returnCode%st%s‘ % (rc, img_url)
32return33         content_length = int(r.headers.get(‘content-length‘, ‘0‘))
34if content_length == 0:
35print‘size0t%s‘ % img_url
36return37try:
38             with open(os.path.join(out_dir, img_name), ‘wb‘) as f:
39for data in r.iter_content(1024):
40                    f.write(data)
41except:
42print‘savefailt%s‘ % img_url
4344def get_imgurl_generate():
45     with open(‘./final.scp‘, ‘r‘) as f:
46         index = 0
47for line in f:
48             index += 1
49if index % 500 == 0:
50print‘execute %s line at %s‘ % (index, time.time())
51ifnot line:
52print ur‘line %s is empty "t"‘ % index
53continue54             line = line.strip()
55try:
56                 imgs = line.split(‘t‘)
57if len(imgs) != 2:
58print ur‘line %s splite error‘ % index
59continue60ifnot imgs[0] ornot imgs[1]:
61print ur‘line %s img is empty‘ % index
62continue63yield imgs
64except:
65print ur‘line %s can not split by "t"‘ % index
666768 lock = threading.Lock()
69def loop(imgs):
70print‘thread %s is running...‘ % threading.current_thread().name
7172while True:
73try:
74            with lock:
75                 img_url, img_name = next(imgs)
76except StopIteration:
77break78try:
79            download(img_url, img_name)
80except:
81print‘exceptfailt%s‘ % img_url
82print‘thread %s is end...‘ % threading.current_thread().name
8384 img_gen = get_imgurl_generate()
8586for i in range(0, thread_num):
87     t = threading.Thread(target=loop, name=‘LoopThread %s‘ % i, args=(img_gen,))
88     t.start()

View Code

原文：http://www.cnblogs.com/lilinwei340/p/6793796.html

【说明】：本文章由站长整理发布，文章内容不代表本站观点，如文中有侵权行为，请与本站客服联系(QQ:254677821)！

python多线程下载文件

相关教程推荐

其他课程推荐