Python多线程图片下载

// An highlighted block

import _thread
import http.client
import os
import re
import socket
import time
import urllib.request
import urllib.error
from time import sleep


def current_time():
    return time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())


def download_img(path, thread_del):
    if not os.path.exists(path):
        print("{} Folder {} not exist, now create it.".format(current_time(), path))
        os.makedirs(path, exist_ok=True)
    else:
        print("{} Folder {} exist.".format(current_time(), path))
        os.chmod(path, 777)

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.190 Safari/537.36'
    }

    root_url = 'https://www.google.com/search?q=kobe&tbm=isch&ved=2ahUKEwim3-nl047vAhXhTPUHHePDB6oQ2-cCegQIABAA'

    req = urllib.request.Request(url=root_url, headers=headers)

    data = urllib.request.urlopen(req).read()

    link_list = re.findall(r"https://.*?.jpg", data.decode("utf-8"))

    link_list_length = len(link_list)

    while thread_del < link_list_length:
        print('{} Downloading {}'.format(current_time(), link_list[thread_del]))
        new_req = urllib.request.Request(url=link_list[thread_del], headers=headers)
        jpg_name = '{}_{}.jpg'.format('razer_image', thread_del)
        abs_jpg_name = '{}\{}'.format(path, jpg_name)
        try:
            if not os.path.exists(abs_jpg_name):
                with urllib.request.urlopen(new_req, timeout=30) as response, open(
                        abs_jpg_name, 'wb') as f_save:
                    print('{} Saving image {}'.format(current_time(), abs_jpg_name))
                    f_save.write(response.read())
                    f_save.flush()
                    f_save.close()
                    print('{} Image {} download success'.format(current_time(), abs_jpg_name))
            else:
                print('{} {} already exist, escape it'.format(current_time(), abs_jpg_name))
        except urllib.error.HTTPError:
            print('{} HTTP error. Image {} download failed'.format(current_time(), abs_jpg_name))
        except urllib.error.URLError:
            print('{} URL error. Image {} download failed'.format(current_time(), abs_jpg_name))
        except http.client.HTTPException:
            print('{} HTTP exception. Image {} download failed'.format(current_time(), abs_jpg_name))
        except socket.timeout:
            print("{} Timeout. Image {} download failed".format(current_time(), abs_jpg_name))
        except UnicodeEncodeError:
            print("{} Unicode encode error. Image {} download failed".format(current_time(), abs_jpg_name))
        except http.client.RemoteDisconnected:
            print("{} HTTP client remote disconnected. Image {} download failed".format(current_time(), abs_jpg_name))
        print("{} Download finished, thread_del now is {}, link list length is {}".format(current_time(), thread_del,
                                                                                          link_list_length))
        thread_del += 5

    print("{} thread exit".format(current_time()))
    _thread.exit()


if __name__ == '__main__':

    path = 'E:\\Software\\Application\\PyCharmProjects\\WxjProject\\excel\\download\\image'

    try:
        _thread.start_new_thread(download_img, (path, 0,))
        _thread.start_new_thread(download_img, (path, 1,))
        _thread.start_new_thread(download_img, (path, 2,))
        _thread.start_new_thread(download_img, (path, 3,))
        _thread.start_new_thread(download_img, (path, 4,))
    except:
        print("Error: unable to start thread")

    count = 1000
    while count > 0:
        pass
        count -= 1
        sleep(10)
    # while True:
    #     pass