Cara menggunakan Python untuk memuat turun imej serentak dengan berbilang benang

pip install requests

import requests

res = requests.get(img_url, stream=True)
count = 1
while res.status_code != 200 and count <= 5:
    res = requests.get(img_url, stream=True)
    print(f&#39;Retry: {count} {img_url}&#39;)
    count += 1

import more required library

import io
from PIL import Image

# lets try to find the image name
image_name = str(img_url[(img_url.rfind('/')) + 1:])
if '?' in image_name:
    image_name = image_name[:image_name.find('?')]

i = Image.open(io.BytesIO(res.content))
i.save(image_name)

def image_downloader(img_url: str):
    """
    Input:
    param: img_url  str (Image url)
    Tries to download the image url and use name provided in headers. Else it randomly picks a name
    """
    print(f'Downloading: {img_url}')
    res = requests.get(img_url, stream=True)
    count = 1
    while res.status_code != 200 and count <= 5:
        res = requests.get(img_url, stream=True)
        print(f&#39;Retry: {count} {img_url}&#39;)
        count += 1
    # checking the type for image
    if &#39;image&#39; not in res.headers.get("content-type", &#39;&#39;):
        print(&#39;ERROR: URL doesnot appear to be an image&#39;)
        return False
    # Trying to red image name from response headers
    try:
        image_name = str(img_url[(img_url.rfind(&#39;/&#39;)) + 1:])
        if &#39;?&#39; in image_name:
            image_name = image_name[:image_name.find(&#39;?&#39;)]
    except:
        image_name = str(random.randint(11111, 99999))+&#39;.jpg&#39;

    i = Image.open(io.BytesIO(res.content))
    download_location = &#39;cats&#39;
    i.save(download_location + &#39;/&#39;+image_name)
    return f&#39;Download complete: {img_url}&#39;

results = ThreadPool(process).imap_unordered(image_downloader, images_url)
for r in results:
    print(r)

def run_downloader(process:int, images_url:list):
    """
    Inputs:
        process: (int) number of process to run
        images_url:(list) list of images url
    """
    print(f'MESSAGE: Running {process} process')
    results = ThreadPool(process).imap_unordered(image_downloader, images_url)
    for r in results:
        print(r)

# -*- coding: utf-8 -*-
import io
import random
import shutil
import sys
from multiprocessing.pool import ThreadPool
import pathlib

import requests
from PIL import Image
import time

start = time.time()

def get_download_location():
    try:
        url_input = sys.argv[1]
    except IndexError:
        print('ERROR: Please provide the txt file\n$python image_downloader.py cats.txt')
    name = url_input.split('.')[0]
    pathlib.Path(name).mkdir(parents=True, exist_ok=True)
    return name

def get_urls():
    """
    通过读取终端中作为参数提供的 txt 文件返回 url 列表
    """
    try:
        url_input = sys.argv[1]
    except IndexError:
        print('ERROR: Please provide the txt file\n Example \n\n$python image_downloader.py dogs.txt \n\n')
        sys.exit()
    with open(url_input, 'r') as f:
        images_url = f.read().splitlines()

    print('{} Images detected'.format(len(images_url)))
    return images_url

def image_downloader(img_url: str):
    """
    输入选项:
    参数: img_url  str (Image url)
    尝试下载图像 url 并使用标题中提供的名称。否则它会随机选择一个名字
    """
    print(f'Downloading: {img_url}')
    res = requests.get(img_url, stream=True)
    count = 1
    while res.status_code != 200 and count <= 5:
        res = requests.get(img_url, stream=True)
        print(f&#39;Retry: {count} {img_url}&#39;)
        count += 1
    # checking the type for image
    if &#39;image&#39; not in res.headers.get("content-type", &#39;&#39;):
        print(&#39;ERROR: URL doesnot appear to be an image&#39;)
        return False
    # Trying to red image name from response headers
    try:
        image_name = str(img_url[(img_url.rfind(&#39;/&#39;)) + 1:])
        if &#39;?&#39; in image_name:
            image_name = image_name[:image_name.find(&#39;?&#39;)]
    except:
        image_name = str(random.randint(11111, 99999))+&#39;.jpg&#39;

    i = Image.open(io.BytesIO(res.content))
    download_location = get_download_location()
    i.save(download_location + &#39;/&#39;+image_name)
    return f&#39;Download complete: {img_url}&#39;

def run_downloader(process:int, images_url:list):
    """
    输入项:
        process: (int) number of process to run
        images_url:(list) list of images url
    """
    print(f&#39;MESSAGE: Running {process} process&#39;)
    results = ThreadPool(process).imap_unordered(image_downloader, images_url)
    for r in results:
        print(r)

try:
    num_process = int(sys.argv[2])
except:
    num_process = 10

images_url = get_urls()
run_downloader(num_process, images_url)

end = time.time()
print(&#39;Time taken to download {}&#39;.format(len(get_urls())))
print(end - start)

python3 image_downloader.py cats.txt

python3 image_downloader.py <filename_with_urls_seperated_by_newline.txt> <num_of_process>

python3 image_downloader.py cats.txt