基于urllib3的新Api实现

>>> import urllib3
>>> http = urllib3.PoolManager()
>>> r = http.request('GET', 'your_url_goes_here')
>>> r.status
   200
>>> r.data
   *****Response Data****

更多信息:https://pypi.org/project/urllib3/

我写了下面的代码，它可以在普通的Python 2或Python 3中工作。

import sys
try:
    import urllib.request
    python3 = True
except ImportError:
    import urllib2
    python3 = False


def progress_callback_simple(downloaded,total):
    sys.stdout.write(
        "\r" +
        (len(str(total))-len(str(downloaded)))*" " + str(downloaded) + "/%d"%total +
        " [%3.2f%%]"%(100.0*float(downloaded)/float(total))
    )
    sys.stdout.flush()

def download(srcurl, dstfilepath, progress_callback=None, block_size=8192):
    def _download_helper(response, out_file, file_size):
        if progress_callback!=None: progress_callback(0,file_size)
        if block_size == None:
            buffer = response.read()
            out_file.write(buffer)

            if progress_callback!=None: progress_callback(file_size,file_size)
        else:
            file_size_dl = 0
            while True:
                buffer = response.read(block_size)
                if not buffer: break

                file_size_dl += len(buffer)
                out_file.write(buffer)

                if progress_callback!=None: progress_callback(file_size_dl,file_size)
    with open(dstfilepath,"wb") as out_file:
        if python3:
            with urllib.request.urlopen(srcurl) as response:
                file_size = int(response.getheader("Content-Length"))
                _download_helper(response,out_file,file_size)
        else:
            response = urllib2.urlopen(srcurl)
            meta = response.info()
            file_size = int(meta.getheaders("Content-Length")[0])
            _download_helper(response,out_file,file_size)

import traceback
try:
    download(
        "https://geometrian.com/data/programming/projects/glLib/glLib%20Reloaded%200.5.9/0.5.9.zip",
        "output.zip",
        progress_callback_simple
    )
except:
    traceback.print_exc()
    input()

注:

支持“进度条”回调。 从我的网站上下载一个4 MB的测试包。zip。

import os,requests
def download(url):
    get_response = requests.get(url,stream=True)
    file_name  = url.split("/")[-1]
    with open(file_name, 'wb') as f:
        for chunk in get_response.iter_content(chunk_size=1024):
            if chunk: # filter out keep-alive new chunks
                f.write(chunk)


download("https://example.com/example.jpg")

基于urllib3的新Api实现

>>> import urllib3
>>> http = urllib3.PoolManager()
>>> r = http.request('GET', 'your_url_goes_here')
>>> r.status
   200
>>> r.data
   *****Response Data****

更多信息:https://pypi.org/project/urllib3/

Python 3

urllib.request.urlopen 进口urllib.request Response = urllib.request.urlopen('http://www.example.com/') HTML = response.read() urllib.request.urlretrieve 进口urllib.request urllib.request.urlretrieve (' http://www.example.com/songs/mp3.mp3 ', ' mp3.mp3 ') 注意:根据文档，urllib.request.urlretrieve是一个“遗留接口”，并且“在未来可能会被弃用”(感谢gerrit)

Python 2

urllib2。urlopen(谢谢科里) 进口urllib2 Response = urllib2.urlopen('http://www.example.com/') HTML = response.read() urllib。urlretrieve(感谢PabloG) 进口urllib urllib.urlretrieve (' http://www.example.com/songs/mp3.mp3 ', ' mp3.mp3 ')

为了完整起见，还可以使用子流程包调用任何程序来检索文件。专用于检索文件的程序比Python函数(如urlretrieve)更强大。例如，wget可以递归下载目录(-R)，可以处理FTP、重定向、HTTP代理，可以避免重新下载现有文件(-nc)，而aria2可以进行多连接下载，这可能会加快下载速度。

import subprocess
subprocess.check_output(['wget', '-O', 'example_output_file.html', 'https://example.com'])

在Jupyter Notebook中，也可以直接使用!语法:

!wget -O example_output_file.html https://example.com