Python 进度条和下载

Question

我有一个 Python 脚本，它启动一个可下载文件的 URL。有没有办法让 Python 显示下载进度而不是启动浏览器？

Answer 1

我刚刚为此编写了一个超级简单（有点笨拙）的方法，用于从某个站点上抓取 PDF。请注意，它只能在基于 Unix 的系统（Linux、mac os）上正常工作，因为 PowerShell 无法处理 "\r"：

import sys
import requests

link = "http://indy/abcde1245"
file_name = "download.data"
with open(file_name, "wb") as f:
    print("Downloading %s" % file_name)
    response = requests.get(link, stream=True)
    total_length = response.headers.get('content-length')

    if total_length is None: # no content length header
        f.write(response.content)
    else:
        dl = 0
        total_length = int(total_length)
        for data in response.iter_content(chunk_size=4096):
            dl += len(data)
            f.write(data)
            done = int(50 * dl / total_length)
            sys.stdout.write("\r[%s%s]" % ('=' * done, ' ' * (50-done)) )    
            sys.stdout.flush()

它使用requests library，因此您需要安装它。这会在您的控制台中输出如下内容：

>正在下载download.data

>[=============                           ]

脚本中的进度条有 52 个字符宽（2 个字符就是 []，所以进度条有 50 个字符）。每个= 代表下载量的 2%。

Answer 2

您可以使用“clint”包（由与“请求”相同的作者编写）为您的下载添加一个简单的进度条，如下所示：

from clint.textui import progress

r = requests.get(url, stream=True)
path = '/some/path/for/file.txt'
with open(path, 'wb') as f:
    total_length = int(r.headers.get('content-length'))
    for chunk in progress.bar(r.iter_content(chunk_size=1024), expected_size=(total_length/1024) + 1): 
        if chunk:
            f.write(chunk)
            f.flush()

这将为您提供如下所示的动态输出：

[################################] 5210/5210 - 00:00:01

它应该也可以在多个平台上运行！你 can also change 条形到点或带有 .dots 和 .mill 而不是 .bar 的微调器。

享受吧！

Answer 3

带有 TQDM 的 Python 3

这是来自TQDM docs 的建议技术。

import urllib.request

from tqdm import tqdm


class DownloadProgressBar(tqdm):
    def update_to(self, b=1, bsize=1, tsize=None):
        if tsize is not None:
            self.total = tsize
        self.update(b * bsize - self.n)


def download_url(url, output_path):
    with DownloadProgressBar(unit='B', unit_scale=True,
                             miniters=1, desc=url.split('/')[-1]) as t:
        urllib.request.urlretrieve(url, filename=output_path, reporthook=t.update_to)

Answer 4

requests 和 tqdm 有答案。

import requests
from tqdm import tqdm


def download(url: str, fname: str):
    resp = requests.get(url, stream=True)
    total = int(resp.headers.get('content-length', 0))
    with open(fname, 'wb') as file, tqdm(
        desc=fname,
        total=total,
        unit='iB',
        unit_scale=True,
        unit_divisor=1024,
    ) as bar:
        for data in resp.iter_content(chunk_size=1024):
            size = file.write(data)
            bar.update(size)

要点：https://gist.github.com/yanqd0/c13ed29e29432e3cf3e7c38467f42f51

Answer 5

您也可以使用click。它有一个很好的进度条库：

import click

with click.progressbar(length=total_size, label='Downloading files') as bar:
    for file in files:
        download(file)
        bar.update(file.size)

Answer 6

抱歉回复晚了；刚刚更新了tqdm 文档：

https://github.com/tqdm/tqdm/#hooks-and-callbacks

使用 urllib.urlretrieve 和 OOP：

import urllib
from tqdm.auto import tqdm

class TqdmUpTo(tqdm):
    """Provides `update_to(n)` which uses `tqdm.update(delta_n)`."""
    def update_to(self, b=1, bsize=1, tsize=None):
        """
        b  : Blocks transferred so far
        bsize  : Size of each block
        tsize  : Total size
        """
        if tsize is not None:
            self.total = tsize
        self.update(b * bsize - self.n)  # will also set self.n = b * bsize

eg_link = "https://github.com/tqdm/tqdm/releases/download/v4.46.0/tqdm-4.46.0-py2.py3-none-any.whl"
eg_file = eg_link.split('/')[-1]
with TqdmUpTo(unit='B', unit_scale=True, unit_divisor=1024, miniters=1,
              desc=eg_file) as t:  # all optional kwargs
    urllib.urlretrieve(
        eg_link, filename=eg_file, reporthook=t.update_to, data=None)
    t.total = t.n

或使用requests.get 和文件包装器：

import requests
from tqdm.auto import tqdm

eg_link = "https://github.com/tqdm/tqdm/releases/download/v4.46.0/tqdm-4.46.0-py2.py3-none-any.whl"
eg_file = eg_link.split('/')[-1]
response = requests.get(eg_link, stream=True)
with tqdm.wrapattr(open(eg_file, "wb"), "write", miniters=1,
                   total=int(response.headers.get('content-length', 0)),
                   desc=eg_file) as fout:
    for chunk in response.iter_content(chunk_size=4096):
        fout.write(chunk)

你当然可以混搭技巧。

Answer 7

另一个不错的选择是wget:

import wget
wget.download('http://download.geonames.org/export/zip/US.zip')

输出将如下所示：

11% [........                                     ] 73728 / 633847

来源：https://medium.com/@petehouston/download-files-with-progress-in-python-96f14f6417a2

Answer 8

tqdm 包现在包含一个专门用于处理此类情况的函数：wrapattr。您只需包装对象的read（或write）属性，其余的由tqdm 处理。这是一个简单的下载功能，将所有内容与requests 放在一起：

def download(url, filename):
    import functools
    import pathlib
    import shutil
    import requests
    import tqdm
    
    r = requests.get(url, stream=True, allow_redirects=True)
    if r.status_code != 200:
        r.raise_for_status()  # Will only raise for 4xx codes, so...
        raise RuntimeError(f"Request to {url} returned status code {r.status_code}")
    file_size = int(r.headers.get('Content-Length', 0))

    path = pathlib.Path(filename).expanduser().resolve()
    path.parent.mkdir(parents=True, exist_ok=True)

    desc = "(Unknown total file size)" if file_size == 0 else ""
    r.raw.read = functools.partial(r.raw.read, decode_content=True)  # Decompress if needed
    with tqdm.tqdm.wrapattr(r.raw, "read", total=file_size, desc=desc) as r_raw:
        with path.open("wb") as f:
            shutil.copyfileobj(r_raw, f)

    return path

Answer 9

#定义进度条功能

def print_progressbar(total, current, barsize=60):
    progress = int(current*barsize/total)
    completed = str(int(current*100/total)) + '%'
    print('[', chr(9608)*progress, ' ', completed, '.'*(barsize-progress), '] ', str(i)+'/'+str(total), sep='', end='\r', flush=True)

# 示例代码

total = 6000
barsize = 60
print_frequency = max(min(total//barsize, 100), 1)
print("Start Task..", flush=True)
for i in range(1, total+1):
  if i%print_frequency == 0 or i == 1:
    print_progressbar(total, i, barsize)
print("\nFinished", flush=True)

#进度条截图：

以下行仅用于说明。在命令提示符下，您将看到显示增量进度的单个进度条。

[ 0%............................................................] 1/6000

[██████████ 16%..................................................] 1000/6000

[████████████████████ 33%........................................] 2000/6000

[██████████████████████████████ 50%..............................] 3000/6000

[████████████████████████████████████████ 66%....................] 4000/6000

[██████████████████████████████████████████████████ 83%..........] 5000/6000

[████████████████████████████████████████████████████████████ 100%] 6000/6000

Answer 10

只是对@rich-jones 回答的一些改进

 import re
 import request
 from clint.textui import progress

 def get_filename(cd):
    """
    Get filename from content-disposition
    """
    if not cd:
        return None
    fname = re.findall('filename=(.+)', cd)
    if len(fname) == 0:
        return None
    return fname[0].replace('"', "")

def stream_download_file(url, output, chunk_size=1024, session=None, verbose=False):
    
    if session:
        file = session.get(url, stream=True)
    else:
        file = requests.get(url, stream=True)
        
    file_name = get_filename(file.headers.get('content-disposition'))
    filepath = "{}/{}".format(output, file_name)
    
    if verbose: 
        print ("Downloading {}".format(file_name))
        
    with open(filepath, 'wb') as f:
        total_length = int(file.headers.get('content-length'))
        for chunk in progress.bar(file.iter_content(chunk_size=chunk_size), expected_size=(total_length/chunk_size) + 1): 
            if chunk:
                f.write(chunk)
                f.flush()
    if verbose: 
        print ("Finished")

Answer 11

您可以在此处流式传输下载 -> Stream a Download。

你也可以Stream Uploads。

除非您尝试访问 response.content，否则最重要的流式请求已完成 只有 2 行

for line in r.iter_lines():    
    if line:
        print(line)

Stream Requests