对变量的请求+ Tqdm

Question

我从这个问题 (ctrl+ f表示“有一个请求和tqdm的答案”)获得了这个函数：

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='b',
        unit_scale=True,
        unit_divisor=1024,
    ) as bar:
        for data in resp.iter_content(chunk_size=1024):
            size = file.write(data)
            bar.update(size)

基本上，它下载一个文件并将其写到一个文件中，我希望它返回一个变量，该变量表示下载的文件，因此我做了如下操作：

def download(url: str, fname: str):
    import requests
    from tqdm import tqdm
    import os
    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='b',
        unit_scale=True,
        unit_divisor=1024,
    ) as bar:
        for data in resp.iter_content(chunk_size=1024):
            size = file.write(data)
            bar.update(size)
    with open(fname, "rb") as f:
        returned = f.read()
    os.remove(fname)
    return returned

现在，它保存文件，读取文件并将其保存到变量中，删除文件并返回变量。有什么方法可以直接将它保存到变量中吗？

Answer 1

那么，您可以只返回一个tqdm迭代器，并对块执行您喜欢的任何操作：

import requests
import tqdm
import io

def download(url: str):
    resp = requests.get(url, stream=True)
    total = int(resp.headers.get('content-length', 0))
    with tqdm.tqdm(
        desc=url,
        total=total,
        unit='b',
        unit_scale=True,
        unit_divisor=1024,
    ) as bar:
        for chunk in resp.iter_content(chunk_size=65536):
            bar.update(len(chunk))
            yield chunk

bio = io.BytesIO()

for chunk in download('http://...'):
    # Do something with the chunk; this just stores it in memory.
    bio.write(chunk)

content = bio.getvalue()  # Get the contents of the BytesIO() as a bytes.

当然，您可以将其重构为

import requests
import tqdm
import io


def download_as_bytes_with_progress(url: str) -> bytes:
    resp = requests.get(url, stream=True)
    total = int(resp.headers.get('content-length', 0))
    bio = io.BytesIO()
    with tqdm.tqdm(
        desc=url,
        total=total,
        unit='b',
        unit_scale=True,
        unit_divisor=1024,
    ) as bar:
        for chunk in resp.iter_content(chunk_size=65536):
            bar.update(len(chunk))
            bio.write(chunk)
    return bio.getvalue()