Hướng dẫn python request file name - tên tệp yêu cầu python

Theo tài liệu, cả

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

4 và thuộc tính

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

5 của nó đều không cần thiết. Ngoài ra, tôi đã kiểm tra hàng chục liên kết trên internet và không tìm thấy phản hồi với tiêu đề

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

4. Vì vậy, trong hầu hết các trường hợp, tôi sẽ không dựa vào nó nhiều và chỉ lấy thông tin này từ URL yêu cầu (lưu ý: Tôi đang lấy nó từ

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

7 vì có thể có chuyển hướng và chúng tôi muốn lấy tên tệp thực). Tôi đã sử dụng

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

8 bởi vì nó trông mạnh mẽ hơn và xử lý các tên tệp được trích dẫn và chưa được trích dẫn. Cuối cùng, tôi đã đưa ra giải pháp này (hoạt động từ Python 3.8):

from urllib.parse import urlparse

import requests
import werkzeug


def get_filename(url: str):
    try:
        with requests.get(url) as req:
            if content_disposition := req.headers.get("Content-Disposition"):
                param, options = werkzeug.http.parse_options_header(content_disposition)
                if param == 'attachment' and (filename := options.get('filename')):
                    return filename

            path = urlparse(req.url).path
            name = path[path.rfind('/') + 1:]
            return name
    except requests.exceptions.RequestException as e:
        raise e

Tôi đã viết một số bài kiểm tra bằng cách sử dụng

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

9 và

import urllib
import os

output_dir = '/tmp'
image_url = 'https://vinasupport.com/assets/img/vinasupport_logo.png'

# Make output directory if not exist
if not os.path.exists(output_dir):
    os.makedirs(output_dir)

# save path
image_save_path = output_dir + '/' + os.path.basename(image_url)

# Download file from url
urllib.request.urlretrieve(image, image_save_path)
print(image_save_path)

0:

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

Bạn có thể download file (File ảnh, File text, …) từ 1 đường dẫn trên web sử dụng thư viện urllib của Python 3.

Đoạn source code Python 3 như sau:

import urllib
import os

output_dir = '/tmp'
image_url = 'https://vinasupport.com/assets/img/vinasupport_logo.png'

# Make output directory if not exist
if not os.path.exists(output_dir):
    os.makedirs(output_dir)

# save path
image_save_path = output_dir + '/' + os.path.basename(image_url)

# Download file from url
urllib.request.urlretrieve(image, image_save_path)
print(image_save_path)

Trong ví dụ trên, mình thực hiện download file ảnh có đường dẫn là: https://vinasupport.com/assets/img/vinasupport_logo.png

Và lưu nó xuống dường dẫn trên server /tmp/vinasupport_logo.png

Một cách khác là sử dụng thư viện requests

Đầu tiên cài đặt requests thông qua trình quản lý module / packages của Python 3

pip install requests

Sử dụng requests để download file:

from requests import get  # to make GET request

def download(url, file_name):
    # open in binary mode
    with open(file_name, "wb") as file:
        # get request
        response = get(url)
        # write to file
        file.write(response.content)

Nguồn: vinasupport.com

---

Python provides different modules like urllib, requests etc to download files from the web. I am going to use the request library of python to efficiently download files from the URLs.

Let’s start a look at step by step procedure to download files using URLs using request library−

1. Import module

import requests

2. Get the link or url

url = 'https://www.facebook.com/favicon.ico'
r = requests.get(url, allow_redirects=True)

3. Save the content with name.

open('facebook.ico', 'wb').write(r.content)

save the file as facebook.ico.

Example

import requests


url = 'https://www.facebook.com/favicon.ico'
r = requests.get(url, allow_redirects=True)

open('facebook.ico', 'wb').write(r.content)

Result

We can see the file is downloaded(icon) in our current working directory.

But we may need to download different kind of files like image, text, video etc from the web. So let’s first get the type of data the url is linking to−

>>> r = requests.get(url, allow_redirects=True)
>>> print(r.headers.get('content-type'))
image/png

However, there is a smarter way, which involved just fetching the headers of a url before actually downloading it. This allows us to skip downloading files which weren’t meant to be downloaded.

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

0

To restrict the download by file size, we can get the filezie from the content-length header and then do as per our requirement.

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

1

Get filename from an URL

To get the filename, we can parse the url. Below is a sample routine which fetches the last string after backslash(/).

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

2

Above will give the filename of the url. However, there are many cases where filename information is not present in the url for example – http://url.com/download. In such a case, we need to get the Content-Disposition header, which contains the filename information.

import pytest
import requests
import requests_mock

from main import get_filename

TEST_URL = 'https://pwrk.us/report.pdf'


@pytest.mark.parametrize(
    'headers,expected_filename',
    [
        (
                {'Content-Disposition': 'attachment; filename="filename.pdf"'},
                "filename.pdf"
        ),
        (
                # The string following filename should always be put into quotes;
                # but, for compatibility reasons, many browsers try to parse unquoted names that contain spaces.
                # https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Disposition#directives
                {'Content-Disposition': 'attachment; filename=filename with spaces.pdf'},
                "filename with spaces.pdf"
        ),
        (
                {'Content-Disposition': 'attachment;'},
                "report.pdf"
        ),
        (
                {'Content-Disposition': 'inline;'},
                "report.pdf"
        ),
        (
                {},
                "report.pdf"
        )
    ]
)
def test_get_filename(headers, expected_filename):
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, text='resp', headers=headers)
        assert get_filename(TEST_URL) == expected_filename


def test_get_filename_exception():
    with requests_mock.Mocker() as m:
        m.get(TEST_URL, exc=requests.exceptions.RequestException)
        with pytest.raises(requests.exceptions.RequestException):
            get_filename(TEST_URL)

3

The above url-parsing code in conjunction with above program will give you filename from Content-Disposition header most of the time.

Updated on 30-Jul-2019 22:30:26

• Related Questions & Answers
• Downloading file using SAP .NET Connector
• How are files extracted from a tar file using Python?
• Rename multiple files using Python
• Using SAP Web Service from WSDL file
• Web Scraping using Python and Scrapy?
• Python Implementing web scraping using lxml
• How to copy files from one folder to another using Python?
• How to copy files from one server to another using Python?
• How to convert PDF files to Excel files using Python?
• How to copy certain files from one folder to another using Python?
• Implementing web scraping using lxml in Python?
• Does HTML5 allow you to interact with local client files from within a web browser?
• Generate temporary files and directories using Python
• How to remove swap files using Python?
• How to create powerpoint files using Python