有没有一种方法可以使用Python脚本发送POST请求来传输文件？
10个回答
250
来源: https://requests.readthedocs.io/en/latest/user/quickstart/#post-a-multipart-encoded-file
使用Requests上传多部分编码的文件非常简单：
with open('report.xls', 'rb') as f:
r = requests.post('http://httpbin.org/post', files={'report.xls': f})
就这样了。我不是在开玩笑——这只有一行代码。文件已经发送。让我们检查一下：
>>> r.text
{
"origin": "179.13.100.4",
"files": {
"report.xls": "<censored...binary...data>"
},
"form": {},
"url": "http://httpbin.org/post",
"args": {},
"headers": {
"Content-Length": "3196",
"Accept-Encoding": "identity, deflate, compress, gzip",
"Accept": "*/*",
"User-Agent": "python-requests/0.8.0",
"Host": "httpbin.org:80",
"Content-Type": "multipart/form-data; boundary=127.0.0.1.502.21746.1321131593.786.1"
},
"data": ""
}
- Piotr Dobrogost
7
31
是的。您可以使用urllib2模块，并使用multipart/form-data内容类型进行编码。以下是一些示例代码，可帮助您入门 - 它不仅适用于文件上传，但您应该能够阅读它并了解其工作方式：
user_agent = "image uploader"
default_message = "Image $current of $total"
import logging
import os
from os.path import abspath, isabs, isdir, isfile, join
import random
import string
import sys
import mimetypes
import urllib2
import httplib
import time
import re
def random_string (length):
return ''.join (random.choice (string.letters) for ii in range (length + 1))
def encode_multipart_data (data, files):
boundary = random_string (30)
def get_content_type (filename):
return mimetypes.guess_type (filename)[0] or 'application/octet-stream'
def encode_field (field_name):
return ('--' + boundary,
'Content-Disposition: form-data; name="%s"' % field_name,
'', str (data [field_name]))
def encode_file (field_name):
filename = files [field_name]
return ('--' + boundary,
'Content-Disposition: form-data; name="%s"; filename="%s"' % (field_name, filename),
'Content-Type: %s' % get_content_type(filename),
'', open (filename, 'rb').read ())
lines = []
for name in data:
lines.extend (encode_field (name))
for name in files:
lines.extend (encode_file (name))
lines.extend (('--%s--' % boundary, ''))
body = '\r\n'.join (lines)
headers = {'content-type': 'multipart/form-data; boundary=' + boundary,
'content-length': str (len (body))}
return body, headers
def send_post (url, data, files):
req = urllib2.Request (url)
connection = httplib.HTTPConnection (req.get_host ())
connection.request ('POST', req.get_selector (),
*encode_multipart_data (data, files))
response = connection.getresponse ()
logging.debug ('response = %s', response.read ())
logging.debug ('Code: %s %s', response.status, response.reason)
def make_upload_file (server, thread, delay = 15, message = None,
username = None, email = None, password = None):
delay = max (int (delay or '0'), 15)
def upload_file (path, current, total):
assert isabs (path)
assert isfile (path)
logging.debug ('Uploading %r to %r', path, server)
message_template = string.Template (message or default_message)
data = {'MAX_FILE_SIZE': '3145728',
'sub': '',
'mode': 'regist',
'com': message_template.safe_substitute (current = current, total = total),
'resto': thread,
'name': username or '',
'email': email or '',
'pwd': password or random_string (20),}
files = {'upfile': path}
send_post (server, data, files)
logging.info ('Uploaded %r', path)
rand_delay = random.randint (delay, delay + 5)
logging.debug ('Sleeping for %.2f seconds------------------------------\n\n', rand_delay)
time.sleep (rand_delay)
return upload_file
def upload_directory (path, upload_file):
assert isabs (path)
assert isdir (path)
matching_filenames = []
file_matcher = re.compile (r'\.(?:jpe?g|gif|png)$', re.IGNORECASE)
for dirpath, dirnames, filenames in os.walk (path):
for name in filenames:
file_path = join (dirpath, name)
logging.debug ('Testing file_path %r', file_path)
if file_matcher.search (file_path):
matching_filenames.append (file_path)
else:
logging.info ('Ignoring non-image file %r', path)
total_count = len (matching_filenames)
for index, file_path in enumerate (matching_filenames):
upload_file (file_path, index + 1, total_count)
def run_upload (options, paths):
upload_file = make_upload_file (**options)
for arg in paths:
path = abspath (arg)
if isdir (path):
upload_directory (path, upload_file)
elif isfile (path):
upload_file (path)
else:
logging.error ('No such path: %r' % path)
logging.info ('Done!')
- John Millikin
2
1在Windows上使用此代码时，我在Python 2.6.6中遇到了Multipart边界解析错误。我不得不像https://dev59.com/xHE85IYBdhLWcg3wViA4#2823331中讨论的那样从string.letters更改为string.ascii_letters才能使其正常工作。边界要求在此处讨论：https://dev59.com/4nVC5IYBdhLWcg3w51ry#147467。 - amit kumar
调用以下代码：
run_upload({'server':'', 'thread':''}, paths=['/path/to/file.txt'])
会导致以下错误：
在这一行中，upload_file(path)需要3个参数
因此我将其替换为以下代码：
upload_file(path, 1, 1) - tabdulradi
4
唯一阻止您直接在文件对象上使用urlopen的事情是，内置文件对象缺少len定义。一个简单的方法是创建一个子类，为urlopen提供正确的文件。
我还修改了下面文件中的Content-Type头。
import os
import urllib2
class EnhancedFile(file):
def __init__(self, *args, **keyws):
file.__init__(self, *args, **keyws)
def __len__(self):
return int(os.fstat(self.fileno())[6])
theFile = EnhancedFile('a.xml', 'r')
theUrl = "http://example.com/abcde"
theHeaders= {'Content-Type': 'text/xml'}
theRequest = urllib2.Request(theUrl, theFile, theHeaders)
response = urllib2.urlopen(theRequest)
theFile.close()
for line in response:
print line
- ilmarinen
2
@robert 我在Python2.7中测试了你的代码，但它没有起作用。urlopen(Request(theUrl, theFile, ...))仅将文件内容编码为普通的post方式，但无法指定正确的表单字段。我甚至尝试了变体urlopen(theUrl, urlencode({'serverside_field_name': EnhancedFile('my_file.txt')}))，它上传了一个文件，但（当然！）内容不正确，如<open file 'my_file.txt', mode 'r' at 0x00D6B718>。我错过了什么吗？ - RayLuo
感谢您的回答。通过使用上述代码，我已经使用PUT请求将2.2 GB的原始图像文件传输到了Web服务器。 - Akshay Patil
2
我将翻译如下：
我正在尝试测试Django REST API，并且它对我有效：
def test_upload_file(self):
filename = "/Users/Ranvijay/tests/test_price_matrix.csv"
data = {'file': open(filename, 'rb')}
client = APIClient()
# client.credentials(HTTP_AUTHORIZATION='Token ' + token.key)
response = client.post(reverse('price-matrix-csv'), data, format='multipart')
print response
self.assertEqual(response.status_code, status.HTTP_200_OK)
- Ranvijay Sachan
1
3这段代码存在内存泄漏 - 你忘记了将一个文件关闭(
close())。 - Chiefir2
Chris Atlee的poster库非常适用于此（特别是方便的函数poster.encode.multipart_encode()）。作为奖励，它支持流式传输大文件而无需将整个文件加载到内存中。另请参见Python问题3244。
- gotgenes
0
def visit_v2(device_code, camera_code):
image1 = MultipartParam.from_file("files", "/home/yuzx/1.txt")
image2 = MultipartParam.from_file("files", "/home/yuzx/2.txt")
datagen, headers = multipart_encode([('device_code', device_code), ('position', 3), ('person_data', person_data), image1, image2])
print "".join(datagen)
if server_port == 80:
port_str = ""
else:
port_str = ":%s" % (server_port,)
url_str = "http://" + server_ip + port_str + "/adopen/device/visit_v2"
headers['nothing'] = 'nothing'
request = urllib2.Request(url_str, datagen, headers)
try:
response = urllib2.urlopen(request)
resp = response.read()
print "http_status =", response.code
result = json.loads(resp)
print resp
return result
except urllib2.HTTPError, e:
print "http_status =", e.code
print e.read()
- user6081103
0
我尝试了这里的一些选项，但是我的头部有一些问题（'files'字段为空）。
使用requests进行POST并解决问题的简单模拟：
import requests
url = 'http://127.0.0.1:54321/upload'
file_to_send = '25893538.pdf'
files = {'file': (file_to_send,
open(file_to_send, 'rb'),
'application/pdf',
{'Expires': '0'})}
reply = requests.post(url=url, files=files)
print(reply.text)
更多内容请参见https://requests.readthedocs.io/en/latest/user/quickstart/
为了测试这段代码，您可以使用一个简单的虚拟服务器，例如这个（适用于GNU/Linux或类似系统）：
import os
from flask import Flask, request, render_template
rx_file_listener = Flask(__name__)
files_store = "/tmp"
@rx_file_listener.route("/upload", methods=['POST'])
def upload_file():
storage = os.path.join(files_store, "uploaded/")
print(storage)
if not os.path.isdir(storage):
os.mkdir(storage)
try:
for file_rx in request.files.getlist("file"):
name = file_rx.filename
destination = "/".join([storage, name])
file_rx.save(destination)
return "200"
except Exception:
return "500"
if __name__ == "__main__":
rx_file_listener.run(port=54321, debug=True)
- xCovelus
0
pip install http_file
#импорт вспомогательных библиотек
import urllib3
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
import requests
#импорт http_file
from http_file import download_file
#создание новой сессии
s = requests.Session()
#соеденение с сервером через созданную сессию
s.get('URL_MAIN', verify=False)
#загрузка файла в 'local_filename' из 'fileUrl' через созданную сессию
download_file('local_filename', 'fileUrl', s)
- Станислав Тышко
2
2通常最好的做法是用英文编写注释。 - obotezat
糟糕的例子。原始问题是关于上传文件，而不是下载。 - undefined
网页内容由stack overflow 提供, 点击上面的可以查看英文原文，
原文链接
原文链接
with open('report.xls', 'rb') as f: r = requests.post('http://httpbin.org/post', files={'report.xls': f})，这样在打开文件后会自动关闭。 - Hjulle