使用来自 Python 脚本的 POST 发送文件

有没有一种从 Python 脚本中使用 POST 发送文件的方法？

336242 次浏览
小开

是的。您将使用 urllib2模块，并使用 multipart/form-data内容类型进行编码。这里有一些示例代码可以帮助您开始——它不仅仅是文件上传，但是您应该能够通读它并了解它是如何工作的:

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!')
小开

您可能还想看看 httplib2和 例子。我发现使用 httplib2比使用内置的 HTTP 模块更简洁。

小开

Chris Atlee 的 海报库在这方面做得非常好(特别是方便的函数 poster.encode.multipart_encode())。额外的好处是，它支持大文件流，而不需要将整个文件加载到内存中。参见 巨蟒3244期。

小开

阻止您直接在 file 对象上使用 urlopen 的唯一原因是内置 file 对象缺少 Len定义。一个简单的方法是创建一个子类，它为 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
小开

发信人: https://requests.readthedocs.io/en/latest/user/quickstart/#post-a-multipart-encoded-file

请求使上传 Multipart 编码的文件变得非常简单:

with open('report.xls', 'rb') as f:
r = requests.post('http://httpbin.org/post', files={'report.xls': f})

就是这样。我不是开玩笑-这是一行代码。文件已经发送了。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": ""
}
小开

看起来 python 请求不能处理极大的多部分文件。

文档建议您查看 requests-toolbelt。

这是他们文档中的相关页面 。

小开 
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()
小开

我正在尝试测试 django rest api，它对我很有用:

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)
小开

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)
小开

我在这里尝试了一些选项，但是头部有一些问题(‘ files’字段为空)。

一个简单的模拟，用来解释我是如何使用请求和修复问题来完成这篇文章的:

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)

https://requests.readthedocs.io/en/latest/user/quickstart/台更多

为了测试这段代码，您可以使用一个简单的虚拟服务器，就像下面这个(可以在 GNU/Linux 或类似的系统中运行) :

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)

提交答案