当前位置:首页> 正文

使用POST从Python脚本发送文件

使用POST从Python脚本发送文件

Send file using POST from a Python script

有没有一种方法可以使用Python脚本中的POST发送文件?


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

通过请求,上传Multipart编码的文件非常简单:

1
2
with open('report.xls', 'rb') as f:
    r = requests.post('http://httpbin.org/post', files={'report.xls': f})

而已。我不是在开玩笑-这是一行代码。文件已发送。让我们检查:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
>>> 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":""
}

是。您将使用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,可以帮助您入门-不仅仅是文件上传,但您应该能够通读它并了解其工作原理:

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
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 = '\
\
'
.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------------------------------\
\
'
, 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!')

看起来python请求无法处理非常大的多部分文件。

该文档建议您查看requests-toolbelt

这是他们文档中的相关页面。


阻止您直接在文件对象上直接使用urlopen的唯一原因是内置文件对象缺少len定义。一种简单的方法是创建一个子类,该子类为urlopen提供正确的文件。
我还修改了下面文件中的Content-Type标头。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
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

我正在尝试测试Django Rest API及其对我的工作:

1
2
3
4
5
6
7
8
9
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)

克里斯·阿特里(Chris Atlee)的海报库在此方面非常有效(尤其是便捷功能poster.encode.multipart_encode())。另外,它支持流式传输大文件,而无需将整个文件加载到内存中。另请参阅Python问题3244。


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
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()

您可能还想看一下带有示例的httplib2。我发现使用httplib2比使用内置HTTP模块更为简洁。


展开全文阅读

相关内容