Python:httppost使用流媒体发布大文件

通过阅读systempuntoout链接到的邮件列表线程,我找到了解决方案的线索。

这个 mmap 模块允许您打开类似字符串的文件。文件的一部分按需加载到内存中。

import urllib2
import mmap

# Open the file as a memory mapped string. Looks like a string, but 
# actually accesses the file behind the scenes. 
f = open('somelargefile.zip','rb')
mmapped_file_as_string = mmap.mmap(f.fileno(), 0, access=mmap.ACCESS_READ)

# Do the request
request = urllib2.Request(url, mmapped_file_as_string)
request.add_header("Content-Type", "application/zip")
response = urllib2.urlopen(request)

#close everything
mmapped_file_as_string.close()
f.close()

你试过吗 Mechanize

from mechanize import Browser
br = Browser()
br.open(url)
br.form.add_file(open('largefile.zip'), 'application/zip', 'largefile.zip')
br.submit()

或者,如果不想使用多部分/表单数据,请选中 this 老职位。

它提出了两种选择:

  1. Use mmap, Memory Mapped file object
  2. Patch httplib.HTTPConnection.send

您需要自己设置内容长度头。如果未设置,urllib2将对数据调用len(),而文件对象不支持。

import os.path
import urllib2

data = open(filename, 'r')
headers = { 'Content-Length' : os.path.getsize(filename) }
response = urllib2.urlopen(url, data, headers)

HTTPConnection 上课时间 httplib.py 在Python 2.7中:

def send(self, data):
    """Send `data' to the server."""
    if self.sock is None:
        if self.auto_open:
            self.connect()
        else:
            raise NotConnected()

    if self.debuglevel > 0:
        print "send:", repr(data)
    blocksize = 8192
    if hasattr(data,'read') and not isinstance(data, array):
        if self.debuglevel > 0: print "sendIng a read()able"
        datablock = data.read(blocksize)
        while datablock:
            self.sock.sendall(datablock)
            datablock = data.read(blocksize)
    else:
        self.sock.sendall(data)

试试pycurl。我没有任何东西安装程序会接受一个大文件

import os
import pycurl

class FileReader:
    def __init__(self, fp):
        self.fp = fp
    def read_callback(self, size):
        return self.fp.read(size)

c = pycurl.Curl()
c.setopt(pycurl.URL, url)
c.setopt(pycurl.UPLOAD, 1)
c.setopt(pycurl.READFUNCTION, FileReader(open(filename, 'rb')).read_callback)
filesize = os.path.getsize(filename)
c.setopt(pycurl.INFILESIZE, filesize)
c.perform()
c.close()

requests 你能做什么

with open('massive-body', 'rb') as f:
    requests.post('http://some.url/streamed', data=f)

here in their docs

下面是Python 2/Python 3的工作示例:

try:
    from urllib2 import urlopen, Request
except:
    from urllib.request import urlopen, Request

headers = { 'Content-length': str(os.path.getsize(filepath)) }
with open(filepath, 'rb') as f:
    req = Request(url, data=f, headers=headers)
    result = urlopen(req).read().decode()