Python 3.x Tornado:stream\u request\u body输出的mime类型
我正在使用Python 3.x Tornado:stream\u request\u body输出的mime类型,python-3.x,mime-types,tornado,content-type,Python 3.x,Mime Types,Tornado,Content Type,我正在使用tornado.web.stream\u request\u body(tornado v4.0.1)保存post数据,但似乎保存的文件的mime类型仍然是application/octet stream 我需要知道上传文件的mime类型,这是我的代码片段 @stream_request_body class MainHandler(tornado.web.RequestHandler): def post(self): pass def prepar
tornado.web.stream\u request\u body
(tornado v4.0.1)保存post数据,但似乎保存的文件的mime类型仍然是application/octet stream
我需要知道上传文件的mime类型,这是我的代码片段
@stream_request_body
class MainHandler(tornado.web.RequestHandler):
def post(self):
pass
def prepare(self):
self.temp_file = tempfile.NamedTemporaryFile(delete=False)
def data_received(self, chunk):
self.temp_file.write(chunk)
额外信息;
使用curl
和--数据二进制
参数正确保存文件
curl-v-XPOST--data binary@example.pdf localhost:8888/
但是浏览器上载带有多部分/表单数据
或带有参数-d
的curl不起作用。
当我用文本编辑器查看保存的文件时,我在第一行看到http post参数
-----------------------------192365691191582744435855330
Content-Disposition: form-data; name="upload"; filename="example.mp3"
Content-Type: audio/mpeg
...
unreadable binary data
有什么想法吗?在stream\u request\u body模式下,您可以获得客户端上传的原始body,而不需要创建self.request.arguments或self.request.files的处理。这是一个多部分/表单数据包装器(不是http头,尽管它们看起来很相似);您需要对此进行解析,以获取文件名和嵌入的数据。我认为标准库的电子邮件包中与mime相关的工具可能是将其保存到文件中后解析它的最佳方法。更新:我为Python3和Tornado 4.0+创建了一个包,可以与PyPi一起安装: 我知道前面的答案已经被接受了,但我也遇到了同样的问题,我可以为Python 3提供一个完整的模块——我们称之为post_streamer——它可以将任何流解析为任何请求的部分,而不需要使用太多内存
#!/usr/bin/env python3
"""Post data streamer for tornadoweb 4.0"""
import os
import re
import random
import tempfile
class SizeLimitError(Exception):
pass
class PostDataStreamer:
"""Parse a stream of multpart/form-data.
Useful for request handlers decorated with tornado.web.stream_request_body"""
SEP = b"\r\n"
LSEP = len(SEP)
PAT_HEADERVALUE = re.compile(r"""([^:]+):\s+([^\s;]+)(.*)""")
PAT_HEADERPARAMS = re.compile(r""";\s*([^=]+)=\"(.*?)\"(.*)""")
# Encoding for the header values. Only header name and parameters
# will be decoded. Streamed data will remain binary.
# This is required because multipart/form-data headers cannot
# be parsed without a valid encoding.
header_encoding = "UTF-8"
def __init__(self, total, tmpdir=None):
self.buf = b""
self.dlen = None
self.delimiter = None
self.in_data = False
self.headers = []
self.parts = []
self.total = total
self.received = 0
self.tmpdir = tmpdir
def _get_raw_header(self,data):
idx = data.find(self.SEP)
if idx>=0:
return (data[:idx], data[idx+self.LSEP:])
else:
return (None, data)
def receive(self, chunk):
self.received += len(chunk)
self.on_progress()
self.buf += chunk
if not self.delimiter:
self.delimiter, self.buf = self._get_raw_header(self.buf)
if self.delimiter:
self.delimiter+=self.SEP
self.dlen = len(self.delimiter)
elif len(self.buf)>1000:
raise Exception("Cannot find multipart delimiter")
else:
return
while True:
if self.in_data:
if (len(self.buf)>3*self.dlen):
idx = self.buf.find(self.SEP+self.delimiter)
if idx>=0:
self.feed_part(self.buf[:idx])
self.end_part()
self.buf = self.buf[idx+len(self.SEP+self.delimiter):]
self.in_data = False
else:
limit = len(self.buf)-2*self.dlen
self.feed_part(self.buf[:limit])
self.buf = self.buf[limit:]
return
else:
return
if not self.in_data:
while True:
header, self.buf = self._get_raw_header(self.buf)
if header==b"":
assert(self.delimiter)
self.in_data = True
self.begin_part(self.headers)
self.headers = []
break
elif header:
self.headers.append(self.parse_header(header))
else:
# Header is None, not enough data yet
return
def parse_header(self,header):
header = header.decode(self.header_encoding)
res = self.PAT_HEADERVALUE.match(header)
if res:
name,value,tail = res.groups()
params = {}
hdr = {"name":name,"value":value,"params":params}
while True:
res = self.PAT_HEADERPARAMS.match(tail)
if not res:
break
fname,fvalue,tail = res.groups()
params[fname] = fvalue
return hdr
else:
return {"value":header}
def begin_part(self,headers):
"""Internal method called when a new part is started."""
self.fout = tempfile.NamedTemporaryFile(
dir=self.tmpdir, delete=False)
self.part = {
"headers":headers,
"size":0,
"tmpfile":self.fout
}
self.parts.append(self.part)
def feed_part(self,data):
"""Internal method called when content is added to the current part."""
self.fout.write(data)
self.part["size"] += len(data)
def end_part(self):
"""Internal method called when receiving the current part has finished."""
# Will not close the file here, so we will be able to read later.
#self.fout.close()
#self.fout.flush() This is not needed because we update part["size"]
pass
def finish_receive(self):
"""Call this after the last receive() call.
You MUST call this before using the parts."""
if self.in_data:
idx = self.buf.rfind(self.SEP+self.delimiter[:-2])
if idx>0:
self.feed_part(self.buf[:idx])
self.end_part()
def release_parts(self):
"""Call this to remove the temporary files."""
for part in self.parts:
part["tmpfile"].close()
os.unlink(part["tmpfile"].name)
def get_part_payload(self, part):
"""Return the contents of a part.
Warning: do not use this for big files!"""
fsource = part["tmpfile"]
fsource.seek(0)
return fsource.read()
def get_part_ct_params(self, part):
"""Get content-disposition parameters.
If there is no content-disposition header then it returns an
empty list."""
for header in part["headers"]:
if header.get("name","").lower().strip()=="content-disposition":
return header.get("params",[])
return []
def get_part_ct_param(self, part, pname, defval=None):
"""Get parameter for a part.
@param part: The part
@param pname: Name of the parameter, case insensitive
@param defval: Value to return when not found.
"""
ct_params = self.get_part_ct_params(part)
for name in ct_params:
if name.lower().strip()==pname:
return ct_params[name]
return defval
def get_part_name(self, part):
"""Get name of a part.
When not given, returns None."""
return self.get_part_ct_param(part, "name", None)
def get_parts_by_name(self, pname):
"""Get a parts by name.
@param pname: Name of the part. This is case sensitive!
Attention! A form may have posted multiple values for the same
name. So the return value of this method is a list of parts!"""
res = []
for part in self.parts:
name = self.get_part_name(part)
if name==pname:
res.append(part)
return res
def get_values(self, fnames, size_limit=10*1024):
"""Return a dictionary of values for the given field names.
@param fnames: A list of field names.
@param size_limit: Maximum size of the value of a single field.
If a field's size exceeds this then SizeLimitError is raised.
Warning: do not use this for big file values.
Warning: a form may have posted multiple values for a field name.
This method returns the first available value for that name.
To get all values, use the get_parts_by_name method.
Tip: use get_nonfile_names() to get a list of field names
that are not originally files.
"""
res = {}
for fname in fnames:
parts = self.get_parts_by_name(fname)
if not parts:
raise KeyError("No such field: %s"%fname)
size = parts[0]["size"]
if size>size_limit:
raise SizeLimitError("Part size=%s > limit=%s"%(size, limit))
res[fname] = self.get_part_payload(parts[0])
return res
def get_nonfile_names(self):
"""Get a list of part names are originally not files.
It examines the filename attribute of the content-disposition header.
Be aware that these fields still may be huge in size."""
res = []
for part in self.parts:
filename = self.get_part_ct_param(part, "filename", None)
if filename is None:
name = self.get_part_name(part)
if name:
res.append(name)
return res
def examine(self):
"""Debugging method for examining received data."""
print("============= structure =============")
for idx,part in enumerate(self.parts):
print("PART #",idx)
print(" HEADERS")
for header in part["headers"]:
print(" ",repr(header.get("name","")),"=",repr(header.get("value","")))
params = header.get("params",None)
if params:
for pname in params:
print(" ",repr(pname),"=",repr(params[pname]))
print(" DATA")
print(" SIZE", part["size"])
print(" LOCATION",part["tmpfile"].name)
if part["size"]<80:
print(" PAYLOAD:",repr(self.get_part_payload(part)))
else:
print(" PAYLOAD:","<too long...>")
print("========== non-file values ==========")
print(self.get_values(self.get_nonfile_names()))
def on_progress(self):
"""Override this function to handle progress of receiving data."""
pass # Received <self.received> of <self.total>
#/usr/bin/env蟒蛇3
“”“TornadowWeb 4.0的Post数据流”“”
导入操作系统
进口稀土
随机输入
导入临时文件
类SizeLimitError(异常):
通过
类PostDataStreamer:
“”“解析多部分/表单数据流。
对于用tornado.web.stream\u请求\u正文“”修饰的请求处理程序非常有用
SEP=b“\r\n”
LSEP=len(九月)
PAT_HEADERVALUE=re.compile(r“”([^:]+):\s+([^\s;]+)(.*))
PAT_HEADERPARAMS=re.compile(r“”;\s*([^=]+)=\“(.*?\”(.*)”)
#标题值的编码。仅标题名称和参数
#将被解码。流式数据将保持二进制。
#这是必需的,因为多部分/表单数据头不能
#无法在没有有效编码的情况下解析。
标题编码=“UTF-8”
def uuu init uuuu(self、total、tmpdir=None):
self.buf=b“”
self.dlen=无
self.delimiter=None
self.in_data=False
self.headers=[]
self.parts=[]
self.total=总计
self.received=0
self.tmpdir=tmpdir
def_获取_原始_标题(自身、数据):
idx=data.find(self.SEP)
如果idx>=0:
返回(数据[:idx],数据[idx+self.LSEP:]
其他:
返回(无,数据)
def接收(自身、区块):
self.received+=len(块)
self.on_progress()
self.buf+=块
如果不是self.delimiter:
self.delimiter,self.buf=self.\u获取\u原始\u头(self.buf)
如果使用self.delimiter:
self.delimiter+=self.SEP
self.dlen=len(self.delimiter)
elif-len(自身buf)>1000:
引发异常(“找不到多部分分隔符”)
其他:
返回
尽管如此:
如果self.in_数据:
如果(len(self.buf)>3*self.dlen):
idx=self.buf.find(self.SEP+self.delimiter)
如果idx>=0:
self.feed_部分(self.buf[:idx])
self.end_part()
self.buf=self.buf[idx+len(self.SEP+self.delimiter):]
self.in_data=False
其他:
极限=len(self.buf)-2*self.dlen
自进给零件(自进给[:极限])
self.buf=self.buf[限制:]
返回
其他:
返回
如果不是self.in_数据:
尽管如此:
标头,self.buf=self.\u获取\u原始\u标头(self.buf)
如果标题==b“”:
断言(self.delimiter)
self.in_data=True
self.begin\u部分(self.headers)
self.headers=[]
打破
elif标题:
self.headers.append(self.parse_头(头))
其他:
#标题为“无”,数据不足
返回
def parse_标头(自身,标头):
header=header.decode(self.header\u编码)
res=self.PAT_HEADERVALUE.match(标题)
如果有的话:
名称、值、尾部=资源组()
参数={}
hdr={“name”:name,“value”:value,“params”:params}
尽管如此:
res=自身。PAT_头参数。匹配(尾)
如果不是,则:
打破
fname,fvalue,tail=res.groups()
params[fname]=fvalue
返回hdr
其他:
返回{“值”:头}
def begin_部件(自身、标题):
“”“启动新部件时调用的内部方法。”“”
self.fout=tempfile.NamedTemporaryFile(
dir=self.tmpdir,delete=False)
self.part={
“标题”:标题,
“大小”:0,
“tmpfile”:self.fout
}
self.parts.append(self.part)
def供给_部件(自身、数据):
“”“将内容添加到当前部分时调用的内部方法。”“”
自寻源写入(数据)
自身零件[“尺寸”]+=len(数据)
def end_部件(自身):
“”“接收当前部件时调用的内部方法已完成。”“”
#不会在此处关闭文件,因此我们可以稍后读取。
#self.fout.close()
#self.fout.flush()这是不需要的,因为我们更新了part[“siz
#!/usr/bin/env python3
from tornado.ioloop import IOLoop
from tornado.web import RequestHandler, Application, url, stream_request_body
from tornado.httpserver import HTTPServer
from tornado.ioloop import IOLoop
from post_streamer import PostDataStreamer
import sys
class MyPostDataStreamer(PostDataStreamer):
percent = 0
def on_progress(self):
"""Override this function to handle progress of receiving data."""
if self.total:
new_percent = self.received*100//self.total
if new_percent != self.percent:
self.percent = new_percent
print("progress",new_percent)
@stream_request_body
class StreamHandler(RequestHandler):
def get(self):
self.write('''<html><body>
<form method="POST" action="/" enctype="multipart/form-data">
File #1: <input name="file1" type="file"><br>
File #2: <input name="file2" type="file"><br>
File #3: <input name="file3" type="file"><br>
Other field 1: <input name="other1" type="text"><br>
Other field 2: <input name="other2" type="text"><br>
Other field 3: <input name="other3" type="text"><br>
<input type="submit">
</form>
</body></html>''')
def post(self):
try:
#self.fout.close()
self.ps.finish_receive()
# Use parts here!
self.set_header("Content-Type","text/plain")
oout = sys.stdout
try:
sys.stdout = self
self.ps.examine()
finally:
sys.stdout = oout
finally:
# Don't forget to release temporary files.
self.ps.release_parts()
def prepare(self):
# TODO: get content length here?
try:
total = int(self.request.headers.get("Content-Length","0"))
except:
total = 0
self.ps = MyPostDataStreamer(total) #,tmpdir="/tmp"
#self.fout = open("raw_received.dat","wb+")
def data_received(self, chunk):
#self.fout.write(chunk)
self.ps.receive(chunk)
def main():
application = Application([
url(r"/", StreamHandler),
])
max_buffer_size = 4 * 1024**3 # 4GB
http_server = HTTPServer(
application,
max_buffer_size=max_buffer_size,
)
http_server.listen(8888)
IOLoop.instance().start()
main()