在 Django 中流式传输一个 CSV 文件时，如果 CSV 文件的大小超过 4MB，需要一种方法让用户能够主动下载这些文件，而不用等待所有数据都创建并提交到内存中。
- 解决方案
可以使用生成器创建一个流响应，并在生成器中逐步生成 CSV 数据。如果想在生成器中引发异常，需要确保使用 get_row_data() 函数创建了正确的数据。
from django.views.decorators.http import condition
@condition(etag_func=None)
def csv_view(request, app_label, model_name):
""" Based on the filters in the query, return a csv file for the given model """
#Get the model
model = models.get_model(app_label, model_name)
#if there are filters in the query
if request.method == 'GET':
#if the query is not empty
if request.META['QUERY_STRING'] != None:
keyword_arg_dict = {}
for key, value in request.GET.items():
#get the query filters
keyword_arg_dict[str(key)] = str(value)
#generate a list of row objects, based on the filters
objects_list = model.objects.filter(**keyword_arg_dict)
else:
#get all the model's objects
objects_list = model.objects.all()
else:
#get all the model's objects
objects_list = model.objects.all()
#create the reponse object with a csv mimetype
response = HttpResponse(
stream_response_generator(model, objects_list),
mimetype='text/plain',
)
response['Content-Disposition'] = "attachment; filename=foo.csv"
return response
def stream_response_generator(model, objects_list):
"""Streaming function to return data iteratively """
for row_item in objects_list:
yield get_row_data(model, row_item)
time.sleep(1)
def get_row_data(model, row):
"""Get a row of csv data from an object"""
#Create a temporary csv handle
csv_handle = cStringIO.StringIO()
#create the csv output object
csv_output = csv.writer(csv_handle)
value_list = []
for field in model._meta.fields:
#if the field is a related field (ForeignKey, ManyToMany, OneToOne)
if isinstance(field, RelatedField):
#get the related model from the field object
related_model = field.rel.to
for key in row.__dict__.keys():
#find the field in the row that matches the related field
if key.startswith(field.name):
#Get the unicode version of the row in the related model, based on the id
try:
entry = related_model.objects.get(
id__exact=int(row.__dict__[key]),
)
except:
pass
else:
value = entry.__unicode__().encode("utf-8")
break
#if it isn't a related field
else:
#get the value of the field
if isinstance(row.__dict__[field.name], basestring):
value = row.__dict__[field.name].encode("utf-8")
else:
value = row.__dict__[field.name]
value_list.append(value)
#add the row of csv values to the csv file
csv_output.writerow(value_list)
#Return the string value of the csv output
return csv_handle.getvalue()
如果需要处理更大的文件，可以使用流响应，这样可以避免内存不足的错误。
import cStringIO as StringIO
import csv
def csv_view(request):
...
response = StreamingHttpResponse(
stream(), content_type='text/csv'
)
disposition = "attachment; filename=file.csv"
response['Content-Disposition'] = disposition
return response
def stream():
buffer_ = StringIO.StringIO()
writer = csv.writer(buffer_)
for row in rows:
writer.writerow(row)
buffer_.seek(0)
data = buffer_.read()
buffer_.seek(0)
buffer_.truncate()
yield data
还可以使用中间件来实现流式传输，这可以避免 Django 的某些中间件导致的问题。
from django.middleware.http import ConditionalGetMiddleware
def compat_middleware_factory(klass):
"""
Class wrapper that only executes `process_response`
if `streaming` is not set on the `HttpResponse` object.
Django has a bad habbit of looking at the content,
which will prematurely exhaust the data source if we're
using generators or buffers.
"""
class compatwrapper(klass):
def process_response(self, req, resp):
if not hasattr(resp, 'streaming'):
return klass.process_response(self, req, resp)
return resp
return compatwrapper
ConditionalMiddlewareCompatProxy = compat_middleware_factory(ConditionalGetMiddleware)
...
response.streaming = True
