def http_response_to_document_iters(response, read_chunk_size=4096):
"""
Takes a successful object-GET HTTP response and turns it into an
iterator of (first-byte, last-byte, length, headers, body-file)
5-tuples.
The response must either be a 200 or a 206; if you feed in a 204 or
something similar, this probably won't work.
:param response: HTTP response, like from bufferedhttp.http_connect(),
not a swob.Response.
"""
chunked = is_chunked(dict(response.getheaders()))
if response.status == 200:
if chunked:
# Single "range" that's the whole object with an unknown length
return iter([(0, None, None, response.getheaders(), response)])
# Single "range" that's the whole object
content_length = int(response.getheader("Content-Length"))
return iter([(0, content_length - 1, content_length, response.getheaders(), response)])
content_type, params_list = parse_content_type(response.getheader("Content-Type"))
if content_type != "multipart/byteranges":
# Single range; no MIME framing, just the bytes. The start and end
# byte indices are in the Content-Range header.
start, end, length = parse_content_range(response.getheader("Content-Range"))
return iter([(start, end, length, response.getheaders(), response)])
else:
# Multiple ranges; the response body is a multipart/byteranges MIME
# document, and we have to parse it using the MIME boundary
# extracted from the Content-Type header.
params = dict(params_list)
return multipart_byteranges_to_document_iters(response, params["boundary"], read_chunk_size)
def http_response_to_document_iters(response, read_chunk_size=4096):
"""
Takes a successful object-GET HTTP response and turns it into an
iterator of (first-byte, last-byte, length, headers, body-file)
5-tuples.
The response must either be a 200 or a 206; if you feed in a 204 or
something similar, this probably won't work.
:param response: HTTP response, like from bufferedhttp.http_connect(),
not a swob.Response.
"""
chunked = is_chunked(dict(response.getheaders()))
if response.status == 200:
if chunked:
# Single "range" that's the whole object with an unknown length
return iter([(0, None, None, response.getheaders(), response)])
# Single "range" that's the whole object
print 'Content-Length : ' + response.getheader('Content-Length')
content_length = int(response.getheader('Content-Length'))
return iter([(0, content_length - 1, content_length,
response.getheaders(), response)])
content_type, params_list = parse_content_type(
response.getheader('Content-Type'))
if content_type != 'multipart/byteranges':
# Single range; no MIME framing, just the bytes. The start and end
# byte indices are in the Content-Range header.
start, end, length = parse_content_range(
response.getheader('Content-Range'))
return iter([(start, end, length, response.getheaders(), response)])
else:
# Multiple ranges; the response body is a multipart/byteranges MIME
# document, and we have to parse it using the MIME boundary
# extracted from the Content-Type header.
params = dict(params_list)
return multipart_byteranges_to_document_iters(response,
params['boundary'],
read_chunk_size)
