adapters.py中的HTTPAdapter，build_response轉換urllib3的response object成為requests的Response
設定了以下屬性: status_code, headers, encoding, raw, reason, cookies
response.raw = resp
raw指的是urllib3 response object
def build_response(self, req, resp):
"""Builds a :class:`Response <requests.Response>` object from a urllib3
response. This should not be called from user code, and is only exposed
for use when subclassing the
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`
:param req: The :class:`PreparedRequest <PreparedRequest>` used to generate the response.
:param resp: The urllib3 response object.
:rtype: requests.Response
"""
response = Response()
# Fallback to None if there's no status_code, for whatever reason.
response.status_code = getattr(resp, 'status', None)
# Make headers case-insensitive.
response.headers = CaseInsensitiveDict(getattr(resp, 'headers', {}))
# Set encoding.
response.encoding = get_encoding_from_headers(response.headers)
response.raw = resp
response.reason = response.raw.reason
if isinstance(req.url, bytes):
response.url = req.url.decode('utf-8')
else:
response.url = req.url
# Add new cookies from the server.
extract_cookies_to_jar(response.cookies, req, resp)
# Give the Response some context.
response.request = req
response.connection = self
return response
除了資料之外要考慮編碼，若需要猜測編碼方式，借用了chardet這個套件的力量
elif self.encoding.lower() == 'utf-8':
encoding = 'utf-8-sig'
On encoding the utf-8-sig codec will write 0xef, 0xbb, 0xbf as the first three bytes to the file. On decoding utf-8-sig will skip those three bytes if they appear as the first three bytes in the file. In UTF-8, the use of the BOM is discouraged and should generally be avoided.
content = str(self.content, encoding, errors='replace')
Replace with a suitable replacement marker; Python will use the official U+FFFD REPLACEMENT CHARACTER for the built-in codecs on decoding, and ‘?’ on encoding. Implemented in replace_errors().
>>> import requests
>>> r = requests.get('https://api.github.com/events')
>>> r.text
u'[{"repository":{"open_issues":0,"url":"https://github.com/...
@property
def text(self):
"""Content of the response, in unicode.
If Response.encoding is None, encoding will be guessed using
``chardet``.
The encoding of the response content is determined based solely on HTTP
headers, following RFC 2616 to the letter. If you can take advantage of
non-HTTP knowledge to make a better guess at the encoding, you should
set ``r.encoding`` appropriately before accessing this property.
"""
# Try charset from content-type
content = None
encoding = self.encoding
if not self.content:
return str('')
# Fallback to auto-detected encoding.
if self.encoding is None:
encoding = self.apparent_encoding
# Forcefully remove BOM from UTF-8
elif self.encoding.lower() == 'utf-8':
encoding = 'utf-8-sig'
# Decode unicode from given encoding.
try:
content = str(self.content, encoding, errors='replace')
except (LookupError, TypeError):
# A LookupError is raised if the encoding was not found which could
# indicate a misspelling or similar mistake.
#
# A TypeError can be raised if encoding is None
#
# So we try blindly encoding.
content = str(self.content, errors='replace')
return content
>>> r.content
b'[{"repository":{"open_issues":0,"url":"https://github.com/...
CONTENT_CHUNK_SIZE的預設值為10 * 1024
利用了yield的概念處理chunk
@property
def content(self):
"""Content of the response, in bytes."""
if self._content is False:
# Read the contents.
if self._content_consumed:
raise RuntimeError(
'The content for this response was already consumed')
if self.status_code == 0 or self.raw is None:
self._content = None
else:
self._content = b''.join(self.iter_content(CONTENT_CHUNK_SIZE)) or b''
# if we had an error - throw the saved error
if self._error is not None:
raise self._error
self._content_consumed = True
# don't need to release the connection; that's been handled by urllib3
# since we exhausted the data.
return self._content
def iter_content(self, chunk_size=1, decode_unicode=False):
"""Iterates over the response data. When stream=True is set on the
request, this avoids reading the content at once into memory for
large responses. The chunk size is the number of bytes it should
read into memory. This is not necessarily the length of each item
returned as decoding can take place.
chunk_size must be of type int or None. A value of None will
function differently depending on the value of `stream`.
stream=True will read data as it arrives in whatever size the
chunks are received. If stream=False, data is returned as
a single chunk.
If decode_unicode is True, content will be decoded using the best
available encoding based on the response.
"""
def generate():
# Special case for urllib3.
if hasattr(self.raw, 'stream'):
try:
for chunk in self.raw.stream(chunk_size, decode_content=True):
yield chunk
except ProtocolError as e:
self._error = ChunkedEncodingError(e)
except DecodeError as e:
self._error = ContentDecodingError(e)
except ReadTimeoutError as e:
self._error = ConnectionError(e)
finally:
# if we had an error - throw the saved error
if self._error:
raise self._error
else:
# Standard file-like object.
while True:
chunk = self.raw.read(chunk_size)
if not chunk:
break
yield chunk
self._content_consumed = True
if self._content_consumed and isinstance(self._content, bool):
raise StreamConsumedError()
elif chunk_size is not None and not isinstance(chunk_size, int):
raise TypeError("chunk_size must be an int, it is instead a %s." % type(chunk_size))
# simulate reading small chunks of the content
reused_chunks = iter_slices(self._content, chunk_size)
stream_chunks = generate()
chunks = reused_chunks if self._content_consumed else stream_chunks
if decode_unicode:
chunks = stream_decode_response_unicode(chunks, self)
return chunks
iThome鐵人賽
看影片追技術