def prepare_response(self, request, cached): """Verify our vary headers match and construct a real urllib3 HTTPResponse object. """ # Special case the '*' Vary value as it means we cannot actually # determine if the cached response is suitable for this request. if "*" in cached.get("vary", {}): return # Ensure that the Vary headers for the cached response match our # request for header, value in list(cached.get("vary", {}).items()): if request.headers.get(header, None) != value: return body_raw = cached["response"].pop("body") headers = CaseInsensitiveDict(data=cached["response"]["headers"]) if headers.get("transfer-encoding", "") == "chunked": headers.pop("transfer-encoding") cached["response"]["headers"] = headers try: body = io.BytesIO(body_raw) except TypeError: # This can happen if cachecontrol serialized to v1 format (pickle) # using Python 2. A Python 2 str(byte string) will be unpickled as # a Python 3 str (unicode string), which will cause the above to # fail with: # # TypeError: 'str' does not support the buffer interface body = io.BytesIO(body_raw.encode("utf8")) return HTTPResponse(body=body, preload_content=False, **cached["response"])
def prepare_response(self, request, cached): """Verify our vary headers match and construct a real urllib3 HTTPResponse object. """ # Special case the '*' Vary value as it means we cannot actually # determine if the cached response is suitable for this request. if "*" in cached.get("vary", {}): return # Ensure that the Vary headers for the cached response match our # request for header, value in cached.get("vary", {}).items(): if request.headers.get(header, None) != value: return body_raw = cached["response"].pop("body") headers = CaseInsensitiveDict(data=cached["response"]["headers"]) if headers.get("transfer-encoding", "") == "chunked": headers.pop("transfer-encoding") cached["response"]["headers"] = headers try: body = io.BytesIO(body_raw) except TypeError: # This can happen if cachecontrol serialized to v1 format (pickle) # using Python 2. A Python 2 str(byte string) will be unpickled as # a Python 3 str (unicode string), which will cause the above to # fail with: # # TypeError: 'str' does not support the buffer interface body = io.BytesIO(body_raw.encode("utf8")) return HTTPResponse(body=body, preload_content=False, **cached["response"])
def cache_response(self, request, response, body=None, status_codes=None): """ Algorithm for caching requests. This assumes a requests Response object. """ # From httplib2: Don't cache 206's since we aren't going to # handle byte range requests cacheable_status_codes = status_codes or self.cacheable_status_codes if response.status not in cacheable_status_codes: logger.debug("Status code %s not in %s", response.status, cacheable_status_codes) return response_headers = CaseInsensitiveDict(response.headers) # If we've been given a body, our response has a Content-Length, that # Content-Length is valid then we can check to see if the body we've # been given matches the expected size, and if it doesn't we'll just # skip trying to cache it. if (body is not None and "content-length" in response_headers and response_headers["content-length"].isdigit() and int(response_headers["content-length"]) != len(body)): return cc_req = self.parse_cache_control(request.headers) cc = self.parse_cache_control(response_headers) cache_url = self.cache_url(request.url) logger.debug('Updating cache with response from "%s"', cache_url) # Delete it from the cache if we happen to have it stored there no_store = False if "no-store" in cc: no_store = True logger.debug('Response header has "no-store"') if "no-store" in cc_req: no_store = True logger.debug('Request header has "no-store"') if no_store and self.cache.get(cache_url): logger.debug('Purging existing cache entry to honor "no-store"') self.cache.delete(cache_url) if no_store: return # https://tools.ietf.org/html/rfc7234#section-4.1: # A Vary header field-value of "*" always fails to match. # Storing such a response leads to a deserialization warning # during cache lookup and is not allowed to ever be served, # so storing it can be avoided. if "*" in response_headers.get("vary", ""): logger.debug('Response header has "Vary: *"') return # If we've been given an etag, then keep the response if self.cache_etags and "etag" in response_headers: logger.debug("Caching due to etag") self.cache.set(cache_url, self.serializer.dumps(request, response, body=body)) # Add to the cache any 301s. We do this before looking that # the Date headers. elif response.status == 301: logger.debug("Caching permanant redirect") self.cache.set(cache_url, self.serializer.dumps(request, response)) # Add to the cache if the response headers demand it. If there # is no date header then we can't do anything about expiring # the cache. elif "date" in response_headers: # cache when there is a max-age > 0 if "max-age" in cc and cc["max-age"] > 0: logger.debug("Caching b/c date exists and max-age > 0") self.cache.set( cache_url, self.serializer.dumps(request, response, body=body)) # If the request can expire, it means we should cache it # in the meantime. elif "expires" in response_headers: if response_headers["expires"]: logger.debug("Caching b/c of expires header") self.cache.set( cache_url, self.serializer.dumps(request, response, body=body))
# a cache entry, but is left here for backwards compatibility. ======= >>>>>>> 71358189c5e72ee2ac9883b408a2f540a7f5745e if "*" in cached.get("vary", {}): return # Ensure that the Vary headers for the cached response match our # request for header, value in cached.get("vary", {}).items(): if request.headers.get(header, None) != value: return body_raw = cached["response"].pop("body") headers = CaseInsensitiveDict(data=cached["response"]["headers"]) if headers.get("transfer-encoding", "") == "chunked": headers.pop("transfer-encoding") cached["response"]["headers"] = headers try: body = io.BytesIO(body_raw) except TypeError: # This can happen if cachecontrol serialized to v1 format (pickle) # using Python 2. A Python 2 str(byte string) will be unpickled as # a Python 3 str (unicode string), which will cause the above to # fail with: # # TypeError: 'str' does not support the buffer interface body = io.BytesIO(body_raw.encode("utf8"))
class Response(object): """The :class:`Response <Response>` object, which contains a server's response to an HTTP request. """ __attrs__ = [ '_content', 'status_code', 'headers', 'url', 'history', 'encoding', 'reason', 'cookies', 'elapsed', 'request', ] def __init__(self): super(Response, self).__init__() self._content = False self._content_consumed = False #: Integer Code of responded HTTP Status. self.status_code = None #: Case-insensitive Dictionary of Response Headers. #: For example, ``headers['content-encoding']`` will return the #: value of a ``'Content-Encoding'`` response header. self.headers = CaseInsensitiveDict() #: File-like object representation of response (for advanced usage). #: Requires that ``stream=True` on the request. # This requirement does not apply for use internally to Requests. self.raw = None #: Final URL location of Response. self.url = None #: Encoding to decode with when accessing r.text. self.encoding = None #: A list of :class:`Response <Response>` objects from #: the history of the Request. Any redirect responses will end #: up here. The list is sorted from the oldest to the most recent request. self.history = [] self.reason = None #: A CookieJar of Cookies the server sent back. self.cookies = cookiejar_from_dict({}) #: The amount of time elapsed between sending the request #: and the arrival of the response (as a timedelta) self.elapsed = datetime.timedelta(0) def __getstate__(self): # Consume everything; accessing the content attribute makes # sure the content has been fully read. if not self._content_consumed: self.content return dict( (attr, getattr(self, attr, None)) for attr in self.__attrs__ ) def __setstate__(self, state): for name, value in state.items(): setattr(self, name, value) # pickled objects do not have .raw setattr(self, '_content_consumed', True) def __repr__(self): return '<Response [%s]>' % (self.status_code) def __bool__(self): """Returns true if :attr:`status_code` is 'OK'.""" return self.ok def __nonzero__(self): """Returns true if :attr:`status_code` is 'OK'.""" return self.ok def __iter__(self): """Allows you to use a response as an iterator.""" return self.iter_content(128) @property def ok(self): try: self.raise_for_status() except RequestException: return False return True @property def apparent_encoding(self): """The apparent encoding, provided by the lovely Charade library (Thanks, Ian!).""" return chardet.detect(self.content)['encoding'] 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. """ if self._content_consumed: # simulate reading small chunks of the content return iter_slices(self._content, chunk_size) def generate(): try: # Special case for urllib3. try: for chunk in self.raw.stream(chunk_size, decode_content=True): yield chunk except IncompleteRead as e: raise ChunkedEncodingError(e) except AttributeError: # Standard file-like object. while True: chunk = self.raw.read(chunk_size) if not chunk: break yield chunk self._content_consumed = True gen = generate() if decode_unicode: gen = stream_decode_response_unicode(gen, self) return gen def iter_lines(self, chunk_size=ITER_CHUNK_SIZE, decode_unicode=None): """Iterates over the response data, one line at a time. When stream=True is set on the request, this avoids reading the content at once into memory for large responses. """ pending = None for chunk in self.iter_content(chunk_size=chunk_size, decode_unicode=decode_unicode): if pending is not None: chunk = pending + chunk lines = chunk.splitlines() if lines and lines[-1] and chunk and lines[-1][-1] == chunk[-1]: pending = lines.pop() else: pending = None for line in lines: yield line if pending is not None: yield pending @property def content(self): """Content of the response, in bytes.""" if self._content is False: # Read the contents. try: if self._content_consumed: raise RuntimeError( 'The content for this response was already consumed') if self.status_code == 0: self._content = None else: self._content = bytes().join(self.iter_content(CONTENT_CHUNK_SIZE)) or bytes() except AttributeError: self._content = None 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 @property def text(self): """Content of the response, in unicode. If Response.encoding is None, encoding will be guessed using ``charade``. """ # 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 # 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 def json(self, **kwargs): """Returns the json-encoded content of a response, if any. :param \*\*kwargs: Optional arguments that ``json.loads`` takes. """ if not self.encoding and len(self.content) > 3: # No encoding set. JSON RFC 4627 section 3 states we should expect # UTF-8, -16 or -32. Detect which one to use; If the detection or # decoding fails, fall back to `self.text` (using chardet to make # a best guess). encoding = guess_json_utf(self.content) if encoding is not None: return json.loads(self.content.decode(encoding), **kwargs) return json.loads(self.text, **kwargs) @property def links(self): """Returns the parsed header links of the response, if any.""" header = self.headers.get('link') # l = MultiDict() l = {} if header: links = parse_header_links(header) for link in links: key = link.get('rel') or link.get('url') l[key] = link return l def raise_for_status(self): """Raises stored :class:`HTTPError`, if one occurred.""" http_error_msg = '' if 400 <= self.status_code < 500: http_error_msg = '%s Client Error: %s' % (self.status_code, self.reason) elif 500 <= self.status_code < 600: http_error_msg = '%s Server Error: %s' % (self.status_code, self.reason) if http_error_msg: raise HTTPError(http_error_msg, response=self) def close(self): """Closes the underlying file descriptor and releases the connection back to the pool. *Note: Should not normally need to be called explicitly.* """ return self.raw.release_conn()