plugin.video.torrenter/resources/scrapers/requests/models.py

838 lines
27 KiB
Python
Raw Normal View History

2015-01-09 14:11:21 +03:00
# -*- coding: utf-8 -*-
"""
requests.models
~~~~~~~~~~~~~~~
This module contains the primary objects that power Requests.
"""
import collections
import datetime
from io import BytesIO, UnsupportedOperation
from .hooks import default_hooks
from .structures import CaseInsensitiveDict
from .auth import HTTPBasicAuth
from .cookies import cookiejar_from_dict, get_cookie_header
from .packages.urllib3.fields import RequestField
from .packages.urllib3.filepost import encode_multipart_formdata
from .packages.urllib3.util import parse_url
from .packages.urllib3.exceptions import (
DecodeError, ReadTimeoutError, ProtocolError)
from .exceptions import (
HTTPError, RequestException, MissingSchema, InvalidURL,
ChunkedEncodingError, ContentDecodingError, ConnectionError,
StreamConsumedError)
from .utils import (
guess_filename, get_auth_from_url, requote_uri,
stream_decode_response_unicode, to_key_val_list, parse_header_links,
iter_slices, guess_json_utf, super_len, to_native_string)
from .compat import (
cookielib, urlunparse, urlsplit, urlencode, str, bytes, StringIO,
is_py2, chardet, json, builtin_str, basestring)
from .status_codes import codes
#: The set of HTTP status codes that indicate an automatically
#: processable redirect.
REDIRECT_STATI = (
codes.moved, # 301
codes.found, # 302
codes.other, # 303
codes.temporary_redirect, # 307
codes.permanent_redirect, # 308
)
DEFAULT_REDIRECT_LIMIT = 30
CONTENT_CHUNK_SIZE = 10 * 1024
ITER_CHUNK_SIZE = 512
json_dumps = json.dumps
class RequestEncodingMixin(object):
@property
def path_url(self):
"""Build the path URL to use."""
url = []
p = urlsplit(self.url)
path = p.path
if not path:
path = '/'
url.append(path)
query = p.query
if query:
url.append('?')
url.append(query)
return ''.join(url)
@staticmethod
def _encode_params(data):
"""Encode parameters in a piece of data.
Will successfully encode parameters when passed as a dict or a list of
2-tuples. Order is retained if data is a list of 2-tuples but arbitrary
if parameters are supplied as a dict.
"""
if isinstance(data, (str, bytes)):
return data
elif hasattr(data, 'read'):
return data
elif hasattr(data, '__iter__'):
result = []
for k, vs in to_key_val_list(data):
if isinstance(vs, basestring) or not hasattr(vs, '__iter__'):
vs = [vs]
for v in vs:
if v is not None:
result.append(
(k.encode('utf-8') if isinstance(k, str) else k,
v.encode('utf-8') if isinstance(v, str) else v))
return urlencode(result, doseq=True)
else:
return data
@staticmethod
def _encode_files(files, data):
"""Build the body for a multipart/form-data request.
Will successfully encode files when passed as a dict or a list of
2-tuples. Order is retained if data is a list of 2-tuples but arbitrary
if parameters are supplied as a dict.
"""
if (not files):
raise ValueError("Files must be provided.")
elif isinstance(data, basestring):
raise ValueError("Data must not be a string.")
new_fields = []
fields = to_key_val_list(data or {})
files = to_key_val_list(files or {})
for field, val in fields:
if isinstance(val, basestring) or not hasattr(val, '__iter__'):
val = [val]
for v in val:
if v is not None:
# Don't call str() on bytestrings: in Py3 it all goes wrong.
if not isinstance(v, bytes):
v = str(v)
new_fields.append(
(field.decode('utf-8') if isinstance(field, bytes) else field,
v.encode('utf-8') if isinstance(v, str) else v))
for (k, v) in files:
# support for explicit filename
ft = None
fh = None
if isinstance(v, (tuple, list)):
if len(v) == 2:
fn, fp = v
elif len(v) == 3:
fn, fp, ft = v
else:
fn, fp, ft, fh = v
else:
fn = guess_filename(v) or k
fp = v
if isinstance(fp, str):
fp = StringIO(fp)
if isinstance(fp, bytes):
fp = BytesIO(fp)
rf = RequestField(name=k, data=fp.read(),
filename=fn, headers=fh)
rf.make_multipart(content_type=ft)
new_fields.append(rf)
body, content_type = encode_multipart_formdata(new_fields)
return body, content_type
class RequestHooksMixin(object):
def register_hook(self, event, hook):
"""Properly register a hook."""
if event not in self.hooks:
raise ValueError('Unsupported event specified, with event name "%s"' % (event))
if isinstance(hook, collections.Callable):
self.hooks[event].append(hook)
elif hasattr(hook, '__iter__'):
self.hooks[event].extend(h for h in hook if isinstance(h, collections.Callable))
def deregister_hook(self, event, hook):
"""Deregister a previously registered hook.
Returns True if the hook existed, False if not.
"""
try:
self.hooks[event].remove(hook)
return True
except ValueError:
return False
class Request(RequestHooksMixin):
"""A user-created :class:`Request <Request>` object.
Used to prepare a :class:`PreparedRequest <PreparedRequest>`, which is sent to the server.
:param method: HTTP method to use.
:param url: URL to send.
:param headers: dictionary of headers to send.
:param files: dictionary of {filename: fileobject} files to multipart upload.
:param data: the body to attach to the request. If a dictionary is provided, form-encoding will take place.
:param json: json for the body to attach to the request (if data is not specified).
:param params: dictionary of URL parameters to append to the URL.
:param auth: Auth handler or (user, pass) tuple.
:param cookies: dictionary or CookieJar of cookies to attach to this request.
:param hooks: dictionary of callback hooks, for internal usage.
Usage::
>>> import requests
>>> req = requests.Request('GET', 'http://httpbin.org/get')
>>> req.prepare()
<PreparedRequest [GET]>
"""
def __init__(self,
method=None,
url=None,
headers=None,
files=None,
data=None,
params=None,
auth=None,
cookies=None,
hooks=None,
json=None):
# Default empty dicts for dict params.
data = [] if data is None else data
files = [] if files is None else files
headers = {} if headers is None else headers
params = {} if params is None else params
hooks = {} if hooks is None else hooks
self.hooks = default_hooks()
for (k, v) in list(hooks.items()):
self.register_hook(event=k, hook=v)
self.method = method
self.url = url
self.headers = headers
self.files = files
self.data = data
self.json = json
self.params = params
self.auth = auth
self.cookies = cookies
def __repr__(self):
return '<Request [%s]>' % (self.method)
def prepare(self):
"""Constructs a :class:`PreparedRequest <PreparedRequest>` for transmission and returns it."""
p = PreparedRequest()
p.prepare(
method=self.method,
url=self.url,
headers=self.headers,
files=self.files,
data=self.data,
json=self.json,
params=self.params,
auth=self.auth,
cookies=self.cookies,
hooks=self.hooks,
)
return p
class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
"""The fully mutable :class:`PreparedRequest <PreparedRequest>` object,
containing the exact bytes that will be sent to the server.
Generated from either a :class:`Request <Request>` object or manually.
Usage::
>>> import requests
>>> req = requests.Request('GET', 'http://httpbin.org/get')
>>> r = req.prepare()
<PreparedRequest [GET]>
>>> s = requests.Session()
>>> s.send(r)
<Response [200]>
"""
def __init__(self):
#: HTTP verb to send to the server.
self.method = None
#: HTTP URL to send the request to.
self.url = None
#: dictionary of HTTP headers.
self.headers = None
# The `CookieJar` used to create the Cookie header will be stored here
# after prepare_cookies is called
self._cookies = None
#: request body to send to the server.
self.body = None
#: dictionary of callback hooks, for internal usage.
self.hooks = default_hooks()
def prepare(self, method=None, url=None, headers=None, files=None,
data=None, params=None, auth=None, cookies=None, hooks=None,
json=None):
"""Prepares the entire request with the given parameters."""
self.prepare_method(method)
self.prepare_url(url, params)
self.prepare_headers(headers)
self.prepare_cookies(cookies)
self.prepare_body(data, files, json)
self.prepare_auth(auth, url)
# Note that prepare_auth must be last to enable authentication schemes
# such as OAuth to work on a fully prepared request.
# This MUST go after prepare_auth. Authenticators could add a hook
self.prepare_hooks(hooks)
def __repr__(self):
return '<PreparedRequest [%s]>' % (self.method)
def copy(self):
p = PreparedRequest()
p.method = self.method
p.url = self.url
p.headers = self.headers.copy() if self.headers is not None else None
p._cookies = self._cookies.copy() if self._cookies is not None else None
p.body = self.body
p.hooks = self.hooks
return p
def prepare_method(self, method):
"""Prepares the given HTTP method."""
self.method = method
if self.method is not None:
self.method = self.method.upper()
def prepare_url(self, url, params):
"""Prepares the given HTTP URL."""
#: Accept objects that have string representations.
#: We're unable to blindy call unicode/str functions
#: as this will include the bytestring indicator (b'')
#: on python 3.x.
#: https://github.com/kennethreitz/requests/pull/2238
if isinstance(url, bytes):
url = url.decode('utf8')
else:
url = unicode(url) if is_py2 else str(url)
# Don't do any URL preparation for non-HTTP schemes like `mailto`,
# `data` etc to work around exceptions from `url_parse`, which
# handles RFC 3986 only.
if ':' in url and not url.lower().startswith('http'):
self.url = url
return
# Support for unicode domain names and paths.
scheme, auth, host, port, path, query, fragment = parse_url(url)
if not scheme:
raise MissingSchema("Invalid URL {0!r}: No schema supplied. "
"Perhaps you meant http://{0}?".format(url))
if not host:
raise InvalidURL("Invalid URL %r: No host supplied" % url)
# Only want to apply IDNA to the hostname
try:
host = host.encode('idna').decode('utf-8')
except UnicodeError:
raise InvalidURL('URL has an invalid label.')
# Carefully reconstruct the network location
netloc = auth or ''
if netloc:
netloc += '@'
netloc += host
if port:
netloc += ':' + str(port)
# Bare domains aren't valid URLs.
if not path:
path = '/'
if is_py2:
if isinstance(scheme, str):
scheme = scheme.encode('utf-8')
if isinstance(netloc, str):
netloc = netloc.encode('utf-8')
if isinstance(path, str):
path = path.encode('utf-8')
if isinstance(query, str):
query = query.encode('utf-8')
if isinstance(fragment, str):
fragment = fragment.encode('utf-8')
enc_params = self._encode_params(params)
if enc_params:
if query:
query = '%s&%s' % (query, enc_params)
else:
query = enc_params
url = requote_uri(urlunparse([scheme, netloc, path, None, query, fragment]))
self.url = url
def prepare_headers(self, headers):
"""Prepares the given HTTP headers."""
if headers:
self.headers = CaseInsensitiveDict((to_native_string(name), value) for name, value in headers.items())
else:
self.headers = CaseInsensitiveDict()
def prepare_body(self, data, files, json=None):
"""Prepares the given HTTP body data."""
# Check if file, fo, generator, iterator.
# If not, run through normal process.
# Nottin' on you.
body = None
content_type = None
length = None
if json is not None:
content_type = 'application/json'
body = json_dumps(json)
is_stream = all([
hasattr(data, '__iter__'),
not isinstance(data, (basestring, list, tuple, dict))
])
try:
length = super_len(data)
except (TypeError, AttributeError, UnsupportedOperation):
length = None
if is_stream:
body = data
if files:
raise NotImplementedError('Streamed bodies and files are mutually exclusive.')
if length is not None:
self.headers['Content-Length'] = builtin_str(length)
else:
self.headers['Transfer-Encoding'] = 'chunked'
else:
# Multi-part file uploads.
if files:
(body, content_type) = self._encode_files(files, data)
else:
if data and json is None:
body = self._encode_params(data)
if isinstance(data, basestring) or hasattr(data, 'read'):
content_type = None
else:
content_type = 'application/x-www-form-urlencoded'
self.prepare_content_length(body)
# Add content-type if it wasn't explicitly provided.
if content_type and ('content-type' not in self.headers):
self.headers['Content-Type'] = content_type
self.body = body
def prepare_content_length(self, body):
if hasattr(body, 'seek') and hasattr(body, 'tell'):
body.seek(0, 2)
self.headers['Content-Length'] = builtin_str(body.tell())
body.seek(0, 0)
elif body is not None:
l = super_len(body)
if l:
self.headers['Content-Length'] = builtin_str(l)
elif (self.method not in ('GET', 'HEAD')) and (self.headers.get('Content-Length') is None):
self.headers['Content-Length'] = '0'
def prepare_auth(self, auth, url=''):
"""Prepares the given HTTP auth data."""
# If no Auth is explicitly provided, extract it from the URL first.
if auth is None:
url_auth = get_auth_from_url(self.url)
auth = url_auth if any(url_auth) else None
if auth:
if isinstance(auth, tuple) and len(auth) == 2:
# special-case basic HTTP auth
auth = HTTPBasicAuth(*auth)
# Allow auth to make its changes.
r = auth(self)
# Update self to reflect the auth changes.
self.__dict__.update(r.__dict__)
# Recompute Content-Length
self.prepare_content_length(self.body)
def prepare_cookies(self, cookies):
"""Prepares the given HTTP cookie data."""
if isinstance(cookies, cookielib.CookieJar):
self._cookies = cookies
else:
self._cookies = cookiejar_from_dict(cookies)
cookie_header = get_cookie_header(self._cookies, self)
if cookie_header is not None:
self.headers['Cookie'] = cookie_header
def prepare_hooks(self, hooks):
"""Prepares the given hooks."""
for event in hooks:
self.register_hook(event, hooks[event])
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, e.g. 404 or 200.
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).
#: Use of ``raw`` requires that ``stream=True`` be set 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 = []
#: Textual reason of responded HTTP Status, e.g. "Not Found" or "OK".
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)
#: The :class:`PreparedRequest <PreparedRequest>` object to which this
#: is a response.
self.request = None
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)
setattr(self, 'raw', None)
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 is_redirect(self):
"""True if this Response is a well-formed HTTP redirect that could have
been processed automatically (by :meth:`Session.resolve_redirects`).
"""
return ('location' in self.headers and self.status_code in REDIRECT_STATI)
@property
def is_permanent_redirect(self):
"""True if this Response one of the permanant versions of redirect"""
return ('location' in self.headers and self.status_code in (codes.moved_permanently, codes.permanent_redirect))
@property
def apparent_encoding(self):
"""The apparent encoding, provided by the chardet library"""
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 decode_unicode is True, content will be decoded using the best
available encoding based on the response.
"""
def generate():
try:
# Special case for urllib3.
try:
for chunk in self.raw.stream(chunk_size, decode_content=True):
yield chunk
except ProtocolError as e:
raise ChunkedEncodingError(e)
except DecodeError as e:
raise ContentDecodingError(e)
except ReadTimeoutError as e:
raise ConnectionError(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
if self._content_consumed and isinstance(self._content, bool):
raise StreamConsumedError()
# 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
def iter_lines(self, chunk_size=ITER_CHUNK_SIZE, decode_unicode=None, delimiter=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
if delimiter:
lines = chunk.split(delimiter)
else:
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
``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
# 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:
try:
return json.loads(self.content.decode(encoding), **kwargs)
except UnicodeDecodeError:
# Wrong UTF codec detected; usually because it's not UTF-8
# but some other 8-bit codec. This is an RFC violation,
# and the server didn't bother to tell us what codec *was*
# used.
pass
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):
"""Releases the connection back to the pool. Once this method has been
called the underlying ``raw`` object must not be accessed again.
*Note: Should not normally need to be called explicitly.*
"""
return self.raw.release_conn()