1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
"""
This module implements the Response class which is used to represent HTTP
responses in Scrapy.
See documentation in docs/topics/request-response.rst
"""
from six.moves.urllib.parse import urljoin
from scrapy.http.request import Request
from scrapy.http.headers import Headers
from scrapy.link import Link
from scrapy.utils.trackref import object_ref
from scrapy.http.common import obsolete_setter
from scrapy.exceptions import NotSupported
class Response(object_ref):
def __init__(self, url, status=200, headers=None, body=b'', flags=None, request=None):
self.headers = Headers(headers or {})
self.status = int(status)
self._set_body(body)
self._set_url(url)
self.request = request
self.flags = [] if flags is None else list(flags)
@property
def meta(self):
try:
return self.request.meta
except AttributeError:
raise AttributeError(
"Response.meta not available, this response "
"is not tied to any request"
)
def _get_url(self):
return self._url
def _set_url(self, url):
if isinstance(url, str):
self._url = url
else:
raise TypeError('%s url must be str, got %s:' % (type(self).__name__,
type(url).__name__))
url = property(_get_url, obsolete_setter(_set_url, 'url'))
def _get_body(self):
return self._body
def _set_body(self, body):
if body is None:
self._body = b''
elif not isinstance(body, bytes):
raise TypeError(
"Response body must be bytes. "
"If you want to pass unicode body use TextResponse "
"or HtmlResponse.")
else:
self._body = body
body = property(_get_body, obsolete_setter(_set_body, 'body'))
def __str__(self):
return "<%d %s>" % (self.status, self.url)
__repr__ = __str__
def copy(self):
"""Return a copy of this Response"""
return self.replace()
def replace(self, *args, **kwargs):
"""Create a new Response with the same attributes except for those
given new values.
"""
for x in ['url', 'status', 'headers', 'body', 'request', 'flags']:
kwargs.setdefault(x, getattr(self, x))
cls = kwargs.pop('cls', self.__class__)
return cls(*args, **kwargs)
def urljoin(self, url):
"""Join this Response's url with a possible relative url to form an
absolute interpretation of the latter."""
return urljoin(self.url, url)
@property
def text(self):
"""For subclasses of TextResponse, this will return the body
as text (unicode object in Python 2 and str in Python 3)
"""
raise AttributeError("Response content isn't text")
def css(self, *a, **kw):
"""Shortcut method implemented only by responses whose content
is text (subclasses of TextResponse).
"""
raise NotSupported("Response content isn't text")
def xpath(self, *a, **kw):
"""Shortcut method implemented only by responses whose content
is text (subclasses of TextResponse).
"""
raise NotSupported("Response content isn't text")
def follow(self, url, callback=None, method='GET', headers=None, body=None,
cookies=None, meta=None, encoding='utf-8', priority=0,
dont_filter=False, errback=None):
# type: (...) -> Request
"""
Return a :class:`~.Request` instance to follow a link ``url``.
It accepts the same arguments as ``Request.__init__`` method,
but ``url`` can be a relative URL or a ``scrapy.link.Link`` object,
not only an absolute URL.
:class:`~.TextResponse` provides a :meth:`~.TextResponse.follow`
method which supports selectors in addition to absolute/relative URLs
and Link objects.
"""
if isinstance(url, Link):
url = url.url
url = self.urljoin(url)
return Request(url, callback,
method=method,
headers=headers,
body=body,
cookies=cookies,
meta=meta,
encoding=encoding,
priority=priority,
dont_filter=dont_filter,
errback=errback)
|
