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
|
"""
This module defines the Link object used in Link extractors.
For actual link extractors implementation see scrapy.contrib.linkextractor, or
its documentation in: docs/topics/link-extractors.rst
"""
class Link(object):
"""Link objects represent an extracted link by the LinkExtractor."""
__slots__ = ['url', 'text', 'fragment', 'nofollow']
def __init__(self, url, text='', fragment='', nofollow=False):
if isinstance(url, unicode):
import warnings
warnings.warn("Do not instantiate Link objects with unicode urls. " \
"Assuming utf-8 encoding (which could be wrong)")
url = url.encode('utf-8')
self.url = url
self.text = text
self.fragment = fragment
self.nofollow = nofollow
def __eq__(self, other):
return self.url == other.url and self.text == other.text and \
self.fragment == other.fragment and self.nofollow == other.nofollow
def __hash__(self):
return hash(self.url) ^ hash(self.text) ^ hash(self.fragment) ^ hash(self.nofollow)
def __repr__(self):
return 'Link(url=%r, text=%r, fragment=%r, nofollow=%r)' % \
(self.url, self.text, self.fragment, self.nofollow)
|
