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
134
135
136
|
"""
scrapy.linkextractors
This package contains a collection of Link Extractors.
For more info see docs/topics/link-extractors.rst
"""
import re
from urllib.parse import urlparse
from warnings import warn
from parsel.csstranslator import HTMLTranslator
from w3lib.url import canonicalize_url
from scrapy.utils.deprecate import ScrapyDeprecationWarning
from scrapy.utils.misc import arg_to_iter
from scrapy.utils.url import (
url_is_from_any_domain, url_has_any_extension,
)
# common file extensions that are not followed if they occur in links
IGNORED_EXTENSIONS = [
# archives
'7z', '7zip', 'bz2', 'rar', 'tar', 'tar.gz', 'xz', 'zip',
# images
'mng', 'pct', 'bmp', 'gif', 'jpg', 'jpeg', 'png', 'pst', 'psp', 'tif',
'tiff', 'ai', 'drw', 'dxf', 'eps', 'ps', 'svg', 'cdr', 'ico',
# audio
'mp3', 'wma', 'ogg', 'wav', 'ra', 'aac', 'mid', 'au', 'aiff',
# video
'3gp', 'asf', 'asx', 'avi', 'mov', 'mp4', 'mpg', 'qt', 'rm', 'swf', 'wmv',
'm4a', 'm4v', 'flv', 'webm',
# office suites
'xls', 'xlsx', 'ppt', 'pptx', 'pps', 'doc', 'docx', 'odt', 'ods', 'odg',
'odp',
# other
'css', 'pdf', 'exe', 'bin', 'rss', 'dmg', 'iso', 'apk'
]
_re_type = type(re.compile("", 0))
def _matches(url, regexs):
return any(r.search(url) for r in regexs)
def _is_valid_url(url):
return url.split('://', 1)[0] in {'http', 'https', 'file', 'ftp'}
class FilteringLinkExtractor:
_csstranslator = HTMLTranslator()
def __new__(cls, *args, **kwargs):
from scrapy.linkextractors.lxmlhtml import LxmlLinkExtractor
if issubclass(cls, FilteringLinkExtractor) and not issubclass(cls, LxmlLinkExtractor):
warn('scrapy.linkextractors.FilteringLinkExtractor is deprecated, '
'please use scrapy.linkextractors.LinkExtractor instead',
ScrapyDeprecationWarning, stacklevel=2)
return super().__new__(cls)
def __init__(self, link_extractor, allow, deny, allow_domains, deny_domains,
restrict_xpaths, canonicalize, deny_extensions, restrict_css, restrict_text):
self.link_extractor = link_extractor
self.allow_res = [x if isinstance(x, _re_type) else re.compile(x)
for x in arg_to_iter(allow)]
self.deny_res = [x if isinstance(x, _re_type) else re.compile(x)
for x in arg_to_iter(deny)]
self.allow_domains = set(arg_to_iter(allow_domains))
self.deny_domains = set(arg_to_iter(deny_domains))
self.restrict_xpaths = tuple(arg_to_iter(restrict_xpaths))
self.restrict_xpaths += tuple(map(self._csstranslator.css_to_xpath,
arg_to_iter(restrict_css)))
self.canonicalize = canonicalize
if deny_extensions is None:
deny_extensions = IGNORED_EXTENSIONS
self.deny_extensions = {'.' + e for e in arg_to_iter(deny_extensions)}
self.restrict_text = [x if isinstance(x, _re_type) else re.compile(x)
for x in arg_to_iter(restrict_text)]
def _link_allowed(self, link):
if not _is_valid_url(link.url):
return False
if self.allow_res and not _matches(link.url, self.allow_res):
return False
if self.deny_res and _matches(link.url, self.deny_res):
return False
parsed_url = urlparse(link.url)
if self.allow_domains and not url_is_from_any_domain(parsed_url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(parsed_url, self.deny_domains):
return False
if self.deny_extensions and url_has_any_extension(parsed_url, self.deny_extensions):
return False
if self.restrict_text and not _matches(link.text, self.restrict_text):
return False
return True
def matches(self, url):
if self.allow_domains and not url_is_from_any_domain(url, self.allow_domains):
return False
if self.deny_domains and url_is_from_any_domain(url, self.deny_domains):
return False
allowed = (regex.search(url) for regex in self.allow_res) if self.allow_res else [True]
denied = (regex.search(url) for regex in self.deny_res) if self.deny_res else []
return any(allowed) and not any(denied)
def _process_links(self, links):
links = [x for x in links if self._link_allowed(x)]
if self.canonicalize:
for link in links:
link.url = canonicalize_url(link.url)
links = self.link_extractor._process_links(links)
return links
def _extract_links(self, *args, **kwargs):
return self.link_extractor._extract_links(*args, **kwargs)
# Top-level imports
from scrapy.linkextractors.lxmlhtml import LxmlLinkExtractor as LinkExtractor
|
