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
|
"""
This is a middleware to respect robots.txt policies. To activate it you must
enable this middleware and enable the ROBOTSTXT_OBEY setting.
"""
import logging
from six.moves.urllib import robotparser
from twisted.internet.defer import Deferred, maybeDeferred
from scrapy.exceptions import NotConfigured, IgnoreRequest
from scrapy.http import Request
from scrapy.utils.httpobj import urlparse_cached
from scrapy.utils.log import failure_to_exc_info
from scrapy.utils.python import to_native_str
logger = logging.getLogger(__name__)
class RobotsTxtMiddleware(object):
DOWNLOAD_PRIORITY = 1000
def __init__(self, crawler):
if not crawler.settings.getbool('ROBOTSTXT_OBEY'):
raise NotConfigured
self.crawler = crawler
self._useragent = crawler.settings.get('USER_AGENT')
self._parsers = {}
@classmethod
def from_crawler(cls, crawler):
return cls(crawler)
def process_request(self, request, spider):
if request.meta.get('dont_obey_robotstxt'):
return
d = maybeDeferred(self.robot_parser, request, spider)
d.addCallback(self.process_request_2, request, spider)
return d
def process_request_2(self, rp, request, spider):
if rp is not None and not rp.can_fetch(
to_native_str(self._useragent), request.url):
logger.debug("Forbidden by robots.txt: %(request)s",
{'request': request}, extra={'spider': spider})
raise IgnoreRequest()
def robot_parser(self, request, spider):
url = urlparse_cached(request)
netloc = url.netloc
if netloc not in self._parsers:
self._parsers[netloc] = Deferred()
robotsurl = "%s://%s/robots.txt" % (url.scheme, url.netloc)
robotsreq = Request(
robotsurl,
priority=self.DOWNLOAD_PRIORITY,
meta={'dont_obey_robotstxt': True}
)
dfd = self.crawler.engine.download(robotsreq, spider)
dfd.addCallback(self._parse_robots, netloc)
dfd.addErrback(self._logerror, robotsreq, spider)
dfd.addErrback(self._robots_error, netloc)
if isinstance(self._parsers[netloc], Deferred):
d = Deferred()
def cb(result):
d.callback(result)
return result
self._parsers[netloc].addCallback(cb)
return d
else:
return self._parsers[netloc]
def _logerror(self, failure, request, spider):
if failure.type is not IgnoreRequest:
logger.error("Error downloading %(request)s: %(f_exception)s",
{'request': request, 'f_exception': failure.value},
exc_info=failure_to_exc_info(failure),
extra={'spider': spider})
return failure
def _parse_robots(self, response, netloc):
rp = robotparser.RobotFileParser(response.url)
body = ''
if hasattr(response, 'text'):
body = response.text
else: # last effort try
try:
body = response.body.decode('utf-8')
except UnicodeDecodeError:
# If we found garbage, disregard it:,
# but keep the lookup cached (in self._parsers)
# Running rp.parse() will set rp state from
# 'disallow all' to 'allow any'.
pass
# stdlib's robotparser expects native 'str' ;
# with unicode input, non-ASCII encoded bytes decoding fails in Python2
rp.parse(to_native_str(body).splitlines())
rp_dfd = self._parsers[netloc]
self._parsers[netloc] = rp
rp_dfd.callback(rp)
def _robots_error(self, failure, netloc):
rp_dfd = self._parsers[netloc]
self._parsers[netloc] = None
rp_dfd.callback(None)
|
