This file is indexed.

/usr/lib/python2.7/dist-packages/scrapy/spiderloader.py is in python-scrapy 1.0.3-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

 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
# -*- coding: utf-8 -*-
from __future__ import absolute_import

from zope.interface import implementer

from scrapy.interfaces import ISpiderLoader
from scrapy.utils.misc import walk_modules
from scrapy.utils.spider import iter_spider_classes


@implementer(ISpiderLoader)
class SpiderLoader(object):
    """
    SpiderLoader is a class which locates and loads spiders
    in a Scrapy project.
    """
    def __init__(self, settings):
        self.spider_modules = settings.getlist('SPIDER_MODULES')
        self._spiders = {}
        for name in self.spider_modules:
            for module in walk_modules(name):
                self._load_spiders(module)

    def _load_spiders(self, module):
        for spcls in iter_spider_classes(module):
            self._spiders[spcls.name] = spcls

    @classmethod
    def from_settings(cls, settings):
        return cls(settings)

    def load(self, spider_name):
        """
        Return the Spider class for the given spider name. If the spider
        name is not found, raise a KeyError.
        """
        try:
            return self._spiders[spider_name]
        except KeyError:
            raise KeyError("Spider not found: {}".format(spider_name))

    def find_by_request(self, request):
        """
        Return the list of spider names that can handle the given request.
        """
        return [name for name, cls in self._spiders.items()
                if cls.handles_request(request)]

    def list(self):
        """
        Return a list with the names of all spiders available in the project.
        """
        return list(self._spiders.keys())