This file is indexed.

/usr/share/pyshared/scrapy/commands/runspider.py is in python-scrapy 0.14.4-1.

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
54
55
56
57
58
59
60
61
62
63
64
65
import sys
import os

from scrapy.utils.spider import iter_spider_classes
from scrapy.command import ScrapyCommand
from scrapy.exceptions import UsageError
from scrapy.utils.conf import arglist_to_dict

def _import_file(filepath):
    abspath = os.path.abspath(filepath)
    dirname, file = os.path.split(abspath)
    fname, fext = os.path.splitext(file)
    if fext != '.py':
        raise ValueError("Not a Python source file: %s" % abspath)
    if dirname:
        sys.path = [dirname] + sys.path
    try:
        module = __import__(fname, {}, {}, [''])
    finally:
        if dirname:
            sys.path.pop(0)
    return module

class Command(ScrapyCommand):

    requires_project = False

    def syntax(self):
        return "[options] <spider_file>"

    def short_desc(self):
        return "Run a self-contained spider (without creating a project)"

    def long_desc(self):
        return "Run the spider defined in the given file"

    def add_options(self, parser):
        ScrapyCommand.add_options(self, parser)
        parser.add_option("-a", dest="spargs", action="append", default=[], metavar="NAME=VALUE", \
            help="set spider argument (may be repeated)")

    def process_options(self, args, opts):
        ScrapyCommand.process_options(self, args, opts)
        try:
            opts.spargs = arglist_to_dict(opts.spargs)
        except ValueError:
            raise UsageError("Invalid -a value, use -a NAME=VALUE", print_help=False)

    def run(self, args, opts):
        if len(args) != 1:
            raise UsageError()
        filename = args[0]
        if not os.path.exists(filename):
            raise UsageError("File not found: %s\n" % filename)
        try:
            module = _import_file(filename)
        except (ImportError, ValueError), e:
            raise UsageError("Unable to load %r: %s\n" % (filename, e))
        spclasses = list(iter_spider_classes(module))
        if not spclasses:
            raise UsageError("No spider found in file: %s\n" % filename)
        spider = spclasses.pop()(**opts.spargs)

        self.crawler.crawl(spider)
        self.crawler.start()