File: fetch.py

package info (click to toggle)
python-scrapy 0.8-3
  • links: PTS, VCS
  • area: main
  • in suites: squeeze
  • size: 2,904 kB
  • ctags: 2,981
  • sloc: python: 15,349; xml: 199; makefile: 68; sql: 64; sh: 34
file content (35 lines) | stat: -rw-r--r-- 1,012 bytes parent folder | download
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
import pprint

from scrapy.command import ScrapyCommand
from scrapy.utils.fetch import fetch

class Command(ScrapyCommand):

    requires_project = False

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

    def short_desc(self):
        return "Fetch a URL using the Scrapy downloader"

    def long_desc(self):
        return "Fetch a URL using the Scrapy downloader and print its content " \
            "to stdout. You may want to use --nolog to disable logging"

    def add_options(self, parser):
        ScrapyCommand.add_options(self, parser)
        parser.add_option("--headers", dest="headers", action="store_true", \
            help="print response HTTP headers instead of body")

    def run(self, args, opts):
        if len(args) != 1:
            print "One URL is required"
            return

        responses = fetch(args)
        if responses:
            if opts.headers:
                pprint.pprint(responses[0].headers)
            else:
                print responses[0].body