4grab/4grab.py

#!/usr/bin/python

######################################################################
# Copyright 2009, 2010 ryuslash
#
# This file is part of 4grab.
#
# 4grab is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# 4grab is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with 4grab.  If not, see <http://www.gnu.org/licenses/>.
######################################################################

import optparse
import sys

import config

import download
import progressbar

def raw_input_with_default(default, prompt):
    inp = raw_input("%s (default=%s): " % (prompt, default))
    if inp == "":
        return default
    return inp
config._optioncreator = raw_input_with_default

base_url = "http://boards.4chan.org/"
parser = optparse.OptionParser()
downloader = download.Downloader(progressbar.Progress)

def walk_with_wizard(baseurl):
    conf = config.Configuration()
    wzrd_msg = "Pilates! *SHAZAM* Here they come!"
    print "Alright, let me put on my robe and wizard hat."
    
    # Single or all
    inp = None
    prompt = "Would you like to download a single thread, or all? "
    inp = raw_input(prompt)
    while (inp != "single" and inp != "all"):
        print "Please type single or all"
        inp = raw_input(prompt)

    if inp == "single":
        inp = raw_input("Which thread would you like to download? ")
        if inp[:7] == "http://":
            t = downloader.get_image_links("", [inp])
        else:
            thread = inp
            inp = raw_input("Which category is this thread in? ")
            print wzrd_msg
            t = downloader.get_image_links("%s%s/res/" % (baseurl, inp),
                                           [thread])
    else:
        inp = raw_input("Which category would you like to download? ")
        conf.set_categories([inp])
        baseurl = "%s%s/" % (baseurl, conf.get_categories()[0])

        print wzrd_msg
        t = downloader.get_thread_links(baseurl)
        t = downloader.get_image_links(baseurl, t)
    (skipped, failed, downloaded, total) = downloader.get_images(t)
    print "Downloaded: ", downloaded
    print "Skipped:    ", skipped
    print "Failed:     ", failed
    print "Total:      ", total

def parse_commands():
    conf = config.Configuration()
    parser.set_usage(
        """%prog [options]

4grab Copyright (C) 2009-2010 ryuslash
This program comes with ABSOLUTELY NO WARRANTY.
This is free software, and you are welcome to redistribute it
under certain conditions.""")
    parser.add_option("-e",
                      nargs=2,
                      dest="confval",
                      metavar="CONF VALUE",
                      help="Set configuration option CONF to be VALUE")
    parser.add_option("-c",
                      "--category",
                      dest="tempcat",
                      metavar="CATEGORY",
                      help="Set the category to CATEGORY only for this run")
    parser.add_option("-t",
                      "--thread",
                      dest="thread",
                      metavar="THREAD",
                      help="Download only THREAD. If THREAD is only an ID, "
                      "CATEGORY must also be set. Otherwise, no problem :-)")
    parser.add_option("-w",
                      "--wizard",
                      action="store_true",
                      dest="wizard",
                      help="I'll put on my robe and wizard hat and help you "
                      "get some of those pictures you like")
    (options, args) = parser.parse_args()

    if options.confval and (options.tempcat
                            or options.thread
                            or options.wizard):
        print "Can't configure something and do something else too."
        exit(1)

    if options.wizard and (options.tempcat 
                           or options.thread
                           or options.confval):
        print "Can't take a walk with the wizard and do something else too."
        exit(1)

    if options.confval:
        if not conf.option_exists(options.confval[0]):
            print ("%s: error: %s is not a valid configuration option" 
                   % (sys.argv[0], options.confval[0]))
            exit(1)
        print "Setting", options.confval[0], "to", options.confval[1]
        conf.set_option(options.confval[0],
                        options.confval[1])
        conf.save()
        exit(0)

    elif options.wizard:
        try:
            walk_with_wizard(base_url)
        except KeyboardInterrupt:
            print
            print "Alright, no more wizard hat and robe then. Goodbye"
        exit(0)

    elif options.thread:
        try:
            if options.thread[:7] == "http://":
                t = downloader.get_image_links("", [options.thread])
            elif options.tempcat:
                url = "%s%s/res/" % (base_url, options.tempcat)
                t = downloader.get_image_links(url, [options.thread])
            else:
                print ("if THREAD is not an absolute URL, "
                       "CATEGORY must also be specified")
                exit(1)
            (skipped, failed, downloaded, total) = downloader.get_images(t)
            print "Downloaded: ", downloaded
            print "Skipped:    ", skipped
            print "Failed:     ", failed
            print "Total:      ", total
        except KeyboardInterrupt:
            print
            print "Goodbye"
        exit(0)

    elif options.tempcat:
        conf.set_categories([options.tempcat])

#base_url = "%s%s/" % (base_url, conf.get_categories())

if __name__ == "__main__":
    conf = config.Configuration()
    parse_commands()
    for category in conf.get_categories():
        base_url = "%s%s/" % (base_url, category)
        try:
            t = downloader.get_thread_links(base_url)
            t = downloader.get_image_links(base_url, t)
            (skipped, failed, downloaded, total) = downloader.get_images(t)
            print "Downloaded: ", downloaded
            print "Skipped:    ", skipped
            print "Failed:     ", failed
            print "Total:      ", total
        except KeyboardInterrupt:
            print
            print "So you don't want these images? Fine! I'll stop then."