4chan-download

#!/usr/bin/env python
# -*- coding: utf-8 -*-

# Copyright (C) <2010>  Gabriel Falcão <[email protected]>
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
# THE SOFTWARE.

import os
import sys
import warnings

warnings.filterwarnings('ignore')

try:
    import bolacha
except ImportError:
    print "you need bolacha installed in order to use this script: [sudo] pip install bolacha"

try:
    import couleur
except ImportError:
    print "you need couleur installed in order to use this script: [sudo] pip install couleur"

try:
    from lxml import html as lhtml
except ImportError:
    print "you need lxml installed in order to use this script: [sudo] pip install lxml"

url = sys.argv[-1]

http = bolacha.Bolacha()
sh = couleur.Shell(linebreak=True, bold=True)

sh.cyan("Preparing to download...")

def dom_of(url):
    return lhtml.fromstring(http.get(url)[1])

def get_main_page(url):
    sh.green_and_blink_bold_white_and_green("Fetching |all| image urls...", replace=True)
    dom = dom_of(url)
    images_items = dom.cssselect("a[target='_blank']")
    urls = [img.attrib['href'] for img in images_items if 'href' in img.attrib and img.attrib['href'].endswith("jpg")]
    sh.yellow("Downloading images ...", replace=True)

    total = len(urls)
    curfiles = filter(lambda x: os.path.isfile(x), os.listdir(os.curdir))

    for i, url in enumerate(urls):
        index = i + 1
        filename = url.split("/")[-1]
        if filename in curfiles:
            sh.red_and_blue("ignoring already downloaded image %s (%d of %d) ..." % (filename, index, total), replace=True)
            continue

        sh.red("Downloading image %d of %d [%s] ..." % (index, total, url), replace=True)
        img = http.get(url)[1]
        sh.green("Saving image %d of %d [%s] ..." % (index, total, url), replace=True)

        f = open(filename, "w")
        f.write(img)
        f.close()
        sh.black("Saved at %s ..." % filename, replace=True)

    sh.green("Done, %d images saved" % total)

get_main_page(url)