4grab/download.py

import urllib
import os
import htmlparser
import progressbar

savedir = "/home/slash/Pictures/4grab/"

def get_thread_links(baseurl):
    myparser = htmlparser.MyParser()
    t = ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10"]
    i = 1
    total = len(t)
    progress = progressbar.Progress(total)

    for pagenum in t:
        progress.show_progress(i)

        url = base_url + pagenum
        tries = 10
        while tries > 0:
            try:
                f = urllib.urlopen(url)
                break
            except IOError:
                tries -= 1
                print "\rTry of", url, "failed,", tries, "tries left"
        if not f is None:
            # Read the response
            s = f.read()
            f.close()

            # Process the page.
            myparser.parse(s)
        else:
            "\rOpening of", url, "did not succeed, trying next one..."
        i += 1
    return myparser.get_hyperlinks()

def get_image_links(baseurl, t = []):
    mysubparser = htmlparser.MySubParser()
    total = len(t)
    progress = progressbar.Progress(total)
    i = 1
    
    for link in t:
        progress.show_progress(i)

        img_url = base_url + link
        tries = 10
        while tries > 0:
            try:
                f = urllib.urlopen(img_url)
                break
            except IOError:
                tries -= 1
                print "\rTry of", img_url, "failed,", tries, "tries left"
        if not f is None:
            s = f.read()
            f.close()

            mysubparser.parse(s)
        else:
            print "\rOpening of", img_url, "did not succeed, trying next one..."
        i += 1

    return mysubparser.get_hyperlinks()

def get_images(t = []):
    total = len(t)
    progress = progressbar.Progress(total)
    i = 1
    for link in t:
        progress.show_progress(i)
        filename = os.path.join(savedir, os.path.split(link)[1])
        if not os.path.exists(filename):
            tries = 10
            while tries > 0:
                try:
                    urllib.urlretrieve(link, filename)
                    break
                except IOError:
                    tries -= 1
                    print "\rDownloading of", link, "failed,", tries, "left"
        else:
            print "\rNot downloading", link, "already downloaded"
        i += 1

if __name__ == "__main__":
    # Get a file-like object for the 4chan.org w/imgboard
    base_url = "http://boards.4chan.org/w/"
 
    # Get the hyperlinks.
    t = get_thread_links(base_url)
    t = get_image_links(base_url, t)
    get_images(t)