скрипт для скачивания целых альбомов с musicmp3spb.ru

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

import mechanize
import re
import urllib2
import sys
import os

top_url = "http://musicmp3spb.org"

def download_file(url, file_name):
    u = urllib2.urlopen(url)
    f = open(file_name, 'wb')
    meta = u.info()
    file_size = int(meta.getheaders("Content-Length")[0])
    print "Downloading: %s Bytes: %s" % (file_name, file_size)

    file_size_dl = 0
    block_sz = 8192
    while True:
        buffer = u.read(block_sz)
        if not buffer:
            break

        file_size_dl += len(buffer)
        f.write(buffer)
        status = r"%10d  [%3.2f%%]" % (file_size_dl, file_size_dl * 100. / file_size)
        status = status + chr(8)*(len(status)+1)
        print status,

    f.close()

def download_song(url, targetFolder):
    print "Downloading song from %s" % url

    browser = get_browser_with(url)

    formcount=0
    action_regexp = re.compile('/file/.*')
    for form in browser.forms():
        if action_regexp.match(form.attrs['action']):
            formcount=formcount+1
            break

    file_name = url + '.mp3'
    for link in browser.links(url_regex='\/file\/'):
        file_name = link.text

    browser.select_form(nr=formcount)
    browser.submit()

    for link in browser.links(url_regex='tempfile\.ru'):
        download_file(link.url, targetFolder + "/" + file_name)


def download_mp3s(browser, targetFolder):
    print "\nMP3"
    title_regexp = re.compile('.*Скачать mp3.*', re.IGNORECASE)
    for link in browser.links(url_regex='/download/.*'):
        for title in [attr for attr in link.attrs if len(attr) == 2 and attr[0] == 'title']:
            title_utf8 = title[1].decode('cp1251').encode('utf8')

            if title_regexp.match(title_utf8):
                url_arr = link.base_url.split('/')
                songUrl = link.url
                if not link.url.startswith('http'):
                    if len(url_arr) > 3 and url_arr[0] == 'http:':
                        page_url = 'http://' + url_arr[2]
                    else:
                        page_url = url_arr[0]
                    songUrl = page_url + link.url
                print songUrl
                download_song(songUrl, targetFolder)

def download_covers(url, targetFolder):
    print "\nCOVERS"
    print "Downloading covers from %s" % url

    browser = get_browser_with(url)

    cover_links = list(browser.links(url_regex='\/images\/'))

    covers_target_folder = targetFolder
    if len(cover_links) > 4:
        covers_target_folder = targetFolder + "/" + "covers"
        if not os.path.exists(covers_target_folder):
            os.makedirs(covers_target_folder)
        print "There are %d covers, therefore they will be downloaded into subfolder %s" % (len(cover_links), covers_target_folder)

    counter = 0
    for link in cover_links:
        counter = counter + 1
        cover_url = top_url + link.url
        print cover_url
        file_name = cover_url.split("/")[-1]
        file_extension = cover_url.split(".")[-1]
        cover_number = "%s" % counter
        if counter < 10:
            cover_number = "0" + cover_number
        cover_target_name = covers_target_folder + "/cover_" + cover_number + "." + file_extension
        download_file(cover_url, cover_target_name)

def get_folder_name_for_album(browser):
    album_and_artist = get_album_and_artist(browser.title())
    if len(album_and_artist) <> 2:
        print "Cannot format an album title automatically, sorry..."
        folder_name = str.join(",", album_and_artist)
        folder_name = remove_characters_illegal_in_paths(folder_name)
        print "Following folder name will be used: " + folder_name
        return folder_name
    year = get_release_year(browser, album_and_artist[0])
    folder_name = album_and_artist[1].strip() + " - " + year + " - " + album_and_artist[0].strip()
    return remove_characters_illegal_in_paths(folder_name)

def remove_characters_illegal_in_paths(inputName):
    result = inputName
    for bad_character_in_path in '\\:*?"<>|/':
        result = result.replace(bad_character_in_path, '_')
    return result

def get_album_and_artist(webPageTitle):
    noiseAtTheEnd = " mp3"
    if webPageTitle.endswith(noiseAtTheEnd):
        webPageTitle = webPageTitle[:-len(noiseAtTheEnd)]
    splitTitle = webPageTitle.split(",")
    return splitTitle

def get_release_year(browser, albumTitle):
    htmlOfWebPage = browser.response().read()
    htmlSnippetBeforeYear = "<div class=\"Name\">\n" + albumTitle + "<br />\n<i>"
    positionOfAlbumTitleWithYear = htmlOfWebPage.find(htmlSnippetBeforeYear)
    if positionOfAlbumTitleWithYear < 0:
        return ""
    yearStartPosition = positionOfAlbumTitleWithYear + len(htmlSnippetBeforeYear)
    return "%s" % htmlOfWebPage[yearStartPosition:yearStartPosition+4]

def get_covers_url(browser):
    covers_regex =re.compile('.*обложки.*', re.IGNORECASE)
    for link in browser.links(url_regex='/covers/.*'):
        return top_url + link.url
    return ""

def get_browser_with(url):
    browser = mechanize.Browser()
    browser.set_handle_robots(False)
    browser.open(url)
    return browser

def download_album(url):

    if not url.startswith(top_url):
        print "Wrong URL! Expected an url beginning with " + top_url
        return

    browser = get_browser_with(url)

    print "-------------------------------------------------------"
    print "Downloading an album from ..."
    print "Url: " + url

    targetFolder = get_folder_name_for_album(browser)
    print "Target folder: %s" % targetFolder
    if not os.path.exists(targetFolder):
        os.makedirs(targetFolder)
    else:
        print "Target folder already exists, cancelling download"
        return

    covers_url = get_covers_url(browser)
    if len(covers_url) > 0:
        download_covers(covers_url, targetFolder)

    download_mp3s(browser, targetFolder)

    print "...downloading album is finished."
    print "-------------------------------------------------------"

def main():
    if len(sys.argv) < 2:
        print "usage %s album_url" % os.path.basename(sys.argv[0])
        sys.exit(1)

    download_album(sys.argv[1])

if __name__ == "__main__":
    main()