gistfile1.py

#!/usr/bin/env python2.6
# -*- coding: utf-8 -*-
"""
Serienjunkies Decrypter
~~~~~~~~~~~~~~~~~~~~~~~

Decrypts a serienjunkies.org download page and outputs a list of links. Easily
copy-paste-able.

:copyright: 2010, Pascal Hartig <phartig@rdrei.net>
:license: GPL v3, see doc/LICENSE for more details.
"""

import subprocess
import sys
import re
from httplib2 import Http
from tempfile import NamedTemporaryFile
from urllib import urlencode


FILE_VIEWER = 'display'


class SerienjunkiesDecrypter(object):
    """
    Expects a URL as argument. Run :meth:`decrypt` to get a list of
    URLs.
    """

    _CAPTCHA_RE = re.compile(r'\<IMG SRC="\/secure\/([^\.]+)\.png" WIDTH="100" '
                             'HEIGHT="60" ALT="" style="border:1px solid #ccc;"\>')
    _SECRET_RE = re.compile(r'\<INPUT TYPE="HIDDEN" NAME="s" VALUE="([a-z0-9]+)"\>')
    _SJ_DOWNLOAD_LINK_RE = re.compile(r'(http:\/\/download.serienjunkies.org\/go-[a-z0-9]+\/)')

    def __init__(self, url):
        self.url = url
        self.http = Http()
        self.proc = None

    def decrypt(self):
        """Returns a list of URLs."""

        content = self._get_content()
        captcha_path = self._get_captcha_path(content)
        captcha_file = self._download_captcha(captcha_path)
        secret = self._get_secret(content)
        captcha_code = self._ask_captcha(captcha_file)
        download_page = self._get_download_page(captcha_code, secret)
        try:
            download_links = self._get_download_links(download_page)
            for link in download_links:
                print(self._get_rapidshare_link_from_go_link(link))
        except InvalidCaptchaError:
            # Start over.
            print("Invalid captcha or decrypter limit. Try again.")
            return self.decrypt()

    def _get_content(self):
        """Returns the page content of ``self.url``."""
        response, content = self.http.request(self.url)
        if response['status'] != '200':
            raise DecrypterError("Unexpected server "
                "response code: {0}" .format(response['status']))

        return content

    def _get_captcha_path(self, content):
        matches = self._CAPTCHA_RE.search(content)
        if matches is not None:
            return "http://download.serienjunkies.org/secure/{0}.png".format(
                matches.group(1))
        else:
            raise DecrypterError("Captcha not found!")

    def _get_secret(self, content):
        matches = self._SECRET_RE.search(content)
        if matches is not None:
            return matches.group(1)
        else:
            raise DecrypterError("Secret not found!")

    def _download_captcha(self, path, file=None):
        """
        Downloads the captcha from ``path`` to ``file``.
        If ``file`` is None, a NamedTemporaryFile is created.
        """

        file = file or NamedTemporaryFile(delete=False)
        response, content = self.http.request(path)

        file.write(content)
        file.close()
        return file

    def _ask_captcha(self, file):
        """
        Displays the captcha to the user and prompts for the shown
        values.
        """

        self._display_graphic(file.name)
        code = raw_input("CODE: ")
        self._terminate_graphic_viewer()
        return code

    def _get_download_page(self, code, secret):
        """Tries to receive the download page."""

        data = {'c': code, 's': secret, 'action': "Download"}
        headers = {'Content-type': 'application/x-www-form-urlencoded'}
        response, content = self.http.request(self.url, "POST",
                                              headers=headers,
                                              body=urlencode(data))
        return content

    def _get_download_links(self, content):
        """Extracts the download links from the content and returns a
        generator over it. If not found, it raises a ``InvalidCaptchaError``."""

        matches = self._SJ_DOWNLOAD_LINK_RE.findall(content)
        if len(matches) > 0:
            for match in matches:
                yield match
        else:
            raise InvalidCaptchaError()

    def _display_graphic(self, filename):
        self.proc = subprocess.Popen([FILE_VIEWER, filename])

    def _terminate_graphic_viewer(self):
        if self.proc:
            self.proc.terminate()

    def _get_rapidshare_link_from_go_link(self, link):
        """
        Accepts a http://download.serienjunkies.org/go-... style URL and turns
        it into a valid rapidshare.com link.
        """

        # Create a local http object that does not follow redirects.
        http = Http()
        http.follow_redirects = False
        link = link.replace("http://download.serienjunkies.org/",
                     "http://download.serienjunkies.org/frame/")
        response, content = http.request(link, 'HEAD')
        return response['location']


class DecrypterError(Exception):
    pass

class InvalidCaptchaError(DecrypterError):
    pass


if __name__ == '__main__':
    decrypter = SerienjunkiesDecrypter(sys.argv[1])
    decrypter.decrypt()