stov/lib_stov/noapi.py

#
#        This file is part of stov, written by Helmut Pozimski 2012-2014.
#
#       stov 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, version 2 of the License.
#
#       stov 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 stov.  If not, see <http://www.gnu.org/licenses/>.


# -*- coding: utf8 -*-

from __future__ import unicode_literals

import subprocess
import sys
import lxml.html

if sys.version_info >= (3,):
    import urllib.request as urllib2
else:
    import urllib2

from lib_stov import youtubeAPI
from lib_stov import stov_exceptions

class Connector(object):
    """This class will retrieve all the necessary data from youtube using
    youtube-dl, thus bypassing the API.
    """
    def __init__(self, type, name, conf, search=""):
        """Populates the object with all necessary data."""
        self._type = type
        self._name = name
        self._search = search
        self._conf = conf
        self._title = ""
        self._url = ""
        self._construct_url()

    def _construct_url(self):
        if self._type == "channel":
            self._url = "https://www.youtube.com/user/%s" \
                        % urllib2.quote(self._name)
        elif self._type == "search":
            self._url = "https://www.youtube.com/results?search_query=%s"\
                        % urllib2.quote(self._search)
        elif self._type == "playlist":
            self._url = "https://www.youtube.com/playlist?list=%s" \
                        % urllib2.quote(self._name)

    def _fetch_title(self):
        """Retrieves the title of the HTML page to use as a title for the
        subscription."""
        data = urllib2.urlopen(self._url)
        parsed_html = lxml.html.parse(data)
        data.close()
        i = 0
        for item in parsed_html.iter("title"):
            if i == 0:
                self._title = item.text_content().strip().replace("\n", "")
            i += 1
        if self._search != "" and self._type == "channel":
            self._title += _(" search %s") % self._search

    def _fetch_videos(self):
        """Retrieves all the relevant videos in a subscription."""
        videos_list = []
        if self._type == "channel" and self._search != "":
            try:
                video_ids = subprocess.check_output([self._conf.values["youtube-dl"], "--max-downloads",
                                                                   self._conf.values["maxvideos"],
                                                                   "--match-title",
                                                                   self._search,
                                                                   "--get-id",
                                                                   self._url]).strip()
            except subprocess.CalledProcessError as e:
                video_ids = e.output.strip()
        else:
            try:
                video_ids = subprocess.check_output([self._conf.values["youtube-dl"], "--max-downloads",
                                                                   self._conf.values["maxvideos"],
                                                                   "--get-id",
                                                                   self._url]).strip()
            except subprocess.CalledProcessError as e:
                video_ids = e.output.strip()
        for video_id in video_ids.split("\n"):
            try:
                video_title = subprocess.check_output([
                self._conf.values["youtube-dl"], "--get-title",
                "https://www.youtube.com/watch?v=%s"
                % video_id]).strip()
                video_description = subprocess.check_output([
                    self._conf.values["youtube-dl"], "--get-description",
                    "https://www.youtube.com/watch?v=%s"
                    % video_id]).strip()
            except subprocess.CalledProcessError:
                raise stov_exceptions.YoutubeDlCallFailed()
            else:
                videos_list.append(youtubeAPI.YtVideo(unicode(video_title, "utf-8"),
                                                        unicode(video_description, "utf-8"),
                                                        unicode(video_id)))
        return videos_list

    def ParseAPIData(self):
        """This method calls all necessary methods to retrieve the data
                and assembles them into a Channel object. The naming of this
                method is set according to the method in youtubeAPI to be
                compatible.
        """
        self._fetch_title()
        videos = self._fetch_videos()
        channel = youtubeAPI.YtChannel()
        channel.title = unicode(self._title)
        channel.videos = videos
        return channel