Merge pull request #24 from 4Christopher/stable

Added Movie2kTo and XvidstageCom plugin (now for Stable …)

2 files changed, 213 insertions, 0 deletions

diff --git a/module/plugins/crypter/Movie2kTo.py b/module/plugins/crypter/Movie2kTo.py
new file mode 100644
index 000000000..a9cdb188b
--- /dev/null
+++ b/module/plugins/crypter/Movie2kTo.py
@@ -0,0 +1,109 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import re
+from module.plugins.Crypter import Crypter
+
+class Movie2kTo(Crypter):
+	__name__ = "Movie2kTo"
+	__type__ = "container"
+	__pattern__ = r"http://(?:www\.)?movie2k\.to/(.*)\.html"
+	__version__ = "0.2"
+	__config__ = [("accepted_hosters", "str", "List of accepted hosters", "Xvidstage, "),
+				("whole_season", "bool", "Download whole season", "False"),
+				("everything", "bool", "Download everything", "False")]
+	__description__ = """Movie2k.to Container Plugin"""
+	__author_name__ = ('4Christopher')
+	__author_mail__ = ('4Christopher@gmx.de')
+	BASE_URL_PATTERN = r'http://(?:www\.)?movie2k\.to/'
+	TVSHOW_URL_PATH_PATTERN = r'tvshows-(?P<id>\d+?)-(?P<name>.+)'
+	FILM_URL_PATH_PATTERN = r'(?P<name>.+?)-(?:online-film|watch-movie)-(?P<id>\d+)'
+	SEASON_PATTERN = r'<div id="episodediv(\d+?)" style="display:(inline|none)">(.*?)</div>'
+	EP_PATTERN = r'<option value="(.+?)"( selected)?>Episode\s*?(\d+?)</option>'
+	BASE_URL = 'http://www.movie2k.to'
+		
+	def decrypt(self, pyfile):
+		self.package = pyfile.package()
+		self.folder = self.package.folder
+		whole_season = self.getConfig('whole_season')
+		everything = self.getConfig('everything')
+		self.getInfo(pyfile.url)
+
+		if (whole_season or everything) and self.format == 'tvshow':
+			self.logDebug('Downloading the whole season')
+			for season, season_sel, html in re.findall(self.SEASON_PATTERN, self.html, re.DOTALL | re.I):
+				if (season_sel == 'inline') or everything:
+					season_links = []
+					for url_path, ep_sel, ep in re.findall(self.EP_PATTERN, html, re.I):
+						season_name = self.name_tvshow(season, ep)
+						self.logDebug('%s: %s' % (season_name, url_path))
+						if ep_sel and (season_sel == 'inline'):
+							self.logDebug('%s selected (in the start URL: %s)' % (season_name, pyfile.url))
+							season_links += self.getInfoAndLinks('%s/%s' % (self.BASE_URL, url_path))
+						elif (whole_season and (season_sel == 'inline')) or everything:
+							season_links += self.getInfoAndLinks('%s/%s' % (self.BASE_URL, url_path))
+					self.packages.append(('%s: Season %s' % (self.name, season), season_links, 'Season %s' % season))
+
+		else:
+			self.packages.append((self.package.name, self.getLinks(), self.package.folder))
+	
+	def tvshow_number(self, number):
+		if int(number) < 10:
+			return '0%s' % number
+		else:
+			return number
+	
+	def name_tvshow(self, season, ep):
+		return '%s S%sE%s' % (self.name, self.tvshow_number(season), self.tvshow_number(ep))
+
+	def getInfo(self, url):
+		self.html = self.load(url)
+		self.url_path = re.match(self.__pattern__, url).group(1)
+		self.format = pattern_re = None
+		if re.match(r'tvshows', self.url_path):
+			self.format = 'tvshow'
+			pattern_re = re.search(self.TVSHOW_URL_PATH_PATTERN, self.url_path)
+		elif re.search(self.FILM_URL_PATH_PATTERN, self.url_path):
+			self.format = 'film'
+			pattern_re = re.search(self.FILM_URL_PATH_PATTERN, self.url_path)
+
+
+		self.name = pattern_re.group('name')
+		self.id = pattern_re.group('id')
+		self.logDebug('URL Path: %s (ID: %s, Name: %s, Format: %s)'
+			% (self.url_path, self.id, self.name, self.format))
+
+	def getInfoAndLinks(self, url):
+		self.getInfo(url)
+		return self.getLinks()
+
+	def getLinks(self):
+		accepted_hosters = re.findall(r'\b(\w+?)\b', self.getConfig('accepted_hosters'))
+		links = []
+		## h_id: hoster_id of a possible hoster
+		re_hoster_id_js = re.compile(r'links\[(\d+?)\].+&nbsp;(.+?)</a>')
+		re_hoster_id_html = re.compile(r'<a href=".*?(\d{7}).*?".+?&nbsp;(.+?)</a>')
+		## I assume that the ID is 7 digits longs
+		if re_hoster_id_js.search(self.html):
+			re_hoster_id = re_hoster_id_js
+		elif re_hoster_id_html.search(self.html):
+			re_hoster_id = re_hoster_id_html
+		for h_id, hoster in re_hoster_id.findall(self.html):
+			if hoster in accepted_hosters:
+				if h_id != self.id:
+					self.html = self.load('%s/tvshows-%s-%s.html' % (self.BASE_URL, h_id, self.name))
+				else:
+					self.logDebug('This is already the right ID')
+				try:
+					url = re.search(r'<a target="_blank" href="(http://.*?)"', self.html).group(1)
+					self.logDebug('id: %s, %s: %s' % (h_id, hoster, url))
+					links.append(url)
+				except:
+					self.logDebug('Failed to find the URL')
+		
+		# self.logDebug(links[-1]) ## Last link, this is probably everything
+		## you will need
+		# links.append('http://localhost/IfTheProcessFunctionReturnsOnlyOneLinkItWillFail')
+		self.logDebug(links)
+		# return links[-1]
+		return links
diff --git a/module/plugins/hoster/XvidstageCom.py b/module/plugins/hoster/XvidstageCom.py
new file mode 100644
index 000000000..38c54efec
--- /dev/null
+++ b/module/plugins/hoster/XvidstageCom.py
@@ -0,0 +1,104 @@
+# -*- coding: utf-8 -*-
+
+"""
+	This program 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; either version 3 of the License,
+	or (at your option) any later version.
+
+	This program 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 this program; if not, see <http://www.gnu.org/licenses/>.
+	
+	@author: 4Christopher
+"""
+
+from module.plugins.Hoster import Hoster
+from module.network.RequestFactory import getURL
+import re
+import HTMLParser
+
+def setup(self):
+	self.wantReconnect = False
+	self.resumeDownload = True
+	self.multiDL = True
+
+def getInfo(urls):
+	result = []
+	
+	for url in urls:
+		result.append(parseFileInfo(url, getInfoMode = True))
+	yield result
+
+def parseFileInfo(url, getInfoMode = False):
+	html = getURL(url)
+	info = {"name" : url, "size" : 0, "status" : 3}
+	info['name'] = re.search(r'(?:Filename|Dateiname):</b></td><td nowrap[^>]*?>(.*?)<', html).group(1)
+	info['size'] = re.search(r'(?:Size|Größe):</b></td><td>.*? <small>\((\d+?) bytes\)', html).group(1)
+	if info['size'] == 0:
+		info['status'] = 1
+	else:
+		info['status'] = 2
+
+	if getInfoMode:
+		return info['name'], info['size'], info['status'], url
+	else:
+		return info['name'], info['size'], info['status'], html
+
+class XvidstageCom(Hoster):
+	__name__ = 'XvidstageCom'
+	__version__ = '0.2'
+	__pattern__ = r'http://(?:www.)?xvidstage.com/(?P<id>[0-9A-Za-z]+)'
+	__type__ = 'hoster'
+	__description__ = """A Plugin that allows you to download files from http://xvidstage.com"""
+	__author_name__ = ('4Christopher')
+	__author_mail__ = ('4Christopher@gmx.de')
+
+
+	def process(self, pyfile):
+		pyfile.name, pyfile.size, pyfile.status, self.html = parseFileInfo(pyfile.url)
+		self.logDebug('Name: %s' % pyfile.name)
+		if pyfile.status == 1: ## offline
+			self.fail()
+		self.id = re.search(self.__pattern__, pyfile.url).group('id')
+
+		wait_sec = int(re.search(r'countdown_str">.+?>(\d+?)<', self.html).group(1))
+		self.setWait(wait_sec, reconnect=False)
+		self.logDebug('Waiting %d seconds before submitting the captcha' % wait_sec)
+		self.wait()
+
+		rand = re.search(r'<input type="hidden" name="rand" value="(.*?)">', self.html).group(1)
+		self.logDebug('rand: %s, id: %s' % (rand, self.id))
+		self.html = self.req.load(pyfile.url, post={'op': 'download2', 'id' : self.id, 'rand' : rand, 'code': self.get_captcha()})
+		file_url = re.search(r'<a href="(?P<url>.*?)">(?P=url)</a>', self.html).group('url')
+		try:
+			hours_file_available = int(re.search(r'This direct link will be available for your IP next (?P<hours>\d+?) hours', self.html).group('hours'))
+			self.logDebug('You have %d hours to download this file with your current IP address.' % hours_file_available)
+		except:
+			self.logDebug('Failed')
+		self.logDebug('Download file: %s' % file_url)
+		self.download(file_url)
+		check = self.checkDownload({'empty': re.compile(r'^$')})
+
+		if check == 'empty':
+			self.logInfo('Downloaded File was empty')
+			# self.retry()
+
+	def get_captcha(self):
+		## <span style='position:absolute;padding-left:7px;padding-top:6px;'>&#49; …
+		cap_chars = {}
+		for pad_left, char in re.findall(r"position:absolute;padding-left:(\d+?)px;.*?;'>(.*?)<", self.html):
+			cap_chars[int(pad_left)] = char
+
+		h = HTMLParser.HTMLParser()
+		## Sorting after padding-left
+		captcha = ''
+		for pad_left in sorted(cap_chars):
+			captcha += h.unescape(cap_chars[pad_left])
+
+		self.logDebug('The captcha is: %s' % captcha)
+		return captcha