API tools faq
paste
Advertisement
Guest User

newpct.py

a guest
Nov 11th, 2017
125
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 18.38 KB | None | 0 0
raw download clone embed print report
  1. # coding=utf-8
  2. # Author: CristianBB
  3. # Greetings to Mr. Pine-apple
  4. # URL: https://sickrage.github.io
  5. #
  6. # This file is part of SickRage.
  7. #
  8. # SickRage is free software: you can redistribute it and/or modify
  9. # it under the terms of the GNU General Public License as published by
  10. # the Free Software Foundation, either version 3 of the License, or
  11. # (at your option) any later version.
  12. #
  13. # SickRage is distributed in the hope that it will be useful,
  14. # but WITHOUT ANY WARRANTY; without even the implied warranty of
  15. # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  16. # GNU General Public License for more details.
  17. #
  18. # You should have received a copy of the GNU General Public License
  19. # along with SickRage. If not, see <http://www.gnu.org/licenses/>.
  20.  
  21. from __future__ import print_function, unicode_literals
  22.  
  23. import re
  24.  
  25. from requests.compat import urljoin
  26.  
  27. from sickbeard import helpers, logger, tvcache
  28. from sickbeard.bs4_parser import BS4Parser
  29. from sickrage.helper.common import convert_size
  30. from sickbeard.show_name_helpers import allPossibleShowNames
  31. from sickrage.providers.torrent.TorrentProvider import TorrentProvider
  32.  
  33.  
  34. class newpctProvider(TorrentProvider):
  35.  
  36. def __init__(self):
  37.  
  38. TorrentProvider.__init__(self, 'Newpct')
  39.  
  40. self.onlyspasearch = None
  41.  
  42. self.url = 'http://www.newpct.com'
  43. self.urls = {'search': [ urljoin(self.url, '/series'),
  44. urljoin(self.url, '/series-hd')],
  45. #urljoin(self.url, '/series-vo')],
  46. 'rss':urljoin(self.url, '/feed'),
  47. 'download': 'http://tumejorserie.com/descargar/index.php?link=torrents/%s.torrent',}
  48.  
  49. self.cache = tvcache.TVCache(self, min_time=20)
  50.  
  51. def _get_season_search_strings(self, ep_obj):
  52. search_string = {'Season': []}
  53.  
  54. for show_name in set(allPossibleShowNames(ep_obj.show)):
  55. search_string['Season'].append(show_name)
  56.  
  57. return [search_string]
  58.  
  59. def _get_episode_search_strings(self, ep_obj, add_string=''):
  60. search_string = {'Episode': []}
  61.  
  62. for show_name in set(allPossibleShowNames(ep_obj.show)):
  63. search_string['Episode'].append(show_name)
  64.  
  65. return [search_string]
  66.  
  67. def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals
  68. """
  69. Search query:
  70. http://www.newpct.com/index.php?l=doSearch&q=fringe&category_=All&idioma_=1&bus_de_=All
  71. q => Show name
  72. category_ = Category 'Shows' (767)
  73. idioma_ = Language Spanish (1), All
  74. bus_de_ = Date from (All, mes, semana, ayer, hoy)
  75. """
  76. results = []
  77.  
  78. # Only search if user conditions are true
  79. lang_info = '' if not ep_obj or not ep_obj.show else ep_obj.show.lang
  80.  
  81. for mode in search_strings:
  82. items = []
  83. logger.log('Search Mode: {0}'.format(mode), logger.DEBUG)
  84.  
  85. if mode == 'RSS':
  86.  
  87. data = self.cache.get_rss_feed(self.urls['rss'], params=None)['entries']
  88. if not data:
  89. logger.log('Data returned from provider does not contain any torrents', logger.DEBUG)
  90. continue
  91.  
  92. for curItem in data:
  93. try:
  94.  
  95. title = curItem['title'].decode('utf8')
  96. download_url = curItem['link']
  97. if not all([title, download_url]):
  98. continue
  99.  
  100. title = self._processTitle(title, None, download_url)
  101. result = {'title': title, 'link': download_url}
  102.  
  103. items.append(result)
  104. except StandardError:
  105. continue
  106.  
  107. else:
  108.  
  109. # Only search if user conditions are true
  110. if self.onlyspasearch and lang_info != 'es':
  111. logger.log('Show info is not spanish, skipping provider search', logger.DEBUG)
  112. continue
  113.  
  114. for series_name in search_strings[mode]:
  115. search_name = re.sub(r'[ \.\(\)]', '-', series_name, flags=re.I)
  116. search_names = [search_name]
  117. search_name = re.sub(r'-+', '-', search_name, flags=re.I)
  118. if not search_name in search_names:
  119. search_names.append(search_name)
  120.  
  121. for search_name in search_names:
  122. for search_url in self.urls['search']:
  123. pg = 1
  124. while True:
  125. url = search_url + '/' + search_name + '//pg/' + str(pg)
  126.  
  127. try:
  128. data = self.get_url(url, params=None, returns='text')
  129. items = self.parse(series_name, data, mode)
  130. if not len(items):
  131. break
  132. results += items
  133. except Exception:
  134. logger.log('No data returned from provider', logger.DEBUG)
  135. break
  136.  
  137. pg += 1
  138.  
  139. results += items
  140.  
  141. return results
  142.  
  143. def parse(self, series_name, data, mode):
  144. """
  145. Parse search results for items.
  146.  
  147. :param data: The raw response from a search
  148. :param mode: The current mode used to search, e.g. RSS
  149.  
  150. :return: A list of items found
  151. """
  152.  
  153. results = []
  154.  
  155. with BS4Parser(data) as html:
  156. torrent_table = html.find('ul', class_='buscar-list')
  157. torrent_rows = torrent_table('li') if torrent_table else []
  158.  
  159. # Continue only if at least one release is found
  160. if not len(torrent_rows):
  161. sickrage.app.srLogger.debug('Data returned from provider does not contain any torrents')
  162. return results
  163.  
  164. for row in torrent_rows:
  165. try:
  166. torrent_anchor = row.find_all('a')[1]
  167. title = torrent_anchor.get_text()
  168. download_url = torrent_anchor.get('href', '')
  169.  
  170. if not all([title, download_url]):
  171. continue
  172.  
  173. row_spans = row.find_all('span')
  174. size = convert_size(row_spans[-2].get_text().strip()) if row_spans and len(row_spans) >= 2 else 0
  175. seeders = 1 # Provider does not provide seeders
  176. leechers = 0 # Provider does not provide leechers
  177.  
  178. title = self._processTitle(title, series_name, download_url)
  179.  
  180. logger.log('Found: {0} # Size {1}'.format(title, size), logger.DEBUG)
  181.  
  182. item = {
  183. 'title': title,
  184. 'link': download_url,
  185. 'size': size,
  186. 'seeders': seeders,
  187. 'leechers': leechers,
  188. }
  189.  
  190. results.append(item)
  191.  
  192. except (AttributeError, TypeError):
  193. continue
  194.  
  195. return results
  196.  
  197.  
  198. def get_url(self, url, post_data=None, params=None, timeout=30, **kwargs): # pylint: disable=too-many-arguments
  199. """
  200. returns='content' when trying access to torrent info (For calling torrent client). Previously we must parse
  201. the URL to get torrent file
  202. """
  203. trickery = kwargs.pop('returns', '')
  204. if trickery == 'content':
  205. kwargs['returns'] = 'text'
  206. data = super(newpctProvider, self).get_url(url, post_data=post_data, params=params, timeout=timeout, **kwargs)
  207.  
  208. download_id = re.search(r'http://tumejorserie.com/descargar/.+?(\d{6}).+?\.html', data, re.DOTALL).group(1)
  209. url = self.urls['download'] % download_id
  210.  
  211. kwargs['returns'] = trickery
  212. return super(newpctProvider, self).get_url(url, post_data=post_data, params=params,
  213. timeout=timeout, **kwargs)
  214.  
  215. def download_result(self, result):
  216. """
  217. Save the result to disk.
  218. """
  219.  
  220. # check for auth
  221. if not self.login():
  222. return False
  223.  
  224. urls, filename = self._make_url(result)
  225.  
  226. for url in urls:
  227. # Search results don't return torrent files directly, it returns show sheets so we must parse showSheet to access torrent.
  228. data = self.get_url(url, returns='text')
  229.  
  230. download_id = re.search(r'http://tumejorserie.com/descargar/.+?(\d{6}).+?\.html', data, re.DOTALL).group(1)
  231. url_torrent = self.urls['download'] % download_id
  232.  
  233. if url_torrent.startswith('http'):
  234. self.headers.update({'Referer': '/'.join(url_torrent.split('/')[:3]) + '/'})
  235.  
  236. logger.log('Downloading a result from {0}'.format(url))
  237.  
  238. if helpers.download_file(url_torrent, filename, session=self.session, headers=self.headers):
  239. if self._verify_download(filename):
  240. logger.log('Saved result to {0}'.format(filename), logger.INFO)
  241. return True
  242. else:
  243. logger.log('Could not download {0}'.format(url), logger.WARNING)
  244. helpers.remove_file_failed(filename)
  245.  
  246. if urls:
  247. logger.log('Failed to download any results', logger.WARNING)
  248.  
  249. return False
  250.  
  251. def _processTitle(self, title, series_name, url, try_download = True):
  252.  
  253. # Newpct titles are very very very inconsistent.
  254.  
  255. # Check if title is well formatted (RSS titles usually are)
  256. # Examples:
  257. # FooSeries - Temporada 2 [HDTV 720p][Cap.204][AC3 5.1 Español Castellano]
  258. # Salvation - Temporada 1 [HDTV][Cap.104-107][Español Castellano]
  259.  
  260. # else try to match list format
  261. # example
  262. # Serie Juego De Tronos Temporada 7 Capitulo 5 - Español Castellano Calidad [ HDTV ]
  263. # Serie Juego De Tronos Temporada [7] Capitulo [5] - Español Castellano Calidad [ HDTV ]
  264.  
  265. # else process download page title
  266. # else compose from download url
  267.  
  268. series_name = series_name or ""
  269.  
  270. logger.log('newpct _processTitle: {} # series_name {} # url {}'.format(title, series_name, url), logger.DEBUG)
  271.  
  272. #clean spaces
  273. title = self._clean_spaces(title)
  274. series_name = self._clean_spaces(series_name)
  275.  
  276. title_stdformat = r'.+-.+\d{1,2}.+\[Cap.\d{2,4}([\-\_]\d{2,4})?\]'
  277. title_listformat = r'Serie ?(.+?) ?-? ?Temporada ?\[?(\d+)\]?.*Capitulos? ?\[?(\d+)\]? ?(al ?\[?(\d+)\]?)?.*- ?(.*) ?Calidad ?(.+)'
  278. title_urlformat = r'.*\/(.*)\/capitulo-(\d{2,4})\/'
  279.  
  280. title_is_proper = re.search(r'\b(proper|repack)', title, flags=re.I)
  281.  
  282. stdformat_match = re.search(title_stdformat, title, flags=re.I)
  283. if not stdformat_match:
  284. #Try to match list format
  285. listformat_match = re.search(title_listformat, title, flags=re.I)
  286. if listformat_match:
  287. if series_name:
  288. name = series_name + ((' (' + title_is_proper.group() + ')') if title_is_proper else "")
  289. else:
  290. name = self._clean_spaces(listformat_match.group(1))
  291. season = self._clean_spaces(listformat_match.group(2))
  292. episode = self._clean_spaces(listformat_match.group(3)).zfill(2)
  293. audioquality = self._clean_spaces(listformat_match.group(6))
  294. quality = self._clean_spaces(listformat_match.group(7))
  295.  
  296. if not listformat_match.group(5):
  297. title = "{0} - Temporada {1} {2} [Cap.{3}{4}]".format(name, season, quality, season, episode)
  298. else:
  299. episode_to = self._clean_spaces(listformat_match.group(5)).zfill(2)
  300. title = "{0} - Temporada {1} {2} [Cap.{3}{4}_{5}{6}]".format(name, season, quality, season, episode, season, episode_to)
  301. logger.log('_processTitle: Matched by listFormat: {}'.format(title), logger.DEBUG)
  302. else:
  303. if try_download:
  304. # Get title from the download page
  305. try:
  306. data = self.get_url(url, params=None, returns='text')
  307. with BS4Parser(data) as details:
  308. title = details.find('h1').get_text().split('/')[1]
  309. logger.log('_processTitle: Title got from details page: {}'.format(title), logger.DEBUG)
  310. return self._processTitle(title, series_name, url, False)
  311. except (AttributeError, TypeError):
  312. logger.error('title could not be retrived')
  313. else:
  314. # Try to compose title from url
  315. url_match = re.search(title_urlformat, url, flags=re.I)
  316. if url_match:
  317. name = series_name if series_name else url_match.group(1).replace('-', ' ')
  318. season, episode = self._process_season_episode(url_match.group(2))
  319. title = '{} - Temporada {} [][Cap.{}{}]'.format(name, season, season, episode)
  320. logger.log('_processTitle: Matched by url: {}'.format(title), logger.DEBUG)
  321. else:
  322. logger.log('_processTitle: Matched by stdFormat: {}'.format(title), logger.DEBUG)
  323.  
  324. # Quality - Use re module to avoid case sensitive problems with replace
  325. title = re.sub(r'\[HDTV 1080p?[^\[]*]', '1080p HDTV x264', title, flags=re.I)
  326. title = re.sub(r'\[HDTV 720p?[^\[]*]', '720p HDTV x264', title, flags=re.I)
  327. title = re.sub(r'\[ALTA DEFINICION 720p?[^\[]*]', '720p HDTV x264', title, flags=re.I)
  328. title = re.sub(r'\[HDTV]', 'HDTV x264', title, flags=re.I)
  329. title = re.sub(r'\[DVD[^\[]*]', 'DVDrip x264', title, flags=re.I)
  330. title = re.sub(r'\[BluRay 1080p?[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  331. title = re.sub(r'\[BluRay Rip 1080p?[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  332. title = re.sub(r'\[BluRay Rip 720p?[^\[]*]', '720p BluRay x264', title, flags=re.I)
  333. title = re.sub(r'\[BluRay MicroHD[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  334. title = re.sub(r'\[MicroHD 1080p?[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  335. title = re.sub(r'\[BLuRay[^\[]*]', '720p BluRay x264', title, flags=re.I)
  336. title = re.sub(r'\[BRrip[^\[]*]', '720p BluRay x264', title, flags=re.I)
  337. title = re.sub(r'\[BDrip[^\[]*]', '720p BluRay x264', title, flags=re.I)
  338.  
  339. #detect hdtv/bluray by url
  340. #hdtv 1080p example url: http://www.newpct.com/descargar-seriehd/foo/capitulo-610/hdtv-1080p-ac3-5-1/
  341. #hdtv 720p example url: http://www.newpct.com/descargar-seriehd/foo/capitulo-26/hdtv-720p-ac3-5-1/
  342. #hdtv example url: http://www.newpct.com/descargar-serie/foo/capitulo-214/hdtv/
  343. #bluray compilation example url: http://www.newpct.com/descargar-seriehd/foo/capitulo-11/bluray-1080p/
  344. title_hdtv = re.search(r'HDTV', title, flags=re.I)
  345. title_720p = re.search(r'720p', title, flags=re.I)
  346. title_1080p = re.search(r'1080p', title, flags=re.I)
  347. title_x264 = re.search(r'x264', title, flags=re.I)
  348. title_bluray = re.search(r'bluray', title, flags=re.I)
  349. title_vo = re.search(r'\[V.O.[^\[]*]', title, flags=re.I)
  350. url_hdtv = re.search(r'HDTV', url, flags=re.I)
  351. url_720p = re.search(r'720p', url, flags=re.I)
  352. url_1080p = re.search(r'1080p', url, flags=re.I)
  353. url_bluray = re.search(r'bluray', url, flags=re.I)
  354. url_serie_hd = re.search(r'descargar\-seriehd', url, flags=re.I)
  355. url_serie_vo = re.search(r'descargar\-serievo', url, flags=re.I)
  356.  
  357. if not title_hdtv and url_hdtv:
  358. title += ' HDTV'
  359. if not title_x264:
  360. title += ' x264'
  361. if not title_bluray and url_bluray:
  362. title += ' BluRay'
  363. if not title_x264:
  364. title += ' x264'
  365. if not title_1080p and url_1080p:
  366. title += ' 1080p'
  367. title_1080p = True
  368. if not title_720p and url_720p:
  369. title += ' 720p'
  370. title_720p = True
  371. if not (title_720p or title_1080p) and url_serie_hd:
  372. title += ' 720p'
  373. if not (title_vo) and url_serie_vo:
  374. title += ' [V.O.]'
  375. title_vo = True
  376.  
  377. # Language
  378. # title = re.sub(r'\[Spanish[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  379. # title = re.sub(r'\[Castellano[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  380. # title = re.sub(ur'\[Espa\u00f1ol[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  381. # title = re.sub(ur'\[Espa\u00f1ol Castellano[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  382. # title = re.sub(r'\[AC3 5\.1[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  383. # title = re.sub(ur'\[AC3 5\.1 Espa\u00f1ol[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  384. # title = re.sub(ur'\[AC3 5\.1 Espa\u00f1ol Castellano[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  385.  
  386. if title_vo:
  387. title += ' -NEWPCTVO'
  388. else:
  389. title += ' -SPANISH AUDIO'
  390. title += ' -NEWPCT'
  391.  
  392. #propers handling
  393. title = re.sub(r'\(?proper\)?', '-PROPER', title, flags=re.I)
  394. title = re.sub(r'\(?repack\)?', '-REPACK', title, flags=re.I)
  395.  
  396. return self._clean_spaces(title)
  397.  
  398. def _process_season_episode(self, season_episode):
  399.  
  400. match = re.search(r'(\d)(\d{1,2})', season_episode, flags=re.I)
  401. if not match:
  402. match = re.search(r'(\d{2})(\d{2})', season_episode, flags=re.I)
  403.  
  404. season = match.group(1)
  405. episode = match.group(2).zfill(2)
  406.  
  407. return season, episode
  408.  
  409. def _clean_spaces(self, value):
  410.  
  411. value = value.strip()
  412. value = re.sub(r'[ ]+', ' ', value, flags=re.I)
  413. value = re.sub(r'\[[ ]+', '[', value, flags=re.I)
  414. value = re.sub(r'[ ]+\]', ']', value, flags=re.I)
  415. value = re.sub(r'\([ ]+', '(', value, flags=re.I)
  416. value = re.sub(r'[ ]+\)', ')', value, flags=re.I)
  417.  
  418. return value
  419.  
  420. provider = newpctProvider()
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!