API tools faq
paste
Advertisement
Guest User

newpct.py

a guest
Feb 23rd, 2018
467
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 20.08 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. 'letter': [ urljoin(self.url, '/series/letter/{0}'),
  48. urljoin(self.url, '/series-hd/letter/{0}')],
  49. #urljoin(self.url, '/series-vo/letter/{0}')],
  50. 'downloadregex': r'[^\"]*/descargar-torrent/\d+_[^\"]*',}
  51.  
  52. self.cache = tvcache.TVCache(self, min_time=20)
  53.  
  54. def _get_season_search_strings(self, ep_obj):
  55. search_string = {'Season': []}
  56.  
  57. for show_name in set(allPossibleShowNames(ep_obj.show)):
  58. search_string['Season'].append(show_name)
  59.  
  60. return [search_string]
  61.  
  62. def _get_episode_search_strings(self, ep_obj, add_string=''):
  63. search_string = {'Episode': []}
  64.  
  65. for show_name in set(allPossibleShowNames(ep_obj.show)):
  66. search_string['Episode'].append(show_name)
  67.  
  68. return [search_string]
  69.  
  70. def search(self, search_strings, age=0, ep_obj=None): # pylint: disable=too-many-locals
  71.  
  72. results = []
  73.  
  74. # Only search if user conditions are true
  75. lang_info = '' if not ep_obj or not ep_obj.show else ep_obj.show.lang
  76.  
  77. for mode in search_strings:
  78. items = []
  79. logger.log('Search Mode: {0}'.format(mode), logger.DEBUG)
  80.  
  81. if mode == 'RSS':
  82.  
  83. data = self.cache.get_rss_feed(self.urls['rss'], params=None)['entries']
  84. if not data:
  85. logger.log('Data returned from provider does not contain any torrents', logger.DEBUG)
  86. continue
  87.  
  88. for curItem in data:
  89. try:
  90.  
  91. title = curItem['title'].decode('utf8')
  92. download_url = curItem['link']
  93. if not all([title, download_url]):
  94. continue
  95.  
  96. title = self._processTitle(title, None, download_url)
  97. result = {'title': title, 'link': download_url}
  98.  
  99. items.append(result)
  100. except StandardError:
  101. continue
  102.  
  103. else:
  104.  
  105. # Only search if user conditions are true
  106. if self.onlyspasearch and lang_info != 'es':
  107. logger.log('Show info is not spanish, skipping provider search', logger.DEBUG)
  108. continue
  109.  
  110. letters = []
  111. series_names_lower = [x.lower() for x in search_strings[mode]]
  112.  
  113. #search series name
  114. for series_name in series_names_lower:
  115. name = series_name.lower().strip()
  116. if name and (name[0] not in letters):
  117. letters.append(name[0])
  118.  
  119. for letter in letters:
  120. for letter_url in self.urls['letter']:
  121. url = letter_url.format(letter) if not letter.isdigit() else letter_url.format('0-9')
  122.  
  123. try:
  124. data = self.get_url(url, params=None, returns='text')
  125. seriesparsed = self.parse_seriestitleurl(series_names_lower, data)
  126. if not len(seriesparsed):
  127. continue
  128.  
  129. for seriesparseditem in seriesparsed:
  130. pg = 1
  131. while pg < 100:
  132. try:
  133. data = self.get_url(seriesparseditem['url'] + '/pg/' + str(pg) , params=None, returns='text')
  134. items = self.parse(seriesparseditem['title'], data, mode)
  135. if not len(items):
  136. break
  137. results += items
  138. except Exception:
  139. logger.log('No data returned from provider', logger.DEBUG)
  140. break
  141.  
  142. pg += 1
  143.  
  144. except Exception as e:
  145. logger.log('No data returned from provider (letter) {0}'.format(str(e)), logger.DEBUG)
  146. continue
  147.  
  148. results += items
  149.  
  150. return results
  151.  
  152.  
  153. def parse_seriestitleurl(self, series_names, data):
  154. results = []
  155.  
  156. with BS4Parser(data) as html:
  157. series_table = html.find('ul', class_='pelilist')
  158. series_rows = series_table('li') if series_table else []
  159.  
  160. # Continue only if at least one series is found
  161. if not len(series_rows):
  162. return results
  163.  
  164. for row in series_rows:
  165. try:
  166. series_anchor = row.find_all('a')[0]
  167. title = series_anchor.get('title', '').lower()
  168. url = series_anchor.get('href', '')
  169. if title and title in series_names:
  170. item = {
  171. 'title': title,
  172. 'url': url,
  173. }
  174. results.append(item)
  175. except Exception as e:
  176. continue
  177.  
  178. return results
  179.  
  180.  
  181. def parse(self, series_name, data, mode):
  182. """
  183. Parse search results for items.
  184.  
  185. :param data: The raw response from a search
  186. :param mode: The current mode used to search, e.g. RSS
  187.  
  188. :return: A list of items found
  189. """
  190.  
  191. results = []
  192.  
  193. with BS4Parser(data) as html:
  194. torrent_table = html.find('ul', class_='buscar-list')
  195. torrent_rows = torrent_table('li') if torrent_table else []
  196.  
  197. # Continue only if at least one release is found
  198. if not len(torrent_rows):
  199. sickrage.app.srLogger.debug('Data returned from provider does not contain any torrents')
  200. return results
  201.  
  202. for row in torrent_rows:
  203. try:
  204. torrent_anchor = row.find_all('a')[1]
  205. title = torrent_anchor.get_text()
  206. download_url = torrent_anchor.get('href', '')
  207.  
  208. if not all([title, download_url]):
  209. continue
  210.  
  211. row_spans = row.find_all('span')
  212. size = convert_size(row_spans[-2].get_text().strip()) if row_spans and len(row_spans) >= 2 else 0
  213. seeders = 1 # Provider does not provide seeders
  214. leechers = 0 # Provider does not provide leechers
  215.  
  216. title = self._processTitle(title, series_name, download_url)
  217.  
  218. logger.log('Found: {0} # Size {1}'.format(title, size), logger.DEBUG)
  219.  
  220. item = {
  221. 'title': title,
  222. 'link': download_url,
  223. 'size': size,
  224. 'seeders': seeders,
  225. 'leechers': leechers,
  226. }
  227.  
  228. results.append(item)
  229.  
  230. except (AttributeError, TypeError):
  231. continue
  232.  
  233. return results
  234.  
  235.  
  236. def get_url(self, url, post_data=None, params=None, timeout=30, **kwargs): # pylint: disable=too-many-arguments
  237. """
  238. returns='content' when trying access to torrent info (For calling torrent client). Previously we must parse
  239. the URL to get torrent file
  240. """
  241. trickery = kwargs.pop('returns', '')
  242. if trickery == 'content':
  243. kwargs['returns'] = 'text'
  244. data = super(newpctProvider, self).get_url(url, post_data=post_data, params=params, timeout=timeout, **kwargs)
  245.  
  246. match = re.search(r'' + self.urls['downloadregex'], data, re.DOTALL)
  247. if not match:
  248. return None
  249. url = match.group()
  250.  
  251. kwargs['returns'] = trickery
  252. return super(newpctProvider, self).get_url(url, post_data=post_data, params=params,
  253. timeout=timeout, **kwargs)
  254.  
  255. def download_result(self, result):
  256. """
  257. Save the result to disk.
  258. """
  259.  
  260. # check for auth
  261. if not self.login():
  262. return False
  263.  
  264. urls, filename = self._make_url(result)
  265.  
  266. for url in urls:
  267. # Search results don't return torrent files directly, it returns show sheets so we must parse showSheet to access torrent.
  268. data = self.get_url(url, returns='text')
  269.  
  270. match = re.search(r'' + self.urls['downloadregex'], data, re.DOTALL)
  271. if not match:
  272. continue
  273. url_torrent = match.group()
  274.  
  275. if url_torrent.startswith('http'):
  276. self.headers.update({'Referer': '/'.join(url_torrent.split('/')[:3]) + '/'})
  277.  
  278. logger.log('Downloading a result from {0}'.format(url))
  279.  
  280. if helpers.download_file(url_torrent, filename, session=self.session, headers=self.headers):
  281. if self._verify_download(filename):
  282. logger.log('Saved result to {0}'.format(filename), logger.INFO)
  283. return True
  284. else:
  285. logger.log('Could not download {0}'.format(url), logger.WARNING)
  286. helpers.remove_file_failed(filename)
  287.  
  288. if urls:
  289. logger.log('Failed to download any results', logger.WARNING)
  290.  
  291. return False
  292.  
  293. def _processTitle(self, title, series_name, url, try_download = True):
  294.  
  295. # Newpct titles are very very very inconsistent.
  296.  
  297. # Check if title is well formatted (RSS titles usually are)
  298. # Examples:
  299. # FooSeries - Temporada 2 [HDTV 720p][Cap.204][AC3 5.1 Español Castellano]
  300. # Salvation - Temporada 1 [HDTV][Cap.104-107][Español Castellano]
  301.  
  302. # else try to match list format
  303. # example
  304. # Serie Juego De Tronos Temporada 7 Capitulo 5 - Español Castellano Calidad [ HDTV ]
  305. # Serie Juego De Tronos Temporada [7] Capitulo [5] - Español Castellano Calidad [ HDTV ]
  306.  
  307. # else process download page title
  308. # else compose from download url
  309.  
  310. series_name = series_name or ""
  311.  
  312. logger.log('newpct _processTitle: {} # series_name {} # url {}'.format(title, series_name, url), logger.DEBUG)
  313.  
  314. #clean spaces
  315. title = self._clean_spaces(title)
  316. series_name = self._clean_spaces(series_name)
  317.  
  318. title_stdformat = r'.+-.+\d{1,2}.+\[Cap.\d{2,4}([\-\_]\d{2,4})?\]'
  319. title_listformat = r'Serie ?(.+?) ?-? ?Temporada ?\[?(\d+)\]?.*Capitulos? ?\[?(\d+)\]? ?(al ?\[?(\d+)\]?)?.*- ?(.*) ?Calidad ?(.+)'
  320. title_urlformat = r'.*\/(.*)\/capitulo-(\d{2,4})\/'
  321.  
  322. title_is_proper = re.search(r'\b(proper|repack)', title, flags=re.I)
  323.  
  324. stdformat_match = re.search(title_stdformat, title, flags=re.I)
  325. if not stdformat_match:
  326. #Try to match list format
  327. listformat_match = re.search(title_listformat, title, flags=re.I)
  328. if listformat_match:
  329. if series_name:
  330. name = series_name + ((' (' + title_is_proper.group() + ')') if title_is_proper else "")
  331. else:
  332. name = self._clean_spaces(listformat_match.group(1))
  333. season = self._clean_spaces(listformat_match.group(2))
  334. episode = self._clean_spaces(listformat_match.group(3)).zfill(2)
  335. audioquality = self._clean_spaces(listformat_match.group(6))
  336. quality = self._clean_spaces(listformat_match.group(7))
  337.  
  338. if not listformat_match.group(5):
  339. title = "{0} - Temporada {1} {2} [Cap.{3}{4}]".format(name, season, quality, season, episode)
  340. else:
  341. episode_to = self._clean_spaces(listformat_match.group(5)).zfill(2)
  342. title = "{0} - Temporada {1} {2} [Cap.{3}{4}_{5}{6}]".format(name, season, quality, season, episode, season, episode_to)
  343. logger.log('_processTitle: Matched by listFormat: {}'.format(title), logger.DEBUG)
  344. else:
  345. if try_download:
  346. # Get title from the download page
  347. try:
  348. data = self.get_url(url, params=None, returns='text')
  349. with BS4Parser(data) as details:
  350. title = details.find('h1').get_text().split('/')[1]
  351. logger.log('_processTitle: Title got from details page: {}'.format(title), logger.DEBUG)
  352. return self._processTitle(title, series_name, url, False)
  353. except (AttributeError, TypeError):
  354. logger.error('title could not be retrived')
  355. else:
  356. # Try to compose title from url
  357. url_match = re.search(title_urlformat, url, flags=re.I)
  358. if url_match:
  359. name = series_name if series_name else url_match.group(1).replace('-', ' ')
  360. season, episode = self._process_season_episode(url_match.group(2))
  361. title = '{} - Temporada {} [][Cap.{}{}]'.format(name, season, season, episode)
  362. logger.log('_processTitle: Matched by url: {}'.format(title), logger.DEBUG)
  363. else:
  364. logger.log('_processTitle: Matched by stdFormat: {}'.format(title), logger.DEBUG)
  365.  
  366. # Quality - Use re module to avoid case sensitive problems with replace
  367. title = re.sub(r'\[HDTV 1080p?[^\[]*]', '1080p HDTV x264', title, flags=re.I)
  368. title = re.sub(r'\[HDTV 720p?[^\[]*]', '720p HDTV x264', title, flags=re.I)
  369. title = re.sub(r'\[ALTA DEFINICION 720p?[^\[]*]', '720p HDTV x264', title, flags=re.I)
  370. title = re.sub(r'\[HDTV]', 'HDTV x264', title, flags=re.I)
  371. title = re.sub(r'\[DVD[^\[]*]', 'DVDrip x264', title, flags=re.I)
  372. title = re.sub(r'\[BluRay 1080p?[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  373. title = re.sub(r'\[BluRay Rip 1080p?[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  374. title = re.sub(r'\[BluRay Rip 720p?[^\[]*]', '720p BluRay x264', title, flags=re.I)
  375. title = re.sub(r'\[BluRay MicroHD[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  376. title = re.sub(r'\[MicroHD 1080p?[^\[]*]', '1080p BluRay x264', title, flags=re.I)
  377. title = re.sub(r'\[BLuRay[^\[]*]', '720p BluRay x264', title, flags=re.I)
  378. title = re.sub(r'\[BRrip[^\[]*]', '720p BluRay x264', title, flags=re.I)
  379. title = re.sub(r'\[BDrip[^\[]*]', '720p BluRay x264', title, flags=re.I)
  380.  
  381. #detect hdtv/bluray by url
  382. #hdtv 1080p example url: http://www.newpct.com/descargar-seriehd/foo/capitulo-610/hdtv-1080p-ac3-5-1/
  383. #hdtv 720p example url: http://www.newpct.com/descargar-seriehd/foo/capitulo-26/hdtv-720p-ac3-5-1/
  384. #hdtv example url: http://www.newpct.com/descargar-serie/foo/capitulo-214/hdtv/
  385. #bluray compilation example url: http://www.newpct.com/descargar-seriehd/foo/capitulo-11/bluray-1080p/
  386. title_hdtv = re.search(r'HDTV', title, flags=re.I)
  387. title_720p = re.search(r'720p', title, flags=re.I)
  388. title_1080p = re.search(r'1080p', title, flags=re.I)
  389. title_x264 = re.search(r'x264', title, flags=re.I)
  390. title_bluray = re.search(r'bluray', title, flags=re.I)
  391. title_vo = re.search(r'\[V.O.[^\[]*]', title, flags=re.I)
  392. url_hdtv = re.search(r'HDTV', url, flags=re.I)
  393. url_720p = re.search(r'720p', url, flags=re.I)
  394. url_1080p = re.search(r'1080p', url, flags=re.I)
  395. url_bluray = re.search(r'bluray', url, flags=re.I)
  396. url_serie_hd = re.search(r'descargar\-seriehd', url, flags=re.I)
  397. url_serie_vo = re.search(r'descargar\-serievo', url, flags=re.I)
  398.  
  399. if not title_hdtv and url_hdtv:
  400. title += ' HDTV'
  401. if not title_x264:
  402. title += ' x264'
  403. if not title_bluray and url_bluray:
  404. title += ' BluRay'
  405. if not title_x264:
  406. title += ' x264'
  407. if not title_1080p and url_1080p:
  408. title += ' 1080p'
  409. title_1080p = True
  410. if not title_720p and url_720p:
  411. title += ' 720p'
  412. title_720p = True
  413. if not (title_720p or title_1080p) and url_serie_hd:
  414. title += ' 720p'
  415. if not (title_vo) and url_serie_vo:
  416. title += ' [V.O.]'
  417. title_vo = True
  418.  
  419. # Language
  420. # title = re.sub(r'\[Spanish[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  421. # title = re.sub(r'\[Castellano[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  422. # title = re.sub(ur'\[Espa\u00f1ol[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  423. # title = re.sub(ur'\[Espa\u00f1ol Castellano[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  424. # title = re.sub(r'\[AC3 5\.1[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  425. # title = re.sub(ur'\[AC3 5\.1 Espa\u00f1ol[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  426. # title = re.sub(ur'\[AC3 5\.1 Espa\u00f1ol Castellano[^\[]*]', 'SPANISH AUDIO', title, flags=re.I)
  427.  
  428. if title_vo:
  429. title += ' -NEWPCTVO'
  430. else:
  431. title += ' -SPANISH AUDIO'
  432. title += ' -NEWPCT'
  433.  
  434. #propers handling
  435. title = re.sub(r'\(?proper\)?', '-PROPER', title, flags=re.I)
  436. title = re.sub(r'\(?repack\)?', '-REPACK', title, flags=re.I)
  437.  
  438. return self._clean_spaces(title)
  439.  
  440. def _process_season_episode(self, season_episode):
  441.  
  442. match = re.search(r'(\d)(\d{1,2})', season_episode, flags=re.I)
  443. if not match:
  444. match = re.search(r'(\d{2})(\d{2})', season_episode, flags=re.I)
  445.  
  446. season = match.group(1)
  447. episode = match.group(2).zfill(2)
  448.  
  449. return season, episode
  450.  
  451. def _clean_spaces(self, value):
  452.  
  453. value = value.strip()
  454. value = re.sub(r'[ ]+', ' ', value, flags=re.I)
  455. value = re.sub(r'\[[ ]+', '[', value, flags=re.I)
  456. value = re.sub(r'[ ]+\]', ']', value, flags=re.I)
  457. value = re.sub(r'\([ ]+', '(', value, flags=re.I)
  458. value = re.sub(r'[ ]+\)', ')', value, flags=re.I)
  459.  
  460. return value
  461.  
  462. 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!