parse torrent name

channels/ilcorsaronero.py

@@ -40,9 +40,11 @@ def mainlist(item):
 
 @support.scrape
 def peliculas(item):
+    ptn = True
     patron = r'>(?P<quality>[^"<]+)</td> <TD[^>]+><A class="tab" HREF="(?P<url>[^"]+)"\s*>(?P<title>[^<]+)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>(?P<size>[^<]+)<[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>[^>]+>(?P<seed>[^<]+)'
     def itemHook(item):
-        item.title = item.title.replace('.',' ')
+        # item.title = item.title.replace('.',' ')
+        item.contentType = item.args[1]
         thumb = (item.args[1] if type(item.args) == list else item.args) + '.png'
         item.thumbnail = support.thumb(thumb=thumb)
         return item

core/support.py

@@ -6,6 +6,9 @@ import inspect
 import os
 import re
 import sys
+
+from lib.PTN import PTN
+
 PY3 = False
 if sys.version_info[0] >= 3: PY3 = True; unicode = str; unichr = chr; long = int
 if PY3:
@@ -171,7 +174,7 @@ def cleantitle(title):
     cleantitle = title.replace('"', "'").replace('×', 'x').replace('–', '-').strip()
     return cleantitle
 
-def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, typeContentDict, typeActionDict, blacklist, search, pag, function, lang):
+def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, typeContentDict, typeActionDict, blacklist, search, pag, function, lang, ptn):
     itemlist = []
     log("scrapeBlock qui")
     if debug:
@@ -240,17 +243,6 @@ def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, t
         Type = scraped['type'] if scraped['type'] else ''
         plot = cleantitle(scraped["plot"]) if scraped["plot"] else ''
 
-        # make formatted Title [longtitle]
-        s = ' - '
-        title = episode + (s if episode and title else '') + title
-        longtitle = title + (s if title and title2 else '') + title2
-        longtitle = typo(longtitle, 'bold')
-        longtitle += typo(quality, '_ [] color kod') if quality else ''
-        longtitle += typo(scraped['size'], '_ [] color kod') if scraped['size'] else ''
-        longtitle += typo(scraped['seed']+ ' SEEDS', '_ [] color kod') if scraped['seed'] else ''
-
-        lang1, longtitle = scrapeLang(scraped, lang, longtitle)
-
         # if title is set, probably this is a list of episodes or video sources
         # necessaria l'aggiunta di == scraped["title"] altrimenti non prende i gruppi dopo le categorie
         if item.infoLabels["title"] == scraped["title"]:
@@ -275,6 +267,28 @@ def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, t
             if scraped["rating"]:
                 infolabels['rating'] = scrapertools.decodeHtmlentities(scraped["rating"])
 
+        # make formatted Title [longtitle]
+        s = ' - '
+        title = episode + (s if episode and title else '') + title
+        longtitle = title + (s if title and title2 else '') + title2
+
+        lang1, longtitle = scrapeLang(scraped, lang, longtitle)
+
+        if ptn:
+            titlePTN = PTN().parse(title)
+            title = titlePTN.get('title', '')
+            if titlePTN.get('quality', '') or titlePTN.get('resolution', ''):
+                quality = titlePTN.get('quality', '') + " " + titlePTN.get('resolution', '')
+            if not scraped['year']:
+                infolabels['year'] = titlePTN.get('year', '')
+            if titlePTN.get('episode', None) and titlePTN.get('season', None):
+                longtitle = title + ' - ' + str(titlePTN.get('episode')) + 'x' + str(titlePTN.get('season'))
+
+        longtitle = typo(longtitle, 'bold')
+        longtitle += typo(quality, '_ [] color kod') if quality else ''
+        longtitle += typo(scraped['size'], '_ [] color kod') if scraped['size'] else ''
+        longtitle += typo(scraped['seed'] + ' SEEDS', '_ [] color kod') if scraped['seed'] else ''
+
         AC = CT = ''
         if typeContentDict:
             for name, variants in typeContentDict.items():
@@ -380,6 +394,7 @@ def scrape(func):
         if 'pagination' in args and inspect.stack()[1][3] not in ['add_tvshow', 'get_episodes', 'update', 'find_episodes']: pagination = args['pagination'] if args['pagination'] else 20
         else: pagination = ''
         lang = args['deflang'] if 'deflang' in args else ''
+        ptn = args.get('ptn', False)
         pag = item.page if item.page else 1  # pagination
         matches = []
 
@@ -402,7 +417,7 @@ def scrape(func):
                     if 'season' in bl and bl['season']:
                         item.season = bl['season']
                     blockItemlist, blockMatches = scrapeBlock(item, args, bl['block'], patron, headers, action, pagination, debug,
-                                                typeContentDict, typeActionDict, blacklist, search, pag, function, lang)
+                                                typeContentDict, typeActionDict, blacklist, search, pag, function, lang, ptn)
                     for it in blockItemlist:
                         if 'lang' in bl:
                             it.contentLanguage, it.title = scrapeLang(bl, it.contentLanguage, it.title)
@@ -413,7 +428,7 @@ def scrape(func):
                     matches.extend(blockMatches)
             elif patron:
                 itemlist, matches = scrapeBlock(item, args, data, patron, headers, action, pagination, debug, typeContentDict,
-                                       typeActionDict, blacklist, search, pag, function, lang)
+                                       typeActionDict, blacklist, search, pag, function, lang, ptn)
 
             if 'itemlistHook' in args:
                 itemlist = args['itemlistHook'](itemlist)

lib/PTN/__init__.py

@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+from .parse import PTN
+# https://github.com/divijbindlish/parse-torrent-name
+__author__ = 'Divij Bindlish'
+__email__ = 'dvjbndlsh93@gmail.com'
+__version__ = '1.1.1'
+__license__ = 'MIT'
+
+ptn = PTN()
+
+
+def parse(name):
+    return ptn.parse(name)

lib/PTN/parse.py

@@ -0,0 +1,136 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import re
+from .patterns import patterns, types
+
+
+class PTN(object):
+    def _escape_regex(self, string):
+        return re.sub('[\-\[\]{}()*+?.,\\\^$|#\s]', '\\$&', string)
+
+    def __init__(self):
+        self.torrent = None
+        self.excess_raw = None
+        self.group_raw = None
+        self.start = None
+        self.end = None
+        self.title_raw = None
+        self.parts = None
+
+    def _part(self, name, match, raw, clean):
+        # The main core instructuions
+        self.parts[name] = clean
+
+        if len(match) != 0:
+            # The instructions for extracting title
+            index = self.torrent['name'].find(match[0])
+            if index == 0:
+                self.start = len(match[0])
+            elif self.end is None or index < self.end:
+                self.end = index
+
+        if name != 'excess':
+            # The instructions for adding excess
+            if name == 'group':
+                self.group_raw = raw
+            if raw is not None:
+                self.excess_raw = self.excess_raw.replace(raw, '')
+
+    def _late(self, name, clean):
+        if name == 'group':
+            self._part(name, [], None, clean)
+        elif name == 'episodeName':
+            clean = re.sub('[\._]', ' ', clean)
+            clean = re.sub('_+$', '', clean)
+            self._part(name, [], None, clean.strip())
+
+    def parse(self, name):
+        self.parts = {}
+        self.torrent = {'name': name}
+        self.excess_raw = name
+        self.group_raw = ''
+        self.start = 0
+        self.end = None
+        self.title_raw = None
+
+        for key, pattern in patterns:
+            if key not in ('season', 'episode', 'website'):
+                pattern = r'\b%s\b' % pattern
+
+            clean_name = re.sub('_', ' ', self.torrent['name'])
+            match = re.findall(pattern, clean_name, re.I)
+            if len(match) == 0:
+                continue
+
+            index = {}
+            if isinstance(match[0], tuple):
+                match = list(match[0])
+            if len(match) > 1:
+                index['raw'] = 0
+                index['clean'] = 1
+            else:
+                index['raw'] = 0
+                index['clean'] = 0
+
+            if key in types.keys() and types[key] == 'boolean':
+                clean = True
+            else:
+                clean = match[index['clean']]
+                if key in types.keys() and types[key] == 'integer':
+                    clean = int(clean)
+            if key == 'group':
+                if re.search(patterns[5][1], clean, re.I) \
+                        or re.search(patterns[4][1], clean):
+                    continue  # Codec and quality.
+                if re.match('[^ ]+ [^ ]+ .+', clean):
+                    key = 'episodeName'
+            if key == 'episode':
+                sub_pattern = self._escape_regex(match[index['raw']])
+                self.torrent['map'] = re.sub(
+                    sub_pattern, '{episode}', self.torrent['name']
+                )
+            self._part(key, match, match[index['raw']], clean)
+
+        # Start process for title
+        raw = self.torrent['name']
+        if self.end is not None:
+            raw = raw[self.start:self.end].split('(')[0]
+
+        clean = re.sub('^ -', '', raw)
+        if clean.find(' ') == -1 and clean.find('.') != -1:
+            clean = re.sub('\.', ' ', clean)
+        clean = re.sub('_', ' ', clean)
+        clean = re.sub('([\[\(_]|- )$', '', clean).strip()
+
+        self._part('title', [], raw, clean)
+
+        # Start process for end
+        clean = re.sub('(^[-\. ()]+)|([-\. ]+$)', '', self.excess_raw)
+        clean = re.sub('[\(\)\/]', ' ', clean)
+        match = re.split('\.\.+| +', clean)
+        if len(match) > 0 and isinstance(match[0], tuple):
+            match = list(match[0])
+
+        clean = filter(bool, match)
+        clean = [item for item in filter(lambda a: a != '-', clean)]
+        clean = [item.strip('-') for item in clean]
+        if len(clean) != 0:
+            group_pattern = clean[-1] + self.group_raw
+            if self.torrent['name'].find(group_pattern) == \
+                    len(self.torrent['name']) - len(group_pattern):
+                self._late('group', clean.pop() + self.group_raw)
+
+            if 'map' in self.torrent.keys() and len(clean) != 0:
+                episode_name_pattern = (
+                    '{episode}'
+                    '' + re.sub('_+$', '', clean[0])
+                )
+                if self.torrent['map'].find(episode_name_pattern) != -1:
+                    self._late('episodeName', clean.pop(0))
+
+        if len(clean) != 0:
+            if len(clean) == 1:
+                clean = clean[0]
+            self._part('excess', [], self.excess_raw, clean)
+        return self.parts

lib/PTN/patterns.py

@@ -0,0 +1,43 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+patterns = [
+    ('season', '(s?([0-9]{1,2}))[ex]'),
+    ('episode', '([ex]([0-9]{2})(?:[^0-9]|$))'),
+    ('year', '([\[\(]?((?:19[0-9]|20[01])[0-9])[\]\)]?)'),
+    ('resolution', '([0-9]{3,4}p)'),
+    ('quality', ('((?:PPV\.)?[HP]DTV|(?:HD)?CAM|B[DR]Rip|(?:HD-?)?TS|'
+                 '(?:PPV )?WEB-?DL(?: DVDRip)?|HDRip|DVDRip|DVDRIP|'
+                 'CamRip|W[EB]BRip|BluRay|DvDScr|hdtv|telesync)')),
+    ('codec', '(xvid|[hx]\.?26[45])'),
+    ('audio', ('(MP3|DD5\.?1|Dual[\- ]Audio|LiNE|DTS|'
+               'AAC[.-]LC|AAC(?:\.?2\.0)?|'
+               'AC3(?:\.5\.1)?)')),
+    ('group', '(- ?([^-]+(?:-={[^-]+-?$)?))$'),
+    ('region', 'R[0-9]'),
+    ('extended', '(EXTENDED(:?.CUT)?)'),
+    ('hardcoded', 'HC'),
+    ('proper', 'PROPER'),
+    ('repack', 'REPACK'),
+    ('container', '(MKV|AVI|MP4)'),
+    ('widescreen', 'WS'),
+    ('website', '^(\[ ?([^\]]+?) ?\])'),
+    ('language', '(rus\.eng|ita\.eng)'),
+    ('sbs', '(?:Half-)?SBS'),
+    ('unrated', 'UNRATED'),
+    ('size', '(\d+(?:\.\d+)?(?:GB|MB))'),
+    ('3d', '3D')
+]
+
+types = {
+    'season': 'integer',
+    'episode': 'integer',
+    'year': 'integer',
+    'extended': 'boolean',
+    'hardcoded': 'boolean',
+    'proper': 'boolean',
+    'repack': 'boolean',
+    'widescreen': 'boolean',
+    'unrated': 'boolean',
+    '3d': 'boolean'
+}