Merge pull request #762 from IIIspaceIII/feature/provider-titrari-ro

Feature/provider titrari ro

README.md

@@ -67,6 +67,7 @@ If you need something that is not already part of Bazarr, feel free to create a
 * SubZ
 * Supersubtitles
 * Titlovi
+* Titrari.ro
 * TVSubtitles
 * XSubs
 * Zimuku

bazarr/get_providers.py

@@ -39,7 +39,7 @@ PROVIDER_THROTTLE_MAP = {
 }
 
 PROVIDERS_FORCED_OFF = ["addic7ed", "tvsubtitles", "legendasdivx", "legendastv", "napiprojekt", "shooter", "hosszupuska",
-                        "supersubtitles", "titlovi", "argenteam", "assrt", "subscene"]
+                        "supersubtitles", "titlovi", "titrari", "argenteam", "assrt", "subscene"]
 
 throttle_count = {}
 

libs/subliminal_patch/providers/titrari.py

@@ -0,0 +1,224 @@
+# coding=utf-8
+
+from __future__ import absolute_import
+import io
+import logging
+import re
+from subliminal import __short_version__
+import rarfile
+
+from zipfile import ZipFile, is_zipfile
+from rarfile import RarFile, is_rarfile
+from subliminal_patch.providers import Provider
+from subliminal_patch.providers.mixins import ProviderSubtitleArchiveMixin
+from subliminal_patch.subtitle import Subtitle
+from subliminal_patch.utils import sanitize, fix_inconsistent_naming as _fix_inconsistent_naming
+from subliminal.exceptions import ProviderError
+from subliminal.providers import ParserBeautifulSoup
+from subliminal.video import Episode, Movie
+from subzero.language import Language
+
+# parsing regex definitions
+title_re = re.compile(r'(?P<title>(?:.+(?= [Aa][Kk][Aa] ))|.+)(?:(?:.+)(?P<altitle>(?<= [Aa][Kk][Aa] ).+))?')
+
+
+def fix_inconsistent_naming(title):
+    """Fix titles with inconsistent naming using dictionary and sanitize them.
+
+    :param str title: original title.
+    :return: new title.
+    :rtype: str
+
+    """
+    return _fix_inconsistent_naming(title, {"DC's Legends of Tomorrow": "Legends of Tomorrow",
+                                            "Marvel's Jessica Jones": "Jessica Jones"})
+
+
+logger = logging.getLogger(__name__)
+
+# Configure :mod:`rarfile` to use the same path separator as :mod:`zipfile`
+rarfile.PATH_SEP = '/'
+
+class TitrariSubtitle(Subtitle):
+
+    provider_name = 'titrari'
+
+    def __init__(self, language, download_link, sid, releases, title, imdb_id, year=None, download_count=None, comments=None):
+        super(TitrariSubtitle, self).__init__(language)
+        self.sid = sid
+        self.title = title
+        self.imdb_id = imdb_id
+        self.download_link = download_link
+        self.year = year
+        self.download_count = download_count
+        self.releases = self.release_info = releases
+        self.comments = comments
+
+    @property
+    def id(self):
+        return self.sid
+
+    def __str__(self):
+        return self.title + "(" + str(self.year) + ")" + " -> " + self.download_link
+
+    def __repr__(self):
+        return self.title + "(" + str(self.year) + ")"
+
+    def get_matches(self, video):
+        matches = set()
+
+        if isinstance(video, Movie):
+            # title
+            if video.title and sanitize(self.title) == fix_inconsistent_naming(video.title):
+                matches.add('title')
+
+            if video.year and self.year == video.year:
+                matches.add('year')
+
+            if video.imdb_id and self.imdb_id == video.imdb_id:
+                matches.add('imdb_id')
+
+            if video.release_group and video.release_group in self.comments:
+                matches.add('release_group')
+
+            if video.resolution and video.resolution.lower() in self.comments:
+                matches.add('resolution')
+
+        self.matches = matches
+
+        return matches
+
+
+class TitrariProvider(Provider, ProviderSubtitleArchiveMixin):
+    subtitle_class = TitrariSubtitle
+    languages = {Language(l) for l in ['ron', 'eng']}
+    languages.update(set(Language.rebuild(l, forced=True) for l in languages))
+    api_url = 'https://www.titrari.ro/'
+    query_advanced_search = 'cautareavansata'
+
+    def __init__(self):
+        self.session = None
+
+    def initialize(self):
+        self.session = Session()
+        self.session.headers['User-Agent'] = 'Subliminal/{}'.format(__short_version__)
+
+    def terminate(self):
+        self.session.close()
+
+    def query(self, languages=None, title=None, imdb_id=None, video=None):
+        subtitles = []
+
+        params = self.getQueryParams(imdb_id, title)
+
+        search_response = self.session.get(self.api_url, params=params, timeout=15)
+        search_response.raise_for_status()
+
+        if not search_response.content:
+            logger.debug('[#### Provider: titrari.ro] No data returned from provider')
+            return []
+
+        soup = ParserBeautifulSoup(search_response.content.decode('utf-8', 'ignore'), ['lxml', 'html.parser'])
+
+        # loop over subtitle cells
+        rows = soup.select('td[rowspan=\'5\']')
+        for index, row in enumerate(rows):
+            result_anchor_el = row.select_one('a')
+
+            # Download link
+            href = result_anchor_el.get('href')
+            download_link = self.api_url + href
+
+            fullTitle = row.parent.find("h1").find("a").text
+
+            #Get title
+            try:
+                title = fullTitle.split("(")[0]
+            except:
+                logger.error("[#### Provider: titrari.ro] Error parsing title.")
+
+            # Get downloads count
+            try:
+                downloads = int(row.parent.parent.select("span")[index].text[12:])
+            except:
+                logger.error("[#### Provider: titrari.ro] Error parsing downloads.")
+
+            # Get year
+            try:
+                year = int(fullTitle.split("(")[1].split(")")[0])
+            except:
+                year = None
+                logger.error("[#### Provider: titrari.ro] Error parsing year.")
+
+            # Get imdbId
+            sub_imdb_id = self.getImdbIdFromSubtitle(row)
+
+            try:
+                comments = row.parent.parent.find_all("td", class_=re.compile("comment"))[index*2+1].text
+            except:
+                logger.error("Error parsing comments.")
+
+            subtitle = self.subtitle_class(next(iter(languages)), download_link, index, None, title, sub_imdb_id, year, downloads, comments)
+            logger.debug('[#### Provider: titrari.ro] Found subtitle %r', str(subtitle))
+            subtitles.append(subtitle)
+
+        ordered_subs = self.order(subtitles, video)
+
+        return ordered_subs
+
+    def order(self, subtitles, video):
+        logger.debug("[#### Provider: titrari.ro] Sorting by download count...")
+        sorted_subs = sorted(subtitles, key=lambda s: s.download_count, reverse=True)
+        return sorted_subs
+
+    def getImdbIdFromSubtitle(self, row):
+        try:
+            imdbId = row.parent.parent.find_all(src=re.compile("imdb"))[0].parent.get('href').split("tt")[-1]
+        except:
+            logger.error("[#### Provider: titrari.ro] Error parsing imdbId.")
+        if imdbId is not None:
+            return "tt" + imdbId
+        else:
+            return None
+
+
+    def getQueryParams(self, imdb_id, title):
+        queryParams = {
+            'page': self.query_advanced_search,
+            'z8': '1'
+        }
+        if imdb_id is not None:
+            queryParams["z5"] = imdb_id
+        elif title is not None:
+            queryParams["z7"] = title
+
+        return queryParams
+
+    def list_subtitles(self, video, languages):
+        title = fix_inconsistent_naming(video.title)
+        imdb_id = video.imdb_id[2:]
+        return [s for s in
+                self.query(languages, title, imdb_id, video)]
+
+    def download_subtitle(self, subtitle):
+        r = self.session.get(subtitle.download_link, headers={'Referer': self.api_url}, timeout=10)
+        r.raise_for_status()
+
+        # open the archive
+        archive_stream = io.BytesIO(r.content)
+        if is_rarfile(archive_stream):
+            logger.debug('[#### Provider: titrari.ro] Archive identified as rar')
+            archive = RarFile(archive_stream)
+        elif is_zipfile(archive_stream):
+            logger.debug('[#### Provider: titrari.ro] Archive identified as zip')
+            archive = ZipFile(archive_stream)
+        else:
+            subtitle.content = r.content
+            if subtitle.is_valid():
+                return
+            subtitle.content = None
+
+            raise ProviderError('[#### Provider: titrari.ro] Unidentified archive type')
+
+        subtitle.content = self.get_subtitle_from_archive(subtitle, archive)
+

libs/subzero/language.py

@@ -30,6 +30,7 @@ repl_map = {
     "rum": "ro",
     "slo": "sk",
     "tib": "bo",
+    "ron": "ro",
 }
 
 ALPHA2_LIST = list(set(filter(lambda x: x, map(lambda x: x.alpha2, LANGUAGE_MATRIX)))) + list(repl_map.values())

views/providers.tpl

@@ -756,6 +756,28 @@
                             </div>
                         </div>
 
+                        <div class="middle aligned row">
+                            <div class="right aligned four wide column">
+                                <label>Titrari.ro</label>
+                            </div>
+                            <div class="one wide column">
+                                <div id="titrari" class="ui toggle checkbox provider">
+                                    <input type="checkbox">
+                                    <label></label>
+                                </div>
+                            </div>
+                            <div class="collapsed column">
+                                <div class="collapsed center aligned column">
+                                    <div class="ui basic icon" data-tooltip="Romanian Subtitles Provider." data-inverted="">
+                                        <i class="help circle large icon"></i>
+                                     </div>
+                                 </div>
+                             </div>
+                        </div>
+                        <div id="titrari_option" class="ui grid container">
+
+                        </div>
+
                         <div class="middle aligned row">
                             <div class="right aligned four wide column">
                                 <label>TVSubtitles</label>