mirror of https://github.com/morpheus65535/bazarr
Subtitrarinoi provider: add several improvements
* Fix episode matches (#2018) * Use standard utils to download subtitles * Use standard utils to guess matches (partially implemented)
This commit is contained in:
parent
e6864a9001
commit
1233026adc
|
@ -1,28 +1,30 @@
|
||||||
# coding=utf-8
|
# coding=utf-8
|
||||||
|
|
||||||
from __future__ import absolute_import
|
from __future__ import absolute_import
|
||||||
import os
|
|
||||||
import io
|
|
||||||
import logging
|
import logging
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from zipfile import ZipFile, is_zipfile
|
from subliminal.providers import ParserBeautifulSoup
|
||||||
from rarfile import RarFile, is_rarfile
|
from subliminal.video import Episode
|
||||||
from guessit import guessit
|
from subliminal.video import Movie
|
||||||
from subliminal_patch.providers import Provider
|
from subliminal_patch.providers import Provider
|
||||||
from subliminal_patch.providers.mixins import ProviderSubtitleArchiveMixin
|
from subliminal_patch.providers.mixins import ProviderSubtitleArchiveMixin
|
||||||
from subliminal_patch.subtitle import Subtitle, guess_matches
|
from subliminal_patch.providers.utils import get_archive_from_bytes
|
||||||
from subliminal_patch.utils import sanitize, fix_inconsistent_naming as _fix_inconsistent_naming
|
from subliminal_patch.providers.utils import get_subtitle_from_archive
|
||||||
from .utils import FIRST_THOUSAND_OR_SO_USER_AGENTS as AGENT_LIST
|
from subliminal_patch.providers.utils import update_matches
|
||||||
from subliminal.exceptions import ProviderError
|
from subliminal_patch.subtitle import guess_matches
|
||||||
from subliminal.providers import ParserBeautifulSoup
|
from subliminal_patch.subtitle import Subtitle
|
||||||
from subliminal.video import Episode, Movie
|
from subliminal_patch.utils import \
|
||||||
from subliminal.subtitle import SUBTITLE_EXTENSIONS
|
fix_inconsistent_naming as _fix_inconsistent_naming
|
||||||
|
from subliminal_patch.utils import sanitize
|
||||||
from subzero.language import Language
|
from subzero.language import Language
|
||||||
|
|
||||||
# parsing regex definitions
|
# parsing regex definitions
|
||||||
title_re = re.compile(r'(?P<title>(?:.+(?= [Aa][Kk][Aa] ))|.+)(?:(?:.+)(?P<altitle>(?<= [Aa][Kk][Aa] ).+))?')
|
title_re = re.compile(r'(?P<title>(?:.+(?= [Aa][Kk][Aa] ))|.+)(?:(?:.+)(?P<altitle>(?<= [Aa][Kk][Aa] ).+))?')
|
||||||
|
|
||||||
|
_SEASON_RE = re.compile(r"(s|(season|sezonul)\s)(?P<x>\d{1,2})", flags=re.IGNORECASE)
|
||||||
|
|
||||||
|
|
||||||
def fix_inconsistent_naming(title):
|
def fix_inconsistent_naming(title):
|
||||||
"""Fix titles with inconsistent naming using dictionary and sanitize them.
|
"""Fix titles with inconsistent naming using dictionary and sanitize them.
|
||||||
|
@ -48,7 +50,7 @@ class SubtitrarinoiSubtitle(Subtitle):
|
||||||
super(SubtitrarinoiSubtitle, self).__init__(language)
|
super(SubtitrarinoiSubtitle, self).__init__(language)
|
||||||
self.sid = sid
|
self.sid = sid
|
||||||
self.title = title
|
self.title = title
|
||||||
self.imdb_id = imdb_id
|
self.imdb_id = (imdb_id or "").rstrip("/")
|
||||||
self.download_link = download_link
|
self.download_link = download_link
|
||||||
self.year = year
|
self.year = year
|
||||||
self.download_count = download_count
|
self.download_count = download_count
|
||||||
|
@ -87,8 +89,7 @@ class SubtitrarinoiSubtitle(Subtitle):
|
||||||
if video.imdb_id and self.imdb_id == video.imdb_id:
|
if video.imdb_id and self.imdb_id == video.imdb_id:
|
||||||
matches.add('imdb_id')
|
matches.add('imdb_id')
|
||||||
|
|
||||||
# guess match others
|
update_matches(matches, video, self.comments)
|
||||||
matches |= guess_matches(video, guessit(self.comments, {"type": "movie"}))
|
|
||||||
|
|
||||||
else:
|
else:
|
||||||
# title
|
# title
|
||||||
|
@ -100,16 +101,19 @@ class SubtitrarinoiSubtitle(Subtitle):
|
||||||
if video.series_imdb_id and self.imdb_id == video.series_imdb_id:
|
if video.series_imdb_id and self.imdb_id == video.series_imdb_id:
|
||||||
matches.add('imdb_id')
|
matches.add('imdb_id')
|
||||||
|
|
||||||
# season
|
season = _SEASON_RE.search(self.comments)
|
||||||
if f"Sezonul {video.season}" in self.comments:
|
if season is not None:
|
||||||
matches.add('season')
|
season = int(season.group("x"))
|
||||||
|
if season == video.season:
|
||||||
|
matches.add('season')
|
||||||
|
|
||||||
|
logger.debug("Season matched? %s [%s -> %s]", "season" in matches, video.season, self.comments)
|
||||||
|
|
||||||
# episode
|
# episode
|
||||||
if {"imdb_id", "season"}.issubset(matches):
|
if {"imdb_id", "season"}.issubset(matches):
|
||||||
matches.add('episode')
|
matches.add('episode')
|
||||||
|
|
||||||
# guess match others
|
update_matches(matches, video, self.comments)
|
||||||
matches |= guess_matches(video, guessit(self.comments, {"type": "episode"}))
|
|
||||||
|
|
||||||
self.matches = matches
|
self.matches = matches
|
||||||
|
|
||||||
|
@ -277,42 +281,5 @@ class SubtitrarinoiProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||||
r = self.session.get(subtitle.download_link, headers={'Referer': self.api_url}, timeout=10)
|
r = self.session.get(subtitle.download_link, headers={'Referer': self.api_url}, timeout=10)
|
||||||
r.raise_for_status()
|
r.raise_for_status()
|
||||||
|
|
||||||
# open the archive
|
archive = get_archive_from_bytes(r.content)
|
||||||
archive_stream = io.BytesIO(r.content)
|
subtitle.content = get_subtitle_from_archive(archive, episode=subtitle.desired_episode)
|
||||||
if is_rarfile(archive_stream):
|
|
||||||
logger.debug('Archive identified as rar')
|
|
||||||
archive = RarFile(archive_stream)
|
|
||||||
elif is_zipfile(archive_stream):
|
|
||||||
logger.debug('Archive identified as zip')
|
|
||||||
archive = ZipFile(archive_stream)
|
|
||||||
else:
|
|
||||||
subtitle.content = r.content
|
|
||||||
if subtitle.is_valid():
|
|
||||||
return
|
|
||||||
subtitle.content = None
|
|
||||||
|
|
||||||
raise ProviderError('Unidentified archive type')
|
|
||||||
|
|
||||||
if subtitle.is_episode:
|
|
||||||
subtitle.content = self._get_subtitle_from_archive(subtitle, archive)
|
|
||||||
else:
|
|
||||||
subtitle.content = self.get_subtitle_from_archive(subtitle, archive)
|
|
||||||
|
|
||||||
@staticmethod
|
|
||||||
def _get_subtitle_from_archive(subtitle, archive):
|
|
||||||
for name in archive.namelist():
|
|
||||||
# discard hidden files
|
|
||||||
if os.path.split(name)[-1].startswith('.'):
|
|
||||||
continue
|
|
||||||
|
|
||||||
# discard non-subtitle files
|
|
||||||
if not name.lower().endswith(SUBTITLE_EXTENSIONS):
|
|
||||||
continue
|
|
||||||
|
|
||||||
_guess = guessit(name)
|
|
||||||
if subtitle.desired_episode == _guess['episode']:
|
|
||||||
return archive.read(name)
|
|
||||||
|
|
||||||
return None
|
|
||||||
|
|
||||||
# vim: set expandtab ts=4 sw=4:
|
|
||||||
|
|
|
@ -0,0 +1,54 @@
|
||||||
|
import pytest
|
||||||
|
from subliminal_patch.providers.subtitrarinoi import SubtitrarinoiProvider
|
||||||
|
from subliminal_patch.providers.subtitrarinoi import SubtitrarinoiSubtitle
|
||||||
|
from subzero.language import Language
|
||||||
|
|
||||||
|
romanian = Language("ron")
|
||||||
|
|
||||||
|
|
||||||
|
def test_list_subtitles(episodes):
|
||||||
|
episode = episodes["breaking_bad_s01e01"]
|
||||||
|
with SubtitrarinoiProvider() as provider:
|
||||||
|
assert provider.list_subtitles(episode, [romanian])
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.fixture
|
||||||
|
def subtitrari_subtitle():
|
||||||
|
yield SubtitrarinoiSubtitle(
|
||||||
|
romanian,
|
||||||
|
"https://www.subtitrari-noi.ro/7493-subtitrari noi.ro\ ",
|
||||||
|
3,
|
||||||
|
"Sezonul 1 ep. 1-7 Sincronizari si pentru variantele HDTV x264 (Sincro atty)",
|
||||||
|
"Breaking Bad",
|
||||||
|
"tt0903747/",
|
||||||
|
"Alice",
|
||||||
|
"https://www.subtitrari-noi.ro/index.php?page=movie_details&act=1&id=7493",
|
||||||
|
2008,
|
||||||
|
4230,
|
||||||
|
True,
|
||||||
|
1,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize("comment", ["season 01", "Sezonul 1 ep. 1-7", "S01"])
|
||||||
|
def test_subtitle_get_matches_episode(subtitrari_subtitle, episodes, comment):
|
||||||
|
episode = episodes["breaking_bad_s01e01"]
|
||||||
|
episode.episode = 1
|
||||||
|
subtitrari_subtitle.comments = comment
|
||||||
|
assert {"season", "episode", "series", "imdb_id"}.issubset(
|
||||||
|
subtitrari_subtitle.get_matches(episode)
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
@pytest.mark.parametrize("comment", ["season 02", "Sezonul 2 ep. 1-7", "version 01"])
|
||||||
|
def test_subtitle_get_matches_episode_false(subtitrari_subtitle, episodes, comment):
|
||||||
|
episode = episodes["breaking_bad_s01e01"]
|
||||||
|
episode.episode = 1
|
||||||
|
subtitrari_subtitle.comments = comment
|
||||||
|
assert not {"season", "episode"}.issubset(subtitrari_subtitle.get_matches(episode))
|
||||||
|
|
||||||
|
|
||||||
|
def test_provider_download_subtitle(subtitrari_subtitle):
|
||||||
|
with SubtitrarinoiProvider() as provider:
|
||||||
|
provider.download_subtitle(subtitrari_subtitle)
|
||||||
|
assert subtitrari_subtitle.is_valid()
|
Loading…
Reference in New Issue