Python MovieParser.parse方法代码示例

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
    def on_feed_exit(self, feed, config):
        """Add downloaded movies to the database"""
        log.debug('check for learning')
        for entry in feed.accepted:
            if 'imdb_id' not in entry:
                log.debug('`%s` does not have imdb_id' % entry['title'])
                continue

            parser = MovieParser()
            parser.data = entry['title']
            parser.parse()

            quality = parser.quality.name

            log.debug('quality: %s' % quality)
            log.debug('imdb_id: %s' % entry['imdb_id'])
            log.debug('proper count: %s' % parser.proper_count)

            proper_movie = feed.session.query(ProperMovie).\
                filter(ProperMovie.imdb_id == entry['imdb_id']).\
                filter(ProperMovie.quality == quality).\
                filter(ProperMovie.proper_count == parser.proper_count).first()

            if not proper_movie:
                pm = ProperMovie()
                pm.title = entry['title']
                pm.feed = feed.name
                pm.imdb_id = entry['imdb_id']
                pm.quality = quality
                pm.proper_count = parser.proper_count
                feed.session.add(pm)
                log.debug('added %s' % pm)
            else:
                log.debug('%s already exists' % proper_movie)

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
class MovieComparator(StringComparator):
    """Compares two strings for similarity based on extracted movie title, year and quality."""

    def __init__(self):
        self.a_year, self.b_year = None, None
        self.a_quality, self.b_quality = qualities.UNKNOWN, qualities.UNKNOWN
        self.parser = MovieParser()
        super(MovieComparator, self).__init__(cutoff=0.9)

    def set_seq1(self, a):
        """Set first string for comparison."""
        self.parser.parse(a)
        super(MovieComparator, self).set_seq1(self.parser.name)
        self.a_year = self.parser.year
        self.a_quality = self.parser.quality

    def set_seq2(self, b):
        """Set second string for comparison."""
        self.parser.parse(b)
        super(MovieComparator, self).set_seq2(self.parser.name)
        self.b_year = self.parser.year
        self.b_quality = self.parser.quality

    def matches(self, other=None):
        """Compare the two strings, return True if they appear to be the same movie.

        :param other: String to compare against. If not specified, last specified string will be used.
        :return: True if match is close enough.
        """
        result = super(MovieComparator, self).matches(other)
        if self.a_quality > qualities.UNKNOWN:
            if self.a_quality != self.b_quality:
                return False
        if self.a_year and self.b_year:
            if self.a_year != self.b_year:
                # TODO: Make this fuzzier? tmdb and imdb years do not always match
                return False
        return result

    def search_string(self):
        """Return a cleaned string based on seq1 that can be used for searching."""
        result = self.a
        if isinstance(result, unicode):
            # Convert to combined form for better search results
            result = normalize('NFC', result)
        if self.a_year:
            result += ' %s' % self.a_year
        if self.a_quality > qualities.UNKNOWN:
            # Shorten some quality strings in search because of multiple acceptable forms
            if '720p' in self.a_quality.name:
                result += ' 720p'
            elif '1080p' in self.a_quality.name:
                result += ' 1080p'
            else:
                result += ' %s' % self.a_quality
        return result

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
 def smart_match(self, raw_name):
     """Accepts messy name, cleans it and uses information available to make smartest and best match"""
     from flexget.utils.titles.movie import MovieParser
     parser = MovieParser()
     parser.data = raw_name
     parser.parse()
     name = parser.name
     year = parser.year
     if name == '':
         log.critical('Failed to parse name from %s' % raw_name)
         return None
     log.debug('smart_match name=%s year=%s' % (name, str(year)))
     return self.best_match(name, year)

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
 def parse_movie(self, data, **kwargs):
     log.debug('Parsing movie: `%s` kwargs: %s', data, kwargs)
     start = preferred_clock()
     parser = MovieParser()
     try:
         parser.parse(data)
     except ParseWarning as pw:
         log_once(pw.value, logger=log)
     result = MovieParseResult(
         data=data,
         name=parser.name,
         year=parser.year,
         quality=parser.quality,
         proper_count=parser.proper_count,
         valid=bool(parser.name)
     )
     log.debug('Parsing result: %s (in %s ms)', parser, (preferred_clock() - start) * 1000)
     return result

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
    def on_feed_filter(self, feed, config):
        log.debug('check for enforcing')

        # parse config
        if isinstance(config, bool):
            # configured a boolean false, disable plugin
            if not config:
                return
            # configured a boolean true, disable timeframe
            timeframe = None
        else:
            # parse time window
            amount, unit = config.split(' ')
            log.debug('amount: %s unit: %s' % (repr(amount), repr(unit)))
            params = {unit: int(amount)}
            try:
                timeframe = timedelta(**params)
            except TypeError:
                raise PluginError('Invalid time format', log)

        # throws DependencyError if not present aborting feed
        imdb_lookup = get_plugin_by_name('imdb_lookup').instance

        for entry in feed.entries:
            if 'imdb_id' not in entry:
                try:
                    imdb_lookup.lookup(entry)
                except PluginError, pe:
                    log_once(pe.value)
                    continue

            parser = MovieParser()
            parser.data = entry['title']
            parser.parse()

            quality = parser.quality.name

            log.debug('quality: %s' % quality)
            log.debug('imdb_id: %s' % entry['imdb_id'])
            log.debug('current proper count: %s' % parser.proper_count)

            proper_movie = feed.session.query(ProperMovie).\
                filter(ProperMovie.imdb_id == entry['imdb_id']).\
                filter(ProperMovie.quality == quality).\
                order_by(desc(ProperMovie.proper_count)).first()

            if not proper_movie:
                log.debug('no previous download recorded for %s' % entry['imdb_id'])
                continue

            highest_proper_count = proper_movie.proper_count
            log.debug('highest_proper_count: %i' % highest_proper_count)

            accept_proper = False
            if parser.proper_count > highest_proper_count:
                log.debug('proper detected: %s ' % proper_movie)

                if timeframe is None:
                    accept_proper = True
                else:
                    expires = proper_movie.added + timeframe
                    log.debug('propers timeframe: %s' % timeframe)
                    log.debug('added: %s' % proper_movie.added)
                    log.debug('propers ignore after: %s' % str(expires))
                    if datetime.now() < expires:
                        accept_proper = True
                    else:
                        log.verbose('Proper `%s` has past it\'s expiration time' % entry['title'])

            if accept_proper:
                log.info('Accepting proper version previously downloaded movie `%s`' % entry['title'])
                # TODO: does this need to be called?
                # fire_event('forget', entry['imdb_url'])
                fire_event('forget', entry['imdb_id'])
                feed.accept(entry, 'proper version of previously downloaded movie')

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
    def on_feed_filter(self, feed, config):
        log.debug('check for enforcing')

        # parse config
        if isinstance(config, bool):
            # configured a boolean false, disable plugin
            if not config:
                return
            # configured a boolean true, disable timeframe
            timeframe = None
        else:
            # parse time window
            log.debug('interval: %s' % config)
            try:
                timeframe = parse_timedelta(config)
            except ValueError:
                raise PluginError('Invalid time format', log)

        # throws DependencyError if not present aborting feed
        imdb_lookup = get_plugin_by_name('imdb_lookup').instance

        for entry in feed.entries:

            parser = MovieParser()
            parser.data = entry['title']
            parser.parse()

            # if we have imdb_id already evaluated
            if entry.get('imdb_id', None, eval_lazy=False) is None:
                try:
                    # TODO: fix imdb_id_lookup, cumbersome that it returns None and or throws exception
                    # Also it's crappy name!
                    imdb_id = imdb_lookup.imdb_id_lookup(movie_title=parser.name, raw_title=entry['title'])
                    if imdb_id is None:
                        continue
                    entry['imdb_id'] = imdb_id
                except PluginError, pe:
                    log_once(pe.value)
                    continue

            quality = parser.quality.name

            log.debug('quality: %s' % quality)
            log.debug('imdb_id: %s' % entry['imdb_id'])
            log.debug('current proper count: %s' % parser.proper_count)

            proper_movie = feed.session.query(ProperMovie).\
                filter(ProperMovie.imdb_id == entry['imdb_id']).\
                filter(ProperMovie.quality == quality).\
                order_by(desc(ProperMovie.proper_count)).first()

            if not proper_movie:
                log.debug('no previous download recorded for %s' % entry['imdb_id'])
                continue

            highest_proper_count = proper_movie.proper_count
            log.debug('highest_proper_count: %i' % highest_proper_count)

            accept_proper = False
            if parser.proper_count > highest_proper_count:
                log.debug('proper detected: %s ' % proper_movie)

                if timeframe is None:
                    accept_proper = True
                else:
                    expires = proper_movie.added + timeframe
                    log.debug('propers timeframe: %s' % timeframe)
                    log.debug('added: %s' % proper_movie.added)
                    log.debug('propers ignore after: %s' % str(expires))
                    if datetime.now() < expires:
                        accept_proper = True
                    else:
                        log.verbose('Proper `%s` has past it\'s expiration time' % entry['title'])

            if accept_proper:
                log.info('Accepting proper version previously downloaded movie `%s`' % entry['title'])
                # TODO: does this need to be called?
                # fire_event('forget', entry['imdb_url'])
                fire_event('forget', entry['imdb_id'])
                feed.accept(entry, 'proper version of previously downloaded movie')

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
    def on_task_filter(self, task, config):
        if not task.accepted:
            log.debug('nothing accepted, aborting')
            return

        config = self.build_config(config)
        imdb_lookup = get_plugin_by_name('imdb_lookup').instance

        incompatible_dirs = 0
        incompatible_entries = 0
        count_entries = 0
        count_dirs = 0

        # list of imdb ids gathered from paths / cache
        imdb_ids = []

        for path in config:
            # see if this path has already been scanned
            if path in self.cache:
                log.verbose('Using cached scan for %s ...' % path)
                imdb_ids.extend(self.cache[path])
                continue

            path_ids = []

            # with unicode it crashes on some paths ..
            path = str(os.path.expanduser(path))
            if not os.path.exists(path):
                log.critical('Path %s does not exist' % path)
                continue

            log.verbose('Scanning path %s ...' % path)

            # Help debugging by removing a lot of noise
            #logging.getLogger('movieparser').setLevel(logging.WARNING)
            #logging.getLogger('imdb_lookup').setLevel(logging.WARNING)

            # scan through
            for root, dirs, files in os.walk(path):
                # convert filelists into utf-8 to avoid unicode problems
                dirs = [x.decode('utf-8', 'ignore') for x in dirs]
                # files = [x.decode('utf-8', 'ignore') for x in files]

                # TODO: add also video files?
                for item in dirs:
                    if item.lower() in self.skip:
                        continue
                    count_dirs += 1

                    movie = MovieParser()
                    movie.parse(item)

                    try:
                        imdb_id = imdb_lookup.imdb_id_lookup(movie_title=movie.name,
                                                             raw_title=item,
                                                             session=task.session)
                        if imdb_id in path_ids:
                            log.trace('duplicate %s' % item)
                            continue
                        if imdb_id is not None:
                            log.trace('adding: %s' % imdb_id)
                            path_ids.append(imdb_id)
                    except PluginError, e:
                        log.trace('%s lookup failed (%s)' % (item, e.value))
                        incompatible_dirs += 1

            # store to cache and extend to found list
            self.cache[path] = path_ids
            imdb_ids.extend(path_ids)

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
    def on_task_filter(self, task, config):
        if not task.accepted:
            log.debug("nothing accepted, aborting")
            return

        config = self.build_config(config)
        imdb_lookup = plugin.get_plugin_by_name("imdb_lookup").instance

        incompatible_dirs = 0
        incompatible_entries = 0
        count_entries = 0
        count_dirs = 0

        # list of imdb ids gathered from paths / cache
        imdb_ids = []

        for path in config:
            # see if this path has already been scanned
            if path in self.cache:
                log.verbose("Using cached scan for %s ..." % path)
                imdb_ids.extend(self.cache[path])
                continue

            path_ids = []

            # with unicode it crashes on some paths ..
            path = str(os.path.expanduser(path))
            if not os.path.exists(path):
                log.critical("Path %s does not exist" % path)
                continue

            log.verbose("Scanning path %s ..." % path)

            # Help debugging by removing a lot of noise
            # logging.getLogger('movieparser').setLevel(logging.WARNING)
            # logging.getLogger('imdb_lookup').setLevel(logging.WARNING)

            # scan through
            for root, dirs, files in os.walk(path, followlinks=True):
                # convert filelists into utf-8 to avoid unicode problems
                dirs = [x.decode("utf-8", "ignore") for x in dirs]
                # files = [x.decode('utf-8', 'ignore') for x in files]

                # TODO: add also video files?
                for item in dirs:
                    if item.lower() in self.skip:
                        continue
                    count_dirs += 1

                    movie = MovieParser()
                    movie.parse(item)

                    try:
                        imdb_id = imdb_lookup.imdb_id_lookup(
                            movie_title=movie.name, raw_title=item, session=task.session
                        )
                        if imdb_id in path_ids:
                            log.trace("duplicate %s" % item)
                            continue
                        if imdb_id is not None:
                            log.trace("adding: %s" % imdb_id)
                            path_ids.append(imdb_id)
                    except plugin.PluginError as e:
                        log.trace("%s lookup failed (%s)" % (item, e.value))
                        incompatible_dirs += 1

            # store to cache and extend to found list
            self.cache[path] = path_ids
            imdb_ids.extend(path_ids)

        log.debug("-- Start filtering entries ----------------------------------")

        # do actual filtering
        for entry in task.accepted:
            count_entries += 1
            if not entry.get("imdb_id", eval_lazy=False):
                try:
                    imdb_lookup.lookup(entry)
                except plugin.PluginError as e:
                    log.trace("entry %s imdb failed (%s)" % (entry["title"], e.value))
                    incompatible_entries += 1
                    continue

            # actual filtering
            if entry["imdb_id"] in imdb_ids:
                entry.reject("movie exists")

        if incompatible_dirs or incompatible_entries:
            log.verbose(
                "There were some incompatible items. %s of %s entries "
                "and %s of %s directories could not be verified."
                % (incompatible_entries, count_entries, incompatible_dirs, count_dirs)
            )

        log.debug("-- Finished filtering entries -------------------------------")

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
                                log.verbose(entry['series_name'])
                            parser.data = cur_filename
                            parser.parse
                            log.debug(parser.id_type)
                            if parser.id_type == 'ep':
                                entry['series_id'] = ''.join(['S', str(parser.season).rjust(2, str('0')), 'E',
                                                             str(parser.episode).rjust(2, str('0'))])
                            elif parser.id_type == 'sequence':
                                entry['series_id'] = parser.episode
                            elif parser.id_type and parser.id:
                                entry['series_id'] = parser.id
                    else:
                        from flexget.utils.titles.movie import MovieParser
                        parser = MovieParser()
                        parser.data = cur_file
                        parser.parse()
                        log.info(parser)
                        testname = parser.name
                        testyear = parser.year
                        parser.data = entry['title']
                        parser.parse()
                        log.info(parser)
                        if len(parser.name) > len(testname):
                            entry['name'] = parser.name
                            entry['movie_name'] = parser.name
                        else:
                            entry['name'] = testname
                            entry['movie_name'] = testname
                        entry['year'] = parser.year
                        entry['movie_year'] = parser.year

# 需要导入模块: from flexget.utils.titles.movie import MovieParser [as 别名]
# 或者: from flexget.utils.titles.movie.MovieParser import parse [as 别名]
    def on_task_filter(self, task, config):
        if not task.accepted:
            log.debug('nothing accepted, aborting')
            return

        config = self.build_config(config)
        imdb_lookup = plugin.get_plugin_by_name('imdb_lookup').instance

        incompatible_dirs = 0
        incompatible_entries = 0
        count_entries = 0
        count_dirs = 0

        # list of imdb ids gathered from paths / cache
        imdb_ids = []

        for folder in config:
            folder = path(folder).expanduser()
            # see if this path has already been scanned
            if folder in self.cache:
                log.verbose('Using cached scan for %s ...' % folder)
                imdb_ids.extend(self.cache[folder])
                continue

            path_ids = []

            if not folder.isdir():
                log.critical('Path %s does not exist' % folder)
                continue

            log.verbose('Scanning path %s ...' % folder)

            # Help debugging by removing a lot of noise
            #logging.getLogger('movieparser').setLevel(logging.WARNING)
            #logging.getLogger('imdb_lookup').setLevel(logging.WARNING)

            # scan through

            # TODO: add also video files?
            for item in folder.walkdirs(errors='warn'):
                if item.name.lower() in self.skip:
                    continue
                count_dirs += 1

                movie = MovieParser()
                movie.parse(item.name)

                try:
                    imdb_id = imdb_lookup.imdb_id_lookup(movie_title=movie.name,
                                                         raw_title=item.name,
                                                         session=task.session)
                    if imdb_id in path_ids:
                        log.trace('duplicate %s' % item)
                        continue
                    if imdb_id is not None:
                        log.trace('adding: %s' % imdb_id)
                        path_ids.append(imdb_id)
                except plugin.PluginError as e:
                    log.trace('%s lookup failed (%s)' % (item, e.value))
                    incompatible_dirs += 1

            # store to cache and extend to found list
            self.cache[folder] = path_ids
            imdb_ids.extend(path_ids)

        log.debug('-- Start filtering entries ----------------------------------')

        # do actual filtering
        for entry in task.accepted:
            count_entries += 1
            if not entry.get('imdb_id', eval_lazy=False):
                try:
                    imdb_lookup.lookup(entry)
                except plugin.PluginError as e:
                    log.trace('entry %s imdb failed (%s)' % (entry['title'], e.value))
                    incompatible_entries += 1
                    continue

            # actual filtering
            if entry['imdb_id'] in imdb_ids:
                entry.reject('movie exists')

        if incompatible_dirs or incompatible_entries:
            log.verbose('There were some incompatible items. %s of %s entries '
                        'and %s of %s directories could not be verified.' %
                (incompatible_entries, count_entries, incompatible_dirs, count_dirs))

        log.debug('-- Finished filtering entries -------------------------------')