def search_titles(self, titles, season, title_year, imdb_id):
"""Search for titles matching the `title`.
For episodes, each season has it own title
:param str titles: the titles to search for.
:param int season: season of the title
:param int title_year: year of the title
:return: found titles.
:rtype: dict
"""
titles_found = {}
for title in titles:
sanitized_titles = [sanitize(title)]
ignore_characters = {'\'', '.'}
if any(c in title for c in ignore_characters):
sanitized_titles.append(
sanitize(title, ignore_characters=ignore_characters))
for sanitized_title in sanitized_titles:
# make the query
if season:
logger.info('Searching episode title %r for season %r',
sanitized_title, season)
else:
logger.info('Searching movie title %r', sanitized_title)
r = self.session.get(
self.server_url +
'legenda/sugestao/{}'.format(sanitized_title),
timeout=10)
raise_for_status(r)
results = json.loads(r.text)
# loop over results
for result in results:
source = result['_source']
# extract id
title_id = int(source['id_filme'])
# extract type
title = {
'type': type_map[source['tipo']],
'title2': None,
'imdb_id': None
}
# extract title, year and country
name, year, country = title_re.match(
source['dsc_nome']).groups()
title['title'] = name
if "dsc_nome_br" in source:
name2, ommit1, ommit2 = title_re.match(
source['dsc_nome_br']).groups()
title['title2'] = name2
# extract imdb_id
if source['id_imdb'] != '0':
if not source['id_imdb'].startswith('tt'):
title['imdb_id'] = 'tt' + source['id_imdb'].zfill(
7)
else:
title['imdb_id'] = source['id_imdb']
# extract season
if title['type'] == 'episode':
if source['temporada'] and source['temporada'].isdigit(
):
title['season'] = int(source['temporada'])
else:
match = season_re.search(source['dsc_nome_br'])
if match:
title['season'] = int(match.group('season'))
else:
logger.debug(
'No season detected for title %d (%s)',
title_id, name)
# extract year
if year:
title['year'] = int(year)
elif source['dsc_data_lancamento'] and source[
'dsc_data_lancamento'].isdigit():
# year is based on season air date hence the adjustment
title['year'] = int(
source['dsc_data_lancamento']) - title.get(
'season', 1) + 1
# add title only if is valid
# Check against title without ignored chars
if self.is_valid_title(title, title_id,
sanitized_titles[0], season,
title_year, imdb_id):
logger.debug(u'Found title: %s', title)
titles_found[title_id] = title
logger.debug('Found %d titles', len(titles_found))
return titles_found
def search_titles(self, title, season, title_year, imdb_id):
"""Search for titles matching the `title`.
For episodes, each season has it own title
:param str title: the title to search for.
:param int season: season of the title
:param int title_year: year of the title
:return: found titles.
:rtype: dict
"""
titles = {}
sanitized_titles = [sanitize(title)]
ignore_characters = {'\'', '.'}
if any(c in title for c in ignore_characters):
sanitized_titles.append(sanitize(title, ignore_characters=ignore_characters))
for sanitized_title in sanitized_titles:
# make the query
if season:
logger.info('Searching episode title %r for season %r', sanitized_title, season)
else:
logger.info('Searching movie title %r', sanitized_title)
r = self.session.get(self.server_url + 'legenda/sugestao/{}'.format(sanitized_title), timeout=10)
raise_for_status(r)
results = json.loads(r.text)
# loop over results
for result in results:
source = result['_source']
# extract id
title_id = int(source['id_filme'])
# extract type
title = {'type': type_map[source['tipo']], 'title2': None, 'imdb_id': None}
# extract title, year and country
name, year, country = title_re.match(source['dsc_nome']).groups()
title['title'] = name
if "dsc_nome_br" in source:
name2, ommit1, ommit2 = title_re.match(source['dsc_nome_br']).groups()
title['title2'] = name2
# extract imdb_id
if source['id_imdb'] != '0':
if not source['id_imdb'].startswith('tt'):
title['imdb_id'] = 'tt' + source['id_imdb'].zfill(7)
else:
title['imdb_id'] = source['id_imdb']
# extract season
if title['type'] == 'episode':
if source['temporada'] and source['temporada'].isdigit():
title['season'] = int(source['temporada'])
else:
match = season_re.search(source['dsc_nome_br'])
if match:
title['season'] = int(match.group('season'))
else:
logger.debug('No season detected for title %d (%s)', title_id, name)
# extract year
if year:
title['year'] = int(year)
elif source['dsc_data_lancamento'] and source['dsc_data_lancamento'].isdigit():
# year is based on season air date hence the adjustment
title['year'] = int(source['dsc_data_lancamento']) - title.get('season', 1) + 1
# add title only if is valid
# Check against title without ignored chars
if self.is_valid_title(title, title_id, sanitized_titles[0], season, title_year, imdb_id):
logger.debug(u'Found title: %s', title)
titles[title_id] = title
logger.debug('Found %d titles', len(titles))
return titles