def __init__(self, dbDirectory, adultSearch=1, *arguments, **keywords):
"""Initialize the access system.
The directory with the files must be supplied.
"""
IMDbLocalAndSqlAccessSystem.__init__(self, *arguments, **keywords)
self.__db = os.path.expandvars(dbDirectory)
self.__db = os.path.expanduser(self.__db)
if hasattr(os.path, 'realpath'):
self.__db = os.path.realpath(self.__db)
self.__db = os.path.normpath(self.__db)
self.__db = self.__db + getattr(os.path, 'sep', '/')
self.__db = os.path.normcase(self.__db)
if not os.path.isdir(self.__db):
raise IMDbDataAccessError, '"%s" is not a directory' % self.__db
# These indices are used to quickly get the mopID
# for a given title/name.
self.__namesScan = KeyFScan('%snames.key' % self.__db)
self.__titlesScan = KeyFScan('%stitles.key' % self.__db)
self.do_adult_search(adultSearch)
def __init__(self, dbDirectory, adultSearch=1, *arguments, **keywords):
"""Initialize the access system.
The directory with the files must be supplied.
"""
IMDbLocalAndSqlAccessSystem.__init__(self, *arguments, **keywords)
self.__db = os.path.expandvars(dbDirectory)
self.__db = os.path.expanduser(self.__db)
if hasattr(os.path, 'realpath'):
self.__db = os.path.realpath(self.__db)
self.__db = os.path.normpath(self.__db)
self.__db = self.__db + getattr(os.path, 'sep', '/')
self.__db = os.path.normcase(self.__db)
if not os.path.isdir(self.__db):
raise IMDbDataAccessError, '"%s" is not a directory' % self.__db
# These indices are used to quickly get the mopID
# for a given title/name.
self.__namesScan = KeyFScan('%snames.key' % self.__db)
self.__titlesScan = KeyFScan('%stitles.key' % self.__db)
self.do_adult_search(adultSearch)
class IMDbLocalAccessSystem(IMDbLocalAndSqlAccessSystem):
"""The class used to access IMDb's data through a local installation."""
accessSystem = 'local'
def __init__(self, dbDirectory, adultSearch=1, *arguments, **keywords):
"""Initialize the access system.
The directory with the files must be supplied.
"""
IMDbLocalAndSqlAccessSystem.__init__(self, *arguments, **keywords)
self.__db = os.path.expandvars(dbDirectory)
self.__db = os.path.expanduser(self.__db)
if hasattr(os.path, 'realpath'):
self.__db = os.path.realpath(self.__db)
self.__db = os.path.normpath(self.__db)
self.__db = self.__db + getattr(os.path, 'sep', '/')
self.__db = os.path.normcase(self.__db)
if not os.path.isdir(self.__db):
raise IMDbDataAccessError, '"%s" is not a directory' % self.__db
# These indices are used to quickly get the mopID
# for a given title/name.
self.__namesScan = KeyFScan('%snames.key' % self.__db)
self.__titlesScan = KeyFScan('%stitles.key' % self.__db)
self.do_adult_search(adultSearch)
def _getTitleID(self, title):
return self.__titlesScan.getID(title)
def _getNameID(self, name):
return self.__namesScan.getID(name)
def _get_lastID(self, indexF):
fsize = os.stat(indexF)[ST_SIZE]
return (fsize / 4) - 1
def get_lastMovieID(self):
"""Return the last movieID"""
return self._get_lastID('%stitles.index' % self.__db)
def get_lastPersonID(self):
"""Return the last personID"""
return self._get_lastID('%snames.index' % self.__db)
def _normalize_movieID(self, movieID):
"""Normalize the given movieID."""
try:
return int(movieID)
except (ValueError, OverflowError):
raise IMDbError, 'movieID "%s" can\'t be converted to integer' % \
movieID
def _normalize_personID(self, personID):
"""Normalize the given personID."""
try:
return int(personID)
except (ValueError, OverflowError):
raise IMDbError, 'personID "%s" can\'t be converted to integer' % \
personID
def _normalize_characterID(self, characterID):
"""Normalize the given characterID."""
try:
return int(characterID)
except (ValueError, OverflowError):
raise IMDbError, 'characterID "%s" can\'t be converted to integer' \
% characterID
def _normalize_companyID(self, companyID):
"""Normalize the given companyID."""
try:
return int(companyID)
except (ValueError, OverflowError):
raise IMDbError, 'companyID "%s" can\'t be converted to integer' \
% companyID
def _get_real_movieID(self, movieID):
"""Handle title aliases."""
rid = getFullIndex('%saka-titles.index' % self.__db, movieID,
kind='akatidx')
if rid is not None: return rid
return movieID
def _get_real_personID(self, personID):
"""Handle name aliases."""
rid = getFullIndex('%saka-names.index' % self.__db, personID,
kind='akanidx')
if rid is not None: return rid
return personID
def get_imdbMovieID(self, movieID):
"""Translate a movieID in an imdbID.
Try an Exact Primary Title search on IMDb;
return None if it's unable to get the imdbID.
"""
titline = getLabel(movieID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
if titline is None: return None
return self.title2imdbID(titline)
def get_imdbPersonID(self, personID):
"""Translate a personID in an imdbID.
Try an Exact Primary Name search on IMDb;
return None if it's unable to get the imdbID.
"""
name = getLabel(personID, '%snames.index' % self.__db,
'%snames.key' % self.__db)
if name is None: return None
return self.name2imdbID(name)
def get_imdbCharacterID(self, characterID):
"""Translate a characterID in an imdbID.
Try an Exact Primary Name search on IMDb;
return None if it's unable to get the imdbID.
"""
name = getCharacterName(characterID,
'%scharacters.index' % self.__db,
'%scharacters.data' % self.__db)
if not name:
return None
return self.character2imdbID(name)
def get_imdbCompanyID(self, companyID):
"""Translate a companyID in an imdbID.
Try an Exact Primary Name search on IMDb;
return None if it's unable to get the imdbID.
"""
name = getCompanyName(companyID,
'%scompanies.index' % self.__db,
'%scompanies.data' % self.__db)
if not name:
return None
return self.company2imdbID(name)
def do_adult_search(self, doAdult):
"""If set to 0 or False, movies in the Adult category are not
shown in the results of a search."""
self.doAdult = doAdult
def _search_movie(self, title, results):
title = title.strip()
if not title: return []
# Search for these title variations.
title1, title2, title3 = titleVariations(title)
resultsST = results
if not self.doAdult: resultsST = 0
res = _scan_titles('%stitles.key' % self.__db,
title1, title2, title3, resultsST)
if self.doAdult and results > 0: res[:] = res[:results]
res[:] = [x[1] for x in res]
# Check for adult movies.
if not self.doAdult:
newlist = []
for entry in res:
genres = getMovieMisc(movieID=entry[0],
dataF='%s%s.data' % (self.__db, 'genres'),
indexF='%s%s.index' % (self.__db, 'genres'),
attrIF='%sattributes.index' % self.__db,
attrKF='%sattributes.key' % self.__db)
if 'Adult' not in genres: newlist.append(entry)
res[:] = newlist
if results > 0: res[:] = res[:results]
return res
def get_movie_main(self, movieID):
# Information sets provided by this method.
infosets = ('main', 'vote details')
tl = getLabel(movieID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
# No title, no party.
if tl is None:
raise IMDbDataAccessError, 'unable to get movieID "%s"' % movieID
res = analyze_title(tl)
# Build the cast list.
actl = []
for castG in ('actors', 'actresses'):
midx = getFullIndex('%s%s.titles' % (self.__db, castG),
movieID, multi=1)
if midx is not None:
params = {'movieID': movieID,
'dataF': '%s%s.data' % (self.__db, castG),
'indexF': '%snames.index' % self.__db,
'keyF': '%snames.key' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db,
'charNF': '%scharacter2id.index' % self.__db,
'offsList': midx, 'doCast': 1}
actl += getMovieCast(**params)
if actl:
actl.sort()
res['cast'] = actl
# List of other workers.
works = ('writer', 'cinematographer', 'composer',
'costume-designer', 'director', 'editor', 'miscellaneou',
'producer', 'production-designer', 'cinematographer')
for i in works:
index = getFullIndex('%s%ss.titles' % (self.__db, i),
movieID, multi=1)
if index is not None:
params = {'movieID': movieID,
'dataF': '%s%s.data' % (self.__db, i),
'indexF': '%snames.index' % self.__db,
'keyF': '%snames.key' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db,
'offsList': index}
name = key = i
if '-' in name:
name = name.replace('-', ' ')
elif name == 'miscellaneou':
name = 'miscellaneous crew'
key = 'miscellaneou'
elif name == 'writer':
params['doWriters'] = 1
params['dataF'] = '%s%ss.data' % (self.__db, key)
data = getMovieCast(**params)
if name == 'writer': data.sort()
res[name] = data
# Rating.
rt = self.get_movie_vote_details(movieID)['data']
if rt: res.update(rt)
# Various information.
miscInfo = (('runtimes', 'running-times'), ('color info', 'color-info'),
('genres', 'genres'), ('distributors', 'distributors'),
('languages', 'language'), ('certificates', 'certificates'),
('special effects companies', 'special-effects-companies'),
('sound mix', 'sound-mix'), ('tech info', 'technical'),
('production companies', 'production-companies'),
('countries', 'countries'))
for name, fname in miscInfo:
params = {'movieID': movieID,
'dataF': '%s%s.data' % (self.__db, fname),
'indexF': '%s%s.index' % (self.__db, fname),
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
data = getMovieMisc(**params)
if name in ('distributors', 'special effects companies',
'production companies'):
for nitem in xrange(len(data)):
n, notes = split_company_name_notes(data[nitem])
company = Company(name=n, companyID=getCompanyID(n,
'%scompany2id.index' % self.__db),
notes=notes,
accessSystem=self.accessSystem)
data[nitem] = company
if data: res[name] = data
if res.has_key('runtimes') and len(res['runtimes']) > 0:
rt = res['runtimes'][0]
episodes = re_episodes.findall(rt)
if episodes:
res['runtimes'][0] = re_episodes.sub('', rt)
res['number of episodes'] = episodes[0]
# AKA titles.
akas = getAkaTitles(movieID,
'%saka-titles.data' % self.__db,
'%stitles.index' % self.__db,
'%stitles.key' % self.__db,
'%sattributes.index' % self.__db,
'%sattributes.key' % self.__db)
if akas:
# normalize encoding.
for i in xrange(len(akas)):
ts = akas[i].split('::')
if len(ts) != 2: continue
t = ts[0]
n = ts[1]
nt = self._changeAKAencoding(n, t)
if nt is not None: akas[i] = '%s::%s' % (nt, n)
res['akas'] = akas
if res.get('kind') == 'episode':
# Things to do if this is a tv series episode.
episodeOf = res.get('episode of')
if episodeOf is not None:
parentSeries = Movie(data=res['episode of'],
accessSystem='local')
seriesID = self._getTitleID(parentSeries.get(
'long imdb canonical title'))
parentSeries.movieID = seriesID
res['episode of'] = parentSeries
if not res.get('year'):
year = getFullIndex('%smovies.data' % self.__db,
movieID, kind='moviedata', rindex=1)
if year: res['year'] = year
# MPAA info.
mpaa = getMPAA(movieID, '%smpaa-ratings-reasons.index' % self.__db,
'%smpaa-ratings-reasons.data' % self.__db)
if mpaa: res.update(mpaa)
return {'data': res, 'info sets': infosets}
def get_movie_plot(self, movieID):
pl = getPlot(movieID, '%splot.index' % self.__db,
'%splot.data' % self.__db)
trefs, nrefs = self._extractRefs(pl)
if pl: return {'data': {'plot': pl},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_taglines(self, movieID):
tg = getTaglines(movieID, '%staglines.index' % self.__db,
'%staglines.data' % self.__db)
if tg: return {'data': {'taglines': tg}}
return {'data': {}}
def get_movie_keywords(self, movieID):
params = {'movieID': movieID,
'dataF': '%skeywords.data' % self.__db,
'indexF': '%skeywords.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
kwds = getMovieMisc(**params)
if kwds: return {'data': {'keywords': kwds}}
return {'data': {}}
def get_movie_alternate_versions(self, movieID):
av = parseMinusList(movieID, '%salternate-versions.data' % self.__db,
'%salternate-versions.index' % self.__db)
trefs, nrefs = self._extractRefs(av)
if av: return {'data': {'alternate versions': av},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_crazy_credits(self, movieID):
cc = parseMinusList(movieID, '%scrazy-credits.data' % self.__db,
'%scrazy-credits.index' % self.__db)
trefs, nrefs = self._extractRefs(cc)
if cc: return {'data': {'crazy credits': cc},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_goofs(self, movieID):
goo = parseMinusList(movieID, '%sgoofs.data' % self.__db,
'%sgoofs.index' % self.__db)
trefs, nrefs = self._extractRefs(goo)
if goo: return {'data': {'goofs': goo},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_soundtrack(self, movieID):
goo = parseMinusList(movieID, '%ssoundtracks.data' % self.__db,
'%ssoundtracks.index' % self.__db)
trefs, nrefs = self._extractRefs(goo)
if goo: return {'data': {'soundtrack': goo},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_quotes(self, movieID):
mq = getQuotes(movieID, '%squotes.data' % self.__db,
'%squotes.index' % self.__db)
trefs, nrefs = self._extractRefs(mq)
if mq: return {'data': {'quotes': mq},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_release_dates(self, movieID):
params = {'movieID': movieID,
'dataF': '%srelease-dates.data' % self.__db,
'indexF': '%srelease-dates.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
data = getMovieMisc(**params)
if data: return {'data': {'release dates': data}}
return {'data': {}}
def get_movie_miscellaneous_companies(self, movieID):
params = {'movieID': movieID,
'dataF': '%smiscellaneous-companies.data' % self.__db,
'indexF': '%smiscellaneous-companies.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
try:
data = getMovieMisc(**params)
except IMDbDataAccessError:
import warnings
warnings.warn('miscellaneous-companies files not found; '
'run the misc-companies4local.py script.')
return {'data': {}}
for nitem in xrange(len(data)):
n, notes = split_company_name_notes(data[nitem])
company = Company(name=n, companyID=getCompanyID(n,
'%scompany2id.index' % self.__db),
notes=notes,
accessSystem=self.accessSystem)
data[nitem] = company
if data: return {'data': {'miscellaneous companies': data}}
return {'data': {}}
def get_movie_vote_details(self, movieID):
data = getRatingData(movieID, '%sratings.data' % self.__db)
return {'data': data}
def get_movie_trivia(self, movieID):
triv = parseMinusList(movieID, '%strivia.data' % self.__db,
'%strivia.index' % self.__db)
trefs, nrefs = self._extractRefs(triv)
if triv: return {'data': {'trivia': triv},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_locations(self, movieID):
params = {'movieID': movieID,
'dataF': '%slocations.data' % self.__db,
'indexF': '%slocations.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
data = getMovieMisc(**params)
if data: return {'data': {'locations': data}}
return {'data': {}}
def get_movie_connections(self, movieID):
mc = getMovieLinks(movieID, '%smovie-links.data' % self.__db,
'%stitles.index' % self.__db,
'%stitles.key' % self.__db)
if mc: return {'data': {'connections': mc}}
return {'data': {}}
def get_movie_business(self, movieID):
mb = getBusiness(movieID, '%sbusiness.index' % self.__db,
'%sbusiness.data' % self.__db)
trefs, nrefs = self._extractRefs(mb)
if mb: return {'data': {'business': mb},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_literature(self, movieID):
ml = getLiterature(movieID, '%sliterature.index' % self.__db,
'%sliterature.data' % self.__db)
if ml: return {'data': {'literature': ml}}
return {'data': {}}
def get_movie_laserdisc(self, movieID):
ml = getLaserdisc(movieID, '%slaserdisc.index' % self.__db,
'%slaserdisc.data' % self.__db)
trefs, nrefs = self._extractRefs(ml)
if ml: return {'data': {'laserdisc': ml},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def _buildEpisodes(self, eps_list, parentID):
episodes = {}
parentTitle = getLabel(parentID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
parentSeries = Movie(title=parentTitle,
movieID=parentID, accessSystem='local')
for episodeID, episodeTitle in eps_list:
episodeTitle = unicode(episodeTitle, 'latin_1', 'replace')
data = analyze_title(episodeTitle, canonical=1)
m = Movie(data=data, movieID=episodeID, accessSystem='local')
m['episode of'] = parentSeries
if data.get('year') is None:
year = getFullIndex('%smovies.data' % self.__db,
key=episodeID, kind='moviedata', rindex=1)
if year: m['year'] = year
season = data.get('season', 'UNKNOWN')
if not episodes.has_key(season): episodes[season] = {}
ep_number = data.get('episode')
if ep_number is None:
ep_number = max((episodes[season].keys() or [0])) + 1
episodes[season][ep_number] = m
return episodes
def get_movie_episodes(self, movieID):
try:
me = get_episodes(movieID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
except IOError, e:
raise IMDbDataAccessError, str(e)
if me:
episodes = self._buildEpisodes(me, movieID)
data = {'episodes': episodes}
data['number of episodes'] = sum([len(x) for x
in episodes.values()])
data['number of seasons'] = len(episodes.keys())
return {'data': data}
return {'data': {}}
class IMDbLocalAccessSystem(IMDbLocalAndSqlAccessSystem):
"""The class used to access IMDb's data through a local installation."""
accessSystem = 'local'
def __init__(self, dbDirectory, adultSearch=1, *arguments, **keywords):
"""Initialize the access system.
The directory with the files must be supplied.
"""
IMDbLocalAndSqlAccessSystem.__init__(self, *arguments, **keywords)
self.__db = os.path.expandvars(dbDirectory)
self.__db = os.path.expanduser(self.__db)
if hasattr(os.path, 'realpath'):
self.__db = os.path.realpath(self.__db)
self.__db = os.path.normpath(self.__db)
self.__db = self.__db + getattr(os.path, 'sep', '/')
self.__db = os.path.normcase(self.__db)
if not os.path.isdir(self.__db):
raise IMDbDataAccessError, '"%s" is not a directory' % self.__db
# These indices are used to quickly get the mopID
# for a given title/name.
self.__namesScan = KeyFScan('%snames.key' % self.__db)
self.__titlesScan = KeyFScan('%stitles.key' % self.__db)
self.do_adult_search(adultSearch)
def _getTitleID(self, title):
return self.__titlesScan.getID(title)
def _getNameID(self, name):
return self.__namesScan.getID(name)
def _get_lastID(self, indexF):
fsize = os.stat(indexF)[ST_SIZE]
return (fsize / 4) - 1
def get_lastMovieID(self):
"""Return the last movieID"""
return self._get_lastID('%stitles.index' % self.__db)
def get_lastPersonID(self):
"""Return the last personID"""
return self._get_lastID('%snames.index' % self.__db)
def _normalize_movieID(self, movieID):
"""Normalize the given movieID."""
try:
return int(movieID)
except (ValueError, OverflowError):
raise IMDbError, 'movieID "%s" can\'t be converted to integer' % \
movieID
def _normalize_personID(self, personID):
"""Normalize the given personID."""
try:
return int(personID)
except (ValueError, OverflowError):
raise IMDbError, 'personID "%s" can\'t be converted to integer' % \
personID
def _normalize_characterID(self, characterID):
"""Normalize the given characterID."""
try:
return int(characterID)
except (ValueError, OverflowError):
raise IMDbError, 'characterID "%s" can\'t be converted to integer' \
% characterID
def _normalize_companyID(self, companyID):
"""Normalize the given companyID."""
try:
return int(companyID)
except (ValueError, OverflowError):
raise IMDbError, 'companyID "%s" can\'t be converted to integer' \
% companyID
def _get_real_movieID(self, movieID):
"""Handle title aliases."""
rid = getFullIndex('%saka-titles.index' % self.__db, movieID,
kind='akatidx')
if rid is not None: return rid
return movieID
def _get_real_personID(self, personID):
"""Handle name aliases."""
rid = getFullIndex('%saka-names.index' % self.__db, personID,
kind='akanidx')
if rid is not None: return rid
return personID
def get_imdbMovieID(self, movieID):
"""Translate a movieID in an imdbID.
Try an Exact Primary Title search on IMDb;
return None if it's unable to get the imdbID.
"""
titline = getLabel(movieID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
if titline is None: return None
return self.title2imdbID(titline)
def get_imdbPersonID(self, personID):
"""Translate a personID in an imdbID.
Try an Exact Primary Name search on IMDb;
return None if it's unable to get the imdbID.
"""
name = getLabel(personID, '%snames.index' % self.__db,
'%snames.key' % self.__db)
if name is None: return None
return self.name2imdbID(name)
def get_imdbCharacterID(self, characterID):
"""Translate a characterID in an imdbID.
Try an Exact Primary Name search on IMDb;
return None if it's unable to get the imdbID.
"""
name = getCharacterName(characterID,
'%scharacters.index' % self.__db,
'%scharacters.data' % self.__db)
if not name:
return None
return self.character2imdbID(name)
def get_imdbCompanyID(self, companyID):
"""Translate a companyID in an imdbID.
Try an Exact Primary Name search on IMDb;
return None if it's unable to get the imdbID.
"""
name = getCompanyName(companyID,
'%scompanies.index' % self.__db,
'%scompanies.data' % self.__db)
if not name:
return None
return self.company2imdbID(name)
def do_adult_search(self, doAdult):
"""If set to 0 or False, movies in the Adult category are not
shown in the results of a search."""
self.doAdult = doAdult
def _search_movie(self, title, results, _episodes=False):
title = title.strip()
if not title: return []
# Search for these title variations.
if not _episodes:
title1, title2, title3 = titleVariations(title, fromPtdf=1)
else:
title1 = normalizeTitle(title)
title2 = ''
title3 = ''
# XXX: only a guess: results are shrinked, to exclude Adult
# titles and to remove duplicated entries.
resultsST = results * 3
res = _scan_titles('%stitles.key' % self.__db,
title1, title2, title3, resultsST, _episodes)
res[:] = [x[1] for x in res]
# Check for adult movies.
if not self.doAdult:
newlist = []
for entry in res:
genres = getMovieMisc(movieID=entry[0],
dataF='%s%s.data' % (self.__db, 'genres'),
indexF='%s%s.index' % (self.__db, 'genres'),
attrIF='%sattributes.index' % self.__db,
attrKF='%sattributes.key' % self.__db)
if 'Adult' not in genres: newlist.append(entry)
res[:] = newlist
# Get the real name, if this is an AKA.
# XXX: duplicated code!
new_res = []
seen_MID = []
for idx, (movieID, r) in enumerate(res):
# Remove duplicates.
# XXX: find a way to prefer titles with an AKA? Or prefer
# the original title?
if movieID in seen_MID:
continue
else:
seen_MID.append(movieID)
realMID = self._get_real_movieID(movieID)
if movieID == realMID:
new_res.append((movieID, r))
continue
if realMID in seen_MID:
continue
else:
seen_MID.append(realMID)
aka_title = build_title(r, canonical=0)
real_title = getLabel(realMID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
if aka_title == real_title:
new_res.append((realMID, r))
continue
new_r = analyze_title(real_title, canonical=1)
new_r['akas'] = [aka_title]
new_res.append((realMID, new_r))
if results > 0: new_res[:] = new_res[:results]
return new_res
def _search_episode(self, title, results):
title = title.strip()
if not title: return
_episodes = True
if analyze_title(title)['kind'] == 'episode':
_episodes = False
return self._search_movie(title, results, _episodes=_episodes)
def get_movie_main(self, movieID):
# Information sets provided by this method.
infosets = ('main', 'vote details')
tl = getLabel(movieID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
# No title, no party.
if tl is None:
raise IMDbDataAccessError, 'unable to get movieID "%s"' % movieID
res = analyze_title(tl)
# Build the cast list.
actl = []
for castG in ('actors', 'actresses'):
midx = getFullIndex('%s%s.titles' % (self.__db, castG),
movieID, multi=1)
if midx is not None:
params = {'movieID': movieID,
'dataF': '%s%s.data' % (self.__db, castG),
'indexF': '%snames.index' % self.__db,
'keyF': '%snames.key' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db,
'charNF': '%scharacter2id.index' % self.__db,
'offsList': midx, 'doCast': 1}
actl += getMovieCast(**params)
if actl:
actl.sort()
res['cast'] = actl
# List of other workers.
works = ('writer', 'cinematographer', 'composer',
'costume-designer', 'director', 'editor', 'miscellaneou',
'producer', 'production-designer', 'cinematographer')
for i in works:
index = getFullIndex('%s%ss.titles' % (self.__db, i),
movieID, multi=1)
if index is not None:
params = {'movieID': movieID,
'dataF': '%s%s.data' % (self.__db, i),
'indexF': '%snames.index' % self.__db,
'keyF': '%snames.key' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db,
'offsList': index}
name = key = i
if '-' in name:
name = name.replace('-', ' ')
elif name == 'miscellaneou':
name = 'miscellaneous crew'
key = 'miscellaneou'
elif name == 'writer':
params['doWriters'] = 1
params['dataF'] = '%s%ss.data' % (self.__db, key)
data = getMovieCast(**params)
if name == 'writer': data.sort()
res[name] = data
# Rating.
rt = self.get_movie_vote_details(movieID)['data']
if rt: res.update(rt)
# Various information.
miscInfo = (('runtimes', 'running-times'), ('color info', 'color-info'),
('genres', 'genres'), ('distributors', 'distributors'),
('languages', 'language'), ('certificates', 'certificates'),
('special effects companies', 'special-effects-companies'),
('sound mix', 'sound-mix'), ('tech info', 'technical'),
('production companies', 'production-companies'),
('countries', 'countries'))
for name, fname in miscInfo:
params = {'movieID': movieID,
'dataF': '%s%s.data' % (self.__db, fname),
'indexF': '%s%s.index' % (self.__db, fname),
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
data = getMovieMisc(**params)
if name in ('distributors', 'special effects companies',
'production companies'):
for nitem in xrange(len(data)):
n, notes = split_company_name_notes(data[nitem])
company = Company(name=n, companyID=getCompanyID(n,
'%scompany2id.index' % self.__db),
notes=notes,
accessSystem=self.accessSystem)
data[nitem] = company
if data: res[name] = data
if res.has_key('runtimes') and len(res['runtimes']) > 0:
rt = res['runtimes'][0]
episodes = re_episodes.findall(rt)
if episodes:
res['runtimes'][0] = re_episodes.sub('', rt)
res['number of episodes'] = episodes[0]
# AKA titles.
akas = getAkaTitles(movieID,
'%saka-titles.data' % self.__db,
'%stitles.index' % self.__db,
'%stitles.key' % self.__db,
'%sattributes.index' % self.__db,
'%sattributes.key' % self.__db)
if akas:
# normalize encoding.
for i in xrange(len(akas)):
ts = akas[i].split('::')
if len(ts) != 2: continue
t = ts[0]
n = ts[1]
nt = self._changeAKAencoding(n, t)
if nt is not None: akas[i] = '%s::%s' % (nt, n)
res['akas'] = akas
if res.get('kind') == 'episode':
# Things to do if this is a tv series episode.
episodeOf = res.get('episode of')
if episodeOf is not None:
parentSeries = Movie(data=res['episode of'],
accessSystem='local')
seriesID = self._getTitleID(parentSeries.get(
'long imdb canonical title'))
parentSeries.movieID = seriesID
res['episode of'] = parentSeries
if not res.get('year'):
year = getFullIndex('%smovies.data' % self.__db,
movieID, kind='moviedata', rindex=1)
if year: res['year'] = year
# MPAA info.
mpaa = getMPAA(movieID, '%smpaa-ratings-reasons.index' % self.__db,
'%smpaa-ratings-reasons.data' % self.__db)
if mpaa: res.update(mpaa)
return {'data': res, 'info sets': infosets}
def get_movie_plot(self, movieID):
pl = getPlot(movieID, '%splot.index' % self.__db,
'%splot.data' % self.__db)
trefs, nrefs = self._extractRefs(pl)
if pl: return {'data': {'plot': pl},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_taglines(self, movieID):
tg = getTaglines(movieID, '%staglines.index' % self.__db,
'%staglines.data' % self.__db)
if tg: return {'data': {'taglines': tg}}
return {'data': {}}
def get_movie_keywords(self, movieID):
params = {'movieID': movieID,
'dataF': '%skeywords.data' % self.__db,
'indexF': '%skeywords.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
kwds = getMovieMisc(**params)
if kwds: return {'data': {'keywords': kwds}}
return {'data': {}}
def get_movie_alternate_versions(self, movieID):
av = parseMinusList(movieID, '%salternate-versions.data' % self.__db,
'%salternate-versions.index' % self.__db)
trefs, nrefs = self._extractRefs(av)
if av: return {'data': {'alternate versions': av},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_crazy_credits(self, movieID):
cc = parseMinusList(movieID, '%scrazy-credits.data' % self.__db,
'%scrazy-credits.index' % self.__db)
trefs, nrefs = self._extractRefs(cc)
if cc: return {'data': {'crazy credits': cc},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_goofs(self, movieID):
goo = parseMinusList(movieID, '%sgoofs.data' % self.__db,
'%sgoofs.index' % self.__db)
trefs, nrefs = self._extractRefs(goo)
if goo: return {'data': {'goofs': goo},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_soundtrack(self, movieID):
goo = parseMinusList(movieID, '%ssoundtracks.data' % self.__db,
'%ssoundtracks.index' % self.__db)
trefs, nrefs = self._extractRefs(goo)
if goo: return {'data': {'soundtrack': goo},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_quotes(self, movieID):
mq = getQuotes(movieID, '%squotes.data' % self.__db,
'%squotes.index' % self.__db)
trefs, nrefs = self._extractRefs(mq)
for idx, quote in enumerate(mq):
mq[idx] = quote.split('::')
if mq: return {'data': {'quotes': mq},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_release_dates(self, movieID):
params = {'movieID': movieID,
'dataF': '%srelease-dates.data' % self.__db,
'indexF': '%srelease-dates.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
data = getMovieMisc(**params)
if data: return {'data': {'release dates': data}}
return {'data': {}}
def get_movie_miscellaneous_companies(self, movieID):
params = {'movieID': movieID,
'dataF': '%smiscellaneous-companies.data' % self.__db,
'indexF': '%smiscellaneous-companies.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
try:
data = getMovieMisc(**params)
except IMDbDataAccessError:
import warnings
warnings.warn('miscellaneous-companies files not found; '
'run the misc-companies4local.py script.')
return {'data': {}}
for nitem in xrange(len(data)):
n, notes = split_company_name_notes(data[nitem])
company = Company(name=n, companyID=getCompanyID(n,
'%scompany2id.index' % self.__db),
notes=notes,
accessSystem=self.accessSystem)
data[nitem] = company
if data: return {'data': {'miscellaneous companies': data}}
return {'data': {}}
def get_movie_vote_details(self, movieID):
data = getRatingData(movieID, '%sratings.data' % self.__db)
return {'data': data}
def get_movie_trivia(self, movieID):
triv = parseMinusList(movieID, '%strivia.data' % self.__db,
'%strivia.index' % self.__db)
trefs, nrefs = self._extractRefs(triv)
if triv: return {'data': {'trivia': triv},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_locations(self, movieID):
params = {'movieID': movieID,
'dataF': '%slocations.data' % self.__db,
'indexF': '%slocations.index' % self.__db,
'attrIF': '%sattributes.index' % self.__db,
'attrKF': '%sattributes.key' % self.__db}
data = getMovieMisc(**params)
if data: return {'data': {'locations': data}}
return {'data': {}}
def get_movie_connections(self, movieID):
mc = getMovieLinks(movieID, '%smovie-links.data' % self.__db,
'%stitles.index' % self.__db,
'%stitles.key' % self.__db)
if mc: return {'data': {'connections': mc}}
return {'data': {}}
def get_movie_business(self, movieID):
mb = getBusiness(movieID, '%sbusiness.index' % self.__db,
'%sbusiness.data' % self.__db)
trefs, nrefs = self._extractRefs(mb)
if mb: return {'data': {'business': mb},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def get_movie_literature(self, movieID):
ml = getLiterature(movieID, '%sliterature.index' % self.__db,
'%sliterature.data' % self.__db)
if ml: return {'data': {'literature': ml}}
return {'data': {}}
def get_movie_laserdisc(self, movieID):
ml = getLaserdisc(movieID, '%slaserdisc.index' % self.__db,
'%slaserdisc.data' % self.__db)
trefs, nrefs = self._extractRefs(ml)
if ml: return {'data': {'laserdisc': ml},
'titlesRefs': trefs, 'namesRefs': nrefs}
return {'data': {}}
def _buildEpisodes(self, eps_list, parentID):
episodes = {}
parentTitle = getLabel(parentID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
parentSeries = Movie(title=parentTitle,
movieID=parentID, accessSystem='local')
for episodeID, episodeTitle in eps_list:
episodeTitle = unicode(episodeTitle, 'latin_1', 'replace')
data = analyze_title(episodeTitle, canonical=1)
m = Movie(data=data, movieID=episodeID, accessSystem='local')
m['episode of'] = parentSeries
if data.get('year') is None:
year = getFullIndex('%smovies.data' % self.__db,
key=episodeID, kind='moviedata', rindex=1)
if year: m['year'] = year
season = data.get('season', 'UNKNOWN')
if not episodes.has_key(season): episodes[season] = {}
ep_number = data.get('episode')
if ep_number is None:
ep_number = max((episodes[season].keys() or [0])) + 1
episodes[season][ep_number] = m
return episodes
def get_movie_episodes(self, movieID):
try:
me = get_episodes(movieID, '%stitles.index' % self.__db,
'%stitles.key' % self.__db)
except IOError, e:
raise IMDbDataAccessError, str(e)
if me:
episodes = self._buildEpisodes(me, movieID)
data = {'episodes': episodes}
data['number of episodes'] = sum([len(x) for x
in episodes.values()])
data['number of seasons'] = len(episodes.keys())
return {'data': data}
return {'data': {}}
