File: __init__.py

package info (click to toggle)
imdbpy 2.7-2
  • links: PTS
  • area: main
  • in suites: etch, etch-m68k
  • size: 780 kB
  • ctags: 1,295
  • sloc: python: 8,867; ansic: 440; makefile: 44
file content (691 lines) | stat: -rw-r--r-- 29,970 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
"""
parser.local package (imdb package).

This package provides the IMDbLocalAccessSystem class used to access
IMDb's data through a local installation.
the imdb.IMDb function will return an instance of this class when
called with the 'accessSystem' argument set to "local" or "files".

Copyright 2004-2006 Davide Alberani <da@erlug.linux.it>

This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
"""

from __future__ import generators

import os
from stat import ST_SIZE

from imdb._exceptions import IMDbDataAccessError, IMDbError
from imdb.utils import analyze_title, analyze_name, re_episodes

from imdb.Person import Person
from imdb.Movie import Movie
from personParser import getFilmography, getBio, getAkaNames
from movieParser import getLabel, getMovieCast, getAkaTitles, parseMinusList, \
                        getPlot, getRatingData, getMovieMisc, getTaglines, \
                        getQuotes, getMovieLinks, getBusiness, getLiterature, \
                        getLaserdisc
from utils import getFullIndex, KeyFScan, latin2utf
from imdb.parser.common.locsql import IMDbLocalAndSqlAccessSystem, \
                                        titleVariations, nameVariations

try:
    from imdb.parser.common.cutils import get_episodes
except ImportError:
    import warnings
    warnings.warn('Unable to import the cutils.get_episodes function.'
                    '  Retrieving episodes list of tv series will be'
                    ' a bit slower.')

    def get_episodes(movieID, indexFile, keyFile):
        if movieID < 0:
            raise IMDbDataAccessError, "movieID must be positive."
        try:
            ifile = open(indexFile, 'rb')
        except IOError, e:
            raise IMDbDataAccessError, str(e)
        ifile.seek(4L*movieID, 0)
        indexStr = ifile.read(4)
        ifile.close()
        if len(indexStr) != 4:
            raise IMDbDataAccessError, \
                    "unable to read indexFile; movieID too high?"
        kfIndex = 0L
        for i in (0, 1, 2, 3):
            kfIndex |= ord(indexStr[i]) << i*8L;
        try:
            kfile = open(keyFile, 'rt')
        except IOError, e:
            raise IMDbDataAccessError, str(e)
        kfile.seek(kfIndex, 0)
        seriesTitle = kfile.readline().split('|')[0].strip()
        if seriesTitle[0:1] != '"' or seriesTitle[-1:] != ')':
            return []
        stLen = len(seriesTitle)
        results = []
        for line in kfile:
            if not line.strip(): break
            epsTitle, epsID = line.split('|')
            if epsTitle[:stLen] != seriesTitle: break
            if epsTitle[stLen+1] != '{' or epsTitle[-1] != '}':
                break
            results.append((int(epsID.strip(), 16), epsTitle))
        kfile.close()
        return results

try:
    from imdb.parser.common.cutils import search_name

    def _scan_names(keyFile, name1, name2, name3, results=0):
        """Scan the given file, using the cutils.search_name
        C function, for name variations."""
        # the search_name function in the cutils C module manages
        # latin_1 encoded strings.
        name1, name2, name3 = [x.encode('latin_1', 'replace')
                                for x in name1, name2, name3]
        sn = search_name(keyFile, name1, name2, name3, results)
        res = []
        for x in sn:
            tmpd = analyze_name(latin2utf(x[2]))
            res.append((x[0], (x[1], tmpd)))
        return res
except ImportError:
    import warnings
    warnings.warn('Unable to import the cutils.search_name function.'
                    '  Searching names using the "local" data access system'
                    ' will be REALLY slow.')

    from imdb.parser.common.locsql import scan_names

    def _readNamesKeyFile(keyFile):
        """Iterate over the given file, returning tuples suited for
        the common.locsql.scan_names function."""
        try: kf = open(keyFile, 'r')
        except IOError, e: raise IMDbDataAccessError, str(e)
        for line in kf:
            ls = line.split('|')
            if not ls[0]: continue
            named = analyze_name(latin2utf(ls[0]))
            yield (long(ls[1], 16), named)
        kf.close()

    def _scan_names(keyFile, name1, name2, name3, results=0):
        """Scan the given file, using the common.locsql.scan_names
        pure-Python function, for name variations."""
        return scan_names(_readNamesKeyFile(keyFile),
                            name1, name2, name3, results)

try:
    from imdb.parser.common.cutils import search_title

    def _scan_titles(keyFile, title1, title2, title3, results=0):
        """Scan the given file, using the cutils.search_title
        C function, for title variations."""
        title1, title2, title3 = [x.encode('latin_1', 'replace')
                                    for x in title1, title2, title3]
        st = search_title(keyFile, title1, title2, title3, results)
        res = []
        for x in st:
            tmpd = analyze_title(latin2utf(x[2]))
            res.append((x[0], (x[1], tmpd)))
        return res
except ImportError:
    import warnings
    warnings.warn('Unable to import the cutils.search_title function.'
                    '  Searching titles using the "local" data access system'
                    ' will be REALLY slow.')

    from imdb.parser.common.locsql import scan_titles

    def _readTitlesKeyFile(keyFile, searchingEpisode=0, lenTitle=1):
        """Iterate over the given file, returning tuples suited for
        the common.locsql.scan_titles function."""
        STRING_MAXLENDIFFER = 0.7
        lenTitle = float(lenTitle)
        try: kf = open(keyFile, 'r')
        except IOError, e: raise IMDbDataAccessError, str(e)
        for line in kf:
            ls = line.split('|')
            t = ls[0]
            if not t: continue
            l_t = len(t)
            if (lenTitle > l_t): threshold = l_t / lenTitle
            else: threshold = lenTitle / l_t
            # don't compare too different lenght strings.
            if threshold < STRING_MAXLENDIFFER: continue
            if searchingEpisode:
                if t[-1] != '}': continue
            elif t[-1] == '}': continue
            titled = analyze_title(latin2utf(t))
            yield (long(ls[1], 16), titled)
        kf.close()

    def _scan_titles(keyFile, title1, title2, title3, results=0):
        """Scan the given file, using the common.locsql.scan_titles
        pure-Python function, for title variations."""
        se = 0
        if title3 and title3[-1] == '}': se = 1
        return scan_titles(_readTitlesKeyFile(keyFile, searchingEpisode=se,
                            lenTitle=len(title3 or title1)),
                            title1, title2, title3, results)


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 _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 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,
                            '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 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
        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_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:
            return {'data': {'episodes': self._buildEpisodes(me, movieID)}}
        return {'data': {}}

    def _search_person(self, name, results):
        name = name.strip()
        if not name: return []
        name1, name2, name3 = nameVariations(name)
        resultsST = results
        if not self.doAdult: resultsST = 0
        res =  _scan_names('%snames.key' % self.__db,
                            name1, name2, name3, resultsST)
        if results > 0: res[:] = res[:results]
        res[:] = [x[1] for x in res]
        return res

    def get_person_main(self, personID):
        infosets = ('main', 'biography', 'other works')
        nl = getLabel(personID, '%snames.index' % self.__db,
                        '%snames.key' % self.__db)
        # No name, no party.
        if nl is None:
            raise IMDbDataAccessError, 'unable to get personID "%s"' % personID
        res = analyze_name(nl)
        res.update(getBio(personID, '%sbiographies.index' % self.__db,
                    '%sbiographies.data' % self.__db))
        akas = getAkaNames(personID,
                    '%saka-names.data' % self.__db,
                    '%snames.index' % self.__db,
                    '%snames.key' % self.__db)
        if akas: res['akas'] = akas
        # XXX: horrible hack!  The getBio() function is not able to
        #      retrieve the movieID!
        #      A cleaner solution, would be to NOT return Movies object
        #      at first, from the getBio() function.
        # XXX: anyway, this is no more needed, since "guest appearances"
        #      are gone with the new tv series episodes support.
        if res.has_key('notable tv guest appearances'):
            nl = []
            for m in res['notable tv guest appearances']:
                movieID = self._getTitleID(m.get('long imdb canonical title'))
                if movieID is None: continue
                m.movieID = movieID
                nl.append(m)
            if nl:
                nl.sort()
                res['notable tv guest appearances'][:] = nl
            else: del res['notable tv guest appearances']
        trefs, nrefs = self._extractRefs(res)
        return {'data': res, 'info sets': infosets,
                'titlesRefs': trefs, 'namesRefs': nrefs}

    def get_person_filmography(self, personID):
        infosets = ('filmography', 'episodes')
        res = {}
        episodes = {}
        works = ('actor', 'actresse', 'producer', 'writer',
                'cinematographer', 'composer', 'costume-designer',
                'director', 'editor', 'miscellaneou', 'production-designer')
        for i in works:
            index = getFullIndex('%s%ss.names' % (self.__db, i), personID)
            if index is not None:
                params = {'offset': index,
                            'indexF': '%stitles.index' % self.__db,
                            'keyF': '%stitles.key' % self.__db,
                            'attrIF': '%sattributes.index' % self.__db,
                            'attrKF': '%sattributes.key' % self.__db}
                name = key = i
                if '-' in name:
                    name = name.replace('-', ' ')
                elif name == 'actresse':
                    name = 'actress'
                    params['doCast'] = 1
                elif name == 'miscellaneou':
                    name = 'miscellaneous crew'
                    key = 'miscellaneou'
                elif name == 'actor':
                    params['doCast'] = 1
                elif name == 'writer':
                    params['doWriters'] = 1
                params['dataF'] = '%s%ss.data' % (self.__db, key)
                data = getFilmography(**params)
                movies = []
                eps = []
                # Split normal titles from episodes.
                for d in data:
                    if d.get('kind') != 'episode':
                        movies.append(d)
                    else:
                        eps.append(d)
                movies.sort()
                if movies:
                    res[name] = movies
                for e in eps:
                    series = Movie(data=e['episode of'], accessSystem='local')
                    seriesID = self._getTitleID(series.get(
                                                'long imdb canonical title'))
                    series.movieID = seriesID
                    if not e.get('year'):
                        year = getFullIndex('%smovies.data' % self.__db,
                                            e.movieID, kind='moviedata',
                                            rindex=1)
                        if year: e['year'] = year
                    if not e.currentRole and name not in ('actor', 'actress'):
                        if e.notes: e.notes = ' %s' % e.notes
                        e.notes = '[%s]%s' % (name, e.notes)
                    episodes.setdefault(series, []).append(e)
        if episodes:
            for k in episodes:
                episodes[k].sort()
                episodes[k].reverse()
            res['episodes'] = episodes
        return {'data': res, 'info sets': tuple(infosets)}

    get_person_biography = get_person_main
    get_person_other_works = get_person_main
    get_person_episodes = get_person_filmography