/usr/lib/python2.7/dist-packages/imdb/parser/http/personParser.py is in python-imdbpy 4.8.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | """
parser.http.personParser module (imdb package).
This module provides the classes (and the instances), used to parse
the IMDb pages on the akas.imdb.com server about a person.
E.g., for "Mel Gibson" the referred pages would be:
categorized: http://akas.imdb.com/name/nm0000154/maindetails
biography: http://akas.imdb.com/name/nm0000154/bio
...and so on...
Copyright 2004-20101 Davide Alberani <da@erlug.linux.it>
2008 H. Turgut Uyar <uyar@tekir.org>
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
"""
import re
from imdb.Movie import Movie
from imdb.utils import analyze_name, canonicalName, normalizeName, \
analyze_title, date_and_notes
from utils import build_movie, DOMParserBase, Attribute, Extractor, \
analyze_imdbid
from movieParser import _manageRoles
_reRoles = re.compile(r'(<li>.*? \.\.\.\. )(.*?)(</li>|<br>)',
re.I | re.M | re.S)
def build_date(date):
day = date.get('day')
year = date.get('year')
if day and year:
return "%s %s" % (day, year)
if day:
return day
if year:
return year
return ""
class DOMHTMLMaindetailsParser(DOMParserBase):
"""Parser for the "categorized" (maindetails) page of a given person.
The page should be provided as a string, as taken from
the akas.imdb.com server. The final result will be a
dictionary, with a key for every relevant section.
Example:
cparser = DOMHTMLMaindetailsParser()
result = cparser.parse(categorized_html_string)
"""
_containsObjects = True
_birth_attrs = [Attribute(key='birth date',
path='.//time[@itemprop="birthDate"]/@datetime'),
Attribute(key='birth place',
path=".//a[starts-with(@href, " \
"'/search/name?birth_place=')]/text()")]
_death_attrs = [Attribute(key='death date',
path='.//time[@itemprop="deathDate"]/@datetime'),
Attribute(key='death place',
path=".//a[starts-with(@href, " \
"'/search/name?death_place=')]/text()")]
_film_attrs = [Attribute(key=None,
multi=True,
path={
'link': "./b/a[1]/@href",
'title': "./b/a[1]/text()",
'notes': "./b/following-sibling::text()",
'year': "./span[@class='year_column']/text()",
'status': "./a[@class='in_production']/text()",
'rolesNoChar': './/br/following-sibling::text()',
'chrRoles': "./a[@imdbpyname]/@imdbpyname",
'roleID': "./a[starts-with(@href, '/character/')]/@href"
},
postprocess=lambda x:
build_movie(x.get('title') or u'',
year=x.get('year'),
movieID=analyze_imdbid(x.get('link') or u''),
rolesNoChar=(x.get('rolesNoChar') or u'').strip(),
chrRoles=(x.get('chrRoles') or u'').strip(),
additionalNotes=x.get('notes'),
roleID=(x.get('roleID') or u''),
status=x.get('status') or None))]
extractors = [
Extractor(label='name',
path="//h1[@class='header']",
attrs=Attribute(key='name',
path=".//text()",
postprocess=lambda x: analyze_name(x,
canonical=1))),
Extractor(label='birth info',
path="//div[h4='Born:']",
attrs=_birth_attrs),
Extractor(label='death info',
path="//div[h4='Died:']",
attrs=_death_attrs),
Extractor(label='headshot',
path="//td[@id='img_primary']/a",
attrs=Attribute(key='headshot',
path="./img/@src")),
Extractor(label='akas',
path="//div[h4='Alternate Names:']",
attrs=Attribute(key='akas',
path="./text()",
postprocess=lambda x: x.strip().split(' '))),
Extractor(label='filmography',
group="//div[starts-with(@id, 'filmo-head-')]",
group_key="./a[@name]/text()",
group_key_normalize=lambda x: x.lower().replace(': ', ' '),
path="./following-sibling::div[1]" \
"/div[starts-with(@class, 'filmo-row')]",
attrs=_film_attrs),
Extractor(label='indevelopment',
path="//div[starts-with(@class,'devitem')]",
attrs=Attribute(key='in development',
multi=True,
path={
'link': './a/@href',
'title': './a/text()'
},
postprocess=lambda x:
build_movie(x.get('title') or u'',
movieID=analyze_imdbid(x.get('link') or u''),
roleID=(x.get('roleID') or u'').split('/'),
status=x.get('status') or None)))
]
preprocessors = [('<div class="clear"/> </div>', ''),
('<br/>', '<br />'),
(re.compile(r'(<a href="/character/ch[0-9]{7}")>(.*?)</a>'),
r'\1 imdbpyname="\2@@">\2</a>')]
def postprocess_data(self, data):
for what in 'birth date', 'death date':
if what in data and not data[what]:
del data[what]
# XXX: the code below is for backwards compatibility
# probably could be removed
for key in data.keys():
if key.startswith('actor '):
if not data.has_key('actor'):
data['actor'] = []
data['actor'].extend(data[key])
del data[key]
if key.startswith('actress '):
if not data.has_key('actress'):
data['actress'] = []
data['actress'].extend(data[key])
del data[key]
if key.startswith('self '):
if not data.has_key('self'):
data['self'] = []
data['self'].extend(data[key])
del data[key]
if key == 'birth place':
data['birth notes'] = data[key]
del data[key]
if key == 'death place':
data['death notes'] = data[key]
del data[key]
return data
class DOMHTMLBioParser(DOMParserBase):
"""Parser for the "biography" page of a given person.
The page should be provided as a string, as taken from
the akas.imdb.com server. The final result will be a
dictionary, with a key for every relevant section.
Example:
bioparser = DOMHTMLBioParser()
result = bioparser.parse(biography_html_string)
"""
_defGetRefs = True
_birth_attrs = [Attribute(key='birth date',
path={
'day': "./a[starts-with(@href, " \
"'/date/')]/text()",
'year': "./a[starts-with(@href, " \
"'/search/name?birth_year=')]/text()"
},
postprocess=build_date),
Attribute(key='birth notes',
path="./a[starts-with(@href, " \
"'/search/name?birth_place=')]/text()")]
_death_attrs = [Attribute(key='death date',
path={
'day': "./a[starts-with(@href, " \
"'/date/')]/text()",
'year': "./a[starts-with(@href, " \
"'/search/name?death_date=')]/text()"
},
postprocess=build_date),
Attribute(key='death notes',
path="./text()",
# TODO: check if this slicing is always correct
postprocess=lambda x: u''.join(x).strip()[2:])]
extractors = [
Extractor(label='headshot',
path="//a[@name='headshot']",
attrs=Attribute(key='headshot',
path="./img/@src")),
Extractor(label='birth info',
path="//div[h5='Date of Birth']",
attrs=_birth_attrs),
Extractor(label='death info',
path="//div[h5='Date of Death']",
attrs=_death_attrs),
Extractor(label='nick names',
path="//div[h5='Nickname']",
attrs=Attribute(key='nick names',
path="./text()",
joiner='|',
postprocess=lambda x: [n.strip().replace(' (',
'::(', 1) for n in x.split('|')
if n.strip()])),
Extractor(label='birth name',
path="//div[h5='Birth Name']",
attrs=Attribute(key='birth name',
path="./text()",
postprocess=lambda x: canonicalName(x.strip()))),
Extractor(label='height',
path="//div[h5='Height']",
attrs=Attribute(key='height',
path="./text()",
postprocess=lambda x: x.strip())),
Extractor(label='mini biography',
path="//div[h5='Mini Biography']",
attrs=Attribute(key='mini biography',
multi=True,
path={
'bio': "./p//text()",
'by': "./b/following-sibling::a/text()"
},
postprocess=lambda x: "%s::%s" % \
(x.get('bio').strip(),
(x.get('by') or u'').strip() or u'Anonymous'))),
Extractor(label='spouse',
path="//div[h5='Spouse']/table/tr",
attrs=Attribute(key='spouse',
multi=True,
path={
'name': "./td[1]//text()",
'info': "./td[2]//text()"
},
postprocess=lambda x: ("%s::%s" % \
(x.get('name').strip(),
(x.get('info') or u'').strip())).strip(':'))),
Extractor(label='trade mark',
path="//div[h5='Trade Mark']/p",
attrs=Attribute(key='trade mark',
multi=True,
path=".//text()",
postprocess=lambda x: x.strip())),
Extractor(label='trivia',
path="//div[h5='Trivia']/p",
attrs=Attribute(key='trivia',
multi=True,
path=".//text()",
postprocess=lambda x: x.strip())),
Extractor(label='quotes',
path="//div[h5='Personal Quotes']/p",
attrs=Attribute(key='quotes',
multi=True,
path=".//text()",
postprocess=lambda x: x.strip())),
Extractor(label='salary',
path="//div[h5='Salary']/table/tr",
attrs=Attribute(key='salary history',
multi=True,
path={
'title': "./td[1]//text()",
'info': "./td[2]/text()",
},
postprocess=lambda x: "%s::%s" % \
(x.get('title').strip(),
x.get('info').strip()))),
Extractor(label='where now',
path="//div[h5='Where Are They Now']/p",
attrs=Attribute(key='where now',
multi=True,
path=".//text()",
postprocess=lambda x: x.strip())),
]
preprocessors = [
(re.compile('(<h5>)', re.I), r'</div><div class="_imdbpy">\1'),
(re.compile('(</table>\n</div>\s+)</div>', re.I + re.DOTALL), r'\1'),
(re.compile('(<div id="tn15bot">)'), r'</div>\1'),
(re.compile('\.<br><br>([^\s])', re.I), r'. \1')
]
def postprocess_data(self, data):
for what in 'birth date', 'death date':
if what in data and not data[what]:
del data[what]
return data
class DOMHTMLOtherWorksParser(DOMParserBase):
"""Parser for the "other works" and "agent" pages of a given person.
The page should be provided as a string, as taken from
the akas.imdb.com server. The final result will be a
dictionary, with a key for every relevant section.
Example:
owparser = DOMHTMLOtherWorksParser()
result = owparser.parse(otherworks_html_string)
"""
_defGetRefs = True
kind = 'other works'
# XXX: looks like the 'agent' page is no more public.
extractors = [
Extractor(label='other works',
path="//h5[text()='Other works']/" \
"following-sibling::div[1]",
attrs=Attribute(key='self.kind',
path=".//text()",
postprocess=lambda x: x.strip().split('\n\n')))
]
preprocessors = [
(re.compile('(<h5>[^<]+</h5>)', re.I),
r'</div>\1<div class="_imdbpy">'),
(re.compile('(</table>\n</div>\s+)</div>', re.I), r'\1'),
(re.compile('(<div id="tn15bot">)'), r'</div>\1'),
(re.compile('<br/><br/>', re.I), r'\n\n')
]
def _build_episode(link, title, minfo, role, roleA, roleAID):
"""Build an Movie object for a given episode of a series."""
episode_id = analyze_imdbid(link)
notes = u''
minidx = minfo.find(' -')
# Sometimes, for some unknown reason, the role is left in minfo.
if minidx != -1:
slfRole = minfo[minidx+3:].lstrip()
minfo = minfo[:minidx].rstrip()
if slfRole.endswith(')'):
commidx = slfRole.rfind('(')
if commidx != -1:
notes = slfRole[commidx:]
slfRole = slfRole[:commidx]
if slfRole and role is None and roleA is None:
role = slfRole
eps_data = analyze_title(title)
eps_data['kind'] = u'episode'
# FIXME: it's wrong for multiple characters (very rare on tv series?).
if role is None:
role = roleA # At worse, it's None.
if role is None:
roleAID = None
if roleAID is not None:
roleAID = analyze_imdbid(roleAID)
e = Movie(movieID=episode_id, data=eps_data, currentRole=role,
roleID=roleAID, notes=notes)
# XXX: are we missing some notes?
# XXX: does it parse things as "Episode dated 12 May 2005 (12 May 2005)"?
if minfo.startswith('('):
pe = minfo.find(')')
if pe != -1:
date = minfo[1:pe]
if date != '????':
e['original air date'] = date
if eps_data.get('year', '????') == '????':
syear = date.split()[-1]
if syear.isdigit():
e['year'] = int(syear)
return e
class DOMHTMLSeriesParser(DOMParserBase):
"""Parser for the "by TV series" page of a given person.
The page should be provided as a string, as taken from
the akas.imdb.com server. The final result will be a
dictionary, with a key for every relevant section.
Example:
sparser = DOMHTMLSeriesParser()
result = sparser.parse(filmoseries_html_string)
"""
_containsObjects = True
extractors = [
Extractor(label='series',
group="//div[@class='filmo']/span[1]",
group_key="./a[1]",
path="./following-sibling::ol[1]/li/a[1]",
attrs=Attribute(key=None,
multi=True,
path={
'link': "./@href",
'title': "./text()",
'info': "./following-sibling::text()",
'role': "./following-sibling::i[1]/text()",
'roleA': "./following-sibling::a[1]/text()",
'roleAID': "./following-sibling::a[1]/@href"
},
postprocess=lambda x: _build_episode(x.get('link'),
x.get('title'),
(x.get('info') or u'').strip(),
x.get('role'),
x.get('roleA'),
x.get('roleAID'))))
]
def postprocess_data(self, data):
if len(data) == 0:
return {}
nd = {}
for key in data.keys():
dom = self.get_dom(key)
link = self.xpath(dom, "//a/@href")[0]
title = self.xpath(dom, "//a/text()")[0][1:-1]
series = Movie(movieID=analyze_imdbid(link),
data=analyze_title(title),
accessSystem=self._as, modFunct=self._modFunct)
nd[series] = []
for episode in data[key]:
# XXX: should we create a copy of 'series', to avoid
# circular references?
episode['episode of'] = series
nd[series].append(episode)
return {'episodes': nd}
class DOMHTMLPersonGenresParser(DOMParserBase):
"""Parser for the "by genre" and "by keywords" pages of a given person.
The page should be provided as a string, as taken from
the akas.imdb.com server. The final result will be a
dictionary, with a key for every relevant section.
Example:
gparser = DOMHTMLPersonGenresParser()
result = gparser.parse(bygenre_html_string)
"""
kind = 'genres'
_containsObjects = True
extractors = [
Extractor(label='genres',
group="//b/a[@name]/following-sibling::a[1]",
group_key="./text()",
group_key_normalize=lambda x: x.lower(),
path="../../following-sibling::ol[1]/li//a[1]",
attrs=Attribute(key=None,
multi=True,
path={
'link': "./@href",
'title': "./text()",
'info': "./following-sibling::text()"
},
postprocess=lambda x: \
build_movie(x.get('title') + \
x.get('info').split('[')[0],
analyze_imdbid(x.get('link')))))
]
def postprocess_data(self, data):
if len(data) == 0:
return {}
return {self.kind: data}
from movieParser import DOMHTMLTechParser
from movieParser import DOMHTMLOfficialsitesParser
from movieParser import DOMHTMLAwardsParser
from movieParser import DOMHTMLNewsParser
_OBJECTS = {
'maindetails_parser': ((DOMHTMLMaindetailsParser,), None),
'bio_parser': ((DOMHTMLBioParser,), None),
'otherworks_parser': ((DOMHTMLOtherWorksParser,), None),
#'agent_parser': ((DOMHTMLOtherWorksParser,), {'kind': 'agent'}),
'person_officialsites_parser': ((DOMHTMLOfficialsitesParser,), None),
'person_awards_parser': ((DOMHTMLAwardsParser,), {'subject': 'name'}),
'publicity_parser': ((DOMHTMLTechParser,), {'kind': 'publicity'}),
'person_series_parser': ((DOMHTMLSeriesParser,), None),
'person_contacts_parser': ((DOMHTMLTechParser,), {'kind': 'contacts'}),
'person_genres_parser': ((DOMHTMLPersonGenresParser,), None),
'person_keywords_parser': ((DOMHTMLPersonGenresParser,),
{'kind': 'keywords'}),
'news_parser': ((DOMHTMLNewsParser,), None),
}
|