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
|
"""
helpers module (imdb package).
This module provides functions not used directly by the imdb package,
but useful for IMDbPY-based programs.
Copyright 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
"""
# XXX: find better names for the functions in this modules.
import re
from cgi import escape
from types import UnicodeType, TupleType, ListType
# The modClearRefs can be used to strip names and titles references from
# the strings in Movie and Person objects.
from utils import modClearRefs, re_titleRef, re_nameRef
from imdb import IMDb
from imdb.parser.http.utils import re_entcharrefssub, entcharrefs, \
entcharrefsget, subXMLRefs, subSGMLRefs
# An URL, more or less.
_re_href = re.compile(r'(http://.+?)(?=\s|$)', re.I)
_re_hrefsub = _re_href.sub
def makeCgiPrintEncoding(encoding):
"""Make a function to pretty-print strings for the web."""
def cgiPrint(s):
"""Encode the given string using the %s encoding, and replace
chars outside the given charset with XML char references.""" % encoding
s = escape(s, quote=1)
if isinstance(s, UnicodeType):
s = s.encode(encoding, 'xmlcharrefreplace')
return s
return cgiPrint
# cgiPrint uses the latin_1 encoding.
cgiPrint = makeCgiPrintEncoding('latin_1')
def makeModCGILinks(movieTxt, personTxt):
"""Make a function used to pretty-print movies and persons refereces;
movieTxt and personTxt are the strings used for the substitutions.
movieTxt must contains %(movieID)s and %(title)s, while personTxt
must contains %(personID)s and %(name)s."""
def modCGILinks(s, titlesRefs, namesRefs):
"""Substitute movies and persons references."""
# XXX: look ma'... more nested scopes! <g>
def _replaceMovie(match):
to_replace = match.group(1)
item = titlesRefs.get(to_replace)
if item:
movieID = item.movieID
to_replace = movieTxt % {'movieID': movieID,
'title': unicode(cgiPrint(to_replace),
'latin_1',
'xmlcharrefreplace')}
return to_replace
def _replacePerson(match):
to_replace = match.group(1)
item = namesRefs.get(to_replace)
if item:
personID = item.personID
to_replace = personTxt % {'personID': personID,
'name': unicode(cgiPrint(to_replace),
'latin_1',
'xmlcharrefreplace')}
return to_replace
s = s.replace('<', '<').replace('>', '>')
s = _re_hrefsub(r'<a href="\1">\1</a>', s)
s = re_titleRef.sub(_replaceMovie, s)
s = re_nameRef.sub(_replacePerson, s)
return s
return modCGILinks
# links to the imdb.com web site.
modHtmlLinks = makeModCGILinks(
movieTxt='<a href="http://akas.imdb.com/title/tt%(movieID)s">%(title)s</a>',
personTxt='<a href="http://akas.imdb.com/name/nm%(personID)s">%(name)s</a>')
everyentcharrefs = entcharrefs.copy()
for k, v in {'lt':u'<','gt':u'>','amp':u'&','quot':u'"','apos':u'\''}.items():
everyentcharrefs[k] = v
everyentcharrefs['#%s' % ord(v)] = v
everyentcharrefsget = everyentcharrefs.get
re_everyentcharrefs = re.compile('&(%s|\#160|\#\d{1,5});' %
'|'.join(map(re.escape, everyentcharrefs)))
re_everyentcharrefssub = re_everyentcharrefs.sub
def _replAllXMLRef(match):
"""Replace the matched XML reference."""
ref = match.group(1)
value = everyentcharrefsget(ref)
if value is None:
if ref[0] == '#':
return unichr(int(ref[1:]))
else:
return ref
return value
def subXMLHTMLSGMLRefs(s):
"""Return the given string with XML/HTML/SGML entity and char references
replaced."""
return re_everyentcharrefssub(_replAllXMLRef, s)
def sortedSeasons(m):
"""Return a sorted list of seasons of the given series."""
seasons = m.get('episodes', {}).keys()
seasons.sort()
return seasons
def sortedEpisodes(m, season=None):
"""Return a sorted list of episodes of the given series,
considering only the specified season(s) (every season, if None)."""
episodes = []
seasons = season
if season is None:
seasons = sortedSeasons(m)
else:
if not isinstance(season, (TupleType, ListType)):
seasons = [season]
for s in seasons:
eps_indx = m.get('episodes', {}).get(s, {}).keys()
eps_indx.sort()
for e in eps_indx:
episodes.append(m['episodes'][s][e])
return episodes
# Idea an portions of the code courtesy of none none (dclist at gmail.com)
_re_imdbIDurl = re.compile(r'\b(nm|tt)([0-9]{7})\b')
def get_byURL(url, info=None, args=None, kwds=None):
"""Return a Movie or Person object for the given URL; info is the
info set to retrieve, args and kwds are respectively a list and a
dictionary or arguments to initialize the data access system.
Returns None if unable to correctly parse the url; can raise
exceptions if unable to retrieve the data."""
if args is None: args = []
if kwds is None: kwds = {}
ia = IMDb(*args, **kwds)
match = _re_imdbIDurl.search(url)
if not match:
return None
imdbtype = match.group(1)
imdbID = match.group(2)
if imdbtype == 'tt':
return ia.get_movie(imdbID, info=info)
elif imdbtype == 'nm':
return ia.get_person(imdbID, info=info)
return None
|
