2010-07-07 23:25:57 +00:00
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# vi:si:et:sw=4:sts=4:ts=4
|
|
|
|
import urllib2
|
|
|
|
from urllib import quote, unquote
|
|
|
|
import re
|
|
|
|
import os
|
|
|
|
import time
|
|
|
|
|
|
|
|
import ox
|
2010-07-10 08:24:56 +00:00
|
|
|
from ox import findRe, stripTags
|
2010-07-07 23:25:57 +00:00
|
|
|
from ox.normalize import normalizeTitle, normalizeImdbId
|
2010-10-08 16:07:39 +00:00
|
|
|
import ox.cache
|
2010-07-19 10:05:01 +00:00
|
|
|
from ox.cache import readUrl
|
2010-07-07 23:25:57 +00:00
|
|
|
|
|
|
|
from siteparser import SiteParser
|
|
|
|
import google
|
|
|
|
|
2010-10-08 16:07:39 +00:00
|
|
|
def readUrl(url, data=None, headers=ox.cache.DEFAULT_HEADERS, timeout=ox.cache.cache_timeout, valid=None):
|
|
|
|
headers = headers.copy()
|
|
|
|
return ox.cache.readUrl(url, data, headers, timeout)
|
|
|
|
|
|
|
|
def readUrlUnicode(url, timeout=ox.cache.cache_timeout):
|
|
|
|
return ox.cache.readUrlUnicode(url, _readUrl=readUrl, timeout=timeout)
|
2010-07-10 08:24:56 +00:00
|
|
|
|
2010-07-07 23:25:57 +00:00
|
|
|
class Imdb(SiteParser):
|
2010-12-09 03:37:28 +00:00
|
|
|
'''
|
|
|
|
>>> Imdb('0068646')['title']
|
|
|
|
u'The Godfather'
|
|
|
|
|
|
|
|
>>> Imdb('0133093')['title']
|
|
|
|
u'The Matrix'
|
|
|
|
'''
|
2010-07-07 23:25:57 +00:00
|
|
|
regex = {
|
2010-07-09 08:54:06 +00:00
|
|
|
'alternative_titles': {
|
|
|
|
'page': 'releaseinfo',
|
|
|
|
're': [
|
|
|
|
'name="akas".*?<table.*?>(.*?)</table>',
|
2010-10-08 15:43:25 +00:00
|
|
|
"td>(.*?)</td>.*?<td>(.*?)</td>"
|
2010-07-09 08:54:06 +00:00
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
|
|
|
|
},
|
2010-07-07 23:25:57 +00:00
|
|
|
'cast': {
|
2010-07-10 11:54:33 +00:00
|
|
|
'page': 'combined',
|
2010-07-10 08:24:56 +00:00
|
|
|
're': [
|
|
|
|
'<td class="nm">.*?>(.*?)</a>.*?<td class="char">(.*?)</td>',
|
|
|
|
lambda ll: [stripTags(l) for l in ll]
|
|
|
|
],
|
2010-07-07 23:25:57 +00:00
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'cinematographers': {
|
2010-07-10 11:54:33 +00:00
|
|
|
'page': 'combined',
|
2010-07-07 23:25:57 +00:00
|
|
|
're': [
|
2010-07-10 08:24:56 +00:00
|
|
|
lambda data: data.split('Series Crew')[0],
|
2010-07-07 23:25:57 +00:00
|
|
|
'Cinematography by</a>(.*?)</table>',
|
|
|
|
'<a href="/name/.*?/">(.*?)</a>'
|
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'connections': {
|
|
|
|
'page': 'movieconnections',
|
|
|
|
're': '<h5>(.*?)</h5>(.*?)\n\n',
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'countries': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': '<a href="/Sections/Countries/.*?/">(.*?)</a>',
|
|
|
|
'type': 'list'
|
|
|
|
},
|
2010-11-28 15:53:47 +00:00
|
|
|
'creators': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': [
|
|
|
|
'<h5>Creators:</h5>.*?<div class="info-content">(.*?)</div>',
|
|
|
|
'<a href="/name/.*?>(.*?)</a>'
|
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
},
|
2010-07-07 23:25:57 +00:00
|
|
|
'directors': {
|
2010-07-10 11:54:33 +00:00
|
|
|
'page': 'combined',
|
2010-07-07 23:25:57 +00:00
|
|
|
're': [
|
2010-07-10 08:24:56 +00:00
|
|
|
lambda data: data.split('Series Crew')[0],
|
2010-07-07 23:25:57 +00:00
|
|
|
'Directed by</a>(.*?)</table>',
|
2010-11-28 15:53:47 +00:00
|
|
|
'<a href="/name/.*?>(.*?)</a>'
|
2010-07-07 23:25:57 +00:00
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'editors': {
|
2010-07-10 11:54:33 +00:00
|
|
|
'page': 'combined',
|
2010-07-07 23:25:57 +00:00
|
|
|
're': [
|
2010-07-10 08:24:56 +00:00
|
|
|
lambda data: data.split('Series Crew')[0],
|
2010-07-07 23:25:57 +00:00
|
|
|
'Film Editing by</a>(.*?)</table>',
|
2010-11-28 15:53:47 +00:00
|
|
|
'<a href="/name/.*?>(.*?)</a>'
|
2010-07-07 23:25:57 +00:00
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
},
|
2010-07-12 08:52:26 +00:00
|
|
|
'episode_title': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': '<div id="tn15title">.*?<em>(.*?)</em>',
|
|
|
|
'type': 'string'
|
|
|
|
},
|
2010-07-07 23:25:57 +00:00
|
|
|
'filming_locations': {
|
|
|
|
'page': 'locations',
|
|
|
|
're': '<a href="/search/title\?locations=.*?">(.*?)</a>',
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'genres': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': '<a href="/Sections/Genres/.*?/">(.*?)</a>',
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'keywords': {
|
|
|
|
'page': 'keywords',
|
|
|
|
're': '<a href="/keyword/.*?/">(.*?)</a>',
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'languages': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': '<a href="/Sections/Languages/.*?/">(.*?)</a>',
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'plot': {
|
|
|
|
'page': 'plotsummary',
|
2010-07-09 08:54:06 +00:00
|
|
|
're': '</div>.*?<p class="plotpar">(.*?)<i>',
|
2010-07-07 23:25:57 +00:00
|
|
|
'type': 'string'
|
|
|
|
},
|
|
|
|
'poster_id': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': '/primary-photo/media/rm(.*?)/tt',
|
2010-07-19 10:05:01 +00:00
|
|
|
'type': 'string'
|
2010-07-07 23:25:57 +00:00
|
|
|
},
|
|
|
|
'poster_ids': {
|
|
|
|
'page': 'posters',
|
|
|
|
're': '/unknown-thumbnail/media/rm(.*?)/tt',
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'producers': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': [
|
2010-07-10 18:20:48 +00:00
|
|
|
lambda data: data.split('Series Crew')[0],
|
2010-07-07 23:25:57 +00:00
|
|
|
'Produced by</a>(.*?)</table>',
|
|
|
|
'<a href="/name/.*?/">(.*?)</a>'
|
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'rating': {
|
|
|
|
'page': 'combined',
|
2010-07-10 08:24:56 +00:00
|
|
|
're': '<div class="starbar-meta">.*?<b>([\d,.]?)/10</b>',
|
2010-07-07 23:25:57 +00:00
|
|
|
'type': 'float'
|
|
|
|
},
|
2010-07-12 08:52:26 +00:00
|
|
|
'release date': {
|
2010-07-07 23:25:57 +00:00
|
|
|
'page': 'releaseinfo',
|
|
|
|
're': '<a href="/date/(\d{2})-(\d{2})/">.*?</a> <a href="/year/(\d{4})/">',
|
|
|
|
'type': 'date'
|
|
|
|
},
|
2010-07-08 08:59:15 +00:00
|
|
|
'reviews': {
|
|
|
|
'page': 'externalreviews',
|
|
|
|
're': [
|
|
|
|
'<ol>(.*?)</ol>',
|
|
|
|
'<li><a href="(http.*?)".*?>(.*?)</a></li>'
|
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
},
|
2010-07-07 23:25:57 +00:00
|
|
|
'runtime': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': '<h5>Runtime:</h5><div class="info-content">.*?([0-9]+ sec|[0-9]+ min).*?</div>',
|
|
|
|
'type': 'string'
|
|
|
|
},
|
2010-07-12 08:52:26 +00:00
|
|
|
'season': {
|
|
|
|
'page': 'combined',
|
2010-07-13 09:28:55 +00:00
|
|
|
're': [
|
|
|
|
'<h5>Original Air Date:</h5>.*?<div class="info-content">(.*?)</div>',
|
|
|
|
'\(Season (\d+), Episode \d+\)',
|
|
|
|
],
|
2010-07-12 08:52:26 +00:00
|
|
|
'type': 'int'
|
|
|
|
},
|
|
|
|
'episode': {
|
|
|
|
'page': 'combined',
|
2010-07-13 09:28:55 +00:00
|
|
|
're': [
|
|
|
|
'<h5>Original Air Date:</h5>.*?<div class="info-content">(.*?)</div>',
|
|
|
|
'\(Season \d+, Episode (\d+)\)',
|
|
|
|
],
|
2010-07-12 08:52:26 +00:00
|
|
|
'type': 'int'
|
|
|
|
},
|
|
|
|
'series': {
|
|
|
|
'page': 'combined',
|
|
|
|
're': '<h5>TV Series:</h5>.*?<a href="/title/tt(\d{7})',
|
|
|
|
'type': 'string'
|
|
|
|
},
|
2010-12-09 03:37:28 +00:00
|
|
|
'original_title': {
|
2010-07-07 23:25:57 +00:00
|
|
|
'page': 'combined',
|
|
|
|
're': '<h1>(.*?) <span>',
|
|
|
|
'type': 'string'
|
|
|
|
},
|
|
|
|
'trivia': {
|
|
|
|
'page': 'trivia',
|
|
|
|
're': '<div class="sodatext">(.*?)<br>',
|
|
|
|
'type': 'list',
|
|
|
|
},
|
|
|
|
'votes': {
|
|
|
|
'page': 'combined',
|
2010-07-10 08:24:56 +00:00
|
|
|
're': '<a href="ratings" class="tn15more">([\d,]*?) votes</a>',
|
2010-07-07 23:25:57 +00:00
|
|
|
'type': 'string'
|
|
|
|
},
|
|
|
|
'writers': {
|
2010-07-10 11:54:33 +00:00
|
|
|
'page': 'combined',
|
2010-07-07 23:25:57 +00:00
|
|
|
're': [
|
2010-07-10 08:24:56 +00:00
|
|
|
lambda data: data.split('Series Crew')[0],
|
2010-07-07 23:25:57 +00:00
|
|
|
'Writing credits</a>(.*?)</table>',
|
|
|
|
'<a href="/name/.*?/">(.*?)</a>'
|
|
|
|
],
|
|
|
|
'type': 'list'
|
|
|
|
},
|
|
|
|
'year': {
|
|
|
|
'page': 'combined',
|
2010-12-07 18:29:53 +00:00
|
|
|
're': '="og:title" content=".*?\((\d{4})\).*?"',
|
2010-07-07 23:25:57 +00:00
|
|
|
'type': 'int'
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-10-08 16:07:39 +00:00
|
|
|
def readUrlUnicode(self, url, timeout):
|
|
|
|
return readUrlUnicode(url, timeout)
|
|
|
|
|
2010-07-12 08:52:26 +00:00
|
|
|
def __init__(self, id, timeout=-1):
|
2010-12-09 03:37:28 +00:00
|
|
|
#use akas.imdb.com to always get original title:
|
|
|
|
#http://www.imdb.com/help/show_leaf?titlelanguagedisplay
|
|
|
|
self.baseUrl = "http://akas.imdb.com/title/tt%s/" % id
|
2010-07-12 08:52:26 +00:00
|
|
|
super(Imdb, self).__init__(timeout)
|
2010-07-07 23:25:57 +00:00
|
|
|
|
2010-12-09 03:37:28 +00:00
|
|
|
def is_international_title(t):
|
|
|
|
if 'usa' in t[1].lower(): return True
|
|
|
|
if 'international' in t[1].lower(): return True
|
|
|
|
return False
|
|
|
|
ititle = filter(is_international_title, self['alternative_titles'])
|
|
|
|
if ititle:
|
|
|
|
self['english_title'] = ititle[0][0]
|
|
|
|
|
|
|
|
self['title'] = self.get('english_title', self['original_title'])
|
|
|
|
|
2010-07-12 08:52:26 +00:00
|
|
|
if 'title' in self and self['title'].startswith('"') and self['title'].endswith('"'):
|
|
|
|
self['title'] = self['title'][1:-1]
|
2010-07-08 08:03:57 +00:00
|
|
|
if 'runtime' in self and self['runtime']:
|
2010-07-07 23:25:57 +00:00
|
|
|
if 'min' in self['runtime']: base=60
|
|
|
|
else: base=1
|
|
|
|
self['runtime'] = int(findRe(self['runtime'], '([0-9]+)')) * base
|
2010-07-10 08:24:56 +00:00
|
|
|
if 'runtime' in self and not self['runtime']:
|
|
|
|
del self['runtime']
|
2010-07-09 08:54:06 +00:00
|
|
|
if 'votes' in self: self['votes'] = self['votes'].replace(',', '')
|
2010-07-07 23:25:57 +00:00
|
|
|
if 'connections' in self:
|
|
|
|
cc={}
|
2010-07-08 08:03:57 +00:00
|
|
|
if len(self['connections']) == 2 and isinstance(self['connections'][0], basestring):
|
|
|
|
self['connections'] = [self['connections']]
|
2010-07-07 23:25:57 +00:00
|
|
|
for rel, data in self['connections']:
|
|
|
|
cc[unicode(rel)] = re.compile('<a href="/title/tt(\d{7})/">').findall(data)
|
|
|
|
self['connections'] = cc
|
|
|
|
|
2010-07-09 08:54:06 +00:00
|
|
|
for key in ('countries', 'genres'):
|
2010-07-10 08:24:56 +00:00
|
|
|
if key in self:
|
|
|
|
self[key] = filter(lambda x: x.lower() != 'home', self[key])
|
2010-07-09 08:54:06 +00:00
|
|
|
|
2010-11-28 15:53:47 +00:00
|
|
|
if 'creators' in self:
|
|
|
|
self['directors'] = self['creators']
|
|
|
|
del self['creators']
|
2010-07-12 08:52:26 +00:00
|
|
|
if 'series' in self:
|
|
|
|
if 'episode_title' in self:
|
|
|
|
self['series_title'] = self['title']
|
|
|
|
self['title'] = "%s: %s" % (self['series_title'], self['episode_title'])
|
|
|
|
if 'episode_title' in self and 'season' in self and 'episode' in self:
|
|
|
|
self['title'] = "%s (S%02dE%02d) %s" % (
|
|
|
|
self['series_title'], self['season'], self['episode'], self['episode_title'])
|
2010-11-28 15:53:47 +00:00
|
|
|
for key in ('directors', 'year'):
|
2010-12-07 18:29:53 +00:00
|
|
|
if key in self:
|
|
|
|
self['episode_%s'%key] = self[key]
|
2010-11-28 15:53:47 +00:00
|
|
|
series = Imdb(self['series'])
|
|
|
|
for key in ['directors', 'year']:
|
2010-12-07 18:29:53 +00:00
|
|
|
if key in series:
|
|
|
|
self[key] =series[key]
|
2010-07-12 08:52:26 +00:00
|
|
|
else:
|
|
|
|
for key in ('series_title', 'episode_title', 'season', 'episode'):
|
|
|
|
if key in self:
|
|
|
|
del self[key]
|
2010-07-09 08:54:06 +00:00
|
|
|
|
2010-07-18 18:24:36 +00:00
|
|
|
class ImdbCombined(Imdb):
|
|
|
|
def __init__(self, id, timeout=-1):
|
|
|
|
_regex = {}
|
|
|
|
for key in self.regex:
|
2010-10-08 16:07:39 +00:00
|
|
|
if self.regex[key]['page'] == 'combined':
|
2010-07-18 18:24:36 +00:00
|
|
|
_regex[key] = self.regex[key]
|
|
|
|
self.regex = _regex
|
|
|
|
super(ImdbCombined, self).__init__(id, timeout)
|
|
|
|
|
2010-07-18 18:57:22 +00:00
|
|
|
def getMovieId(title, director='', year=''):
|
|
|
|
'''
|
|
|
|
>>> getMovieId('The Matrix')
|
2010-09-03 21:19:19 +00:00
|
|
|
u'0133093'
|
|
|
|
|
|
|
|
>>> getMovieId('2 or 3 Things I Know About Her', 'Jean-Luc Godard')
|
|
|
|
u'0060304'
|
|
|
|
|
|
|
|
>>> getMovieId('2 or 3 Things I Know About Her', 'Jean-Luc Godard', '1967')
|
|
|
|
u'0060304'
|
2010-07-18 18:57:22 +00:00
|
|
|
'''
|
|
|
|
if director:
|
2010-09-03 21:19:19 +00:00
|
|
|
query = 'site:imdb.com %s "%s" ' % (director, title)
|
2010-07-18 18:57:22 +00:00
|
|
|
else:
|
2010-09-03 21:19:19 +00:00
|
|
|
query = 'site:imdb.com "%s" ' % title
|
|
|
|
if year:
|
|
|
|
query += year
|
2010-07-18 18:57:22 +00:00
|
|
|
for (name, url, desc) in google.find(query, 5, timeout=-1):
|
|
|
|
if url.startswith('http://www.imdb.com/title/tt'):
|
|
|
|
return url[28:35]
|
|
|
|
return ''
|
|
|
|
|
2010-07-19 10:05:01 +00:00
|
|
|
def getMoviePoster(imdbId):
|
2010-09-17 08:46:37 +00:00
|
|
|
'''
|
|
|
|
>>> getMoviePoster('0133093')
|
|
|
|
'http://ia.media-imdb.com/images/M/MV5BMjEzNjg1NTg2NV5BMl5BanBnXkFtZTYwNjY3MzQ5._V1._SX338_SY475_.jpg'
|
|
|
|
|
|
|
|
>>> getMoviePoster('0994352')
|
|
|
|
'http://ia.media-imdb.com/images/M/MV5BMjA3NzMyMzU1MV5BMl5BanBnXkFtZTcwNjc1ODUwMg@@._V1._SX594_SY755_.jpg'
|
|
|
|
'''
|
2010-07-19 10:05:01 +00:00
|
|
|
info = ImdbCombined(imdbId)
|
|
|
|
if 'poster_id' in info:
|
|
|
|
url = "http://www.imdb.com/rg/action-box-title/primary-photo/media/rm%s/tt%s" % (info['poster_id'], imdbId)
|
|
|
|
data = readUrl(url)
|
|
|
|
poster = findRe(data, 'img id="primary-img".*?src="(.*?)"')
|
|
|
|
return poster
|
2010-09-17 08:46:37 +00:00
|
|
|
elif 'series' in info:
|
|
|
|
return getMoviePoster(info['series'])
|
2010-07-19 10:05:01 +00:00
|
|
|
return ''
|
|
|
|
|
2010-07-07 23:25:57 +00:00
|
|
|
def guess(title, director='', timeout=google.DEFAULT_TIMEOUT):
|
|
|
|
#FIXME: proper file -> title
|
2010-12-08 00:56:37 +00:00
|
|
|
'''
|
|
|
|
//this is not needed
|
2010-07-07 23:25:57 +00:00
|
|
|
title = title.split('-')[0]
|
|
|
|
title = title.split('(')[0]
|
|
|
|
title = title.split('.')[0]
|
|
|
|
title = title.strip()
|
2010-12-08 00:56:37 +00:00
|
|
|
'''
|
2010-07-07 23:25:57 +00:00
|
|
|
imdb_url = 'http://www.imdb.com/find?q=%s' % quote(title.encode('utf-8'))
|
|
|
|
return_url = ''
|
|
|
|
|
|
|
|
#lest first try google
|
2010-07-10 08:24:56 +00:00
|
|
|
#i.e. site:imdb.com Michael Stevens "Sin"
|
2010-07-07 23:25:57 +00:00
|
|
|
if director:
|
|
|
|
search = 'site:imdb.com %s "%s"' % (director, title)
|
|
|
|
else:
|
|
|
|
search = 'site:imdb.com "%s"' % title
|
2010-12-08 00:56:37 +00:00
|
|
|
|
2010-07-07 23:25:57 +00:00
|
|
|
for (name, url, desc) in google.find(search, 2, timeout=timeout):
|
|
|
|
if url.startswith('http://www.imdb.com/title/tt'):
|
|
|
|
return normalizeImdbId(int(ox.intValue(url)))
|
|
|
|
|
|
|
|
try:
|
|
|
|
req = urllib2.Request(imdb_url, None, ox.net.DEFAULT_HEADERS)
|
|
|
|
u = urllib2.urlopen(req)
|
|
|
|
data = u.read()
|
|
|
|
return_url = u.url
|
|
|
|
u.close()
|
|
|
|
except:
|
|
|
|
return None
|
|
|
|
if return_url.startswith('http://www.imdb.com/title/tt'):
|
|
|
|
return return_url[28:35]
|
|
|
|
if data:
|
|
|
|
imdb_id = findRe(data.replace('\n', ' '), 'Popular Results.*?<ol><li>.*?<a href="/title/tt(.......)')
|
|
|
|
if imdb_id:
|
|
|
|
return imdb_id
|
|
|
|
|
|
|
|
imdb_url = 'http://www.imdb.com/find?q=%s;s=tt;site=aka' % quote(title.encode('utf-8'))
|
|
|
|
req = urllib2.Request(imdb_url, None, ox.net.DEFAULT_HEADERS)
|
|
|
|
u = urllib2.urlopen(req)
|
|
|
|
data = u.read()
|
|
|
|
return_url = u.url
|
|
|
|
u.close()
|
|
|
|
if return_url.startswith('http://www.imdb.com/title/tt'):
|
|
|
|
return return_url[28:35]
|
|
|
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
import json
|
|
|
|
print json.dumps(Imdb('0306414'), indent=2)
|
|
|
|
#print json.dumps(Imdb('0133093'), indent=2)
|
|
|
|
|