. @@ -168,8 +168,6 @@ def decode_html(html): return match.group(0) return charrefpat.sub(entitydecode, html).replace(u'\xa0', ' ') -decodeHtml = decode_html - def highlight(text, query, hlClass="hl"): """ >>> highlight('me & you and $&%', 'and') diff --git a/ox/location.py b/ox/location.py index 3efc479..101ce7c 100644 --- a/ox/location.py +++ b/ox/location.py @@ -18,7 +18,7 @@ def latlngspan2latlng(lat, lng, latSpan, lngSpan): lat_ne = lat + latSpan, lng_ne = lng + latSpan ) -def parseLocationString(location_string): +def parse_location_string(location_string): l = location_string.split('+') if len(l) == 1: l = location_string.split(';') diff --git a/ox/movie.py b/ox/movie.py index f9649b2..a0966e6 100644 --- a/ox/movie.py +++ b/ox/movie.py @@ -8,8 +8,8 @@ import hashlib import os import re -from normalize import normalizeName -from text import get_sort_name, findRe +from normalize import normalize_name +from text import get_sort_name, find_re __all__ = ['parse_movie_path', 'create_movie_path', 'get_oxid'] @@ -308,14 +308,14 @@ def parse_movie_path(path): if title.endswith('_'): title = title[:-1] + '.' - year = findRe(title, '(\(\d{4}\))') + year = find_re(title, '(\(\d{4}\))') if not year: - year = findRe(title, '(\(\d{4}-\d*\))') + year = find_re(title, '(\(\d{4}-\d*\))') if year and title.endswith(year): title = title[:-len(year)].strip() year = year[1:-1] if '-' in year: - year = findRe(year, '\d{4}') + year = find_re(year, '\d{4}') #director if len(parts) == 4: @@ -323,7 +323,7 @@ def parse_movie_path(path): if director.endswith('_'): director = "%s." % director[:-1] director = director.split('; ') - director = [normalizeName(d).strip() for d in director] + director = [normalize_name(d).strip() for d in director] director = filter(lambda d: d not in ('Unknown Director', 'Various Directors'), director) else: director = [] @@ -338,13 +338,13 @@ def parse_movie_path(path): language = '' #season/episode/episodeTitle - season = findRe(parts[-1], '\.Season (\d+)\.') + season = find_re(parts[-1], '\.Season (\d+)\.') if season: season = int(season) else: season = None - episode = findRe(parts[-1], '\.Episode (\d+)\.') + episode = find_re(parts[-1], '\.Episode (\d+)\.') if episode: episode = int(episode) else: @@ -373,7 +373,7 @@ def parse_movie_path(path): title = u'%s %s' % (title, episodeTitle) #part - part = findRe(parts[-1], '\.Part (\d+)\.') + part = find_re(parts[-1], '\.Part (\d+)\.') if part: part = int(part) else: diff --git a/ox/normalize.py b/ox/normalize.py index f2a4016..5359d95 100644 --- a/ox/normalize.py +++ b/ox/normalize.py @@ -37,13 +37,13 @@ _noarticles = ( 'i was', ) -def canonicalTitle(title): +def canonical_title(title): """Return the title in the canonic format 'Movie Title, The'. - >>> canonicalTitle('The Movie Title') + >>> canonical_title('The Movie Title') 'Movie Title, The' - >>> canonicalTitle('Los Angeles Plays Itself') + >>> canonical_title('Los Angeles Plays Itself') 'Los Angeles Plays Itself' """ try: @@ -72,10 +72,10 @@ def canonicalTitle(title): ## break return title -def normalizeTitle(title): +def normalize_title(title): """Return the title in the normal "The Title" format. - >>> normalizeTitle('Movie Title, The') + >>> normalize_title('Movie Title, The') 'The Movie Title' """ stitle = title.split(', ') @@ -85,14 +85,14 @@ def normalizeTitle(title): title = '%s%s%s' % (stitle[-1], sep, ', '.join(stitle[:-1])) return title -def normalizeImdbId(imdbId): +def normalize_imdbid(imdbId): """Return 7 digit imdbId. - >>> normalizeImdbId('http://www.imdb.com/title/tt0159206/') + >>> normalize_imdbid('http://www.imdb.com/title/tt0159206/') '0159206' - >>> normalizeImdbId(159206) + >>> normalize_imdbid(159206) '0159206' - >>> normalizeImdbId('tt0159206') + >>> normalize_imdbid('tt0159206') '0159206' """ if isinstance(imdbId, basestring): @@ -106,20 +106,20 @@ def normalizeImdbId(imdbId): _sname_suffixes = ('de', 'la', 'der', 'den', 'del', 'y', 'da', 'van', 'e', 'von', 'vom', 'the', 'di', 'du', 'el', 'al') -def canonicalName(name): +def canonical_name(name): """Return the given name in canonical "Surname, Name" format. It assumes that name is in the 'Name Surname' format. - >>> canonicalName('Jean Luc Godard') + >>> canonical_name('Jean Luc Godard') 'Godard, Jean Luc' - >>> canonicalName('Ivan Ivanov-Vano') + >>> canonical_name('Ivan Ivanov-Vano') 'Ivanov-Vano, Ivan' - >>> canonicalName('Gus Van Sant') + >>> canonical_name('Gus Van Sant') 'Van Sant, Gus' - >>> canonicalName('Brian De Palma') + >>> canonical_name('Brian De Palma') 'De Palma, Brian' """ @@ -167,19 +167,19 @@ def canonicalName(name): name = '%s, %s' % (sname[-1], ' '.join(sname[:-1])) return name -def normalizeName(name): +def normalize_name(name): """Return a name in the normal "Name Surname" format. - >>> normalizeName('Godard, Jean Luc') + >>> normalize_name('Godard, Jean Luc') 'Jean Luc Godard' - >>> normalizeName('Ivanov-Vano, Ivan') + >>> normalize_name('Ivanov-Vano, Ivan') 'Ivan Ivanov-Vano' - >>> normalizeName('Van Sant, Gus') + >>> normalize_name('Van Sant, Gus') 'Gus Van Sant' - >>> normalizeName('De Palma, Brian') + >>> normalize_name('De Palma, Brian') 'Brian De Palma' """ sname = name.split(', ') @@ -187,12 +187,12 @@ def normalizeName(name): name = '%s %s' % (sname[1], sname[0]) return name -def normalizePath(path): +def normalize_path(path): path = path.replace(':', '_').replace('/', '_') if path.endswith('.'): path = path[:-1] + '_' return path -def stripAccents(s): +def strip_accents(s): if isinstance(s, str): s = unicode(s) return ''.join((c for c in unicodedata.normalize('NFD', s) if unicodedata.category(c) != 'Mn')) diff --git a/ox/oembed.py b/ox/oembed.py index 822ff14..26e100d 100644 --- a/ox/oembed.py +++ b/ox/oembed.py @@ -1,7 +1,7 @@ # -*- coding: utf-8 -*- # ci:si:et:sw=4:sts=4:ts=4 import re -from text import findRe +from text import find_re import cache from utils import json, ET @@ -13,14 +13,14 @@ def get_embed_code(url, maxwidth=None, maxheight=None): json_oembed = filter(lambda l: 'json+oembed' in l, re.compile('
(.*?)
')).strip()
data['themes'] = parseList(html, 'themes')
data['types'] = parseList(html, 'types')
- data['year'] = findRe(html, '.*?(\d+)')
+ data['year'] = find_re(html, '.*?(\d+)')
#data['stills'] = [re.sub('_derived.*?/', '', i) for i in re.compile('(.*?)')).strip()
+ data['review'] = strip_tags(find_re(html, '(.*?)
')).strip()
return data
def getUrl(id):
return "http://allmovie.com/work/%s" % id
def parseEntry(html, title):
- html = findRe(html, '(.*?)').split('')[:-1]
+ find_re(html, '
(.*?)').split('')[:-1]
)
def parseText(html, title):
- return strip_tags(findRe(html, '%s
(.*?)
(.*?)