python-oxweb/oxweb/wikipedia.py

# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
from urllib import urlencode

import simplejson
from oxlib.cache import getUrl, getUrlUnicode
from oxlib import findRe, decodeHtml


def getMovieId(title, director='', year=''):
    query = '"%s" film %s %s' % (title, director, year)
    result = find(query, 1)
    if result:
        return result[0][1]
    return ''

def getUrlByImdb(imdbId):
    query = '"imdb_id = %s"'% imdbId
    result = find(query)
    if result:
        url = result[0][1]
        return url
    if str(imdbId).startswith('0'):
        imdbId = imdbId[1:]
        return getUrlByImdb(imdbId)

def getUrlByAmbId(amg_id):
    query = '"amg_id = %s"'% amg_id
    result = find(query)
    if result:
        url = result[0][1]
        return url
    return ''

def getWikiData(wikipediaUrl):
    title = wikipediaUrl.replace('http://en.wikipedia.org/wiki/', '')
    url =   "http://en.wikipedia.org/w/index.php?title=%s&action=edit" % title
    html = getUrlUnicode(url)
    data = decodeHtml(findRe(html, "<textarea.*?>(.*?)</textarea>"))
    return data

def getMovieData(wikipediaUrl):
    data = getWikiData(wikipediaUrl)
    filmbox_data = findRe(data, '''\{\{Infobox Film(.*?)\}\}''')
    filmbox = {}
    for row in filmbox_data.strip().split('|'): 
        d = row.split('=')
        if len(d) == 2:
            key = d[0].strip()
            value = d[1].strip()
            filmbox[key] = value
    return filmbox

def getAmgId(wikipediaUrl):
    data = getMovieData(wikipediaUrl)
    return data.get('amg_id', '')

def find(query, max_results=10):
    query = {'action': 'query', 'list':'search', 'format': 'json',
             'srlimit': max_results, 'srwhat': 'text', 'srsearch': query.encode('utf-8')}
    url = "http://en.wikipedia.org/w/api.php?" + urlencode(query)
    data = getUrl(url)
    if not data:
        data  = getUrl(url, timeout=0)
    result = simplejson.loads(data)
    results = []
    for r in result['query']['search']:
        title = r['title']
        url = "http://en.wikipedia.org/wiki/%s" % title.replace(' ', '_')
        results.append((title, url, ''))
    return results