python-oxweb/oxweb/allmovie.py

79 lines
2.7 KiB
Python
Raw Normal View History

2008-07-04 13:56:02 +00:00
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
import time
from oxlib import stripTags, findRe
from oxlib.cache import readUrlUnicode
2008-07-04 13:56:02 +00:00
2009-07-13 22:25:07 +00:00
def getId(url):
return url.split("/")[-2]
def getData(id):
2009-07-13 22:34:00 +00:00
'''
>>> getData('129689')['cast'][1][1]
u'Marianne'
>>> getData('129689')['credits'][0][0]
u'Jean-Luc Godard'
>>> getData('129689')['posters'][0]
u'http://image.allmusic.com/00/adg/cov200/dru800/u812/u81260bbffr.jpg'
>>> getData('129689')['rating']
u'4.5'
'''
2009-07-13 22:25:07 +00:00
data = {
"url": getUrl(id)
}
html = readUrlUnicode(data["url"])
2009-07-13 22:25:07 +00:00
data['aka'] = parseList(html, 'AKA')
data['category'] = findRe(html, 'http://allmovie.com/explore/category/.*?">(.*?)</a>')
data['countries'] = parseList(html, 'Countries')
data['director'] = parseEntry(html, 'Director')
data['genres'] = parseList(html, 'Genres')
2008-07-25 14:06:50 +00:00
data['keywords'] = parseList(html, 'Keywords')
2009-07-13 22:25:07 +00:00
data['posters'] = [findRe(html, '<img src="(http://image\..*?)"')]
data['produced'] = parseList(html, 'Produced by')
data['rating'] = findRe(html, 'Stars" title="(.*?) Stars"')
2008-07-25 14:35:12 +00:00
data['released'] = parseEntry(html, 'Released by')
2009-07-13 22:25:07 +00:00
data['releasedate'] = parseEntry(html, 'Release')[0:10].replace(' ', '-')
data['runtime'] = findRe(html, '<td class="formed-sub" style="width: 86px;">(\d+) min.</td>')
data['set'] = parseEntry(html, 'Set In')
data['synopsis'] = parseText(html, 'Plot Synopsis')
data['themes'] = parseList(html, 'Themes')
data['types'] = parseList(html, 'Types')
data['year'] = findRe(html, '"http://allmovie.com/explore/year/(.*?)"')
html = readUrlUnicode("http://allmovie.com/work/%s/cast" % id)
2009-07-13 22:25:07 +00:00
data['cast'] = parseTable(html)
html = readUrlUnicode("http://allmovie.com/work/%s/credits" % id)
2009-07-13 22:25:07 +00:00
data['credits'] = parseTable(html)
html = readUrlUnicode("http://allmovie.com/work/%s/review" % id)
2009-07-13 22:25:07 +00:00
data['review'] = parseText(html, 'Review')
2008-07-25 11:54:20 +00:00
return data
2008-07-04 13:56:02 +00:00
2009-07-13 22:25:07 +00:00
def getUrl(id):
return "http://allmovie.com/work/%s/" % id
2008-07-04 13:56:02 +00:00
2008-07-25 14:35:12 +00:00
def parseEntry(html, title):
2009-07-13 22:25:07 +00:00
return stripTags(findRe(html, '<span>%s</span>(.*?)</table>' % title)).strip()
2008-07-25 14:35:12 +00:00
2008-07-25 14:06:50 +00:00
def parseList(html, title):
2009-07-13 22:25:07 +00:00
html = findRe(html, '<span>%s</span>(.*?)</table>' % title)
return map(lambda x: stripTags(x), re.compile('<li>(.*?)</li>', re.DOTALL).findall(html))
def parseTable(html):
return map(
lambda x: map(
lambda x: stripTags(x).strip().replace('&nbsp;', ''),
x.split('<td width="305">-')
),
findRe(html, '<div id="results-table">(.*?)</table>').split('</tr>')[:-1]
)
def parseText(html, title):
return stripTags(findRe(html, '%s</td>.*?<td colspan="2"><p>(.*?)</td>' % title)).strip()
2008-07-25 14:06:50 +00:00
if __name__ == '__main__':
2009-07-13 22:25:07 +00:00
print getData('129689')
# print getData('177524')