36 lines
1.5 KiB
Python
36 lines
1.5 KiB
Python
# -*- 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 getUrlUnicode
|
|
|
|
def getMovieData(allmovieId):
|
|
html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T0" % allmovieId)
|
|
data = {}
|
|
data['poster'] = findRe(html, '<img src="(http://image.*?)"')
|
|
data['synopsis'] = stripTags(findRe(html, 'Plot Synopsis</td>.*?<td colspan="2"><p>(.*?)</td>'))
|
|
data['year'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&sql=24:\d{4}">(\d{4})</a>')
|
|
data['rating'] = findRe(html, '" alt="(\d+?) Stars"')
|
|
data['country'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&sql=24:D\|\|\|206">(.*?)</')
|
|
data['director'] = stripTags(findRe(html, '<td class="formed-sub"><a href="/cg/avg.dll\?p=avg&sql=2:\d+">(.*?)</td>')).split(', ')
|
|
data['genre'] = parseList(html, 'Genre / Type')
|
|
data['keywords'] = parseList(html, 'Keywords')
|
|
data['themes'] = parseList(html, 'Themes')
|
|
html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T1" % allmovieId)
|
|
data['review'] = stripTags(findRe(html, 'Review</td>.*?<td colspan="2"><p>(.*?)</td>'))
|
|
return data
|
|
|
|
def getMoviePoster(allmovieId):
|
|
data = getMovieData(allmovieId)
|
|
if data:
|
|
return data['poster']
|
|
return ''
|
|
|
|
def parseList(html, title):
|
|
return map(lambda x: stripTags(x), findRe(html, '<span>%s</span>(.*?)</table>' % title).split('</li><li>'))
|
|
|
|
if __name__ == '__main__':
|
|
print getMovieData('177524')
|
|
|