better criterion.py

This commit is contained in:
Rolux 2008-05-09 12:21:59 +02:00
parent 8a124fca9d
commit 252f9c371c

View file

@ -1,33 +1,26 @@
import re
import ox.imdb as imdb
from oxutils.cache import getUrl
from oxutils.cache import getUrlUnicode
from oxutils.html import stripTags
from oxutils.text import findRe
def getPosterUrl(title, director):
# imdb module is currently broken
'''
imdbId = imdb.getMovieId(title, director)
'''
html = getUrl('http://criterion.com/asp/list.asp?sort=spine')
html = getUrlUnicode('http://criterion.com/asp/list.asp?sort=spine', timeout = -1)
strings = findRe(html, '<table cellspacing="0" id="browse-all-table">(.*?)</table>').split('<tr>')
strings.pop(0)
for string in strings:
criterionid = findRe(string, '"release.asp\?id=(.*?)"')
criterionId = findRe(string, '"release.asp\?id=(.*?)"')
criterionTitle = findRe(string, 'class="title">(.*?)</a>')
criterionTitle = re.sub('(?<=\\w)<br>(?=\\w)', ' / ', criterionTitle)
criterionTitle = criterionTitle.replace('<br>', '')
criterionDirector = stripTags(findRe(string, '</a>.*?</td>(.*?)</td>')).strip()
print '%s: %s (%s)' % (criterionId, criterionTitle, criterionDirector)
'''
# print ('%s: %s (%s)' % (criterionId, criterionTitle, criterionDirector)).encode('utf-8')
if imdb.getMovieId(criterionTitle, criterionDirector) == imdbId:
return 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % criterionId
'''
return ''
def test():
return
if __name__ == '__main__':
getPosterUrl('Le mepris', 'Jean-Luc Godard')