0x2620/python-oxweb
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

even better criterion.py

Browse source
This commit is contained in:
Rolux 2008-05-09 12:39:20 +02:00
parent 252f9c371c
commit 9578097c45
1 changed files with 18 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
ox/criterion.py
View file

@ -5,22 +5,33 @@ from oxutils.cache import getUrlUnicode
from oxutils.html import stripTags from oxutils.html import stripTags
from oxutils.text import findRe from oxutils.text import findRe
def getPosterUrl(title, director): def getMovieId(title = '', director = '', imdbId = ''):
# imdb module is currently broken if not imdbId:
imdbId = imdb.getMovieId(title, director) imdbId = imdb.getMovieId(title, director)
html = getUrlUnicode('http://criterion.com/asp/list.asp?sort=spine', timeout = -1) 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 = findRe(html, '<table cellspacing="0" id="browse-all-table">(.*?)</table>').split('<tr>')
strings.pop(0) strings.pop(0)
for string in strings: for string in strings:
criterionId = findRe(string, '"release.asp\?id=(.*?)"') id = findRe(string, '"release.asp\?id=(.*?)"')
criterionTitle = findRe(string, 'class="title">(.*?)</a>') criterionTitle = findRe(string, 'class="title">(.*?)</a>')
criterionTitle = re.sub('(?<=\\w)<br>(?=\\w)', ' / ', criterionTitle) criterionTitle = re.sub('(?<=\\w)<br>(?=\\w)', ' / ', criterionTitle)
criterionTitle = criterionTitle.replace('<br>', '') criterionTitle = criterionTitle.replace('<br>', '')
criterionDirector = stripTags(findRe(string, '</a>.*?</td>(.*?)</td>')).strip() criterionDirector = stripTags(findRe(string, '</a>.*?</td>(.*?)</td>')).strip()
# print ('%s: %s (%s)' % (criterionId, criterionTitle, criterionDirector)).encode('utf-8')
if imdb.getMovieId(criterionTitle, criterionDirector) == imdbId: if imdb.getMovieId(criterionTitle, criterionDirector) == imdbId:
return 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % criterionId return id
return '' return ''
def getMovieData(title = '', director = '', imdbId = ''):
if not imdbId:
imdbId = imdb.getMovieId(title, director)
id = getMovieId(imdbId = imdbId)
if id:
html = getUrlUnicode('http://criterion.com/asp/release.asp?id=%s' % id)
data = {}
data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>'))
data['posterUrl'] = 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % id
return data
return {}
if __name__ == '__main__': if __name__ == '__main__':
getPosterUrl('Le mepris', 'Jean-Luc Godard') print getMovieData('Le mepris', 'Jean-Luc Godard')