adding impawards module

This commit is contained in:
Rolux 2008-05-09 13:21:42 +02:00
parent 9578097c45
commit 8e9d0e8304
2 changed files with 49 additions and 4 deletions

View file

@ -22,16 +22,16 @@ def getMovieId(title = '', director = '', imdbId = ''):
return ''
def getMovieData(title = '', director = '', imdbId = ''):
data = {}
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['id'] = id
data['posterUrl'] = 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % id
return data
return {}
data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>'))
return data
if __name__ == '__main__':
print getMovieData('Le mepris', 'Jean-Luc Godard')

45
ox/impawards.py Normal file
View file

@ -0,0 +1,45 @@
import re
import ox.imdb as imdb
from oxutils.cache import getUrlUnicode
from oxutils.text import findRe
def getMovieData(title = '', director = '', imdbId = ''):
data = {'posterUrls': []}
if not imdbId:
imdbId = imdb.getMovieId(title, director)
print imdbId
html = getUrlUnicode('http://impawards.com/archives/latest.html', timeout = 0)
pages = int(findRe(html, '<a href = page(.*?).html>'))
for page in range(pages + 1, 0, -1):
print page
if page <= pages:
html = getUrlUnicode('http://impawards.com/archives/page%s.html' % page, timeout = -1)
urls = parseArchivePage(html)
print urls
for url in urls:
html = getUrlUnicode(url)
d = parseMoviePage(html)
print d
if d['imdbId'] == imdbId:
data['posterUrls'].append(d['posterUrl'])
print d['posterUrl']
data['posterUrls'].sort()
return data
def parseArchivePage(html):
urls = []
results = re.compile('<a href = \.\./(.*?)>', re.DOTALL).findall(html)
for result in results:
urls.append('http://impawards.com/%s' % result)
return urls
def parseMoviePage(html):
data = {}
data['imdbId'] = findRe(html, 'imdb.com/title/tt(.*?) ')
data['posterUrl'] = 'http://impawards.com/%s' % findRe(html, '<td align=center><br><img SRC="(.*?)"')
return data
if __name__ == '__main__':
getMovieData('Brick', 'Rian Johnson')