84 lines
2.8 KiB
Python
84 lines
2.8 KiB
Python
# vi:si:et:sw=4:sts=4:ts=4
|
|
# encoding: utf-8
|
|
import re
|
|
|
|
from oxlib.cache import getUrlUnicode
|
|
from oxlib.html import stripTags
|
|
from oxlib.text import findRe
|
|
|
|
import imdb
|
|
|
|
def getData(id):
|
|
'''
|
|
>>> getData('1991/silence_of_the_lambs')['imdbId']
|
|
u'0102926'
|
|
|
|
>>> getData('1991/silence_of_the_lambs')['posters'][0]
|
|
u'http://www.impawards.com/1991/posters/silence_of_the_lambs_ver1_xlg.jpg'
|
|
|
|
>>> getData('1991/silence_of_the_lambs')['url']
|
|
u'http://www.impawards.com/1991/silence_of_the_lambs_ver1.html'
|
|
'''
|
|
data = {
|
|
'url': getUrl(id)
|
|
}
|
|
html = getUrlUnicode(data['url'])
|
|
data['imdbId'] = findRe(html, 'imdb.com/title/tt(.*?) ')
|
|
data['title'] = stripTags(findRe(html, '<p class="name white">(.*?) \(<a href="alpha1.html">'))
|
|
data['year'] = findRe(html, '\(<a href="alpha1.html">(.*?)</a>\)')
|
|
data['posters'] = []
|
|
results = re.compile('<a href = (%s.*?html)' % id[5:], re.DOTALL).findall(html)
|
|
for result in results:
|
|
result = result.replace('_xlg.html', '.html')
|
|
url = 'http://www.impawards.com/%s/%s' % (data['year'], result)
|
|
html = getUrlUnicode(url)
|
|
result = findRe(html, '<a href = (\w*?_xlg.html)')
|
|
if result:
|
|
url = 'http://www.impawards.com/%s/%s' % (data['year'], result)
|
|
html = getUrlUnicode(url)
|
|
poster = 'http://www.impawards.com/%s/%s' % (data['year'], findRe(html, '<img SRC="(.*?)"'))
|
|
else:
|
|
poster = 'http://www.impawards.com/%s/%s' % (data['year'], findRe(html, '<img src="(posters.*?)" alt='))
|
|
data['posters'].append(poster)
|
|
return data
|
|
|
|
def getId(url):
|
|
split = url.split('/')
|
|
year = split[3]
|
|
split = split[4][:-5].split('_')
|
|
if split[-1] == 'xlg':
|
|
split.pop()
|
|
if findRe(split[-1], 'ver\d+$'):
|
|
split.pop()
|
|
id = '%s/%s' % (year, '_'.join(split))
|
|
return id
|
|
|
|
def getIds():
|
|
ids = []
|
|
html = getUrlUnicode('http://www.impawards.com/archives/latest.html', timeout = 0)
|
|
pages = int(findRe(html, '<a href= page(.*?).html>')) + 1
|
|
for page in range(pages, 0, -1):
|
|
for id in getIdsByPage(page):
|
|
if not id in ids:
|
|
ids.append(id)
|
|
return ids
|
|
|
|
def getIdsByPage(page):
|
|
ids = []
|
|
html = getUrlUnicode('http://www.impawards.com/archives/page%s.html' % page, timeout = -1)
|
|
results = re.compile('<a href = \.\./(.*?)>', re.DOTALL).findall(html)
|
|
for result in results:
|
|
url = 'http://impawards.com/%s' % result
|
|
ids.append(getId(url))
|
|
return set(ids)
|
|
|
|
def getUrl(id):
|
|
url = "http://www.impawards.com/%s.html" % id
|
|
html = getUrlUnicode(url)
|
|
if findRe(html, "No Movie Posters on This Page"):
|
|
url = "http://www.impawards.com/%s_ver1.html" % id
|
|
return url
|
|
|
|
if __name__ == '__main__':
|
|
ids = getIds()
|
|
print sorted(ids), len(ids)
|