some more tv show sites

This commit is contained in:
j 2008-07-03 22:22:32 +02:00
parent 68f7621ac7
commit f653e02887
4 changed files with 110 additions and 1 deletions

43
oxweb/epguides.py Normal file
View file

@ -0,0 +1,43 @@
# -*- 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
import google
def getUrl(title):
'''
Search Epguide Url for Show via Show Title.
Use Google to search the url, this is also done on Epguide.
'''
for (name, url, desc) in google.find('allintitle: site:epguides.com %s' % title, 1):
if url.startswith('http://epguides.com'):
if re.search(title, name):
return url
return None
def getShowData(url):
data = getUrlUnicode(url)
r = {}
r['title'] = stripTags(findRe(data, '<h1>(.*?)</h1>'))
r['imdb'] = findRe(data, '<h1><a href=".*?/title/tt(\d.*?)">.*?</a></h1>')
r['episodes'] = {}
#1. 1- 1 1001 7 Aug 05 You Can't Miss the Bear
for episode in re.compile('(\d+?)\..*?(\d+?-.\d.*?) .*?(\d+?) .*?(.*?) <a target="_blank" href="(.*?)">(.*?)</a>').findall(data):
air_date = episode[3].strip()
#'22 Sep 04' -> 2004-09-22
air_date = time.strftime('%Y-%m-%d', time.strptime(air_date, '%d %b %y'))
s = episode[1].split('-')[0].strip()
e = episode[1].split('-')[-1].strip()
r['episodes']['S%02dE%02d' % (int(s), int(e))] = {
'prod code': episode[2],
'air date': air_date,
'url': episode[4],
'title':episode[5],
}
return r

34
oxweb/rottentomatoes.py Normal file
View file

@ -0,0 +1,34 @@
# -*- coding: UTF-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
from oxlib.cache import getHeaders, getUrl, getUrlUnicode
from oxlib import findRe, stripTags
def getUrlByImdb(imdb):
#this would also wor but does not cache:
'''
from urllib2 import urlopen
u = urlopen(url)
return u.url
'''
url = "http://www.rottentomatoes.com/alias?type=imdbid&s=%s" % imdb
data = getUrl(url)
if "movie_title" in data:
movies = re.compile('(/m/.*?/)').findall(data)
if movies:
return "http://www.rottentomatoes.com" + movies[0]
return None
def getData(url):
data = getUrlUnicode(url)
r = {}
r['title'] = findRe(data, '<h1 class="movie_title">(.*?)</h1>')
if '(' in r['title']:
r['year'] = findRe(r['title'], '\((\d*?)\)')
r['title'] = re.sub('\((\d*?)\)', '', r['title']).strip()
r['synopsis'] = findRe(data, '<span id="movie_synopsis_all".*?>(.*?)</span>')
r['average rating'] = findRe(data, '<div id="bubble_allCritics".*?>(.*?)</div>').strip()
return r

32
oxweb/tv.py Normal file
View file

@ -0,0 +1,32 @@
# -*- 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 getEpisodeData(url):
'''
prases informatin on tvcom episode pages
returns dict with title, show, description, score
example:
getEpisodeData('http://www.tv.com/lost/do-no-harm/episode/399310/summary.html')
'''
data = getUrlUnicode(url)
r = {}
r['description'] = findRe(data, 'div id="main-col">.*?<div>(.*?)</div').split('\r')[0]
r['show'] = findRe(data, '<h1>(.*?)</h1>')
r['title'] = findRe(data, '<title>.*?: (.*?) - TV.com </title>')
#episode score
r['episode score'] = findRe(data, '<span class="f-28 f-bold mt-10 mb-10 f-FF9 db lh-18">(.*?)</span>')
match = re.compile('Episode Number: (\d*?) &nbsp;&nbsp; Season Num: (\d*?) &nbsp;&nbsp; First Aired: (.*?) &nbsp').findall(data)
if match:
r['season'] = int(match[0][1])
r['episode'] = int(match[0][0])
#'Wednesday September 29, 2004' -> 2004-09-29
r['air date'] = time.strftime('%Y-%m-%d', time.strptime(match[0][2], '%A %B %d, %Y'))
return r

View file

@ -17,7 +17,7 @@ setup(
packages=find_packages(), packages=find_packages(),
zip_safe=False, zip_safe=False,
install_requires=[ install_requires=[
'oxutils', 'oxlib',
'feedparser', 'feedparser',
'beautifulsoup', 'beautifulsoup',
], ],