SickGear/lib/imdb/parser/http/topBottomParser.py
echel0n 0d9fbc1ad7 Welcome to our SickBeard-TVRage Edition ...
This version of SickBeard uses both TVDB and TVRage to search and gather it's series data from allowing you to now have access to and download shows that you couldn't before because of being locked into only what TheTVDB had to offer.

Also this edition is based off the code we used in our XEM editon so it does come with scene numbering support as well as all the other features our XEM edition has to offer.

Please before using this with your existing database (sickbeard.db) please make a backup copy of it and delete any other database files such as cache.db and failed.db if present, we HIGHLY recommend starting out with no database files at all to make this a fresh start but the choice is at your own risk!

Enjoy!
2014-03-09 22:39:12 -07:00

106 lines
3.8 KiB
Python

"""
parser.http.topBottomParser module (imdb package).
This module provides the classes (and the instances), used to parse the
lists of top 250 and bottom 100 movies.
E.g.:
http://akas.imdb.com/chart/top
http://akas.imdb.com/chart/bottom
Copyright 2009 Davide Alberani <da@erlug.linux.it>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
"""
from imdb.utils import analyze_title
from utils import DOMParserBase, Attribute, Extractor, analyze_imdbid
class DOMHTMLTop250Parser(DOMParserBase):
"""Parser for the "top 250" page.
The page should be provided as a string, as taken from
the akas.imdb.com server. The final result will be a
dictionary, with a key for every relevant section.
Example:
tparser = DOMHTMLTop250Parser()
result = tparser.parse(top250_html_string)
"""
label = 'top 250'
ranktext = 'top 250 rank'
def _init(self):
self.extractors = [Extractor(label=self.label,
path="//div[@id='main']//table//tr",
attrs=Attribute(key=None,
multi=True,
path={self.ranktext: "./td[1]//text()",
'rating': "./td[2]//text()",
'title': "./td[3]//text()",
'movieID': "./td[3]//a/@href",
'votes': "./td[4]//text()"
}))]
def postprocess_data(self, data):
if not data or self.label not in data:
return []
mlist = []
data = data[self.label]
# Avoid duplicates. A real fix, using XPath, is auspicabile.
# XXX: probably this is no more needed.
seenIDs = []
for d in data:
if 'movieID' not in d: continue
if self.ranktext not in d: continue
if 'title' not in d: continue
theID = analyze_imdbid(d['movieID'])
if theID is None:
continue
theID = str(theID)
if theID in seenIDs:
continue
seenIDs.append(theID)
minfo = analyze_title(d['title'])
try: minfo[self.ranktext] = int(d[self.ranktext].replace('.', ''))
except: pass
if 'votes' in d:
try: minfo['votes'] = int(d['votes'].replace(',', ''))
except: pass
if 'rating' in d:
try: minfo['rating'] = float(d['rating'])
except: pass
mlist.append((theID, minfo))
return mlist
class DOMHTMLBottom100Parser(DOMHTMLTop250Parser):
"""Parser for the "bottom 100" page.
The page should be provided as a string, as taken from
the akas.imdb.com server. The final result will be a
dictionary, with a key for every relevant section.
Example:
tparser = DOMHTMLBottom100Parser()
result = tparser.parse(bottom100_html_string)
"""
label = 'bottom 100'
ranktext = 'bottom 100 rank'
_OBJECTS = {
'top250_parser': ((DOMHTMLTop250Parser,), None),
'bottom100_parser': ((DOMHTMLBottom100Parser,), None)
}