1
0
mirror of https://github.com/moparisthebest/SickRage synced 2024-11-06 01:15:05 -05:00
SickRage/lib/imdb/parser/http/searchCompanyParser.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

72 lines
2.8 KiB
Python

"""
parser.http.searchCompanyParser module (imdb package).
This module provides the HTMLSearchCompanyParser class (and the
search_company_parser instance), used to parse the results of a search
for a given company.
E.g., when searching for the name "Columbia Pictures", the parsed page would be:
http://akas.imdb.com/find?s=co;mx=20;q=Columbia+Pictures
Copyright 2008-2009 Davide Alberani <da@erlug.linux.it>
2008 H. Turgut Uyar <uyar@tekir.org>
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_company_name, build_company_name
from utils import Extractor, Attribute, analyze_imdbid
from searchMovieParser import DOMHTMLSearchMovieParser, DOMBasicMovieParser
class DOMBasicCompanyParser(DOMBasicMovieParser):
"""Simply get the name of a company and the imdbID.
It's used by the DOMHTMLSearchCompanyParser class to return a result
for a direct match (when a search on IMDb results in a single
company, the web server sends directly the company page.
"""
_titleFunct = lambda self, x: analyze_company_name(x or u'')
class DOMHTMLSearchCompanyParser(DOMHTMLSearchMovieParser):
_BaseParser = DOMBasicCompanyParser
_notDirectHitTitle = '<title>imdb company'
_titleBuilder = lambda self, x: build_company_name(x)
_linkPrefix = '/company/co'
_attrs = [Attribute(key='data',
multi=True,
path={
'link': "./a[1]/@href",
'name': "./a[1]/text()",
'notes': "./text()[1]"
},
postprocess=lambda x: (
analyze_imdbid(x.get('link')),
analyze_company_name(x.get('name')+(x.get('notes')
or u''), stripNotes=True)
))]
extractors = [Extractor(label='search',
path="//td[3]/a[starts-with(@href, " \
"'/company/co')]/..",
attrs=_attrs)]
_OBJECTS = {
'search_company_parser': ((DOMHTMLSearchCompanyParser,),
{'kind': 'company', '_basic_parser': DOMBasicCompanyParser})
}