/usr/lib/python2.7/dist-packages/imdb/parser/http/topBottomParser.py is in python-imdbpy 4.8.2-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | """
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)
}
|