|
a |
|
b/OSSEval/IMDBMovieApp/imdb.py |
|
|
1 |
# This Source Code Form of OSSEval is subject to the terms of the GNU AFFERO
|
|
|
2 |
# GENERAL PUBLIC LICENSE, v. 3.0. If a copy of the AGPL was not
|
|
|
3 |
# distributed with this file, You can obtain one at http://www.gnu.org/licenses/agpl.txt
|
|
|
4 |
#
|
|
|
5 |
# OSSeval is powered by the SOS Open Source AGPL edition.
|
|
|
6 |
# The AGPL requires that you do not remove the SOS Open Source attribution and copyright
|
|
|
7 |
# notices from the user interface (see section 5.d below).
|
|
|
8 |
|
|
|
9 |
# OSSEval Copyright 2014 Bitergium SLL
|
|
|
10 |
# SOS Open Source Copyright 2012 Roberto Galoppini
|
|
|
11 |
# Author: Davide Galletti
|
|
|
12 |
|
|
|
13 |
from xml.dom import minidom
|
|
|
14 |
from OSSEval.utils import TrivialJSONEncoder
|
|
|
15 |
import json
|
|
|
16 |
import urllib2
|
|
|
17 |
from lxml import html
|
|
|
18 |
from IMDBMovieApp.models import IMDBMovie
|
|
|
19 |
|
|
|
20 |
class IMDBProxy():
|
|
|
21 |
|
|
|
22 |
@staticmethod
|
|
|
23 |
def search(title):
|
|
|
24 |
print "IMDB searching for " + title
|
|
|
25 |
movie_list = []
|
|
|
26 |
all_results = []
|
|
|
27 |
# s=tt to search on titles
|
|
|
28 |
# q=berlin+wall searches both words
|
|
|
29 |
url_imdb = "http://www.imdb.com/xml/find?json=1&s=tt&q=" + title.replace(" ", "+")
|
|
|
30 |
response = urllib2.urlopen(url_imdb)
|
|
|
31 |
imdb_json = response.read()
|
|
|
32 |
try:
|
|
|
33 |
# if the result is exaclty one movie instead of sending back json as requested
|
|
|
34 |
# they might send the html page of the movie and json load fails
|
|
|
35 |
decoded = json.loads(imdb_json)
|
|
|
36 |
# look for results in title_approx , title_substring , title_exact, title_popular
|
|
|
37 |
if 'title_exact' in decoded.keys():
|
|
|
38 |
all_results += decoded['title_exact']
|
|
|
39 |
if 'title_substring' in decoded.keys():
|
|
|
40 |
all_results += decoded['title_substring']
|
|
|
41 |
if 'title_approx' in decoded.keys():
|
|
|
42 |
all_results += decoded['title_approx']
|
|
|
43 |
if 'title_popular' in decoded.keys():
|
|
|
44 |
all_results += decoded['title_popular']
|
|
|
45 |
for movie in all_results:
|
|
|
46 |
m = IMDBMovie()
|
|
|
47 |
m.imdb_id = movie['id']
|
|
|
48 |
m.title = movie['title']
|
|
|
49 |
m.description = movie['description']
|
|
|
50 |
movie_list.append(m)
|
|
|
51 |
except:
|
|
|
52 |
# it might be an html page with just one movie
|
|
|
53 |
imdb_html = imdb_json
|
|
|
54 |
tree = html.fromstring(imdb_html)
|
|
|
55 |
m = IMDBMovie()
|
|
|
56 |
# <meta property="og:url" content="http://www.imdb.com/title/tt0072684/" />
|
|
|
57 |
url = tree.xpath('//meta[@property="og:url"]')[0].get('content')
|
|
|
58 |
url = url[:-1]
|
|
|
59 |
m.imdb_id = url[url.rfind("/")+1:]
|
|
|
60 |
m.title = tree.xpath('//meta[@property="og:title"]')[0].get('content')
|
|
|
61 |
m.description = tree.xpath('//meta[@property="og:description"]')[0].get('content')
|
|
|
62 |
movie_list.append(m)
|
|
|
63 |
|
|
|
64 |
return movie_list
|
|
|
65 |
|
|
|
66 |
@staticmethod
|
|
|
67 |
def getMovieInfo(project_identifier):
|
|
|
68 |
### perche' ho questo e ho anche IMDBMovie.getInstanceInfo ?
|
|
|
69 |
url_ohloh = "http://www.openhub.net/projects/" + project_identifier + ".xml?api_key=" + Configuration.api_key
|
|
|
70 |
xml = UrllibHelper.urlopen(url_ohloh)
|
|
|
71 |
xmldoc = minidom.parseString(xml)
|
|
|
72 |
info = {}
|
|
|
73 |
|
|
|
74 |
status = xmlElements(xmldoc.getElementsByTagName('status')).firstValue()
|
|
|
75 |
if status == 'success':
|
|
|
76 |
info['id'] = project_identifier
|
|
|
77 |
|
|
|
78 |
return info
|
|
|
79 |
|
|
|
80 |
|