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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
|
#!/usr/bin/env python
"""
wikipedia.py - Phenny Wikipedia Module
Copyright 2008-9, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
"""
import re, urllib
import web
wikiuri = 'http://en.wikipedia.org/wiki/%s'
wikisearch = 'http://en.wikipedia.org/wiki/Special:Search?' \
+ 'search=%s&fulltext=Search'
r_tr = re.compile(r'(?ims)<tr[^>]*>.*?</tr>')
r_paragraph = re.compile(r'(?ims)<p[^>]*>.*?</p>|<li(?!n)[^>]*>.*?</li>')
r_tag = re.compile(r'<(?!!)[^>]+>')
r_whitespace = re.compile(r'[\t\r\n ]+')
r_redirect = re.compile(
r'(?ims)class=.redirectText.>\s*<a\s*href=./wiki/([^"/]+)'
)
abbrs = ['etc', 'ca', 'cf', 'Co', 'Ltd', 'Inc', 'Mt', 'Mr', 'Mrs',
'Dr', 'Ms', 'Rev', 'Fr', 'St', 'Sgt', 'pron', 'approx', 'lit',
'syn', 'transl', 'sess', 'fl', 'Op'] \
+ list('ABCDEFGHIJKLMNOPQRSTUVWXYZ') \
+ list('abcdefghijklmnopqrstuvwxyz')
t_sentence = r'^.{5,}?(?<!\b%s)(?:\.(?=[\[ ][A-Z0-9]|\Z)|\Z)'
r_sentence = re.compile(t_sentence % r')(?<!\b'.join(abbrs))
def unescape(s):
s = s.replace('>', '>')
s = s.replace('<', '<')
s = s.replace('&', '&')
s = s.replace(' ', ' ')
return s
def text(html):
html = r_tag.sub('', html)
html = r_whitespace.sub(' ', html)
return unescape(html).strip()
def search(term):
try: import search
except ImportError, e:
print e
return term
if isinstance(term, unicode):
term = term.encode('utf-8')
else: term = term.decode('utf-8')
term = term.replace('_', ' ')
try: uri = search.result('site:en.wikipedia.org %s' % term)
except IndexError: return term
if uri:
return uri[len('http://en.wikipedia.org/wiki/'):]
else: return term
def wikipedia(term, last=False):
global wikiuri
if not '%' in term:
if isinstance(term, unicode):
t = term.encode('utf-8')
else: t = term
q = urllib.quote(t)
u = wikiuri % q
bytes = web.get(u)
else: bytes = web.get(wikiuri % term)
bytes = r_tr.sub('', bytes)
if not last:
r = r_redirect.search(bytes[:4096])
if r:
term = urllib.unquote(r.group(1))
return wikipedia(term, last=True)
paragraphs = r_paragraph.findall(bytes)
if not paragraphs:
if not last:
term = search(term)
return wikipedia(term, last=True)
return None
# Pre-process
paragraphs = [para for para in paragraphs
if (para and 'technical limitations' not in para
and 'window.showTocToggle' not in para
and 'Deletion_policy' not in para
and 'Template:AfD_footer' not in para
and not (para.startswith('<p><i>') and
para.endswith('</i></p>'))
and not 'disambiguation)"' in para)
and not '(images and media)' in para
and not 'This article contains a' in para
and not 'id="coordinates"' in para
and not 'class="thumb' in para]
# and not 'style="display:none"' in para]
for i, para in enumerate(paragraphs):
para = para.replace('<sup>', '|')
para = para.replace('</sup>', '|')
paragraphs[i] = text(para).strip()
# Post-process
paragraphs = [para for para in paragraphs if
(para and not (para.endswith(':') and len(para) < 150))]
para = text(paragraphs[0])
m = r_sentence.match(para)
if not m:
if not last:
term = search(term)
return wikipedia(term, last=True)
return None
sentence = m.group(0)
maxlength = 275
if len(sentence) > maxlength:
sentence = sentence[:maxlength]
words = sentence[:-5].split(' ')
words.pop()
sentence = ' '.join(words) + ' [...]'
if (('using the Article Wizard if you wish' in sentence)
or ('or add a request for it' in sentence)):
if not last:
term = search(term)
return wikipedia(term, last=True)
return None
sentence = '"' + sentence.replace('"', "'") + '"'
sentence = sentence.decode('utf-8').encode('utf-8')
wikiuri = wikiuri.decode('utf-8').encode('utf-8')
term = term.decode('utf-8').encode('utf-8')
return sentence + ' - ' + (wikiuri % term)
def wik(phenny, input):
origterm = input.groups()[1]
if not origterm:
return phenny.say('Perhaps you meant ".wik Zen"?')
origterm = origterm.encode('utf-8')
term = urllib.unquote(origterm)
term = term[0].upper() + term[1:]
term = term.replace(' ', '_')
try: result = wikipedia(term)
except IOError:
error = "Can't connect to en.wikipedia.org (%s)" % (wikiuri % term)
return phenny.say(error)
if result is not None:
phenny.say(result)
else: phenny.say('Can\'t find anything in Wikipedia for "%s".' % origterm)
wik.commands = ['wik']
wik.priority = 'high'
if __name__ == '__main__':
print __doc__.strip()
|