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
|
#!/usr/bin/env python
"""
search.py - Phenny Web Search Module
Copyright 2008-9, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
"""
import re
import web
class Grab(web.urllib.URLopener):
def __init__(self, *args):
self.version = 'Mozilla/5.0 (Phenny)'
web.urllib.URLopener.__init__(self, *args)
self.addheader('Referer', 'https://github.com/sbp/phenny')
def http_error_default(self, url, fp, errcode, errmsg, headers):
return web.urllib.addinfourl(fp, [headers, errcode], "http:" + url)
def search(query):
"""Search using AjaxSearch, and return its JSON."""
uri = 'http://ajax.googleapis.com/ajax/services/search/web'
args = '?v=1.0&safe=off&q=' + web.urllib.quote(query.encode('utf-8'))
handler = web.urllib._urlopener
web.urllib._urlopener = Grab()
bytes = web.get(uri + args)
web.urllib._urlopener = handler
return web.json(bytes)
def result(query):
results = search(query)
try: return results['responseData']['results'][0]['unescapedUrl']
except IndexError: return None
except TypeError:
print results
return False
def count(query):
results = search(query)
if not results.has_key('responseData'): return '0'
if not results['responseData'].has_key('cursor'): return '0'
if not results['responseData']['cursor'].has_key('estimatedResultCount'):
return '0'
return results['responseData']['cursor']['estimatedResultCount']
def formatnumber(n):
"""Format a number with beautiful commas."""
parts = list(str(n))
for i in range((len(parts) - 3), 0, -3):
parts.insert(i, ',')
return ''.join(parts)
def g(phenny, input):
"""Queries Google for the specified input."""
query = input.group(2)
if not query:
return phenny.reply('.g what?')
uri = result(query)
if uri:
phenny.reply(uri)
if not hasattr(phenny.bot, 'last_seen_uri'):
phenny.bot.last_seen_uri = {}
phenny.bot.last_seen_uri[input.sender] = uri
elif uri is False: phenny.reply("Problem getting data from Google.")
else: phenny.reply("No results found for '%s'." % query)
g.commands = ['g']
g.priority = 'high'
g.example = '.g swhack'
def gc(phenny, input):
"""Returns the number of Google results for the specified input."""
query = input.group(2)
if not query:
return phenny.reply('.gc what?')
num = formatnumber(count(query))
phenny.say(query + ': ' + num)
gc.commands = ['gc']
gc.priority = 'high'
gc.example = '.gc extrapolate'
r_query = re.compile(
r'\+?"[^"\\]*(?:\\.[^"\\]*)*"|\[[^]\\]*(?:\\.[^]\\]*)*\]|\S+'
)
def gcs(phenny, input):
if not input.group(2):
return phenny.reply("Nothing to compare.")
queries = r_query.findall(input.group(2))
if len(queries) > 6:
return phenny.reply('Sorry, can only compare up to six things.')
results = []
for i, query in enumerate(queries):
query = query.strip('[]')
n = int((formatnumber(count(query)) or '0').replace(',', ''))
results.append((n, query))
if i >= 2: __import__('time').sleep(0.25)
if i >= 4: __import__('time').sleep(0.25)
results = [(term, n) for (n, term) in reversed(sorted(results))]
reply = ', '.join('%s (%s)' % (t, formatnumber(n)) for (t, n) in results)
phenny.say(reply)
gcs.commands = ['gcs', 'comp']
r_bing = re.compile(r'<h3><a href="([^"]+)"')
def bing(phenny, input):
"""Queries Bing for the specified input."""
query = input.group(2)
if query.startswith(':'):
lang, query = query.split(' ', 1)
lang = lang[1:]
else: lang = 'en-GB'
if not query:
return phenny.reply('.bing what?')
query = web.urllib.quote(query.encode('utf-8'))
base = 'http://www.bing.com/search?mkt=%s&q=' % lang
bytes = web.get(base + query)
m = r_bing.search(bytes)
if m:
uri = m.group(1)
phenny.reply(uri)
if not hasattr(phenny.bot, 'last_seen_uri'):
phenny.bot.last_seen_uri = {}
phenny.bot.last_seen_uri[input.sender] = uri
else: phenny.reply("No results found for '%s'." % query)
bing.commands = ['bing']
bing.example = '.bing swhack'
r_ddg = re.compile(r'nofollow" class="[^"]+" href="(.*?)">')
def ddg(phenny, input):
query = input.group(2)
if not query: return phenny.reply('.ddg what?')
query = web.urllib.quote(query.encode('utf-8'))
uri = 'http://duckduckgo.com/html/?q=%s&kl=uk-en' % query
bytes = web.get(uri)
m = r_ddg.search(bytes)
if m:
uri = m.group(1)
phenny.reply(uri)
if not hasattr(phenny.bot, 'last_seen_uri'):
phenny.bot.last_seen_uri = {}
phenny.bot.last_seen_uri[input.sender] = uri
else: phenny.reply("No results found for '%s'." % query)
ddg.commands = ['ddg']
if __name__ == '__main__':
print __doc__.strip()
|
