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
|
# import htmlentitydefs
from codecs import getincrementalencoder
from HTMLParser import HTMLParser
from random import choice
import cStringIO
import csv
import os
import re
ua_versions = ('26.0', '27.0', '28.0')
ua_os = ('Windows NT 6.3; WOW64',
'X11; Linux x86_64',
'X11; Linux x86')
ua = "Mozilla/5.0 ({os}) Gecko/20100101 Firefox/{version}"
def gen_useragent():
# TODO
return ua.format(os=choice(ua_os), version=choice(ua_versions))
def searx_useragent():
return 'searx'
def highlight_content(content, query):
if not content:
return None
# ignoring html contents
# TODO better html content detection
if content.find('<') != -1:
return content
query = query.decode('utf-8')
if content.lower().find(query.lower()) > -1:
query_regex = u'({0})'.format(re.escape(query))
content = re.sub(query_regex, '<span class="highlight">\\1</span>',
content, flags=re.I | re.U)
else:
regex_parts = []
for chunk in query.split():
if len(chunk) == 1:
regex_parts.append(u'\W+{0}\W+'.format(re.escape(chunk)))
else:
regex_parts.append(u'{0}'.format(re.escape(chunk)))
query_regex = u'({0})'.format('|'.join(regex_parts))
content = re.sub(query_regex, '<span class="highlight">\\1</span>',
content, flags=re.I | re.U)
return content
class HTMLTextExtractor(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.result = []
def handle_data(self, d):
self.result.append(d)
def handle_charref(self, number):
if number[0] in (u'x', u'X'):
codepoint = int(number[1:], 16)
else:
codepoint = int(number)
self.result.append(unichr(codepoint))
def handle_entityref(self, name):
# codepoint = htmlentitydefs.name2codepoint[name]
# self.result.append(unichr(codepoint))
self.result.append(name)
def get_text(self):
return u''.join(self.result)
def html_to_text(html):
s = HTMLTextExtractor()
s.feed(html)
return s.get_text()
class UnicodeWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = getincrementalencoder(encoding)()
def writerow(self, row):
unicode_row = []
for col in row:
if type(col) == str or type(col) == unicode:
unicode_row.append(col.encode('utf-8').strip())
else:
unicode_row.append(col)
self.writer.writerow(unicode_row)
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and reencode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
for row in rows:
self.writerow(row)
def get_themes(root):
"""Returns available themes list."""
static_path = os.path.join(root, 'static')
static_names = set(os.listdir(static_path))
templates_path = os.path.join(root, 'templates')
templates_names = set(os.listdir(templates_path))
themes = []
for name in static_names.intersection(templates_names):
themes += [name]
return static_path, templates_path, themes
|
