searxng/searx/utils.py

171 lines
4.7 KiB
Python
Raw Normal View History

2014-10-19 10:41:04 +00:00
# import htmlentitydefs
2014-01-20 01:31:20 +00:00
from codecs import getincrementalencoder
2014-04-24 23:46:40 +00:00
from HTMLParser import HTMLParser
from random import choice
2014-11-18 10:37:42 +00:00
from searx.version import VERSION_STRING
from searx import settings
2013-11-15 17:55:18 +00:00
import cStringIO
2014-04-24 23:46:40 +00:00
import csv
import os
2014-01-10 22:38:08 +00:00
import re
2014-11-22 17:37:42 +00:00
ua_versions = ('29.0',
'30.0',
'31.0',
'32.0',
'33.0')
2014-05-20 14:55:49 +00:00
ua_os = ('Windows NT 6.3; WOW64',
'X11; Linux x86_64',
'X11; Linux x86')
2014-11-22 17:37:42 +00:00
ua = "Mozilla/5.0 ({os}) Gecko/20100101 Firefox/{version}"
blocked_tags = ('script',
'style')
2014-03-04 18:26:09 +00:00
2014-01-18 20:53:59 +00:00
def gen_useragent():
2014-01-12 19:13:14 +00:00
# TODO
return ua.format(os=choice(ua_os), version=choice(ua_versions))
2014-01-12 19:13:14 +00:00
2014-10-17 10:34:51 +00:00
def searx_useragent():
return 'searx/{searx_version} {suffix}'.format(
searx_version=VERSION_STRING,
suffix=settings['server'].get('useragent_suffix', ''))
2014-10-19 10:41:04 +00:00
2014-01-10 22:38:08 +00:00
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))
2014-05-16 14:51:23 +00:00
content = re.sub(query_regex, '<span class="highlight">\\1</span>',
content, flags=re.I | re.U)
2014-01-10 22:38:08 +00:00
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))
2014-05-16 14:51:23 +00:00
content = re.sub(query_regex, '<span class="highlight">\\1</span>',
content, flags=re.I | re.U)
2014-01-10 22:38:08 +00:00
return content
2013-11-08 22:44:26 +00:00
2013-11-08 22:44:26 +00:00
class HTMLTextExtractor(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.result = []
self.tags = []
def handle_starttag(self, tag, attrs):
self.tags.append(tag)
def handle_endtag(self, tag):
if tag != self.tags[-1]:
raise Exception("invalid html")
self.tags.pop()
def is_valid_tag(self):
return not self.tags or self.tags[-1] not in blocked_tags
2013-11-08 22:44:26 +00:00
def handle_data(self, d):
if not self.is_valid_tag():
return
2013-11-08 22:44:26 +00:00
self.result.append(d)
def handle_charref(self, number):
if not self.is_valid_tag():
return
2014-01-20 01:31:20 +00:00
if number[0] in (u'x', u'X'):
codepoint = int(number[1:], 16)
else:
codepoint = int(number)
2013-11-08 22:44:26 +00:00
self.result.append(unichr(codepoint))
def handle_entityref(self, name):
if not self.is_valid_tag():
return
2014-10-19 10:41:04 +00:00
# codepoint = htmlentitydefs.name2codepoint[name]
# self.result.append(unichr(codepoint))
2013-11-18 15:47:20 +00:00
self.result.append(name)
2013-11-08 22:44:26 +00:00
def get_text(self):
return u''.join(self.result)
2013-11-08 22:44:26 +00:00
def html_to_text(html):
s = HTMLTextExtractor()
s.feed(html)
return s.get_text()
2013-11-15 17:55:18 +00:00
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
2014-01-20 01:31:20 +00:00
self.encoder = getincrementalencoder(encoding)()
2013-11-15 17:55:18 +00:00
def writerow(self, row):
2014-01-20 01:31:20 +00:00
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)
2013-11-15 17:55:18 +00:00
# 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)
2014-04-24 23:46:40 +00:00
def get_themes(root):
"""Returns available themes list."""
static_path = os.path.join(root, 'static')
templates_path = os.path.join(root, 'templates')
2015-01-01 16:48:12 +00:00
themes = os.listdir(os.path.join(static_path, 'themes'))
2014-04-24 23:46:40 +00:00
return static_path, templates_path, themes
2015-01-01 16:48:12 +00:00
def get_static_files(base_path):
static_files = set()
base_path_length = len(base_path+'/static') + 1
for directory, _, files in os.walk(os.path.join(base_path, 'static')):
for filename in files:
f = os.path.join(directory[base_path_length:], filename)
static_files.add(f)
return static_files