Ponysearch/searx/utils.py

105 lines
2.9 KiB
Python
Raw Normal View History

2013-11-08 23:44:26 +01:00
from HTMLParser import HTMLParser
2013-11-18 16:47:20 +01:00
#import htmlentitydefs
2013-11-15 18:55:18 +01:00
import csv
2014-01-20 02:31:20 +01:00
from codecs import getincrementalencoder
2013-11-15 18:55:18 +01:00
import cStringIO
2014-01-10 23:38:08 +01:00
import re
2014-01-18 21:53:59 +01:00
def gen_useragent():
2014-01-12 20:13:14 +01:00
# TODO
2014-01-20 02:31:20 +01:00
ua = "Mozilla/5.0 (X11; Linux x86_64; rv:26.0) Gecko/20100101 Firefox/26.0"
return ua
2014-01-12 20:13:14 +01:00
2014-01-10 23:38:08 +01:00
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))
content = re.sub(query_regex, '<b>\\1</b>', 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, '<b>\\1</b>', content, flags=re.I | re.U)
return content
2013-11-08 23:44:26 +01:00
2013-11-08 23:44:26 +01:00
class HTMLTextExtractor(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.result = []
2013-11-08 23:44:26 +01:00
def handle_data(self, d):
self.result.append(d)
def handle_charref(self, number):
2014-01-20 02:31:20 +01:00
if number[0] in (u'x', u'X'):
codepoint = int(number[1:], 16)
else:
codepoint = int(number)
2013-11-08 23:44:26 +01:00
self.result.append(unichr(codepoint))
def handle_entityref(self, name):
2013-11-18 16:47:20 +01:00
#codepoint = htmlentitydefs.name2codepoint[name]
#self.result.append(unichr(codepoint))
self.result.append(name)
2013-11-08 23:44:26 +01:00
def get_text(self):
return u''.join(self.result)
2013-11-08 23:44:26 +01:00
def html_to_text(html):
s = HTMLTextExtractor()
s.feed(html)
return s.get_text()
2013-11-15 18:55:18 +01:00
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 02:31:20 +01:00
self.encoder = getincrementalencoder(encoding)()
2013-11-15 18:55:18 +01:00
def writerow(self, row):
2014-01-20 02:31:20 +01:00
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 18:55:18 +01:00
# 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)