| OLD | NEW |
| 1 # This file is part of the Adblock Plus web scripts, | 1 # This file is part of the Adblock Plus web scripts, |
| 2 # Copyright (C) 2006-2016 Eyeo GmbH | 2 # Copyright (C) 2006-2016 Eyeo GmbH |
| 3 # | 3 # |
| 4 # Adblock Plus is free software: you can redistribute it and/or modify | 4 # Adblock Plus is free software: you can redistribute it and/or modify |
| 5 # it under the terms of the GNU General Public License version 3 as | 5 # it under the terms of the GNU General Public License version 3 as |
| 6 # published by the Free Software Foundation. | 6 # published by the Free Software Foundation. |
| 7 # | 7 # |
| 8 # Adblock Plus is distributed in the hope that it will be useful, | 8 # Adblock Plus is distributed in the hope that it will be useful, |
| 9 # but WITHOUT ANY WARRANTY; without even the implied warranty of | 9 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 # GNU General Public License for more details. | 11 # GNU General Public License for more details. |
| 12 # | 12 # |
| 13 # You should have received a copy of the GNU General Public License | 13 # You should have received a copy of the GNU General Public License |
| 14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. | 14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. |
| 15 | 15 |
| 16 """ |
| 17 This script produces the list of top correct domain names currently in the |
| 18 database. |
| 19 """ |
| 20 |
| 16 import sys | 21 import sys |
| 17 import os | 22 import os |
| 18 import re | 23 import re |
| 19 import math | 24 import math |
| 20 import MySQLdb | 25 import MySQLdb |
| 21 from sitescripts.utils import get_config, setupStderr | 26 from sitescripts.utils import get_config, setupStderr |
| 22 | 27 |
| 23 ''' | |
| 24 This script produces the list of top correct domain names currently in the | |
| 25 database. | |
| 26 ''' | |
| 27 | |
| 28 STATUS_TYPED = 1 | 28 STATUS_TYPED = 1 |
| 29 STATUS_TYPO = 2 | 29 STATUS_TYPO = 2 |
| 30 STATUS_CORRECTION = 3 | 30 STATUS_CORRECTION = 3 |
| 31 STATUS_FALSE_POSITIVE = 4 | 31 STATUS_FALSE_POSITIVE = 4 |
| 32 | 32 |
| 33 | 33 |
| 34 def getTopDomains(count=5000): | 34 def getTopDomains(count=5000): |
| 35 db = _get_db() | 35 db = _get_db() |
| 36 cursor = db.cursor(MySQLdb.cursors.DictCursor) | 36 cursor = db.cursor(MySQLdb.cursors.DictCursor) |
| 37 cursor.execute('SELECT id, domain, forceinclusion FROM domains') | 37 cursor.execute('SELECT id, domain, forceinclusion FROM domains') |
| (...skipping 55 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
| 93 else: | 93 else: |
| 94 return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database, | 94 return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database, |
| 95 use_unicode=True, charset='utf8') | 95 use_unicode=True, charset='utf8') |
| 96 | 96 |
| 97 if __name__ == '__main__': | 97 if __name__ == '__main__': |
| 98 setupStderr() | 98 setupStderr() |
| 99 | 99 |
| 100 domains = getTopDomains() | 100 domains = getTopDomains() |
| 101 for domain in domains: | 101 for domain in domains: |
| 102 print domain.encode('utf-8') | 102 print domain.encode('utf-8') |
| OLD | NEW |