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 import MySQLdb | 16 import MySQLdb |
17 import os | 17 import os |
18 import re | 18 import re |
19 import subprocess | 19 import subprocess |
20 from sitescripts.utils import cached, get_config | 20 from sitescripts.utils import cached, get_config |
21 | 21 |
22 | 22 |
23 @cached(600) | 23 @cached(600) |
24 def _get_db(): | 24 def _get_db(): |
25 database = get_config().get("crawler", "database") | 25 database = get_config().get('crawler', 'database') |
26 dbuser = get_config().get("crawler", "dbuser") | 26 dbuser = get_config().get('crawler', 'dbuser') |
27 dbpasswd = get_config().get("crawler", "dbpassword") | 27 dbpasswd = get_config().get('crawler', 'dbpassword') |
28 if os.name == "nt": | 28 if os.name == 'nt': |
29 return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database, | 29 return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database, |
30 use_unicode=True, charset="utf8", named_pipe=True
) | 30 use_unicode=True, charset='utf8', named_pipe=True
) |
31 else: | 31 else: |
32 return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database, | 32 return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database, |
33 use_unicode=True, charset="utf8") | 33 use_unicode=True, charset='utf8') |
34 | 34 |
35 | 35 |
36 def _get_cursor(): | 36 def _get_cursor(): |
37 return _get_db().cursor(MySQLdb.cursors.DictCursor) | 37 return _get_db().cursor(MySQLdb.cursors.DictCursor) |
38 | 38 |
39 | 39 |
40 def _hg(args): | 40 def _hg(args): |
41 return subprocess.check_output(["hg"] + args) | 41 return subprocess.check_output(['hg'] + args) |
42 | 42 |
43 | 43 |
44 def _extract_sites(easylist_dir): | 44 def _extract_sites(easylist_dir): |
45 os.chdir(easylist_dir) | 45 os.chdir(easylist_dir) |
46 process = _hg(["log", "--template", "{desc}\n"]) | 46 process = _hg(['log', '--template', '{desc}\n']) |
47 urls = set([]) | 47 urls = set([]) |
48 | 48 |
49 for line in process.stdout: | 49 for line in process.stdout: |
50 match = re.search(r"\b(https?://\S*)", line) | 50 match = re.search(r'\b(https?://\S*)', line) |
51 if not match: | 51 if not match: |
52 continue | 52 continue |
53 | 53 |
54 url = match.group(1).strip() | 54 url = match.group(1).strip() |
55 urls.add(url) | 55 urls.add(url) |
56 | 56 |
57 return urls | 57 return urls |
58 | 58 |
59 | 59 |
60 def _insert_sites(site_urls): | 60 def _insert_sites(site_urls): |
61 cursor = _get_cursor() | 61 cursor = _get_cursor() |
62 for url in site_urls: | 62 for url in site_urls: |
63 cursor.execute("INSERT IGNORE INTO crawler_sites (url) VALUES (%s)", url
) | 63 cursor.execute('INSERT IGNORE INTO crawler_sites (url) VALUES (%s)', url
) |
64 _get_db().commit() | 64 _get_db().commit() |
65 | 65 |
66 if __name__ == "__main__": | 66 if __name__ == '__main__': |
67 easylist_dir = get_config().get("crawler", "easylist_repository") | 67 easylist_dir = get_config().get('crawler', 'easylist_repository') |
68 site_urls = _extract_sites(easylist_dir) | 68 site_urls = _extract_sites(easylist_dir) |
69 _insert_sites(site_urls) | 69 _insert_sites(site_urls) |
OLD | NEW |