Created
April 23, 2014 17:30
-
-
Save x/11225232 to your computer and use it in GitHub Desktop.
getting csv of paths without xys
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def main(): | |
""" | |
[debug-only] | |
""" | |
define("domain", default="theverge.com") | |
define("path", default=None) | |
define("console", default=True, type=bool) | |
define("debug", default=True, type=bool) | |
define("click_through_host", default="localhost") | |
define("minutes", default=5) | |
from datetime import timedelta | |
from action.link_positions.lib.utils import get_path_and_ctr_range | |
read_options(None) | |
basicConfig(options=options) | |
dbs = init_dbs(click_through_host=options.click_through_host, | |
cellar_host='cellarreplicaset09') | |
#domains = ['theverge com'] | |
domains = dbs['cellar_db'].get_newsbeat_domains() | |
ct_db = dbs['click_through_db'] | |
end = datetime.now() | |
start = end - timedelta(minutes=15) | |
for domain in domains: | |
path, _ = get_path_and_ctr_range(domain, '/') | |
docs = ct_db._get_docs(domain, path, start, end) | |
paths = set(doc[TARGET_PATH] for doc in docs) | |
paths_with_xy = set(doc[TARGET_PATH] for doc in docs if doc[LOCATIONS]) | |
if paths: | |
print(','.join(map(str, [domain, path, len(paths), len(paths - paths_with_xy)]))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment