from boto3.dynamodb.conditions import Key
from extractor.query import Query
from utils.utils import parseTime
an_hour = 60 * 60
default_start_time = parseTime("03-03-2016 12:00")
class ByHourQuery(Query):
def __init__(self,
tag,
limit=100,
plugins=[],
start_time=default_start_time,
interval=an_hour):
super(self.__class__, self).__init__(tag, limit, plugins)
self.limit = None
self.filter = None
self.start_time = start_time
self.start_timestamp = start_time
self.interval = interval
self.send_timestamp = self.start_timestamp + self.interval
self.conditions = self.conditions & Key('timestamp').between(
self.start_timestamp, self.send_timestamp)
def get_results(self):
self._query_()
while self.lastKey and (self.resultCount < self.limit):
self._query_()
return self.restructured()
from boto3.dynamodb.conditions import Key
from extractor.query import Query
from utils.utils import parseTime
an_hour = 60 * 60
default_start_time = parseTime("03-03-2016 12:00")
class ByHourQuery(Query):
def __init__(self, tag, limit=100, plugins=[], start_time=default_start_time, interval=an_hour):
super(self.__class__, self).__init__(tag, limit, plugins)
self.limit = None
self.filter = None
self.start_time = start_time
self.start_timestamp = start_time
self.interval = interval
self.send_timestamp = self.start_timestamp + self.interval
self.conditions = self.conditions & Key('timestamp').between(self.start_timestamp, self.send_timestamp)
def get_results(self):
self._query_()
while self.lastKey and (self.resultCount < self.limit):
self._query_()
return self.restructured()
{'start': '2015-08-1', 'end': '2015-09-1'},
{'start': '2015-11-1', 'end': '2016-12-1'}
]
places = [
{'name': "NewYork", 'id': ".skCPTpTVr.Q3WKW"},
{'name': "Boston", 'id': "5MvaTZJTUbx1uPnP"},
{'name': "Beijing", 'id': "vQ6vOjpTU7_QE6S8"},
{'name': "Hongkong", 'id': "JAJiM7JTU78IjzqC"}
]
results = {}
for place in places:
place_results = results[place.get('name')] = {}
for time in times:
query = Flickr({
'place_id': place.get('id'),
'sort': 'interestingness-desc',
'per_page': 100,
# 'text': 'landscape',
'min_taken_date': parseTime(time.get('start')),
'max_taken_date': parseTime(time.get('end'))
})
# place_results[time.get('start')] = query.results
# The above yields a lot of unused json. Below just the title, and image url.
place_results[time.get('start')] = [{'title': r.get('title'),'url': r.get('url')} for r in query.results]
with open("kini.json", 'w') as outfile:
json.dump(results, outfile, indent=4, sort_keys=True)
