def get_aggregated_feed(_id):
"""
Aggregates feeds give a list of pages and their ids.
Input: A list of tuples
Output: Combined list of posts sorted by timestamp
"""
page_data = get_feed(_id)
for data_dict in page_data:
data_dict['source'] = _id
# data.extend(page_data)
page_data.sort(key=lambda x: parse(x['created_time']), reverse=True)
page_data = prettify_date(page_data)
parser = commonregex.CommonRegex()
for post in page_data:
if 'message' not in post:
# adding dummy message so if a post have no text in it send message
# will not give error
post['message'] = ""
page_data = remove_duplicates(page_data)
page_data.sort(key=lambda x: parse(x['created_time']), reverse=True)
#
json.dump(page_data, open('{}.json'.format(_id), 'w'))
return page_data[0]['id']
def get_aggregated_feed(_id, log):
"""
Aggregates feeds give a list of pages and their ids.
Input: A list of tuples
Output: Combined list of posts sorted by timestamp
"""
#data = list()
#for page_name, _id in pages:
global logger
logger = log
page_data = get_feed(_id)
for data_dict in page_data:
data_dict['source'] = _id
# data.extend(page_data)
page_data.sort(key=lambda x: parse(x['created_time']), reverse=True)
page_data = prettify_date(page_data)
parser = commonregex.CommonRegex()
for post in page_data:
if 'message' in post:
# post['message'] = fixnewlines(post['message'])
if 'flag' not in post:
post['message'] = enable_links(post['message'], parser)
post['flag'] = 1
else:
post[
'message'] = "" #adding dummy message so if a post have no text in it send message will not give error
page_data = remove_duplicates(page_data)
page_data.sort(key=lambda x: parse(x['created_time']), reverse=True)
#
json.dump(page_data, open('FB/page_json/{}.json'.format(_id), 'w'))
return page_data[0]['id']
def validate_args(arg):
"""Validate command line arguments."""
parser = commonregex.CommonRegex()
if not re.search('(?ix) \A [a-z0-9-\.]+ \Z', str(arg.domain)):
raise TypeError("Invalid domain name.")
if not re.search('(?ix) \A [a-z0-9-]+ \Z', str(arg.record)):
raise TypeError("Invalid record.")
return
def enable_links(message):
parser = commonregex.CommonRegex()
links = parser.links(message)
links = list(set(links))
url_identifier = ["www","http","bit.ly",".com",".co.in"]
for link in links:
flag = 0
for keyword in url_identifier :
if keyword in link :
flag = 1
break
if flag is 0 :
break
http_link = link
if not link.startswith('http'):
http_link = "http://{}".format(link)
if len(link) < 25:
link = link[0:25]
message = message.replace(link, " <a href=\"{}\" target=\"_blank\"> {} </a> ".format(http_link, link) , 1)
else:
# message = shortify_string(message)
message = message.replace(link, " <a href=\"{}\" target=\"_blank\"> {} </a> ".format(http_link, link[0:25]+"...") ,1 )
return message
import json
from django.utils.encoding import smart_str
from jinja2 import Template
import commonregex
parser = commonregex.CommonRegex()
def fixnewlines(message):
return message.replace('\n', ' <br> ')
# def shortify_string(message):
# message = message.split(" ")
# new_message = ""
# for mess in message :
# if len(mess) > 25 :
# mess = " <a href='" + mess + "' target='_blank'> " + mess[0:25] + "... </a> "
# new_message = new_message + mess + " "
# return new_message
def truncate(message, length):
while length < len(message):
if message[length] == " ":
return message[0:length]
length = length + 1
return message[0:len(message) - 1]
