def getNewsElements(categories):
news_client=gnewsclient()
news_client.query='';
if categories['newstype'] != None:
news_client.query += categories['newstype'] + ' '
if categories['location'] !=None:
news_client.query += categories['location']
news_items = news_client.get_news()
elements = []
cnt=0
for item in news_items:
cnt =cnt +1
element = {
'type': 'web_url',
'title': item['title'],
'url': item['link']
}
elements.append(element)
if cnt == 3:
break
return elements
#print(getNewsElements(wit_response("show me entertainment news of india")))
def get_news_elements(categories):
news_client = gnewsclient()
news_client.query = ''
if categories['newstype'] != None:
news_client.query += categories['newstype'] + ' '
if categories['location'] != None:
news_client.query += categories['location']
news_items = news_client.get_news()
elements = []
for item in news_items:
element = {
'title':
item['title'],
'buttons': [{
'type': 'web_url',
'title': "Read more",
'url': item['link']
}],
'image_url':
item['img']
}
elements.append(element)
return elements
#print(get_news_elements(wit_response('I want sport news from india')))
def get_news_elements(categories):
news_client=gnewsclient()
news_client.query=''
if categories['newstypes'] != None:
news_client.query += categories['newstypes']+' '
if categories['location'] != None:
news_client.query += categories['location']
return news_client.query
news_items=news_client.get_news()
elements=[]
for item in news_items:
element={
'title':item['title']
'buttons':[{
'type':'web_url',
'title':'Read more',
'url':item['link'],
}],
'image_url':item['img']
elements.append(element)
}
def get_news_elements(categories):
news_client = gnewsclient()
news_client.query = ''
if categories['location'] != None:
news_client.query += categories['location']
if categories['newstype'] != None:
news_client.query += categories['newstype'] + ' '
news_items = news_client.get_news()
elements = []
if news_items is NoneType:
return elements.append('naita')
else:
for item in news_items:
element = {
'title':
item['title'],
'buttons': [{
'type': 'web_url',
'title': "Read more",
'url': item['link']
}],
'image_url':
item['img']
}
elements.append(element)
return elements
def get_news_elements(categories):
news_client = gnewsclient()
news_client.query = ''
if categories['newstype'] != None:
news_client.query += categories['newstype']
if categories['location'] != None:
news_client.query += categories['location']
news_item = news_client.get_news()
elements = []
pprint(categories)
for item in news_item:
element = {
'title':
item['title'],
'buttons': [{
'type': 'web_url',
'url': item['link'],
'title': 'Read More'
}],
'image_url':
item['img']
}
elements.append(element)
return elements
def getNewsElements(categories):
news_client=gnewsclient()
news_client.query='';
if categories['newstype'] != None:
news_client.query += categories['newstype'] + ' '
if categories['location'] !=None:
news_client.query += categories['location']
news_items = news_client.get_news()
elements = []
for item in news_items:
element = {
'title': item['title'],
'buttons': [{
'type': 'web_url',
'title': "Read more",
'url': item['link']
}],
'image_url': item['img']
}
elements.append(element)
return elements
#print(wiki_search('aligarh'))
#=print(wiki_search("mallika sherawat"))
#print(wit_response("show me sports news of usa"))
#print(getNewsElements(wit_response("show me news of USA")))
def __init__(self, name):
self.name = name
self.sia = SentimentIntensityAnalyzer()
self.custom_words = dict()
self.article_list = []
self.sentiment = float()
self.gNews = gnewsclient()
self._update_vader()
records = json.loads(df.T.to_json()).values() #将csv转化为json
print("No account data in MongoDB, attempting to insert", len(records),
"records")
try:
country.insert_many(records) #将记录存到mongodb中的表accounts中
except pymongo.errors.BulkWriteError as e:
print(e, '\n')
#pass
else:
print("There are already", country.count(),
"records in the *country* table")
country_account = country.distinct('country') #此处handle是唯一标识
print(country_account)
client = gnewsclient()
R_contents = []
# print(client.get_config())
# fields = 'title link img'.split()
fields = 'title link'.split()
for keyword in country_account[79:]:
client.query = keyword
R_contents = client.get_news()
'''{'title': "No, the war in Afghanistan isn't a hopeless stalemate - The Conversation US", 'link': 'http://theconversation.com/no-the-war-in-afghanistan-isnt-a-hopeless-stalemate-91130', 'img': 'https://t0.gstatic.com/images?q=tbn:ANd9GcR2MX5jyRM7MWMX_BJkY2hOw_c7hADknZkB5vtQUs0yyOS-VCRrB_VnuN_Mz5en2Db5vQ3WQD1s9Q'}
{'title': 'Procession, funeral planned for northern Colorado soldier killed in ... - FOX31 Denver', 'link': 'http://kdvr.com/2018/05/10/procession-funeral-planned-for-northern-colorado-soldier-killed-in-afghanistan/', 'img': 'https://t2.gstatic.com/images?q=tbn:ANd9GcS5o0KAHkUwV-bfPDXgA69-cJEB-tLPLNeAfwsxjxTLxndCfoYMbYufotOYpcLN1nshKZnf2LI'}
{'title' '''
'''
for i in R_contents:
print(i)
'''
import mq
import redis
import time
from gnewsclient import gnewsclient
import yaml
import os
r = redis.Redis()
CONFIG_PATH = "."
with open(os.path.join(CONFIG_PATH, "config.yml")) as cf:
variables = yaml.load(cf, Loader=yaml.FullLoader)
COMPANY_NAME = variables['COMPANY_NAME']
g = gnewsclient(query=COMPANY_NAME)
def process(news):
news_as_set = []
for i in news:
news_as_set.append(i['title'] + "#$#$#$" + i['releasedAt'])
return set(news_as_set)
setA = set()
while True:
news = g.get_news()
setB = process(news)
new_news = setB - setA
print(f"Retrieved {len(new_news)} new articles")
