def __init__(self, **kwarg):
self.dbName = kwarg['dbName']
self.colName = kwarg['collectionName']
self.IP = kwarg['IP']
self.PORT = kwarg['PORT']
self.Prob = .10
self.realtimeNewsURL = []
self.tm = tm.TextMining(IP="10.3.5.58", PORT=27017)
def __init__(self, **kwarg):
self.ThreadsNum = kwarg['ThreadsNum']
self.dbName = kwarg['dbName']
self.colName = kwarg['collectionName']
self.IP = kwarg['IP']
self.PORT = kwarg['PORT']
self.Prob = .5
self.realtimeNewsURL = []
self.tm = tm.TextMining(IP="localhost", PORT=27017)
def __init__(self,*arg,**kwarg):
self.totalPages = arg[0] #totalPages
self.Range = arg[1] #Range
self.ThreadsNum = kwarg['ThreadsNum']
self.dbName = kwarg['dbName']
self.colName = kwarg['collectionName']
self.IP = kwarg['IP']
self.PORT = kwarg['PORT']
self.Porb = .5
self.realtimeNewsURL = []
self.tm = tm.TextMining(IP="localhost",PORT=27017)
def __init__(self, *arg, **kwarg):
self.startDate = arg[0]
self.endDate = arg[1]
self.Range = arg[2]
self.ThreadsNum = kwarg['ThreadsNum']
self.dbName = kwarg['dbName']
self.user = kwarg['user']
self.passwd = kwarg['passwd']
self.colName = kwarg['collectionName']
self.IP = kwarg['IP']
self.PORT = kwarg['PORT']
self.Prob = .5
self.realtimeNewsURL = []
self.tm = tm.TextMining(IP="localhost", PORT=27017)
web_crawl_obj = WebCrawlFromjrj("2009-01-05","2018-02-03",100,ThreadsNum=4,IP="localhost",PORT=27017,\
dbName="Jrj_Stock",collectionName="jrj_news_company")
web_crawl_obj.classifyRealtimeStockNews()
elif web == 'cnstock':
web_crawl_obj = WebCrawlFromcnstock(IP="localhost",PORT=27017,ThreadsNum=4,\
dbName="Cnstock_Stock",collectionName="cnstock_news_company")
web_crawl_obj.classifyRealtimeStockNews()
elif web == 'stcn':
web_crawl_obj = WebCrawlFromstcn(IP="localhost",PORT=27017,ThreadsNum=4,\
dbName="Stcn_Stock",collectionName="stcn_news_company")
web_crawl_obj.classifyRealtimeStockNews()
if __name__ == '__main__':
# Step 1. Initiate
text_mining_obj = tm.TextMining(IP="localhost", PORT=27017)
# Step 2. Extract relevant stock codes of news(articles/documents) from all database
text_mining_obj.extractStockCodeFromArticle(
"NBD_Stock", "nbd_news_company") # 从每经网的新闻中抽出相关的股票代码
text_mining_obj.extractStockCodeFromArticle(
"Cnstock_Stock", "cnstock_news_company") # 从中国证券网的新闻中抽出相关的股票代码
text_mining_obj.extractStockCodeFromArticle(
"Stcn_Stock", "stcn_news_company") # 从证券时报网的新闻中抽出相关的股票代码
text_mining_obj.extractStockCodeFromArticle(
"Jrj_Stock", "jrj_news_company") # 从金融界网的新闻中抽出相关的股票代码
# Step 3. Extract all news related to specific stock to new database(this step will take long time)
codeLst = text_mining_obj.extractData("Stock", "Basic_Info", ['code']).code
Range = 10
Idx = 0