def yahoo(doc2):
doc = doc2.decode(encoding='UTF-8')
idata=[]
empty = ''
lempty = ['']
atype = 'Yahoo Finance'
info = ''
base = 'https://in.finance.yahoo.com'
timey = time.mktime(datetime.datetime.now().timetuple())
soup = BeautifulSoup(doc,"lxml")
gdata = soup.find_all("",{"class":"description"})
#tdata=[]
#ydata=[]
n = len(gdata)
for i in range(0,n):
j=0
#print i, gdata[i].text
#print i, gdata[i].contents
# get href link
lstr = str(gdata[i].contents)
#print lstr
soup2 = BeautifulSoup(lstr,"lxml")
for link in soup2.find_all('a'):
xlink = base+str(link.get('href'))
break
# get info, announ, atype
t1 = 'More'#+str(175)
t2 = 'More'
xstr = ''.join(str(gdata[i].text.encode('ascii', 'ignore')))
xstr2 = ''.join(xstr).split(t1)
#xstr = (str(gdata[i].text.encode('ascii', 'ignore').split(t1)).replace(t2,''))
#print i, xstr2
if xstr2!=['']:
#tdata.append(xstr2[1])# announ
#tdata.append(xstr2[0])# info
#tdata.append(timey) # time stamp
#tdata.append(xlink) # link
idata.append(classes.ticker(xstr2[1],atype,xlink,timey,xstr2[0],0))
#print i, xstr2[0]
#print i, xstr2[1]
if i==50: break # 50 articles in each page
#soup2 = BeautifulSoup(str(gdata))
#tables = soup2.find_all("tr")
idata.sort(key=lambda x: x.time, reverse=True)
return idata[0:classes.ticker.narticles]
def livemint(doc2,id):
doc = doc2.decode(encoding='UTF-8')
atype = 'livemint'+id
feed = feedparser.parse(doc)
i=0
idata = []
for post in feed.entries:
i=i+1
announ = str(post.title.encode('ascii', 'ignore'))
xlink = str(post.link.encode('ascii', 'ignore'))
timestamp = int(time.mktime(post.updated_parsed))
info = str(post.summary.encode('ascii', 'ignore')).split('>')
idata.append(classes.ticker(announ, atype, xlink, timestamp, info[1],0))
idata.sort(key=lambda x: x.time, reverse=True)
return idata[0:classes.ticker.narticles]
def smera(doc2):
doc = doc2.decode(encoding='UTF-8')
atype = 'SMERA'
soup = BeautifulSoup(doc,"lxml")
gdata = soup.find_all("",{"class":"company"})
idata=[]
for items in gdata:
announ = str(items.text).replace('View','')
xlink = str(items.contents[1].get('href'))
timestamp = int(time.time())
info = ''
idata.append(classes.ticker(announ, atype, xlink, timestamp, info,0))
if(len(idata)==0): idata = None
idata.sort(key=lambda x: x.time, reverse=True)
return idata[0:classes.ticker.narticles]
def etimes(doc2):
doc = doc2.decode(encoding='UTF-8')
atype = 'etimes'
feed = feedparser.parse(doc)
i=0
idata = []
for post in feed.entries:
i=i+1
announ = str(post.title.encode('ascii', 'ignore'))
xlink = str(post.link.encode('ascii', 'ignore'))
timestamp = int(time.mktime(post.updated_parsed))
info = str(post.summary.encode('ascii', 'ignore')).split('>')
#print announ
#print xlink
#print timestamp, util.ts_conv(timestamp)
#print info[3]
idata.append(classes.ticker(announ, atype, xlink, timestamp, info[3],0))
#print i, announ, atype, xlink, timestamp, info[3]
#pline2()
#pline()
idata.sort(key=lambda x: x.time, reverse=True)
return idata[0:classes.ticker.narticles]