def process_ibd_50(self, msg, stocks):
print 'Process IBD 50'
date = msg.split(',')[1]
words = msg.split(',')[2].split(' ')
url = words[-1]
print date, url
soup = utils.get_url_soup(url)
list = soup.body.find('p', attrs={'id': 'posttext'})
items = list.contents
for idx, item in enumerate(items):
if (idx == 0) or (idx % 2 == 1) or len(item) < 2:
continue
num = item.lstrip('\n').split('\t')[0]
sym = item.lstrip('\n').split('\t')[1]
name = item.lstrip('\n').split('\t')[2]
print sym, name
if sym in stocks.keys():
entry = stocks[sym]
if name not in entry.keys():
entry['name'] = name
if 'ibd 50' in entry.keys():
if date not in entry['ibd 50']:
entry['ibd 50'].append(date)
else:
entry['ibd 50'] = [date]
else:
entry = {}
entry['name'] = name
entry['ibd 50'] = [date]
stocks[sym] = entry
def get_classification(self, sym):
url = 'http://finviz.com/quote.ashx?t=' + sym
soup = utils.get_url_soup(url)
table = soup.body.find_all('table', attrs={'class':
'fullview-title'})[0]
rows = table.find_all('tr')
entries = rows[2].find_all('a')
return rows[1].find(
'b').contents[0], entries[0].contents[0], entries[1].contents[0]
def screen(self, base_url):
url = base_url
soup = utils.get_url_soup(base_url)
total = self.get_total(soup)
sym_list = self.get_result(soup)
print sym_list
num = len(sym_list) + 1
while num < total:
url = base_url + '&r=' + str(num)
print url
soup = utils.get_url_soup(url)
syms = self.get_result(soup)
num = num + len(syms)
print syms
sym_list = sym_list + syms
time.sleep(1)
return sym_list
def basic(self, sym):
url = self.sym2url['CSCO']
print url
soup = utils.get_url_soup(url)
#print soup
stock_content = soup.body.find('div', attrs={'class': 'stockContent'})
print stock_content
company_content = soup.body.find('div', attrs={'class': 'companyContent'})
print company_content
group_leaderships = soup.body.find_all('div', attrs={'class': 'group_leadership_block'})
print group_leaderships[0]
print group_leaderships[1]
def basic(self, sym):
url = 'http://quotes.wsj.com/' + sym.upper()
print url
soup = utils.get_url_soup(url)
print soup
def get_quotes_nasdaq(self, sym):
url = self.form_url_nasdaq(sym)
print url
try:
soup = utils.get_url_soup(url)
except:
print 'Request for', url, 'failed'
return None
quote_div = soup.body.find('div', attrs={'id': 'historicalContainer'})
tbody = quote_div.find('tbody')
if tbody is None:
return None
tr = tbody.find_all('tr')
lines = []
for item in tr:
td = item.find_all('td')
line = []
for i in td:
tokens = i.contents[0].splitlines()
if (len(tokens) == 1) or (tokens[1] == ''):
continue
line.append(tokens[1].strip())
lines.append(line)
lines = lines[::-1]
dates = []
open = []
high = []
low = []
close = []
volume = []
for line in lines:
if len(line) == 0:
continue
if line[0] == '16:00':
#dates.append(time.strftime('%Y-%m-%d'))
continue
if line[1] == 'N/A' or line[2] == 'N/A' or line[
3] == 'N/A' or line[4] == 'N/A':
continue
tmp = line[0].split('/')
dates.append(tmp[2] + '-' + tmp[0] + '-' + tmp[1])
open.append(float(line[1].replace(',', '')))
high.append(float(line[2].replace(',', '')))
low.append(float(line[3].replace(',', '')))
close.append(float(line[4].replace(',', '')))
volume.append(int(line[5].replace(',', '')))
df = pd.DataFrame(index=dates)
df['open'] = open
df['high'] = high
df['low'] = low
df['close'] = close
df['volume'] = volume
return df