def tranfer_data_from_stage_to_temp():
dao = Dao()
rows = dao.get_entries_from_stage()
for row in rows:
for key in row:
row[key] = row[key].strip()
if key == 'kilometer_done' or key == 'price':
row[key] = int(row[key].replace(',', ''))
elif key == 'model_year':
row[key] = int(re.search(r'([A-Za-z]{3})(-)(.+\d)', row[key]).group(3))
elif key == 'profile_id':
row[key] = int(re.search(r'(S)(.+\d)', row[key]).group(2))
dao.populateAndExecuteIntoTemp(row)
__author__ = 'aliHitawala'
from DataModels.webcrawler.bikewale.DataExtractor import Extractor
from DataModels.persistence.bikewale.BikeWaleDaoImpl import Dao
if __name__ == '__main__':
filename = 'html_pages_url'
__list = []
urls = []
def readAllUrls():
global urls
f = open(filename, 'r')
urls = f.readlines()
readAllUrls()
instance = Extractor()
daoInstance = Dao()
for url in urls:
dict = instance.extract(url)
if bool(dict):
print dict
daoInstance.populateAndExecute(dict)
