import sys,os |
import sys,os |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
import genericScrapers |
import genericScrapers |
import scrape |
import scrape |
from bs4 import BeautifulSoup |
from bs4 import BeautifulSoup |
from datetime import date |
from datetime import date |
|
|
#http://www.doughellmann.com/PyMOTW/abc/ |
#http://www.doughellmann.com/PyMOTW/abc/ |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
def getTable(self,soup): |
def getTable(self,soup): |
return soup.find(id= "ctl00_MSO_ContentDiv").table |
return soup.find(class_ = "rgMasterTable") |
|
|
def getColumns(self,columns): |
def getColumns(self,columns): |
(id, title, description, notes) = columns |
(id, title, description, notes) = columns |
return (id, title, title, description, notes) |
return (id, title, title, description, notes) |
def getDate(self, content, entry, doc): |
def getDate(self, content, entry, doc): |
edate = date.today().strftime("%Y-%m-%d") |
edate = date.today().strftime("%Y-%m-%d") |
doc.update({'date': edate}) |
doc.update({'date': edate}) |
return |
return |
def getColumnCount(self): |
def getColumnCount(self): |
return 4 |
return 4 |
|
|
if __name__ == '__main__': |
if __name__ == '__main__': |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
ScraperImplementation().doScrape() |
ScraperImplementation().doScrape() |
|
|