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