| 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 datetime | |
| from datetime import date | |
| #http://www.doughellmann.com/PyMOTW/abc/ | |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
| def getColumnCount(self): | |
| return 3 | |
| def getTable(self,soup): | |
| return soup.find(class_ = "internal") | |
| def getColumns(self,columns): | |
| (id, date, description) = columns | |
| return (id, date, description, description, None) | |
| def getTitle(self, content, entry, doc): | |
| doc.update({'title': content.stripped_strings.next()}) | |
| return | |
| def getDate(self, content, entry, doc): | |
| edate = datetime.strptime(content.string.strip(), "%d/%m/%Y").strftime("%Y-%m-%d") | |
| print edate | |
| doc.update({'date': edate}) | |
| return | |
| if __name__ == '__main__': | |
| print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
| print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
| ScraperImplementation().doScrape() | |