more scrapers, fix column order, extract title from lengthy description
[disclosr.git] / documents / scrapers / dfd7414bb0c21a0076ab559901ae0588.py
blob:a/documents/scrapers/dfd7414bb0c21a0076ab559901ae0588.py -> blob:b/documents/scrapers/dfd7414bb0c21a0076ab559901ae0588.py
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
   
#http://www.doughellmann.com/PyMOTW/abc/ #http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
def getColumns(self,columns): def getColumns(self,columns):
(id, date, title, description, notes) = columns (id, date, title, description, notes) = columns
return (id, date, description, title, notes) return (id, date, title, description, notes)
def getTable(self,soup): def getTable(self,soup):
return soup.find(class_ = "content") return soup.find(class_ = "content")
   
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()