cache org ids while importing datagov
[disclosr.git] / documents / scrapers / 1d404c4934f74feacd00dcb434e7c10a.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
import sys,os
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../'))
import genericScrapers
import scrape
from bs4 import BeautifulSoup
 
#http://www.doughellmann.com/PyMOTW/abc/
class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper):
        #def getTable(self,soup):
        #        return soup.find(id = "cphMain_C001_Col01").table       
        def getColumnCount(self):
                return 5
        def getColumns(self,columns):
                (id, date, title, description,notes) = columns
                return (id, date, title, description, notes)
 
if __name__ == '__main__':
    print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
    print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
    ScraperImplementation().doScrape()