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 getDescription(self,content, entry,doc):
		link = None
                links = []
                description = ""
		for atag in entry.find_all('a'):
			if atag.has_attr('href'):
				link = scrape.fullurl(self.getURL(),atag['href'])			
                                (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False)
                                if htcontent != None:
                                        if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml":
                                        # http://www.crummy.com/software/BeautifulSoup/documentation.html
                                                soup = BeautifulSoup(htcontent)
						rowtitle = soup.find(class_ = "wc-title").find("h1").string
                                                if rowtitle != None:
                                                   description = rowtitle + ": "
                                                for row in soup.find(class_ ="wc-content").find_all('td'):
                                                        if row != None:
                                                                for text in row.stripped_strings:
                                                                    description = description + text + "\n"
                                                     		for atag in row.find_all("a"):
                                                                	if atag.has_attr('href'):
                                                                        	links.append(scrape.fullurl(link,atag['href']))

		if links != []:
                 	doc.update({'links': links})
                if description != "":
                        doc.update({ 'description': description})

	def getColumnCount(self):
		return 2
	def getTable(self,soup):
		return soup.find(class_ = "ms-rteTable-default")
	def getColumns(self,columns):
		(date, title) = columns
		return (title, date, title, title, None)

if __name__ == '__main__':
    print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)
    print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper)
    ScraperImplementation().doScrape()