--- a/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.txt +++ b/documents/scrapers/8e874a2fde8aa0ccdc6d14573d766540.txt @@ -1,1 +1,49 @@ +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_key('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) + for row in soup.find(class_ = "ms-rteTable-GreyAlternating").find_all('tr'): + if row != None: + rowtitle = row.find('th').string + description = description + "\n" + rowtitle + ": " + for text in row.find('td').stripped_strings: + description = description + text + for atag in row.find_all("a"): + if atag.has_key('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-GreyAlternating") + 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() +# old site too http://archive.treasury.gov.au/content/foi_publications.asp +