1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 | import sys,os sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) import genericScrapers import scrape from bs4 import BeautifulSoup import dateutil from dateutil.parser import * from datetime import * #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): def getTable(self,soup): return soup.find(class_ = "inner-column").table def getRows(self,table): return table.tbody.find_all('tr',recursive=False) def getColumnCount(self): return 3 def getColumns(self,columns): (date, title, description) = columns return (date, date, title, description, None) def getDate(self, content, entry, doc): i = 0 date = "" for string in content.stripped_strings: if i ==1: date = string i = i+1 edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") print edate doc.update({'date': edate}) return def getTitle(self, content, entry, doc): i = 0 title = "" for string in content.stripped_strings: if i < 2: title = title + string i = i+1 doc.update({'title': title}) #print title return if __name__ == '__main__': #http://www.csiro.au/Portals/About-CSIRO/How-we-work/Governance/FOI-Request-Disclosure-Log-2012-13.aspx #http://www.csiro.au/Portals/About-CSIRO/How-we-work/Governance/FOI-Request-Disclosure-Log-2011-12.aspx print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) ScraperImplementation().doScrape() |