| import sys,os | |
| sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
| import genericScrapers | |
| import dateutil | |
| from dateutil.parser import * | |
| from datetime import * | |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
| def __init__(self): | |
| super(ScraperImplementation, self).__init__() | |
| def getDate(self, content, entry, doc): | |
| date = ''.join(entry.find('th').stripped_strings).strip() | |
| (a, b, c) = date.partition("(") | |
| date = self.remove_control_chars(a.replace("Octber", "October")) | |
| print date | |
| edate = parse(date, dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | |
| print edate | |
| doc.update({'date': edate}) | |
| return | |
| def getColumnCount(self): | |
| return 4 | |
| def getTable(self, soup): | |
| return soup.find(summary="List of Defence documents released under Freedom of Information requets") | |
| def getColumns(self, columns): | |
| (id, description, access, notes) = columns | |
| return (id, None, description, description, notes) | |
| if __name__ == '__main__': | |
| print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | |
| print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | |
| nsi = ScraperImplementation() | |
| nsi.disclogURL = "http://www.defence.gov.au/foi/disclosure_log_201213.cfm" | |
| nsi.doScrape() | |
| nsi.disclogURL = "http://www.defence.gov.au/foi/disclosure_log_201112.cfm" | |
| nsi.doScrape() | |
| nsi.disclogURL = "http://www.defence.gov.au/foi/disclosure_log_201011.cfm" | |
| nsi.doScrape() | |