| import sys,os | import sys,os |
| sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) |
| import genericScrapers | import genericScrapers |
| import scrape | import scrape |
| from bs4 import BeautifulSoup | from bs4 import BeautifulSoup |
| import codecs | import codecs |
| #http://www.doughellmann.com/PyMOTW/abc/ | #http://www.doughellmann.com/PyMOTW/abc/ |
| class NewScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | class NewScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
| def getDescription(self,content, entry,doc): | def getDescription(self,content, entry,doc): |
| link = None | link = None |
| links = [] | links = [] |
| description = "" | description = "" |
| for atag in entry.find_all('a'): | for atag in entry.find_all('a'): |
| if atag.has_key('href'): | if atag.has_attr('href'): |
| link = scrape.fullurl(self.getURL(),atag['href']) | link = scrape.fullurl(self.getURL(),atag['href']) |
| (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False) | (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False) |
| if htcontent != None: | if htcontent != None: |
| if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": | if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": |
| # http://www.crummy.com/software/BeautifulSoup/documentation.html | # http://www.crummy.com/software/BeautifulSoup/documentation.html |
| soup = BeautifulSoup(htcontent) | soup = BeautifulSoup(htcontent) |
| for text in soup.find(class_ = "mainContent").stripped_strings: | for text in soup.find(class_ = "mainContent").stripped_strings: |
| description = description + text.encode('ascii', 'ignore') | description = description + text.encode('ascii', 'ignore') |
| for atag in soup.find(id="SortingTable").find_all("a"): | for atag in soup.find(id="SortingTable").find_all("a"): |
| if atag.has_key('href'): | if atag.has_attr('href'): |
| links.append(scrape.fullurl(link,atag['href'])) | links.append(scrape.fullurl(link,atag['href'])) |
| if links != []: | if links != []: |
| doc.update({'links': links}) | doc.update({'links': links}) |
| if description != "": | if description != "": |
| doc.update({ 'description': description}) | doc.update({ 'description': description}) |
| def getColumnCount(self): | def getColumnCount(self): |
| return 2 | return 2 |
| def getTable(self,soup): | def getTable(self,soup): |
| return soup.find(id = "TwoColumnSorting") | return soup.find(id = "TwoColumnSorting") |
| def getColumns(self,columns): | def getColumns(self,columns): |
| ( title, date) = columns | ( title, date) = columns |
| return (title, date, title, title, None) | return (title, date, title, title, None) |
| class OldScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | class OldScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
| def getDescription(self,content, entry,doc): | def getDescription(self,content, entry,doc): |
| link = None | link = None |
| links = [] | links = [] |
| description = "" | description = "" |
| for atag in entry.find_all('a'): | for atag in entry.find_all('a'): |
| if atag.has_key('href'): | if atag.has_attr('href'): |
| link = scrape.fullurl(self.getURL(),atag['href']) | link = scrape.fullurl(self.getURL(),atag['href']) |
| (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False) | (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False) |
| if htcontent != None: | if htcontent != None: |
| if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": | if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": |
| # http://www.crummy.com/software/BeautifulSoup/documentation.html | # http://www.crummy.com/software/BeautifulSoup/documentation.html |
| soup = BeautifulSoup(htcontent) | soup = BeautifulSoup(htcontent) |
| for text in soup.find(id="content-item").stripped_strings: | for text in soup.find(id="content-item").stripped_strings: |
| description = description + text + " \n" | description = description + text + " \n" |
| for atag in soup.find(id="content-item").find_all("a"): | for atag in soup.find(id="content-item").find_all("a"): |
| if atag.has_key('href'): | if atag.has_attr('href'): |
| links.append(scrape.fullurl(link,atag['href'])) | links.append(scrape.fullurl(link,atag['href'])) |
| if links != []: | if links != []: |
| doc.update({'links': links}) | doc.update({'links': links}) |
| if description != "": | if description != "": |
| doc.update({ 'description': description}) | doc.update({ 'description': description}) |
| if links != []: | if links != []: |
| doc.update({'links': links}) | doc.update({'links': links}) |
| if description != "": | if description != "": |
| doc.update({ 'description': description}) | doc.update({ 'description': description}) |
| def getColumnCount(self): | def getColumnCount(self): |
| return 2 | return 2 |
| def getTable(self,soup): | def getTable(self,soup): |
| return soup.find(class_ = "doc-list") | return soup.find(class_ = "doc-list") |
| def getColumns(self,columns): | def getColumns(self,columns): |
| (date, title) = columns | (date, title) = columns |
| return (title, date, title, title, None) | return (title, date, title, title, None) |
| if __name__ == '__main__': | if __name__ == '__main__': |
| print 'Subclass:', issubclass(NewScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | print 'Subclass:', issubclass(NewScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
| print 'Instance:', isinstance(NewScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | print 'Instance:', isinstance(NewScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
| NewScraperImplementation().doScrape() | NewScraperImplementation().doScrape() |
| print 'Subclass:', issubclass(OldScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | print 'Subclass:', issubclass(OldScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
| print 'Instance:', isinstance(OldScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | print 'Instance:', isinstance(OldScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
| osi = OldScraperImplementation() | osi = OldScraperImplementation() |
| osi.disclogURL = "http://archive.treasury.gov.au/content/foi_publications.asp?year=-1&abstract=0&classification=&=&titl=Disclosure+Log+-+Documents+Released+Under+FOI" | osi.disclogURL = "http://archive.treasury.gov.au/content/foi_publications.asp?year=-1&abstract=0&classification=&=&titl=Disclosure+Log+-+Documents+Released+Under+FOI" |
| osi.doScrape() | osi.doScrape() |