| 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 |
| #RSS feed not detailed | import scrape |
| from bs4 import BeautifulSoup | |
| #http://www.doughellmann.com/PyMOTW/abc/ | #http://www.doughellmann.com/PyMOTW/abc/ |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
| def getDescription(self,content, entry,doc): | def getDescription(self,content, entry,doc): |
| link = None | link = None |
| links = [] | |
| description = "" | |
| for atag in entry.find_all('a'): | for atag in entry.find_all('a'): |
| if atag.has_key('href'): | if atag.has_key('href'): |
| link = scrape.fullurl(url,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(content) | soup = BeautifulSoup(htcontent) |
| links = [] | rowtitle = soup.find(class_ = "wc-title").find("h1").string |
| description = "" | if rowtitle != None: |
| dldivs = soup.find('div',class_="download") | description = rowtitle + ": " |
| if dldivs != None: | for row in soup.find(class_ ="wc-content").find_all('td'): |
| for atag in dldivs.find_all("a"): | if row != None: |
| if atag.has_key('href'): | for text in row.stripped_strings: |
| links.append(scrape.fullurl(url,atag['href'])) | description = description + text + "\n" |
| nodldivs = soup.find('div',class_="incompleteNotification") | for atag in row.find_all("a"): |
| if nodldivs != None and nodldivs.stripped_strings != None: | if atag.has_key('href'): |
| for text in nodldivs.stripped_strings: | links.append(scrape.fullurl(link,atag['href'])) |
| description = description + text | |
| for row in soup.table.find_all('tr'): | if links != []: |
| if row != None: | doc.update({'links': links}) |
| description = description + "\n" + row.find('th').string + ": " | if description != "": |
| for text in row.find('div').stripped_strings: | doc.update({ 'description': description}) |
| description = description + text | |
| if links != []: | |
| doc.update({'links': links}) | |
| if description != "": | |
| doc.update({ 'description': description}) | |
| def getColumnCount(self): | def getColumnCount(self): |
| return 2 | return 2 |
| def getTable(self,soup): | |
| return soup.find(class_ = "ms-rteTable-default") | |
| 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(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) | print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
| print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) | print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
| ScraperImplementation().doScrape() | ScraperImplementation().doScrape() |