| 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 | #RSS feed not detailed |
| import scrape | import scrape |
| from bs4 import BeautifulSoup | from bs4 import BeautifulSoup |
| #http://www.doughellmann.com/PyMOTW/abc/ | #http://www.doughellmann.com/PyMOTW/abc/ |
| class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper): | class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper): |
| def getDescription(self,content, entry,doc): | def getDescription(self,content, entry,doc): |
| (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, entry.link, "foidocuments", self.getAgencyID(), False) | (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, entry.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(content) |
| links = [] | links = [] |
| description = "" | description = "" |
| dldivs = soup.find('div',class_="download") | dldivs = soup.find('div',class_="download") |
| if dldivs != None: | if dldivs != None: |
| for atag in dldivs.find_all("a"): | for atag in dldivs.find_all("a"): |
| if atag.has_key('href'): | if atag.has_attr('href'): |
| links.append(scrape.fullurl(url,atag['href'])) | links.append(scrape.fullurl(url,atag['href'])) |
| nodldivs = soup.find('div',class_="incompleteNotification") | nodldivs = soup.find('div',class_="incompleteNotification") |
| if nodldivs != None and nodldivs.stripped_strings != None: | if nodldivs != None and nodldivs.stripped_strings != None: |
| for text in nodldivs.stripped_strings: | for text in nodldivs.stripped_strings: |
| description = description + text | description = description + text |
| for row in soup.table.find_all('tr'): | for row in soup.table.find_all('tr'): |
| if row != None: | if row != None: |
| description = description + "\n" + row.find('th').string + ": " | description = description + "\n" + row.find('th').string + ": " |
| for text in row.find('div').stripped_strings: | for text in row.find('div').stripped_strings: |
| description = description + text | description = description + text |
| 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 __name__ == '__main__': | if __name__ == '__main__': |
| print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper) | print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper) |
| print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper) | print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper) |
| ScraperImplementation().doScrape() | ScraperImplementation().doScrape() |