| 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 dateutil |
| from dateutil.parser import * | |
| from datetime import * | |
| import scrape | |
| from bs4 import BeautifulSoup | |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | |
| #http://www.doughellmann.com/PyMOTW/abc/ | def __init__(self): |
| class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper): | super(ScraperImplementation, self).__init__() |
| def getColumns(self,columns): | def getTable(self, soup): |
| (id, date, title, description, notes) = columns | return soup.find(id='content') |
| return (id, date, title, description, notes) | |
| def getDescription(self,content, entry,doc): | |
| link = None | |
| links = [] | |
| description = "" | |
| for atag in entry.find_all('a'): | |
| if atag.has_attr('href'): | |
| link = scrape.fullurl(self.getURL(), atag['href']) | |
| (url, mime_type, htcontent) = scrape.fetchURL(scrape.docsdb, link, "foidocuments", self.getAgencyID(), False) | |
| if htcontent != None: | |
| if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml": | |
| soup = BeautifulSoup(htcontent) | |
| row = soup.find(id="foidetails") | |
| if row == None: | |
| row = soup.find(id="content").table | |
| if row == None: | |
| row = soup.find(id="content") | |
| description = ''.join(row.stripped_strings) | |
| for atag in row.find_all("a"): | |
| if atag.has_attr('href'): | |
| links.append(scrape.fullurl(link, atag['href'])) | |
| if links != []: | |
| doc.update({'links': links}) | |
| if description != "": | |
| doc.update({ 'description': description}) | |
| def getColumnCount(self): | |
| return 3 | |
| def getColumns(self, columns): | |
| (id, title, date) = columns | |
| return (id, date, title, title, None) | |
| if __name__ == '__main__': | if __name__ == '__main__': |
| print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper) | print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) |
| print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericRSSDisclogScraper) | print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) |
| ScraperImplementation().doScrape() | ScraperImplementation().doScrape() |