| 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 |
| #http://www.doughellmann.com/PyMOTW/abc/ | #http://www.doughellmann.com/PyMOTW/abc/ |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
| def getTable(self,soup): | def getTable(self,soup): |
| return soup.find(class_ = "ms-rtestate-field").table | return soup.find(class_ = "ms-rtestate-field").table |
| def getColumns(self,columns): | def getColumns(self,columns): |
| (id, date, title, description, notes) = columns | (id, date, title, description, notes) = columns |
| return (id, date, title, description, notes) | return (id, date, title, description, notes) |
| def getLinks(self, content, entry, doc): | def getLinks(self, content, entry, doc): |
| link = None | link = None |
| links = [] | links = [] |
| 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 atag in soup.find(class_ = "article-content").find_all('a'): | for atag in soup.find(class_ = "article-content").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}) |
| doc.update({'url': link}) | doc.update({'url': link}) |
| return | return |
| 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() |