--- a/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py +++ b/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py @@ -1,42 +1,42 @@ import sys,os sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) import genericScrapers -#RSS feed not detailed +import scrape +from bs4 import BeautifulSoup #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): def getDescription(self,content, entry,doc): link = None + links = [] + description = "" for atag in entry.find_all('a'): if atag.has_key('href'): - link = scrape.fullurl(url,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": - # http://www.crummy.com/software/BeautifulSoup/documentation.html - soup = BeautifulSoup(content) - links = [] - description = "" - dldivs = soup.find('div',class_="download") - if dldivs != None: - for atag in dldivs.find_all("a"): - if atag.has_key('href'): - links.append(scrape.fullurl(url,atag['href'])) - nodldivs = soup.find('div',class_="incompleteNotification") - if nodldivs != None and nodldivs.stripped_strings != None: - for text in nodldivs.stripped_strings: - description = description + text - for row in soup.table.find_all('tr'): - if row != None: - description = description + "\n" + row.find('th').string + ": " - for text in row.find('div').stripped_strings: - description = description + text - if links != []: - doc.update({'links': links}) - if description != "": - doc.update({ 'description': description}) + 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": + # http://www.crummy.com/software/BeautifulSoup/documentation.html + soup = BeautifulSoup(htcontent) + for row in soup.find(class_ = "ms-rteTable-GreyAlternating").find_all('tr'): + if row != None: + rowtitle = row.find('th').string + description = description + "\n" + rowtitle + ": " + for text in row.find('td').stripped_strings: + description = description + text + for atag in row.find_all("a"): + if atag.has_key('href'): + links.append(scrape.fullurl(link,atag['href'])) + + if links != []: + doc.update({'links': links}) + if description != "": + doc.update({ 'description': description}) + def getColumnCount(self): return 2 + def getTable(self,soup): + return soup.find(class_ = "ms-rteTable-GreyAlternating") def getColumns(self,columns): (date, title) = columns return (title, date, title, title, None)