From: maxious Date: Sat, 10 Nov 2012 09:15:21 +0000 Subject: derive agencyID and disclog url from filename X-Git-Url: http://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=8ac510d67c62c859f6f548b3224996516ef1708b --- derive agencyID and disclog url from filename Former-commit-id: eddf90809214ee502e593c769c4bd0b0b2fafc3a --- --- a/documents/genericScrapers.py +++ b/documents/genericScrapers.py @@ -8,17 +8,36 @@ import feedparser import abc -class GenericRSSDisclogScraper(object): +class GenericDisclogScraper(object): __metaclass__ = abc.ABCMeta - @abc.abstractmethod + agencyID = None + disclogURL = None def getAgencyID(self): """ disclosr agency id """ - return + if self.agencyID == None: + self.agencyID = os.path.basename(sys.argv[0]).replace(".py","") + return self.agencyID - @abc.abstractmethod def getURL(self): """ disclog URL""" - return + if self.disclogURL == None: + agency = scrape.agencydb.get(self.getAgencyID()) + self.disclogURL = agency['FOIDocumentsURL'] + return self.disclogURL + + @abc.abstractmethod + def doScrape(self): + """ do the scraping """ + return + + + +class GenericRSSDisclogScraper(GenericDisclogScraper): + def getDescription(self, entry, doc): + """ get description from rss entry""" + doc['description'] = entry.summary + return + def doScrape(self): foidocsdb = scrape.couch['disclosr-foidocuments'] (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, self.getURL(), "foidocuments", self.getAgencyID()) @@ -26,29 +45,22 @@ for entry in feed.entries: #print entry print entry.id - hash = scrape.mkhash(entry.link) + hash = scrape.mkhash(entry.id) + #print hash doc = foidocsdb.get(hash) + #print doc if doc == None: print "saving" edate = datetime.fromtimestamp(mktime( entry.published_parsed)).strftime("%Y-%m-%d") - doc = {'id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id, - "date": edate, "description": entry.summary,"title": entry.title} + doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': entry.link, 'docID': entry.id, + "date": edate,"title": entry.title} + self.getDescription(entry, doc) foidocsdb.save(doc) else: print "already saved" -class GenericOAICDisclogScraper(object): - __metaclass__ = abc.ABCMeta - @abc.abstractmethod - def getAgencyID(self): - """ disclosr agency id """ - return - - @abc.abstractmethod - def getURL(self): - """ disclog URL""" - return - +class GenericOAICDisclogScraper(GenericDisclogScraper): + __metaclass__ = abc.ABCMeta @abc.abstractmethod def getColumns(self,columns): """ rearranges columns if required """ @@ -86,7 +98,7 @@ edate = ""+str(dtdate[0])+'-'+str(dtdate[1])+'-'+str(dtdate[2]) else: edate = "" - doc = {'id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), "links": links, 'docID': id.string, + doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), "links": links, 'docID': id.string, "date": edate, "description": descriptiontxt,"title": title.string,"notes": notes.string} foidocsdb.save(doc) else: --- a/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py +++ b/documents/scrapers/3cd40b1240e987cbcd3f0e67054ce259.py @@ -5,12 +5,6 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): - def getAgencyID(self): - return "3cd40b1240e987cbcd3f0e67054ce259" - - def getURL(self): - return "http://www.apvma.gov.au/about/foi/disclosure/index.php" - def getColumns(self,columns): (id, date, description, title, notes) = columns return (id, date, description, title, notes) @@ -19,3 +13,4 @@ print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) ScraperImplementation().doScrape() + --- a/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py +++ b/documents/scrapers/8c9421f852c441910bf1d93a57b31d64.py @@ -5,12 +5,6 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): - def getAgencyID(self): - return "8c9421f852c441910bf1d93a57b31d64" - - def getURL(self): - return "http://www.daff.gov.au/about/foi/ips/disclosure-log" - def getColumns(self,columns): (id, date, title, description, notes) = columns return (id, date, description, title, notes) --- a/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py +++ b/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py @@ -2,14 +2,37 @@ 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.GenericRSSDisclogScraper): - def getAgencyID(self): - return "be9996f0ac58f71f23d074e82d44ead3" + def getDescription(self,entry,doc): + (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, entry.link, "foidocuments", self.getAgencyID(), False) + if content != 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}) - def getURL(self): - return "http://foi.deewr.gov.au/disclosure-log/rss" if __name__ == '__main__': print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericRSSDisclogScraper) --- a/documents/scrapers/e2a845e55bc9986e6c75c5ad2c508b8d.py +++ b/documents/scrapers/e2a845e55bc9986e6c75c5ad2c508b8d.py @@ -5,12 +5,6 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper): - def getAgencyID(self): - return "be9996f0ac58f71f23d074e82d44ead3" - - def getURL(self): - return "http://foi.deewr.gov.au/disclosure-log/rss" - def getColumns(self,columns): (id, date, title, description, notes) = columns return (id, date, description, title, notes) --- a/documents/scrapers/rtk.py +++ b/documents/scrapers/rtk.py @@ -5,12 +5,6 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper): - def getAgencyID(self): - return "be9996f0ac58f71f23d074e82d44ead3" - - def getURL(self): - return "http://foi.deewr.gov.au/disclosure-log/rss" - def getColumns(self,columns): (id, date, title, description, notes) = columns return (id, date, description, title, notes) --- a/documents/template.inc.php +++ b/documents/template.inc.php @@ -69,7 +69,7 @@