From: Maxious Date: Sun, 18 Nov 2012 23:57:12 +0000 Subject: Merge branch 'master' of ssh://maxious.lambdacomplex.org/git/disclosr X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=fb39d2af0763c0435788110d46b48877e9200843 --- Merge branch 'master' of ssh://maxious.lambdacomplex.org/git/disclosr Former-commit-id: 406a4f269604c98cb406ec3ddb8842a8f203ab1c --- --- a/documents/genericScrapers.py +++ b/documents/genericScrapers.py @@ -30,13 +30,14 @@ """ do the scraping """ return + @abc.abstractmethod + def getDescription(self, content, entry, doc): + """ get description""" + 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'] @@ -54,16 +55,29 @@ 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,"title": entry.title} - self.getDescription(entry, doc) + self.getDescription(entry,entry, doc) foidocsdb.save(doc) else: print "already saved" + def getDescription(self, content, entry, doc): + """ get description from rss entry""" + doc.update({'description': content.summary}) + return class GenericOAICDisclogScraper(GenericDisclogScraper): __metaclass__ = abc.ABCMeta @abc.abstractmethod def getColumns(self,columns): """ rearranges columns if required """ + return + def getColumnCount(self): + return 5 + def getDescription(self, content, entry, doc): + """ get description from rss entry""" + descriptiontxt = "" + for string in content.stripped_strings: + descriptiontxt = descriptiontxt + " \n" + string + doc.update({'description': descriptiontxt}) return def doScrape(self): @@ -76,7 +90,7 @@ soup = BeautifulSoup(content) for row in soup.table.find_all('tr'): columns = row.find_all('td') - if len(columns) == 5: + if len(columns) == self.getColumnCount(): (id, date, description, title, notes) = self.getColumns(columns) print id.string hash = scrape.mkhash(url+id.string) @@ -85,9 +99,6 @@ if atag.has_key('href'): links.append(scrape.fullurl(url,atag['href'])) doc = foidocsdb.get(hash) - descriptiontxt = "" - for string in description.stripped_strings: - descriptiontxt = descriptiontxt + " \n" + string if doc == None: print "saving" @@ -97,14 +108,20 @@ print dtdate 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, - "date": edate, "description": descriptiontxt,"title": title.string,"notes": notes.string} + edate = datetime.strptime(date.string, "%d %B %Y").strftime("%Y-%m-%d") + doc = {'_id': hash, 'agencyID': self.getAgencyID(), 'url': self.getURL(), 'docID': id.string, + "date": edate,"title": title.string} + self.getDescription(description,row, doc) + + if links != []: + doc.update({'links': links}) + if notes != None: + doc.update({ 'notes': notes.string}) foidocsdb.save(doc) else: - print "already saved" + print "already saved "+hash - elif len(row.find_all('th')) == 5: + elif len(row.find_all('th')) == self.getColumnCount(): print "header row" else: --- /dev/null +++ b/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py @@ -1,1 +1,48 @@ +import sys,os +sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) +import genericScrapers +#RSS feed not detailed +#http://www.doughellmann.com/PyMOTW/abc/ +class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): + def getDescription(self,content, entry,doc): + link = None + 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}) + def getColumnCount(self): + return 2 + def getColumns(self,columns): + (date, title) = columns + return (title, date, title, title, None) + +if __name__ == '__main__': + print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) + print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) + ScraperImplementation().doScrape() + --- /dev/null +++ b/documents/scrapers/820c3df09aa62f6ee7468c73bea0e323.py @@ -1,1 +1,18 @@ +import sys,os +sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) +import genericScrapers +#RSS feed not detailed +#http://www.doughellmann.com/PyMOTW/abc/ +class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): + def getColumnCount(self): + return 2 + def getColumns(self,columns): + (date, title) = columns + return (title, date, title, title, None) + +if __name__ == '__main__': + print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) + print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) + ScraperImplementation().doScrape() + --- /dev/null +++ b/documents/scrapers/bb96fe4065afb7e0872136dd657f9369.txt @@ -1,1 +1,2 @@ +# does not have any disclog entries or table --- a/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py +++ b/documents/scrapers/be9996f0ac58f71f23d074e82d44ead3.py @@ -6,9 +6,9 @@ from bs4 import BeautifulSoup #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericRSSDisclogScraper): - def getDescription(self,entry,doc): - (url,mime_type,content) = scrape.fetchURL(scrape.docsdb, entry.link, "foidocuments", self.getAgencyID(), False) - if content != None: + def getDescription(self,content, entry,doc): + (url,mime_type,htcontent) = scrape.fetchURL(scrape.docsdb, entry.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) --- /dev/null +++ b/documents/scrapers/c43ca6780764f4e61918e8836be74420.py @@ -1,1 +1,16 @@ +import sys,os +sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) +import genericScrapers +#RSS feed not detailed +#http://www.doughellmann.com/PyMOTW/abc/ +class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): + def getColumns(self,columns): + (id, date, title,description,notes) = columns + return (id, date, description, title, notes) + +if __name__ == '__main__': + print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper) + print 'Instance:', isinstance(ScraperImplementation(), genericScrapers.GenericOAICDisclogScraper) + ScraperImplementation().doScrape() +