| 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 dateutil | import dateutil |
| from dateutil.parser import * | from dateutil.parser import * |
| from datetime import * | from datetime import * |
| import scrape | import scrape |
| from bs4 import BeautifulSoup | from bs4 import BeautifulSoup |
| class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): | class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): |
| def __init__(self): | def __init__(self): |
| super(ScraperImplementation, self).__init__() | super(ScraperImplementation, self).__init__() |
| def getTable(self, soup): | def getTable(self, soup): |
| return soup.find(id='content') | return soup.find(id='zone-content') |
| def getDescription(self,content, entry,doc): | def getDescription(self,content, entry,doc): |
| link = None | link = None |
| links = [] | links = [] |
| description = "" | description = "" |
| for atag in entry.find_all('a'): | for atag in entry.find_all('a'): |
| if atag.has_attr('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": |
| soup = BeautifulSoup(htcontent) | soup = BeautifulSoup(htcontent) |
| row = soup.find(id="foidetails") | row = soup.find(id="foidetails") |
| if row == None: | if row == None: |
| row = soup.find(id="content").table | row = soup.find(id="content").table |
| if row == None: | if row == None: |
| row = soup.find(id="content") | row = soup.find(id="content") |
| description = ''.join(row.stripped_strings) | description = ''.join(row.stripped_strings) |
| for atag in row.find_all("a"): | for atag in row.find_all("a"): |
| if atag.has_attr('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}) |
| if description != "": | if description != "": |
| doc.update({ 'description': description}) | doc.update({ 'description': description}) |
| def getColumnCount(self): | def getColumnCount(self): |
| return 3 | return 3 |
| def getColumns(self, columns): | def getColumns(self, columns): |
| (id, title, date) = columns | (id, title, date) = columns |
| return (id, date, title, title, None) | return (id, date, title, title, None) |
| 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() |