| import sys | |
| import os | |
| sys.path.insert(0, os.path.join(os.path.dirname(__file__) or '.', '../')) | |
| import genericScrapers | |
| import scrape | |
| from datetime import date | |
| from pyquery import PyQuery as pq | |
| from lxml import etree | |
| import urllib | |
| import dateutil | |
| from dateutil.parser import * | |
| class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): | |
| def doScrape(self): | |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | |
| (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | |
| self.getURL(), "foidocuments", self.getAgencyID()) | |
| d = pq(content.read()) | |
| d.make_links_absolute(base_url = self.getURL()) | |
| for item in d('.item-list').items(): | |
| title= item('h3').text() | |
| print title | |
| links = item('a').map(lambda i, e: pq(e).attr('href')) | |
| description = title= item('ul').text() | |
| edate = date.today().strftime("%Y-%m-%d") | |
| print edate | |
| dochash = scrape.mkhash(self.remove_control_chars(title)) | |
| doc = foidocsdb.get(dochash) | |
| if doc is None: | |
| print "saving " + dochash | |
| edate = date.today().strftime("%Y-%m-%d") | |
| doc = {'_id': dochash, 'agencyID': self.getAgencyID() | |
| , 'url': self.getURL(), 'docID': dochash, | |
| "links": links, | |
| "date": edate, "title": title, "description": description} | |
| #print doc | |
| foidocsdb.save(doc) | |
| else: | |
| print "already saved" | |
| if __name__ == '__main__': | |
| print 'Subclass:', issubclass(ACMADisclogScraper, | |
| genericScrapers.GenericDisclogScraper) | |
| print 'Instance:', isinstance(ACMADisclogScraper(), | |
| genericScrapers.GenericDisclogScraper) | |
| ACMADisclogScraper().doScrape() | |