| import sys | import sys |
| import os | import 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 scrape | import scrape |
| from datetime import date | from datetime import date |
| from pyquery import PyQuery as pq | from pyquery import PyQuery as pq |
| from lxml import etree | from lxml import etree |
| import urllib | import urllib |
| import dateutil | |
| from dateutil.parser import * | |
| class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): | class ACMADisclogScraper(genericScrapers.GenericDisclogScraper): |
| def doScrape(self): | def doScrape(self): |
| foidocsdb = scrape.couch['disclosr-foidocuments'] | foidocsdb = scrape.couch['disclosr-foidocuments'] |
| (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, | (url, mime_type, content) = scrape.fetchURL(scrape.docsdb, |
| self.getURL(), "foidocuments", self.getAgencyID()) | self.getURL(), "foidocuments", self.getAgencyID()) |
| d = pq(content) | d = pq(content) |
| d.make_links_absolute() | d.make_links_absolute(base_url = self.getURL()) |
| d.table.filter('.ncTAF_DataTABLE') | for table in d('table').items(): |
| print [i.text() for i in d.items('span')] | title= table('thead').text() |
| description = "" | print self.remove_control_chars(title) |
| dochash = scrape.mkhash(description) | (idate,descA,descB,link,deldate,notes) = table('tbody tr').map(lambda i, e: pq(e).children().eq(1).text()) |
| doc = foidocsdb.get(dochash) | links = table('a').map(lambda i, e: pq(e).attr('href')) |
| if doc is None: | description = descA+" "+descB |
| print "saving " + dochash | try: |
| edate = date.today().strftime("%Y-%m-%d") | edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") |
| doc = {'_id': dochash, 'agencyID': self.getAgencyID() | except ValueError: |
| , 'url': self.getURL(), 'docID': dochash, | edate = date.today().strftime("%Y-%m-%d") |
| "date": edate, "title": "Disclosure Log Updated", "description": description} | pass |
| #foidocsdb.save(doc) | print edate |
| else: | dochash = scrape.mkhash(self.remove_control_chars(title)) |
| print "already saved" | 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, "notes": notes, "title": title, "description": description} | |
| #print doc | |
| foidocsdb.save(doc) | |
| else: | |
| print "already saved" | |
| if __name__ == '__main__': | if __name__ == '__main__': |
| print 'Subclass:', issubclass(ACMADisclogScraper, | print 'Subclass:', issubclass(ACMADisclogScraper, |
| genericScrapers.GenericDisclogScraper) | genericScrapers.GenericDisclogScraper) |
| print 'Instance:', isinstance(ACMADisclogScraper(), | print 'Instance:', isinstance(ACMADisclogScraper(), |
| genericScrapers.GenericDisclogScraper) | genericScrapers.GenericDisclogScraper) |
| ACMADisclogScraper().doScrape() | ACMADisclogScraper().doScrape() |