| 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 | import dateutil |
| from dateutil.parser import * | 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(base_url = self.getURL()) | d.make_links_absolute(base_url = self.getURL()) |
| for table in d('table').items(): | for table in d('table').items(): |
| title= table('thead').text() | title= table('thead').text() |
| print title | print self.remove_control_chars(title) |
| (idate,descA,descB,link,deldate,notes) = table('tbody tr').map(lambda i, e: pq(e).children().eq(1).text()) | (idate,descA,descB,link,deldate,notes) = table('tbody tr').map(lambda i, e: pq(e).children().eq(1).text()) |
| links = table('a').map(lambda i, e: pq(e).attr('href')) | links = table('a').map(lambda i, e: pq(e).attr('href')) |
| description = descA+" "+descB | description = descA+" "+descB |
| edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | try: |
| edate = parse(idate[:12], dayfirst=True, fuzzy=True).strftime("%Y-%m-%d") | |
| except ValueError: | |
| edate = date.today().strftime("%Y-%m-%d") | |
| pass | |
| print edate | print edate |
| dochash = scrape.mkhash(self.remove_control_chars(title)) | dochash = scrape.mkhash(self.remove_control_chars(title)) |
| doc = foidocsdb.get(dochash) | doc = foidocsdb.get(dochash) |
| if doc is None: | if doc is None: |
| print "saving " + dochash | print "saving " + dochash |
| edate = date.today().strftime("%Y-%m-%d") | edate = date.today().strftime("%Y-%m-%d") |
| doc = {'_id': dochash, 'agencyID': self.getAgencyID() | doc = {'_id': dochash, 'agencyID': self.getAgencyID() |
| , 'url': self.getURL(), 'docID': dochash, | , 'url': self.getURL(), 'docID': dochash, |
| "links": links, | "links": links, |
| "date": edate, "notes": notes, "title": title, "description": description} | "date": edate, "notes": notes, "title": title, "description": description} |
| #print doc | #print doc |
| foidocsdb.save(doc) | foidocsdb.save(doc) |
| else: | else: |
| print "already saved" | 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() |