From: Maxious <maxious@lambdacomplex.org>
Date: Thu, 06 Dec 2012 05:27:26 +0000
Subject: add ACMA scraper
X-Git-Url: http://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=b8235880edb41472ba7a5d15ef71dfb9229ef4b9
---
add ACMA scraper


Former-commit-id: 79c714f2e5d9cc2ebd82d89d586fe3ed43ed2cd5
---


--- a/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.py
+++ b/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.py
@@ -7,6 +7,8 @@
 from pyquery import PyQuery as pq
 from lxml import etree
 import urllib
+import dateutil
+from dateutil.parser import *
 
 class ACMADisclogScraper(genericScrapers.GenericDisclogScraper):
 
@@ -14,23 +16,30 @@
         foidocsdb = scrape.couch['disclosr-foidocuments']
         (url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
              self.getURL(), "foidocuments", self.getAgencyID())
-
-        d = pq(content)
-        d.make_links_absolute()
-        d.table.filter('.ncTAF_DataTABLE')
-        print [i.text() for i in d.items('span')]
-        description = ""
-        dochash = scrape.mkhash(description)
-        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,
-            "date": edate, "title": "Disclosure Log Updated", "description": description}
-            #foidocsdb.save(doc)
-        else:
-            print "already saved"
+        
+        d = pq(content.read())
+        d.make_links_absolute(base_url = self.getURL())
+        for table in d('table').items():
+            title= table('thead').text()
+            print title
+            (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'))
+            description = descA+" "+descB
+            edate = parse(idate[:12], dayfirst=True, fuzzy=True).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, "notes": notes, "title": "Disclosure Log Updated", "description": description}
+                #print doc
+                foidocsdb.save(doc)
+            else:
+                print "already saved"
 
 
 if __name__ == '__main__':

--- a/documents/scrapers/7c6adc1d41cf029bf1a0959e5156477a.txt
+++ /dev/null
@@ -1,1 +1,1 @@
-acma style
+