[disclosr.git] / scrape.py
--- a/scrape.py
+++ b/scrape.py
@@ -1,64 +1,1 @@
-#http://packages.python.org/CouchDB/client.html
-import couchdb
-import urllib2
-from BeautifulSoup import BeautifulSoup
-import re
 
-couch = couchdb.Server() # Assuming localhost:5984
-# If your CouchDB server is running elsewhere, set it up like this:
-# couch = couchdb.Server('http://example.com:5984/')
-
-# select database
-agencydb = couch['disclosr-agencies']
-
-for row in agencydb.view('app/getScrapeRequired'): #not recently scraped agencies view?
-    agency = agencydb.get(row.id)
-    print agency['agencyName']
-
-#http://diveintopython.org/http_web_services/etags.html
-class NotModifiedHandler(urllib2.BaseHandler):  
-    def http_error_304(self, req, fp, code, message, headers):
-        addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url())
-        addinfourl.code = code
-        return addinfourl
-
-def scrapeAndStore(URL, depth, agency):
-    URL = "http://www.hole.fi/jajvirta/weblog/"
-    req = urllib2.Request(URL)
-    
-    #if there is a previous version sotred in couchdb, load caching helper tags
-    if etag:
-        req.add_header("If-None-Match", etag)
-    if last_modified:
-        req.add_header("If-Modified-Since", last_modified)
-     
-    opener = urllib2.build_opener(NotModifiedHandler())
-    url_handle = opener.open(req)
-    headers = url_handle.info() # the addinfourls have the .info() too
-    etag = headers.getheader("ETag")
-    last_modified = headers.getheader("Last-Modified") 
-    web_server = headers.getheader("Server") 
-    file_size = headers.getheader("Content-Length") 
-    mime_type = headers.getheader("Content-Type") 
-     
-    if hasattr(url_handle, 'code') and url_handle.code == 304:
-        print "the web page has not been modified"
-    else:
-        print "error %s in downloading %s", url_handle.code, URL
-        #record/alert error to error database
-    
-    #do scraping
-    html = ?
-    # http://www.crummy.com/software/BeautifulSoup/documentation.html
-    soup = BeautifulSoup(html)
-links = soup.findAll('a') # soup.findAll('a', id=re.compile("^p-"))
-for link in links:
-    print link['href']
-    #for each unique link
-    #if html mimetype
-    # go down X levels,
-    # diff with last stored attachment, store in document
-    #if not
-    #   remember to save parentURL and title (link text that lead to document)
-    
-    #store as attachment epoch-filename