From: Maxious <maxious@lambdacomplex.org>
Date: Sun, 29 Jan 2012 03:46:58 +0000
Subject: Hash urls for insertion during scraping
X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=84ebf67bf7e5f62eeb263b59689d822b95f63989
---
Hash urls for insertion during scraping


Former-commit-id: 68bfb5914592737b5409075f197de39d8ab19319
---


--- a/scrape.py
+++ b/scrape.py
@@ -3,6 +3,7 @@
 import urllib2
 from BeautifulSoup import BeautifulSoup
 import re
+import hashlib
 
 #http://diveintopython.org/http_web_services/etags.html
 class NotModifiedHandler(urllib2.BaseHandler):  
@@ -11,25 +12,25 @@
         addinfourl.code = code
         return addinfourl
 
-def scrapeAndStore(URL, depth, agency):
-    URL = "http://www.google.com"
-    req = urllib2.Request(URL)
-    etag = 'y'
-    last_modified = 'y'
-    #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)
+def scrapeAndStore(docsdb, url, depth, agencyID):
+    hash = hashlib.md5(url).hexdigest()
+    req = urllib2.Request(url)
+    print "Fetching %s", url
+    doc = docsdb['hash']
+    #if there is a previous version stored in couchdb, load caching helper tags
+    if doc.has_key('etag'):
+        req.add_header("If-None-Match", doc['etag'])
+    if doc.has_key('last_modified'):
+        req.add_header("If-Modified-Since", doc['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") 
+    doc['etag'] = headers.getheader("ETag")
+    doc['last_modified'] = headers.getheader("Last-Modified") 
+    doc['web_server'] = headers.getheader("Server") 
+    doc['file_size'] = headers.getheader("Content-Length") 
+    doc['mime_type'] = headers.getheader("Content-Type") 
      
     if hasattr(url_handle, 'code'): 
         if url_handle.code == 304:
@@ -41,13 +42,14 @@
             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)
+            if link.has_key("href"):
+                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
     else:
@@ -68,9 +70,10 @@
 
 # select database
 agencydb = couch['disclosr-agencies']
+docsdb = couch['disclosr-documents']
 
 for row in agencydb.view('app/getScrapeRequired'): #not recently scraped agencies view?
     agency = agencydb.get(row.id)
     print agency['name']
-scrapeAndStore("A",1,1)
+    scrapeAndStore(docsdb, agency['website'],1,agency['_id'])