--- a/scrape.py +++ b/scrape.py @@ -3,15 +3,6 @@ import urllib2 from BeautifulSoup import BeautifulSoup import re - -couch = couchdb.Server('http://192.168.1.148:5984/') - -# 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): @@ -21,9 +12,10 @@ return addinfourl def scrapeAndStore(URL, depth, agency): - URL = "http://www.hole.fi/jajvirta/weblog/" + 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) @@ -39,7 +31,7 @@ file_size = headers.getheader("Content-Length") mime_type = headers.getheader("Content-Type") - if hasattr(url_handle, 'code') + if hasattr(url_handle, 'code'): if url_handle.code == 304: print "the web page has not been modified" else: @@ -63,3 +55,22 @@ #record/alert error to error database + + + + + + + + + +couch = couchdb.Server('http://192.168.1.148:5984/') + +# 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['name'] +scrapeAndStore("A",1,1) +