######################################### # Simple table of values from one scraper ######################################### from scraperwiki.apiwrapper import getKeys, getData, getDataByDate, getDataByLocation import re sourcescraper = "swale-democratic-services-events-diary" limit = 30 offset = 0 keys = getKeys(sourcescraper) data = getData(sourcescraper, 1, offset) #res ure = re.compile(".*(http.*uid=[0-9]*)", re.DOTALL) nre = re.compile(".*strong.(.*strong)", re.DOTALL) allre = re.compile(".*", re.DOTALL) #meta for row in getData(sourcescraper, limit, offset): updated = "%s%s" % (row.get('datetime'), "Z") break print """<?xml version="1.0" encoding="utf-8"?> <feed xmlns='http://www.w3.org/2005/Atom'> <title type='text'>Swale Democratic Services Calendar</title> <subtitle type='html'>Open Swale</subtitle> <updated>%s</updated> <id>http://scraperwikiviews.com/run/feed/?</id>
######################################### # Simple table of values from one scraper ######################################### from scraperwiki.apiwrapper import getKeys, getData, getDataByDate, getDataByLocation sourcescraper = "datagovuk-catalogue" limit = 20 offset = 0 all_keys = getKeys(sourcescraper) keys = ['title', 'name', 'department', 'agency', 'notes', 'url', 'resources'] keys += sorted(set(all_keys) - set(keys)) print '<h2>Some data from scraper: %s (%d columns)</h2>' % (sourcescraper, len(keys)) print '<table border="1" style="border-collapse:collapse;">' # column headings print "<tr>", for key in keys: print "<th>%s</th>" % key, print "</tr>" # rows for row in getData(sourcescraper, limit, offset): print "<tr>", for key in keys: print "<td>%s</td>" % row.get(key), print "</tr>"
######################################### # Simple table of values from one scraper ######################################### from scraperwiki.apiwrapper import getKeys, getData, getDataByDate, getDataByLocation sourcescraper = "cost_of_gov_websites" limit = 20 offset = 0 keys = getKeys(sourcescraper) keys.sort() # alphabetically print '<h2>Some data from scraper: %s (%d columns)</h2>' % (sourcescraper, len(keys)) print '<table border="1" style="border-collapse:collapse;">' # column headings print "<tr>", for key in keys: print "<th>%s</th>" % key, print "</tr>" # rows for row in getData(sourcescraper, limit, offset): print "<tr>", for key in keys: print "<td>%s</td>" % row.get(key), print "</tr>" print "</table>" #########################################
######################################### # Simple table of values from one scraper ######################################### from scraperwiki.apiwrapper import getKeys, getData, getDataByDate, getDataByLocation sourcescraper = "datagovuk-catalogue" limit = 20 offset = 0 all_keys = getKeys(sourcescraper) keys = ['title', 'name', 'department', 'agency', 'notes', 'url', 'resources'] keys += sorted(set(all_keys) - set(keys)) print '<h2>Some data from scraper: %s (%d columns)</h2>' % (sourcescraper, len(keys)) print '<table border="1" style="border-collapse:collapse;">' # column headings print "<tr>", for key in keys: print "<th>%s</th>" % key, print "</tr>" # rows for row in getData(sourcescraper, limit, offset): print "<tr>", for key in keys: print "<td>%s</td>" % row.get(key), print "</tr>" print "</table>"