def oparl_file_downloadUrl_data(params):
file_data = db.get_file(deref={'values': ['file']},
search_params={'_id': ObjectId(params['file_id'])})
if len(file_data) == 0:
# TODO: Rendere informativere 404 Seite
abort(404)
file_data = file_data[0]
# 'file' property is not set (e.g. due to depublication)
if 'file' not in file_data:
if 'depublication' in file_data:
abort(410) # Gone
else:
# TODO: log this as unexplicable...
abort(500)
handler = db.get_file_data(file_data['file']['_id'])
response = make_response(handler.read(), 200)
response.mimetype = file_data['mimetype']
response.headers['X-Robots-Tag'] = 'noarchive'
response.headers['ETag'] = file_data['sha1Checksum']
response.headers['Last-modified'] = util.rfc1123date(file_data['file']['uploadDate'])
response.headers['Expires'] = util.expires_date(hours=(24 * 30))
response.headers['Cache-Control'] = util.cache_max_age(hours=(24 * 30))
response.headers['Content-Disposition'] = 'attachment; filename=' + file_data['filename']
return response
def oparl_file_downloadUrl_data(params):
file_data = db.get_file(deref={'values': ['file']},
search_params={'_id': ObjectId(params['file_id'])})
if len(file_data) == 0:
# TODO: Rendere informativere 404 Seite
abort(404)
file_data = file_data[0]
# 'file' property is not set (e.g. due to depublication)
if 'file' not in file_data:
if 'depublication' in file_data:
abort(410) # Gone
else:
# TODO: log this as unexplicable...
abort(500)
handler = db.get_file_data(file_data['file']['_id'])
response = make_response(handler.read(), 200)
response.mimetype = file_data['mimetype']
response.headers['X-Robots-Tag'] = 'noarchive'
response.headers['ETag'] = file_data['sha1Checksum']
response.headers['Last-modified'] = util.rfc1123date(file_data['file']['uploadDate'])
response.headers['Expires'] = util.expires_date(hours=(24 * 30))
response.headers['Cache-Control'] = util.cache_max_age(hours=(24 * 30))
response.headers['Content-Disposition'] = 'attachment; filename=' + file_data['filename']
return response
def attachment_view(attachment_id, extension, savefile=False):
"""
Abruf/Download eines Attachments
"""
attachment_info = db.get_attachment(attachment_id)
#pprint.pprint(attachment_info)
if attachment_info is None:
# TODO: Rendere informativere 404 Seite
abort(404)
# extension doesn't match file extension (avoiding arbitrary URLs)
proper_extension = attachment_info['filename'].split('.')[-1]
if proper_extension != extension:
abort(404)
# 'file' property is not set (e.g. due to depublication)
if 'file' not in attachment_info:
if 'depublication' in attachment_info:
abort(410) # Gone
else:
# TODO: log this as unexplicable...
abort(500)
# handle conditional GET
if 'If-Modified-Since' in request.headers:
file_date = attachment_info['file']['uploadDate'].replace(tzinfo=None)
request_date = util.parse_rfc1123date(request.headers['If-Modified-Since'])
difference = file_date - request_date
if difference < datetime.timedelta(0, 1): # 1 second
return Response(status=304)
#if 'if-none-match' in request.headers:
# print "Conditional GET: If-None-Match"
# TODO: handle ETag in request
handler = db.get_file(attachment_info['file']['_id'])
response = make_response(handler.read(), 200)
response.mimetype = attachment_info['mimetype']
response.headers['X-Robots-Tag'] = 'noarchive'
response.headers['ETag'] = attachment_info['sha1']
response.headers['Last-modified'] = util.rfc1123date(
attachment_info['file']['uploadDate'])
response.headers['Expires'] = util.expires_date(
hours=(24 * 30))
response.headers['Cache-Control'] = util.cache_max_age(
hours=(24 * 30))
# Save to file option
if savefile == True:
response.headers['Content-Disposition'] = 'attachment; filename=%s' % attachment_info['filename']
response.headers['X-Robots-Tag'] = 'noindex'
# See https://support.google.com/webmasters/answer/139394
response.headers['Link'] = '<%sanhang/%s.%s>; rel="canonical"' % (
app.config['BASE_URL'], attachment_id, extension)
return response
def suche_feed():
start_time = time.time()
jsonp_callback = request.args.get('callback', None)
q = request.args.get('q', '*:*')
fq = request.args.get('fq', '')
date_param = request.args.get('date', '')
region = request.args.get('r', app.config['region_default'])
# Suche wird durchgeführt
query = db.query_paper(region=region, q=q, fq=fq, sort='publishedDate:desc', start=0,
papers_per_page=50, facets=False)
# Generate Root and Metainfos
search_url = "%s/suche/?r=%s&q=%s&fq=%s" % (app.config['base_url'], region, q, fq)
feed_url = "%s/suche/feed/?r=%s&q=%s&fq=%s" % (app.config['base_url'], region, q, fq)
root = etree.Element("rss", version="2.0", nsmap={'atom': 'http://www.w3.org/2005/Atom'})
channel = etree.SubElement(root, "channel")
etree.SubElement(channel, "title").text = 'Offenes Ratsinformationssystem: Paper-Feed'
etree.SubElement(channel, "link").text = search_url
etree.SubElement(channel, "language").text = 'de-de'
description = u"Neue oder geänderte Dokumente mit dem Suchbegriff %s in %s" % (q, app.config['regions'][region]['name'])
# TODO: Einschränkungen mit in die Description
if fq:
description += ''
etree.SubElement(channel, "description").text = description
etree.SubElement(channel, '{http://www.w3.org/2005/Atom}link', href=feed_url, rel="self", type="application/rss+xml")
# Generate Result Items
for paper in query['result']:
item = etree.SubElement(channel, "item")
paper_link = "%s/paper/%s" % (app.config['base_url'], paper['id'])
description = 'Link: ' + paper_link + '</br>'
if 'paperType' in paper:
description = 'Art des Papers: ' + paper['paperType'] + '<br />'
if 'publishedDate' in paper:
description += u"Erstellt am: %s<br />" % dateutil.parser.parse(paper['publishedDate']).strftime('%d.%m.%Y')
if 'lastModified' in paper:
description += u"Zuletzt geändert am: %s<br />" % dateutil.parser.parse(paper['lastModified']).strftime('%d.%m.%Y')
etree.SubElement(item, "pubDate").text = util.rfc1123date(paper['lastModified'] if 'lastModified' in paper else datetime.datetime.now())
etree.SubElement(item, "title").text = paper['name'] if 'name' in paper else 'Kein Titel'
etree.SubElement(item, "description").text = description
etree.SubElement(item, "link").text = paper_link
etree.SubElement(item, "guid").text = paper_link
response = make_response(etree.tostring(root, pretty_print=True), 200)
response.mimetype = 'application/rss+xml'
response.headers['Expires'] = util.expires_date(hours=24)
response.headers['Cache-Control'] = util.cache_max_age(hours=24)
return response
def attachment_download(attachment_id, extension):
"""
Download eines Attachments
"""
attachment_info = db.get_attachment(attachment_id)
#pprint.pprint(attachment_info)
if attachment_info is None:
# TODO: Rendere informativere 404 Seite
abort(404)
# extension doesn't match file extension (avoiding arbitrary URLs)
proper_extension = attachment_info['filename'].split('.')[-1]
if proper_extension != extension:
abort(404)
# 'file' property is not set (e.g. due to depublication)
if 'file' not in attachment_info:
if 'depublication' in attachment_info:
abort(410) # Gone
else:
# TODO: log this as unexplicable...
abort(500)
# handle conditional GET
if 'If-Modified-Since' in request.headers:
file_date = attachment_info['file']['uploadDate'].replace(tzinfo=None)
request_date = util.parse_rfc1123date(request.headers['If-Modified-Since'])
difference = file_date - request_date
if difference < datetime.timedelta(0, 1): # 1 second
return Response(status=304)
#if 'if-none-match' in request.headers:
# print "Conditional GET: If-None-Match"
# TODO: handle ETag in request
handler = db.get_file(attachment_info['file']['_id'])
response = make_response(handler.read(), 200)
response.mimetype = attachment_info['mimetype']
response.headers['X-Robots-Tag'] = 'noarchive'
response.headers['ETag'] = attachment_info['sha1']
response.headers['Last-modified'] = util.rfc1123date(
attachment_info['file']['uploadDate'])
response.headers['Expires'] = util.expires_date(
hours=(24 * 30))
response.headers['Cache-Control'] = util.cache_max_age(
hours=(24 * 30))
return response
def attachment_download(attachment_id, extension):
"""
Download eines Attachments
"""
attachment_info = db.get_attachment(attachment_id)
#pprint.pprint(attachment_info)
if attachment_info is None:
# TODO: Rendere informativere 404 Seite
abort(404)
# extension doesn't match file extension (avoiding arbitrary URLs)
proper_extension = attachment_info['filename'].split('.')[-1]
if proper_extension != extension:
abort(404)
# 'file' property is not set (e.g. due to depublication)
if 'file' not in attachment_info:
if 'depublication' in attachment_info:
abort(410) # Gone
else:
# TODO: log this as unexplicable...
abort(500)
# handle conditional GET
if 'If-Modified-Since' in request.headers:
file_date = attachment_info['file']['uploadDate'].replace(tzinfo=None)
request_date = util.parse_rfc1123date(
request.headers['If-Modified-Since'])
difference = file_date - request_date
if difference < datetime.timedelta(0, 1): # 1 second
return Response(status=304)
#if 'if-none-match' in request.headers:
# print "Conditional GET: If-None-Match"
# TODO: handle ETag in request
handler = db.get_file(attachment_info['file']['_id'])
response = make_response(handler.read(), 200)
response.mimetype = attachment_info['mimetype']
response.headers['X-Robots-Tag'] = 'noarchive'
response.headers['ETag'] = attachment_info['sha1']
response.headers['Last-modified'] = util.rfc1123date(
attachment_info['file']['uploadDate'])
response.headers['Expires'] = util.expires_date(hours=(24 * 30))
response.headers['Cache-Control'] = util.cache_max_age(hours=(24 * 30))
return response
def oparl_file_accessUrl_data(params):
file_data = db.get_file(deref={'values': ['file']},
search_params={'_id': ObjectId(params['file_id'])})
if len(file_data) == 0:
# TODO: Rendere informativere 404 Seite
abort(404)
file_data = file_data[0]
# extension doesn't match file extension (avoiding arbitrary URLs)
#proper_extension = attachment_info['filename'].split('.')[-1]
#if proper_extension != extension:
# abort(404)
# 'file' property is not set (e.g. due to depublication)
if 'file' not in file_data:
if 'depublication' in file_data:
abort(410) # Gone
else:
# TODO: log this as unexplicable...
abort(500)
# handle conditional GET
#if 'If-Modified-Since' in request.headers:
# file_date = attachment_info['file']['uploadDate'].replace(tzinfo=None)
# request_date = util.parse_rfc1123date(request.headers['If-Modified-Since'])
# difference = file_date - request_date
# if difference < datetime.timedelta(0, 1): # 1 second
# return Response(status=304)
#if 'if-none-match' in request.headers:
# print "Conditional GET: If-None-Match"
# TODO: handle ETag in request
handler = db.get_file_data(file_data['file']['_id'])
response = make_response(handler.read(), 200)
response.mimetype = file_data['mimetype']
response.headers['X-Robots-Tag'] = 'noarchive'
response.headers['ETag'] = file_data['sha1Checksum']
response.headers['Last-modified'] = util.rfc1123date(file_data['file']['uploadDate'])
response.headers['Expires'] = util.expires_date(hours=(24 * 30))
response.headers['Cache-Control'] = util.cache_max_age(hours=(24 * 30))
return response
def oparl_file_accessUrl_data(params):
file_data = db.get_file(deref={'values': ['file']},
search_params={'_id': ObjectId(params['file_id'])})
if len(file_data) == 0:
# TODO: Rendere informativere 404 Seite
abort(404)
file_data = file_data[0]
# extension doesn't match file extension (avoiding arbitrary URLs)
#proper_extension = attachment_info['filename'].split('.')[-1]
#if proper_extension != extension:
# abort(404)
# 'file' property is not set (e.g. due to depublication)
if 'file' not in file_data:
if 'depublication' in file_data:
abort(410) # Gone
else:
# TODO: log this as unexplicable...
abort(500)
# handle conditional GET
#if 'If-Modified-Since' in request.headers:
# file_date = attachment_info['file']['uploadDate'].replace(tzinfo=None)
# request_date = util.parse_rfc1123date(request.headers['If-Modified-Since'])
# difference = file_date - request_date
# if difference < datetime.timedelta(0, 1): # 1 second
# return Response(status=304)
#if 'if-none-match' in request.headers:
# print "Conditional GET: If-None-Match"
# TODO: handle ETag in request
handler = db.get_file_data(file_data['file']['_id'])
response = make_response(handler.read(), 200)
response.mimetype = file_data['mimetype']
response.headers['X-Robots-Tag'] = 'noarchive'
response.headers['ETag'] = file_data['sha1Checksum']
response.headers['Last-modified'] = util.rfc1123date(file_data['file']['uploadDate'])
response.headers['Expires'] = util.expires_date(hours=(24 * 30))
response.headers['Cache-Control'] = util.cache_max_age(hours=(24 * 30))
return response
def suche_feed():
start_time = time.time()
jsonp_callback = request.args.get('callback', None)
q = request.args.get('q', '*:*')
fq = request.args.get('fq', '')
date_param = request.args.get('date', '')
region = request.args.get('r', app.config['region_default'])
# Suche wird durchgeführt
query = db.query_paper(region=region,
q=q,
fq=fq,
sort='publishedDate:desc',
start=0,
papers_per_page=50,
facets=False)
# Generate Root and Metainfos
search_url = "%s/suche/?r=%s&q=%s&fq=%s" % (app.config['base_url'], region,
q, fq)
feed_url = "%s/suche/feed/?r=%s&q=%s&fq=%s" % (app.config['base_url'],
region, q, fq)
root = etree.Element("rss",
version="2.0",
nsmap={'atom': 'http://www.w3.org/2005/Atom'})
channel = etree.SubElement(root, "channel")
etree.SubElement(
channel, "title").text = 'Offenes Ratsinformationssystem: Paper-Feed'
etree.SubElement(channel, "link").text = search_url
etree.SubElement(channel, "language").text = 'de-de'
description = u"Neue oder geänderte Dokumente mit dem Suchbegriff %s in %s" % (
q, app.config['regions'][region]['name'])
# TODO: Einschränkungen mit in die Description
if fq:
description += ''
etree.SubElement(channel, "description").text = description
etree.SubElement(channel,
'{http://www.w3.org/2005/Atom}link',
href=feed_url,
rel="self",
type="application/rss+xml")
# Generate Result Items
for paper in query['result']:
item = etree.SubElement(channel, "item")
paper_link = "%s/paper/%s" % (app.config['base_url'], paper['id'])
description = 'Link: ' + paper_link + '</br>'
if 'paperType' in paper:
description = 'Art des Papers: ' + paper['paperType'] + '<br />'
if 'publishedDate' in paper:
description += u"Erstellt am: %s<br />" % dateutil.parser.parse(
paper['publishedDate']).strftime('%d.%m.%Y')
if 'modified' in paper:
description += u"Zuletzt geändert am: %s<br />" % dateutil.parser.parse(
paper['modified']).strftime('%d.%m.%Y')
etree.SubElement(item, "pubDate").text = util.rfc1123date(
paper['modified'] if 'modified' in
paper else datetime.datetime.now())
etree.SubElement(
item,
"title").text = paper['name'] if 'name' in paper else 'Kein Titel'
etree.SubElement(item, "description").text = description
etree.SubElement(item, "link").text = paper_link
etree.SubElement(item, "guid").text = paper_link
response = make_response(etree.tostring(root, pretty_print=True), 200)
response.mimetype = 'application/rss+xml'
response.headers['Expires'] = util.expires_date(hours=24)
response.headers['Cache-Control'] = util.cache_max_age(hours=24)
return response
