class BrasRNCHTMLParser(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.inColumn = False
self.chart = None
self.column = 0
self.base_url = ''
self.catalog = RncChartCatalog()
self.catalog.title = "Brasil RNC Charts"
self.inLink = False
def handle_starttag(self, tag, attrs):
if tag == 'tr':
self.chart = Chart()
self.chart.chart_format = 'Sailing Chart, International Chart'
elif tag == 'td':
self.inColumn = True
self.column += 1
elif tag == 'a' and self.inColumn and self.column == 3:
for attr in attrs:
if attr[0] == 'href':
self.chart.url = self.base_url + attr[1]
elif tag == 'a' and self.inColumn and self.column == 2:
for attr in attrs:
if attr[0] == 'href':
self.inLink = True
def handle_endtag(self, tag):
if tag == 'tr':
if self.chart.is_valid():
self.catalog.add_chart(self.chart)
else:
print "<!-- unavailable/invalid?"
pprint(vars(self.chart))
print "-->"
self.column = 0
elif tag == 'td':
self.inColumn = False
def handle_data(self, data):
if self.inColumn:
if self.inColumn:
if self.column == 1:
self.chart.number = data.strip().replace(" ", "_")
if self.column == 2:
if self.inLink and data.strip() != '':
self.chart.title = data.strip()
self.inLink = False
if self.column == 4:
try:
self.chart.zipfile_ts = datetime.strptime(
data.strip(), '%d/%m/%Y')
except:
pass
if self.column == 5:
self.chart.ntm_edition_last_correction = data.strip()
def print_xml(self):
self.catalog.print_xml(True)
"""Script to process the JSON feed of the Dutch IENC charts list and convert it to the XML catalog format
Part of the ChartCatalogs project
Copyright (c) 2019-2020 Marcel Verpaalen
Licensed under GPLv2 or, at your will later version
"""
import sys
from ChartCatalogs import Chart, RncChartCatalog
from datetime import datetime
import json
catalog = RncChartCatalog()
catalog.title = "Netherlands Inland ENC Charts"
with open(sys.argv[1]) as f:
data = json.load(f)
cnt = 0
for tileset in data:
chart = Chart()
chart.chart_format = 'Sailing Chart, International Chart'
chart.url = "https://vaarweginformatie.nl/fdd/main/wicket/resource/org.apache.wicket.Application/downloadfileResource?fileId=%s" % tileset[
'fileId']
chart.number = "%s" % cnt
chart.title = "%s" % tileset['name']
chart.zipfile_ts = datetime.fromtimestamp(tileset['date'] / 1000)
chart.target_filename = "%s.zip" % tileset['name']
catalog.add_chart(chart)
cnt = cnt + 1
catalog.print_xml(True)