def parse_stop_route(self):
stop_id = self.id
type = self.get_node_text(self.root, "//div[@class='transportType']/h3").lower()
# get route info in this stop
route_nodes = self.root.xpath("//div[@class='lineInformationInner']/div/ul/li")
for node in route_nodes:
route_name = self.get_node_text(node, 'a')
route_id = self.get_node(node, 'a').get('href').split('/')[-1]
db.update_table('route', 'id', route_id, name=route_name, type=type)
title=link=line_id=None
for ttn in node.xpath('ul'):
title = self.get_node_text(ttn, 'li')
link = self.get_node(ttn, 'li/ul/li/a').get('href')
groups = self.timetable_url_pattern.findall(link)
if (len(groups) > 0):
line_id = groups[0][0]
tt_id = utils.get_timetable_id(route_id, stop_id, line_id)
print " ", "parsed timetable '%s' %s" % (title, tt_id)
db.update_table('timetable_index', 'id', tt_id,
route_id=route_id, stop_id=stop_id, line_id=line_id,
title=title, link=link)
def parse_timetable(self):
tt_node = self.get_node(self.root, "//div[@class='timetablesInner']/ul")
li_nodes = tt_node.xpath(".//li")
for node in li_nodes:
title = self.get_node_text(node, "./a")
link = self.get_node(node, "./a").get('href')
if link=="": continue
line_id = self.timetable_lineid_pattern.findall(link)[0]
tt_id = utils.get_timetable_id(route_id=self.id, line_id=line_id)
print " ", "parsed timetable '%s' %s" % (title, tt_id)
db.update_table('timetable_index', 'id', tt_id,
route_id=self.id, line_id=line_id, link=link, title=title)
