def get(self):
code = int(self.request.get('code', '0'))
q = Department.gql('WHERE dptCode >= :1 ORDER BY dptCode', code)
dpts = q.fetch(limit=2)
nowDpt = dpts[0]
soup = BeautifulSoup( urllib2.urlopen( nowDpt.dptLink ) )
list = soup.table.findAll('a')
for one in list:
text = one.text;
name = re.split('[0-9]', text)[0]
code = text[ len(name):].split(' ')[0].split('(')[0] # Dealing w/ the special cases
doc = Doctor.all().filter('docCode =', code).get()
if not doc and len(code) != 0:
doc = Doctor()
doc.docName = name
doc.docCode = code
doc.put()
if( len(dpts) > 1):
nextDpt = dpts[1]
nextUrl = '/parse/doctor?code=%d' % nextDpt.dptCode
nextName = nextDpt.dptName
else:
nextUrl = '/'
nextName = 'END OF PARSING'
context = {
'type' : 'Doctor',
'nextUrl' : nextUrl,
'nextName': nextName,
}
path = os.path.join( os.path.dirname('__file__'), 'templates', 'parser.html')
self.response.out.write( template.render( path, context) )
def get(self):
code = int(self.request.get('code', '0'))
q = Department.gql('WHERE dptCode >= :1 ORDER BY dptCode', code)
dpts = q.fetch(limit=2)
nowDpt = dpts[0]
soup = BeautifulSoup( urllib2.urlopen( nowDpt.dptLink ) )
trlist = soup.table.findAll('tr', align='left')
for tr in trlist:
tdlist = tr.findAll('td')
column = 0;
for td in tdlist:
if column == 0:
dateStr = td.text.split('(')[1].split(')')[0]
month = dateStr.split('/')[0]
day = dateStr.split('/')[1]
year = str(datetime.datetime.now().year)
else:
if column == 1:
timeStr = 'A'
elif column == 2:
timeStr = 'B'
else:
timeStr = 'C'
alist = td.findAll(lambda tag: tag.name == 'a' and len(tag.attrs) == 2)
for a in alist:
text = a.text
name = re.split('[0-9]', text)[0]
doc = Doctor.all().filter('docName = ', name).get()
if doc:
clinic = Clinic()
link = a['href']
code = link.split('data=')[1].split('&sLoc')[0]
clinic.link = tzuPrifix + link
clinic.code = code
clinic.doctor = doc.key()
clinic.dept = nowDpt.key()
clinic.date = year + '-' + month + '-' + day + '-' + timeStr
clinic.put()
column = column + 1
if( len(dpts) > 1):
nextDpt = dpts[1]
nextUrl = '/parse/clinic?code=%d' % nextDpt.dptCode
nextName = nextDpt.dptName
else:
nextUrl = '/'
nextName = 'END OF PARSING'
context = {
'type' : 'Clinic',
'nextUrl' : nextUrl,
'nextName': nextName,
}
path = os.path.join( os.path.dirname('__file__'), 'templates', 'parser.html')
self.response.out.write( template.render( path, context) )