def get_pnr(pnr):
url = 'http://www.indianrail.gov.in/cgi_bin/inet_pnstat_cgi_10521.cgi'
values = {
'lccp_pnrno1': pnr,
'lccp_cap_val': 30000, # random value
'lccp_capinp_val': 30000
}
header = {
"Origin": "http://www.indianrail.gov.in",
"Host": "www.indianrail.gov.in",
"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer": "http://www.indianrail.gov.in/pnr_Enq.html"
}
html = fetchpage(url, values, header)
d = {}
num = re.findall(r"(?<=_both\">)\*?[0-9 -]+", html)
strings = re.findall(r"(?<=_both\">)[0-9A-Z ]+[A-Z]+", html)
strings = [s.strip() for s in strings]
psgr = re.findall(r"(?<=B>Passenger )[0-9]+", html)
status = re.findall(r"(?<=B>)(?!Passenger)[0-9A-Za-z/, ]+(?=</B>)", html)
status = [s.strip() for s in status]
booking_status = []
current_status = []
for i in range(0, len(status), 2):
booking_status.append(status[i])
current_status.append(status[i + 1])
try:
d['pnr'] = pnr
d['number'] = num[0][1:]
d['doj'] = strip_inline_space(num[1])
d['name'] = strings[0]
d['from'] = strings[1]
d['to'] = strings[2]
d['upto'] = strings[3]
d['boarding'] = strings[4]
d['class'] = strings[5]
d['chart'] = 'N' if strings[6] == 'CHART NOT PREPARED' else 'Y'
d['total'] = len(psgr)
d['booking_status'] = booking_status
d['current_status'] = current_status
d['error'] = False
except IndexError as e:
d['number'] = ''
d['doj'] = ''
d['name'] = ''
d['from'] = ''
d['to'] = ''
d['upto'] = ''
d['boarding'] = ''
d['class'] = ''
d['chart'] = ''
d['pnr'] = ''
d['total'] = 0
d['booking_status'] = ''
d['current_status'] = ''
d['error'] = True
return d
return d
def runningtime(url):
global pos
html=fetchpage(url)
stn=re.findall("(?<=td>)(?!Source|Destination)[A-Za-z() ]+",html)
times=re.findall("(?<=span=\"2\">)Source|(?<=td>)[0-9]+:[0-9]+ [PAM]+ / Destination|(?<=td>)Source / [0-9]+:[0-9]+ [PAM]+|(?<=td>)[0-9]+:[0-9]+ [PAM]+ / [0-9]+:[0-9]+ [PAM]+|(?<=td>)[0-9]+:[0-9]+ [PAM]+|(?<=td>)Source|(?<=td>)Destination|(?<=span=\"2\">)E.T.A.:[0-9PAM :]+|Waiting for Update",html)
status=re.findall("(?<=green\">)No Delay|(?<=red\">)[0-9]+ [A-Za-z0-9 ]+|(?<=blue\">)[A-Za-z 0-9.]+",html)
pos=re.search('(?<=br>Currently)[A-Za-z()0-9 ,<>\"\'=/:.]+(?=</p>)',html)
if pos!=None:
pos=remove_tag(pos.group(0))
lst=[]
i=0
for j in range(len(stn)):
d={}
d['station']=stn[j]
d['sch_arrival']=times[i]
d['sch_departure']=times[i+1]
try:
tm=times[i+2]
t=tm.split('/')
d['act_arrival']=t[0].strip()
d['act_departure']=t[1].strip()
except IndexError:
d['act_arrival']=tm
d['act_departure']='-'
lst.append(d)
i+=3
return lst
def extract_class(train):
url="http://erail.in/"+str(train)+"/route"
html=fetchpage(url)
l=[]
soup=BeautifulSoup(html,"html.parser")
length=0
for i in soup.find_all("b"):
if len(i.attrs)==0:
if(validate_class(i.text)):
for j in i.text.split(" "):
length+=1
l.append(j.strip())
if length<1: # rough heuristic to detect error
print('No data: ',train)
return None
classcode=['1A','FC','2A','3A','3E','CC','SL','2S']
d={}
#d['train-number']=l[3]
#d['train-name']=l[4]
d['class-code']=[]
not_encoutered_day=0
for i,txt in enumerate(l):
if txt in classcode:
d['class-code'].append(txt)
not_encoutered_day=1
elif not_encoutered_day==1:
break
d['route']=[]
return d
def runningtime(url):
global pos
html = fetchpage(url)
stn = re.findall("(?<=td>)(?!Source|Destination)[A-Za-z() ]+", html)
times = re.findall(
"(?<=span=\"2\">)Source|(?<=td>)[0-9]+:[0-9]+ [PAM]+ / Destination|(?<=td>)Source / [0-9]+:[0-9]+ [PAM]+|(?<=td>)[0-9]+:[0-9]+ [PAM]+ / [0-9]+:[0-9]+ [PAM]+|(?<=td>)[0-9]+:[0-9]+ [PAM]+|(?<=td>)Source|(?<=td>)Destination|(?<=span=\"2\">)E.T.A.:[0-9PAM :]+",
html)
status = re.findall(
"(?<=green\">)No Delay|(?<=red\">)[0-9]+ [A-Za-z0-9 ]+|(?<=blue\">)[A-Za-z 0-9.]+",
html)
pos = re.search('(?<=br>Currently)[A-Za-z()0-9 ,<>\"\'=/:.]+(?=</p>)',
html)
if pos != None:
pos = remove_tag(pos.group(0))
lst = []
i = 0
for j in range(len(stn)):
d = {}
d['station'] = stn[j]
d['sch_arrival'] = times[i]
d['sch_departure'] = times[i + 1]
try:
tm = times[i + 2]
t = tm.split('/')
d['act_arrival'] = t[0].strip()
d['act_departure'] = t[1].strip()
except IndexError:
d['act_arrival'] = tm
d['act_departure'] = '-'
lst.append(d)
i += 3
return lst
def extract(train):
url = "http://www.indianrail.gov.in/cgi_bin/inet_trnnum_cgi.cgi"
ref = "http://www.indianrail.gov.in/inet_trn_num.html"
html = fetchpage(url, {"lccp_trnname": train}, {"Referer": ref})
l = []
soup = BeautifulSoup(html)
length = 0
for i in soup.find_all("td"):
if len(i.attrs) == 0:
if validate(i.text):
length += 1
l.append(i.text.strip())
if length < 10: # rough heuristic to detect error
print("No data: ", train)
return None
daycode = ["MON", "TUE", "WED", "THU", "FRI", "SAT", "SUN"]
d = {}
d["train-number"] = l[3]
d["train-name"] = l[4]
d["day-code"] = []
not_encoutered_day = 0
for i, txt in enumerate(l):
if txt in daycode:
d["day-code"].append(txt)
not_encoutered_day = 1
elif not_encoutered_day == 1:
break
d["route"] = []
# for m in l[i:]:
# print(m)
l.append("END_MARKER")
l = iter(l[i:])
nxt = next(l)
while True:
t = {}
t["no"] = nxt
t["station-code"] = next(l)
t["station-name"] = next(l)
t["route-no"] = next(l)
t["arrival-time"] = next(l)
t["departure-time"] = next(l)
nxt = next(l)
# Many times no halt-time is given, this condition handles that case
if ":" not in nxt:
t["halt-time"] = 0
t["distance"] = nxt
else:
t["halt-time"] = nxt
t["distance"] = next(l)
t["day"] = next(l)
d["route"].append(t)
nxt = next(l)
# print(t)
if nxt == "END_MARKER":
break
return d
def between(source,dest,date):
url='http://www.indianrail.gov.in/cgi_bin/inet_srcdest_cgi_date.cgi'
date=date.split('-')
if len(date)==1:
date.append('')
cls="ZZ"
values={"lccp_src_stncode_dis":source,
"lccp_src_stncode":source,
"lccp_dstn_stncode_dis":dest,
"lccp_dstn_stncode":dest,
"lccp_classopt":cls,
"lccp_day":date[0],
"lccp_month":date[1],
"CurrentMonth":"4",
"CurrentDate":"19",
"CurrentYear":"2016"
}
header={"Origin":"http://www.indianrail.gov.in",
"Host":"www.indianrail.gov.in",
"User-Agent":"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer":"http://www.indianrail.gov.in/fare_Enq.html"
}
html=fetchpage(url,values,header)
soup=BeautifulSoup(html)
trains=[]
for link in soup.find_all(href="#SAMETRN"):
trains.append(link.text[1:].strip())
destinations=[]
sources=[]
alter=0
for tdtag in soup.find_all("td"):
tagattr=tdtag.attrs.get('title','')
if 'Station Code' in tagattr or 'temporary' in tagattr:
t={}
t['code']=extract_stn_code(tdtag['title'])
t['name']=sanitize(tdtag.text)
if alter==0:
t['name']=db.station_metadata(t['code'])['fullname']
sources.append(t)
alter=1
else:
destinations.append(t)
alter=0
days=re.findall("(?<=B>)Y|(?<=red>)N",html)
numbers=[]
for link in soup.find_all("input"):
if link.get("onclick",False):
#print(link['onclick'])
num=re.findall("(?<=\')[0-9]+(?=[A-Z]+)",link['onclick'])
if num!=[]:
numbers.append(num[0])
times=re.findall("(?<=TD>)[0-9:]+",html)
return format_result_json(trains,days,numbers,times,sources,destinations)
def get_train(url):
html = fetchpage(url)
progn = re.compile(r"(?<=VALUE=\")[0-9]+", re.IGNORECASE)
num = re.findall(progn, html)
progn = re.compile(r"(?<=LEFT\">)[A-Za-z]+[ A-Za-z]+",
re.IGNORECASE) #Extracts train names
name = re.findall(progn, html)
j = 0
for i in range(0, len(num)):
yield (num[i], name[j].strip())
j = j + 3 #j-2 & j-1 contains the starting and ending station of train
def get_pnr(pnr):
url='http://www.indianrail.gov.in/cgi_bin/inet_pnstat_cgi_10521.cgi'
values={'lccp_pnrno1':pnr,
'lccp_cap_val':30000,# random value
'lccp_capinp_val':30000}
header={"Origin":"http://www.indianrail.gov.in",
"Host":"www.indianrail.gov.in",
"User-Agent":"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer":"http://www.indianrail.gov.in/pnr_Enq.html"
}
html=fetchpage(url,values,header)
d={}
num=re.findall(r"(?<=_both\">)\*?[0-9 -]+",html)
strings=re.findall(r"(?<=_both\">)[0-9A-Z ]+[A-Z]+",html)
strings=[s.strip() for s in strings]
psgr=re.findall(r"(?<=B>Passenger )[0-9]+",html)
status=re.findall(r"(?<=B>)(?!Passenger)[0-9A-Za-z/, ]+(?=</B>)",html)
cancelled=0
if status!=[] and status[-1]=='TRAIN CANCELLED':
cancelled=1
status=[s.strip() for s in status]
booking_status=[]
current_status=[]
for i in range(0,len(status),2):
booking_status.append(status[i])
if cancelled:
current_status.append('TRAIN CANCELLED')
continue
current_status.append(status[i+1])
try:
d['pnr']=pnr
d['number']=num[0][1:]
d['doj']=strip_inline_space(num[1])
d['name']=strings[0]
d['from']=strings[1]
d['to']=strings[2]
d['upto']=strings[3]
d['boarding']=strings[4]
d['class']=strings[5]
d['chart']='N' if strings[6]=='CHART NOT PREPARED' else 'Y'
d['total']=len(psgr)
d['booking_status']=booking_status
d['current_status']=current_status
d['error']=False
except IndexError as e:
d['number']='';d['doj']='';d['name']='';d['from']=''
d['to']='';d['upto']='';d['boarding']='';d['class']=''
d['chart']='';d['pnr']='';d['total']=0;d['booking_status']=''
d['current_status']='';d['error']=True
return d
return d
def get_fare(k):
url = "http://www.indianrail.gov.in/cgi_bin/inet_frenq_cgi.cgi"
doj = k['doj'].split('-')
if len(doj) <= 1:
doj = ['31', '12', '2015'] #Default Date
k['quota'] = k['quota'].upper()
values = {
"lccp_trnno": k['train'],
"lccp_day": doj[0],
"lccp_month": doj[1],
"lccp_srccode": k['source'],
"lccp_dstncode": k['dest'],
#"lccp_classopt":k['pref'],
"lccp_classopt": "ZZ",
"lccp_age": k['age'],
"lccp_frclass1": k['quota'],
"lccp_conc": "ZZZZZZ",
"lccp_enrtcode": None,
"lccp_viacode": None,
"lccp_frclass2": "ZZ",
"lccp_frclass3": "ZZ",
"lccp_frclass4": "ZZ",
"lccp_frclass5": "ZZ",
"lccp_frclass6": "ZZ",
"lccp_frclass7": "ZZ",
"lccp_disp_avl_flg": "1",
"getIt": "Please Wait...",
}
header = {
"Origin": "http://www.indianrail.gov.in",
"Host": "www.indianrail.gov.in",
"User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer": "http://www.indianrail.gov.in/fare_Enq.html"
}
html = fetchpage(url, values, header)
cls = re.findall("(?<=Class -- )[0-9A-Za-z]+", html)
fares = re.findall("(?<=both\">)[0-9]+", html)
f = []
l = len(cls)
for i in range(l):
t = {}
t['class'] = cls[i]
t['fare'] = fares[-l + i]
f.append(t)
return f
def get_fare(k):
url="http://www.indianrail.gov.in/cgi_bin/inet_frenq_cgi.cgi"
doj=k['doj'].split('-')
if len(doj)<=1:
doj=['31','12','2015'] #Default Date
k['quota']=k['quota'].upper()
values={"lccp_trnno":k['train'],
"lccp_day":doj[0],
"lccp_month":doj[1],
"lccp_srccode":k['source'],
"lccp_dstncode":k['dest'],
#"lccp_classopt":k['pref'],
"lccp_classopt":"ZZ",
"lccp_age":k['age'],
"lccp_frclass1":k['quota'],
"lccp_conc":"ZZZZZZ",
"lccp_enrtcode":None,
"lccp_viacode":None,
"lccp_frclass2":"ZZ",
"lccp_frclass3":"ZZ",
"lccp_frclass4":"ZZ",
"lccp_frclass5":"ZZ",
"lccp_frclass6":"ZZ",
"lccp_frclass7":"ZZ",
"lccp_disp_avl_flg":"1",
"getIt":"Please Wait...",
}
header={"Origin":"http://www.indianrail.gov.in",
"Host":"www.indianrail.gov.in",
"User-Agent":"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer":"http://www.indianrail.gov.in/fare_Enq.html"
}
html=fetchpage(url,values,header)
cls=re.findall("(?<=Class -- )[0-9A-Za-z]+",html)
fares=re.findall("(?<=both\">)[0-9]+",html)
f=[]
l=len(cls)
for i in range(l):
t={}
t['class']=cls[i]
t['fare']=fares[-l+i]
f.append(t)
return f
def between(source,dest,date):
url='http://www.indianrail.gov.in/cgi_bin/inet_srcdest_cgi_date.cgi'
date=date.split('-')
cls="ZZ"
values={"lccp_src_stncode_dis":source,
"lccp_src_stncode":source,
"lccp_dstn_stncode_dis":dest,
"lccp_dstn_stncode":dest,
"lccp_classopt":cls,
"lccp_day":date[0],
"lccp_month":date[1],
"CurrentMonth":"4",
"CurrentDate":"19",
"CurrentYear":"2016"
}
header={"Origin":"http://www.indianrail.gov.in",
"Host":"www.indianrail.gov.in",
"User-Agent":"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer":"http://www.indianrail.gov.in/fare_Enq.html"
}
html=fetchpage(url,values,header)
soup=BeautifulSoup(html)
trains=[]
for link in soup.find_all(href="#SAMETRN"):
trains.append(link.text[1:].strip())
days=re.findall("(?<=B>)Y|(?<=red>)N",html)
numbers=[]
for link in soup.find_all("input"):
if link.get("onclick",False):
#print(link['onclick'])
num=re.findall("(?<=\')[0-9]+(?=[A-Z]+)",link['onclick'])
if num!=[]:
numbers.append(num[0])
times=re.findall("(?<=TD>)[0-9:]+",html)
return format_result_json(trains,days,numbers,times)
def get_seat(train,pref,quota,doj,source,dest):
url="http://www.indianrail.gov.in/cgi_bin/inet_accavl_cgi.cgi"
d={}
d['num']=train;d['quota']=quota;d['class']=pref
d['source']=source;d['dest']=dest
doj=doj.split('-')
if len(doj)!=3:
return nullify(d)
values={"lccp_trnno":train,
"lccp_day":doj[0],
"lccp_month":doj[1],
"lccp_srccode":source,
"lccp_dstncode":dest,
"lccp_class1":pref,
"lccp_quota":quota,
"lccp_classopt":"ZZ",
"lccp_class2":"ZZ",
"lccp_class3":"ZZ",
"lccp_class4":"ZZ",
"lccp_class5":"ZZ",
"lccp_class6":"ZZ",
"lccp_class7":"ZZ",
}
header={"Origin":"http://www.indianrail.gov.in",
"Host":"www.indianrail.gov.in",
"User-Agent":"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer":"http://www.indianrail.gov.in/seat_Avail.html"
}
html=fetchpage(url,values,header)
soup=BeautifulSoup(html)
seats=[]
dates=[]
for i in soup.find_all('td'):
if i.get('class',[None])[0]== 'table_border_both':
if len(i.attrs.keys())==1:
txt=i.text
if(ischaralpha(txt[0])):
seats.append(txt)
else:
dates.append(strip_inline_space(txt))
if seats==[]:
return nullify(d)
d['seats']=[]
d['dates']=[]
d['error']=False
#Sometimes the page contains seats for two classes and sometimes only for one
#so 'step' contain total classes shown in the page and adding it to seat gets only the seats for queried class
step=int(len(seats)/len(dates))
if step==0:
return nullify(d)
for i in range(0,len(seats),step):
d['seats'].append(seats[i])
for i in dates:
i=strip_inline_space(i)
d['dates'].append(i)
return d
def runningtime(number,doj):
url='http://runningstatus.in/status/{0}-on-{1}'.format(number,doj)
d={}
d['train_number']=number
nullify(d)
try:
# Converting time from GMT to IST
if len(doj)!=8:
raise
year=int(doj[0:4])
month=int(doj[4:6])
day=int(doj[6:8])
datetimeob=datetime.datetime(year,month,day)
except:
return format_result_json(nullify(d,'Date not in proper format'))
weekday=datetimeob.weekday()
html=fetchpage(url)
soup=BeautifulSoup(html,"lxml")
count=0
for i in soup.find_all("div"):
if i.attrs.get("class",[None])[0]=="runningstatus-widget-content":
if count==1:
dot=i.text.find('.')
if dot!=-1:
end=i.text.find('\n\n\n')
#Some pages of this site has no ending tag for <div>. Handles it.
if end==-1:
d['position']=i.text[dot+1:]
else:
d['position']=i.text[dot+1:end]
count+=1
if "TRAIN IS CANCELLED" in i.text:
return format_result_json(nullify(d,'Train is cancelled'))
delay_time_header=0
for i in soup.find_all("th"):
if i.text.strip()=="Delay Time":
delay_time_header=1
trainmd=db.train_metadata(number)
days=['MON','TUE','WED','THU','FRI','SAT','SUN']
if trainmd['days']!='':
if days[weekday] not in trainmd['days']:
return format_result_json(nullify(d,'Train does not run on given date'))
lst=[]
prog=re.compile("[A-Za-z0-9 .:/()-]+")
for i in soup.find_all("td"):
i=i.text.strip()
if prog.match(i):
lst.append(i)
lst.append('END_MARKER')
liter=iter(lst)
nxt=next(liter)
while True:
t={}
if nxt=='END_MARKER':
break
t['station']=nxt
t['platform']=next(liter)
t['scharr']=next(liter)
t['schdep']=next(liter)
t['actarr-actdep']=next(liter)
t['status']=''
nxt=next(liter)
if station_name_format(nxt) or nxt=='END_MARKER':
d['route'].append(t)
continue
if delay_time_header:
nxt=next(liter)
d['route'].append(t)
continue
t['status']=nxt
d['route'].append(t)
nxt=next(liter)
if d['route']==[]:
return format_result_json(nullify(d,'Invalid Train Number'))
return format_result_json(d)
def get_train(url):
soup = BeautifulSoup(fetchpage(url))
for i in soup.find_all("input"):
if i.attrs.get("value", False):
if i["value"].isnumeric():
yield i["value"]
def get_pnr(pnr):
url='http://www.indianrail.gov.in/cgi_bin/inet_pnstat_cgi_10521.cgi'
values={'lccp_pnrno1':pnr,
'lccp_cap_val':30000,# random value
'lccp_capinp_val':30000}
header={"Origin":"http://www.indianrail.gov.in",
"Host":"www.indianrail.gov.in",
"User-Agent":"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)",
"Referer":"http://www.indianrail.gov.in/pnr_Enq.html"
}
html=fetchpage(url,values,header)
d={}
nullify(d)
d['pnr']=pnr
soup=BeautifulSoup(html,"lxml")
mapper={0:'number',1:'name',2:'doj',3:'from',4:'to',5:'upto',6:'boarding',7:'class',8:'upgraded_class'}
count=0
cancelled=0
limit=8
status=[]
for i in soup.find_all("td"):
if i.attrs.get("class")==["table_border_both"]:
txt=i.text.strip()
if i.attrs.get("align")=="middle":
d['chart']='N' if 'CHART NOT PREPARED' in txt else 'Y'
continue
if count>=limit:
if 'Passenger' not in txt:
if status==[] and 'TRAIN CANCELLED' in txt:
cancelled=1
break
status.append(txt)
else:
d[mapper[count]]=txt
count+=1
elif i.attrs.get("width")=="5%": # <td width="5%">Upgraded class</td>
limit+=1
if cancelled or count==0:
return nullify(d)
if limit==9:
d['class']=d['upgraded_class'] # Updates current class to the upgraded class
total=0
length=len(status)
coachpos=0
if length%2==1:
coachpos=1
status=iter(status)
nxt=p_next(status)
while 1:
if nxt=='':
break
d['booking_status'].append(nxt)
nxt=p_next(status)
d['current_status'].append(nxt)
nxt=p_next(status)
if coachpos:
if nxt!='' and (nxt[0]>='0' and nxt[0]<='9'):
d['coach_position'].append(int(nxt))
nxt=p_next(status)
else:
d['coach_position'].append(0)
else:
d['coach_position'].append(0)
total+=1
d['total']=total
d['error']=False
return d
def extract(train):
url = "http://www.indianrail.gov.in/cgi_bin/inet_trnnum_cgi.cgi"
ref = "http://www.indianrail.gov.in/inet_trn_num.html"
html = fetchpage(url, {'lccp_trnname': train}, {'Referer': ref})
return extract_page(html)
import re
from fetchpage import fetchpage
def remove_tag(s):
IN_TAG=0
OUT_TAG=1
state=OUT_TAG
i=0
new=''
while i<len(s):
c=s[i]
i+=1
if state==OUT_TAG:
if c=='<':
state=IN_TAG
continue
elif state==IN_TAG:
if c=='>':
state=OUT_TAG
continue
new=new+c
return new
html=fetchpage('http://runningstatus.in/status/12555-today')
m=re.search('(?<=br>Currently)[A-Za-z()0-9 ,<>\"\'=/:.]+(?=</p>)',html)
s=m.group(0)
print(s)
print(remove_tag(s))
