def get_races(eventlist):
for race in eventlist:
url = race['url']
try:
r = requests.get(url)
except:
time.sleep(3)
r = requests.get(url)
racelist = []
soup = bs.BeautifulSoup(r.text,'lxml')
for tr in soup.find_all('table'):
tds = tr.find_all('td')
length = len(tds)
for i in range(0,length,8):
#print(tds[i])
#print(tds)
x = tds[2+i].text.strip(' \t\n\r')
# print("X = " + x)
#print(dir(x))
# x = str(x)
#print(type(x))
x = x.replace(" ", "")
url = tds[0+i].find('a')
#print(url)
url = 'http://www.equibase.com' + url.get('href')
tabledic = {
'Race: ' : tds[0+i].text,
'URL' : url,
'Purse' : tds[1+i].text,
'Race Type' : x,
'Distance' : tds[3+i].text,
'Surface' : tds[4+i].text,
'Starters' : tds[5+i].text,
'Est. Post' : tds[6+i].text,
'Horses' : [],
}
#print(type(tabledic))
racelist.append(tabledic)
race['races'] = get_horses(racelist)
jsonero = json.dumps(eventlist)
jsonic = json.loads(jsonero)
print("DATE:", date) #datum
o = Country('1','America',jsonero,date) #datum
o.save()
datic = datetime.date.today()
d = str(datic)
filename = 'USA' + d + '.json'
path = "USFiles"
fullpath = os.path.join(path, filename)
f = open(fullpath,'w')
f.write(jsonero)
f.close()
def get_races(eventlist):
for race in eventlist:
global date
url = race['url']
date = race['date']
try:
r = requests.get(url)
except:
time.sleep(6)
r = requests.get(url)
racelist = []
soup = bs.BeautifulSoup(r.text, 'lxml')
for tr in soup.find_all('table'):
tds = tr.find_all('td')
length = len(tds)
for i in range(0, length, 7):
#print(tds[i])
#print(tds)
x = tds[2 + i].text.strip(' \t\n\r')
# print("X = " + x)
#print(dir(x))
# x = str(x)
#print(type(x))
x = x.replace(" ", "")
# print(tds[0])
url = tds[0 + i].find('a')
#print(url)
url = 'http://www.equibase.com' + url.get('href')
tabledic = {
'Race: ': tds[0 + i].text,
'URL': url,
'Purse': tds[1 + i].text,
'Race Type': x,
'Distance': tds[3 + i].text,
'Surface': tds[4 + i].text,
'Starters': tds[5 + i].text,
'Est. Post': tds[6 + i].text,
'Horses': [],
}
#print(type(tabledic))
racelist.append(tabledic)
race['races'] = get_horses(racelist)
jsonero = json.dumps(eventlist)
print("DATE:", date) #datum
o = Country('3', 'England', jsonero, date) #datum
o.save()
r = requests.put('https://konji-187909.appspot.com/api/regions/uk',
json=jsonero)
f = open('inbreds.json', 'w')
f.write(jsonero)
f.close()
def get_races(eventlist):
for race in eventlist:
url = race['url']
try:
r = requests.get(url)
except:
time.sleep(6)
r = requests.get(url)
racelist = []
soup = bs.BeautifulSoup(r.text, 'lxml')
for tr in soup.find_all('table'):
tds = tr.find_all('td')
length = len(tds)
for i in range(0, length, 8):
#print(tds[i])
#print(tds)
x = tds[2 + i].text.strip(' \t\n\r')
# print("X = " + x)
#print(dir(x))
# x = str(x)
#print(type(x))
x = x.replace(" ", "")
url = tds[0 + i].find('a')
#print(url)
url = 'http://www.equibase.com' + url.get('href')
tabledic = {
'Race: ': tds[0 + i].text,
'URL': url,
'Purse': tds[1 + i].text,
'Race Type': x,
'Distance': tds[3 + i].text,
'Surface': tds[4 + i].text,
'Starters': tds[5 + i].text,
'Est. Post': tds[6 + i].text,
'Horses': [],
}
#print(type(tabledic))
racelist.append(tabledic)
race['races'] = get_horses(racelist)
jsonero = json.dumps(eventlist)
print("DATE:", date) #datum
o = Country('1', 'America', jsonero, date) #datum
o.save()
noder = requests.post('replaceme.com', json=jsonero)
def get_races(eventlist):
for race in eventlist:
url = race['url']
try:
r = requests.get(url)
except:
time.sleep(3)
r = requests.get(url)
racelist = []
soup = bs.BeautifulSoup(r.text, 'lxml')
for tr in soup.find_all('table'):
tds = tr.find_all('td')
length = len(tds)
for i in range(0, length, 8):
#print(tds[i])
#print(tds)
x = tds[2 + i].text.strip(' \t\n\r')
# print("X = " + x)
#print(dir(x))
# x = str(x)
#print(type(x))
x = x.replace(" ", "")
url = tds[0 + i].find('a')
#print(url)
url = 'http://www.equibase.com' + url.get('href')
tabledic = {
'Race: ': tds[0 + i].text,
'URL': url,
'Purse': tds[1 + i].text,
'Race Type': x,
'Distance': tds[3 + i].text,
'Surface': tds[4 + i].text,
'Starters': tds[5 + i].text,
'Est. Post': tds[6 + i].text,
'Horses': [],
}
#print(type(tabledic))
racelist.append(tabledic)
race['races'] = get_horses(racelist)
jsonero = json.dumps(eventlist)
jsonic = json.loads(jsonero)
print("DATE:", date) #datum
o = Country('1', 'America', jsonero, date) #datum
o.save()
datic = datetime.date.today()
d = str(datic)
filename = 'USA' + d + '.json'
path = "USFiles"
fullpath = os.path.join(path, filename)
f = open(fullpath, 'w')
f.write(jsonero)
f.close()
p = Podesavanja.objects.get(id=1)
p.is_scraping = 0
p.save()
headers = {'Authorization': 'Zm9ybXVsYTE='}
scaling_payload = {
"min": "0",
"required": "0",
"max": "9",
}
rer = requests.patch('http://159.65.107.239:8889/api/scaling',
json=scaling_payload,
headers=headers)
print(rer)
def get_races(events):
global fontic
formData = {'raceYmd': 20171209, 'command': 'displayRaceList'}
kk = requests.post('http://210.145.16.108/jair/SelectRace.do',
data=formData)
soup = bs.BeautifulSoup(kk.text, 'lxml')
#print(soup)
#print(time.strftime("%Y/%m/%d"))
soup = soup.find('table', attrs={'width': 584})
tr = soup.find_all('tr')
lop = 0
ev = 0
for trs in tr[1:len(tr)]:
tds = trs.find_all('td')
for i in range(0, len(tds), 3):
#tds0 - vremeprva, #tds1 uputstva za slanje linka
#tds2 - vremedruga, #tds3 uputstva za slanje linka
time = tds[0 + i].text.replace(" ", "")
inform = tds[1 + i]
a = inform.find('a') #informator za post rikvest
#print(inform)
#print(a)
kek = (a.get('href')[19:400].replace("(", "").replace(
")", "").replace(" ", "")).strip(' \t\n\r') #isto kao dolje
kek = kek.split(',')
nl = []
for word in kek: #uklanja /n i ostalo
word = word.strip(" \t\n\r ' ")
#print(word)
nl.append(word)
res = {
'command': 'dispRaceResult',
'raceY': nl[0],
'raceMd': nl[1],
'raceJoCd': nl[2],
'raceKai': nl[3],
'raceHi': nl[4],
'raceNo': nl[5],
'dataKbn': nl[6],
}
race = {
'time': time,
'instr': res,
}
uuu = int(i / 3)
events[uuu]['races'].append(race)
# W#event[lop]['races'] =
#p#rint(res)
for me in events:
for race in (me['races']):
#horselist = []
#print(race['time'])
no = race['instr']['raceNo'].replace(" ", "")
print(race['time'] + " - " + race['instr']['raceNo'])
#print(events)
if (no == ''):
print("no race")
else:
url = 'http://210.145.16.108/jair/SelectDenma.do'
#formData = {'command': 'dispRaceResult', 'raceY': '2017', 'raceMd': '1126', 'raceJoCd': '05', 'raceKai': '05', 'raceHi': '08', 'raceNo': '01', 'dataKbn': '7'}
formData = race['instr']
req = requests.post(url, data=formData)
soup = bs.BeautifulSoup(req.text, 'lxml')
tablic = soup.find_all('table',
attrs={
'cellspacing': 0,
'cellpadding': 1,
'width': 720,
'bgcolor': '#ffffff',
'border': 1
})
print(tablic)
table = soup.find('table',
attrs={
'cellspacing': 0,
'cellpadding': 0,
'width': 720,
'bgcolor': '#ffffff',
'border': 0
})
tr = table.find_all('tr')
newtr = tablic[1].find_all('tr')
length = len(tr)
eventlist = []
#print("kek", length)
horselist = []
for i in range(5, length, 1):
print(i)
tds = tr[i].find_all('td')
newtds = newtr[i - 4].find_all('td')
#print(newtds)
hor = newtds[4].find_all('font')
siredam = newtds[2].find_all('font')
print(tds[2].text + " " + tds[3].text + " Jockey: " +
hor[0].text + " Trainer: " + hor[1].text + "Sire" +
siredam[0].text + "dam" + siredam[1].text)
print("itsthis")
horseurl = 'http://www.equineline.com/Free5XPedigreeSearchResults.cfm?horse_name=' + tds[
3].text + '&page_state=LIST_HITS&foaling_year=&dam_name=&include_sire_line=Y'
print(horseurl)
print("itsthis")
while (1):
proxies = {
'http': 'http://35.231.21.43:8888',
'https': 'https://35.231.21.43:8888',
}
headers = {
'user-agent':
'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0)',
'origin': 'https://www.equibase.com',
'x-requested-with': 'XMLHttpRequest'
}
try:
###proxies = get_proxy()
horsereq = requests.get(horseurl,
headers=headers,
timeout=9,
proxies=proxies)
except:
print('error')
tim.sleep(12)
horsereq = requests.get(horseurl,
headers=headers,
timeout=9,
proxies=proxies)
continue
else:
print("mek")
break
soup = bs.BeautifulSoup(horsereq.text, 'lxml')
h4 = soup.find('h4')
print(h4)
if (str(h4) == '<h4><strong>No Matches Found</strong></h4>'
):
print("Horse doesn't exist in DB")
inftab = 'n/a'
else:
#print(soup)
try:
horsrl = soup.find('a').get('href')
except:
print("Captcha error")
try:
ime = horsereq.history[0].headers[
'x-cache-proxyname']
except:
print("ime error")
tim.sleep(3)
else:
payld = {
'name': ime,
}
print(ime)
headers = {'Authorization': 'd2VhcmVzZWN1cmU='}
ipic = proxies.get('http')
ipic = ipic[0:-1] + '9'
print(ipic)
stop = requests.post(ipic + '/instances/stop',
json=payld,
headers=headers)
print("success")
#tim.sleep(12)
###proxies = get_proxy()
#tim.sleep(6)
while (1):
proxies = {
'http': 'http://35.231.21.43:8888',
'https': 'https://35.231.21.43:8888',
}
try:
##proxies = get_proxy()
horsereq = requests.get(horseurl,
headers=headers,
timeout=9,
proxies=proxies)
soup = bs.BeautifulSoup(
horsereq.text, 'lxml')
horsrl = soup.find('a').get('href')
except:
try:
ime = horsereq.history[0].headers[
'x-cache-proxyname']
print(ime)
payld = {
'name': ime,
}
headers = {
'Authorization': 'd2VhcmVzZWN1cmU='
}
ipic = proxies.get('http')
ipic = ipic[0:-1] + '9'
print(ipic)
stop = requests.post(ipic +
'/instances/stop',
json=payld,
headers=headers)
continue
except:
tim.sleep(2)
else:
break
#soup = bs.BeautifulSoup(horsereq.text, 'lxml')
#h#orsrl = soup.find('a').get('href')
url = 'http://www.equineline.com/' + horsrl
start = url.find('reference_number=')
end = url.find('®istry')
refnum = url[start + 17:end]
print(refnum)
link = 'http://www.equineline.com/Free5XPedigreeNickingDisplay.cfm?page_state=DISPLAY_REPORT&reference_number=' + refnum
#print(url)
#print(link)
while (1):
try:
##proxies = get_proxy()
maker = requests.get(link,
headers=headers,
timeout=9,
proxies=proxies)
supica = bs.BeautifulSoup(maker.text, 'lxml')
table = supica.find('table')
if (table is None):
##proxies = get_proxy()
#soup = bs.BeautifulSoup(r.text,'lxml')
try:
a = supica.find('a').get('href')
except:
a = ''
if (a == 'mailto:[email protected]'):
print("NO horse")
table = 'Notable'
else:
print("stvorena")
maker = requests.get(link,
headers=headers,
timeout=9,
proxies=proxies)
supica = bs.BeautifulSoup(
maker.text, 'lxml')
table = supica.find('table')
except:
continue
else:
break
#print(supica)
# table = supica.find('table')
#print(table)
#print(type(table))
while (1):
try:
if (table is None):
tim.sleep(6)
##proxies = get_proxy()
raise EnvironmentError
else:
break
except:
while (1):
try:
maker = requests.get(link,
headers=headers,
timeout=9)
except:
continue
else:
break
break
supica = bs.BeautifulSoup(maker.text, 'lxml')
table = supica.find('table')
if (table == 'Notable'):
inftab = 'n/a'
else:
inftab = get_table(table)
ud = str(uuid.uuid4())
horsedic = {
'P#': tds[2].text,
'Name': tds[3].text,
'Claim': 'No claim',
'Wgt': tds[5].text,
'Jockey': hor[0].text,
'Trainer': hor[1].text,
'Sire': siredam[0].text,
'Dam': siredam[1].text,
'info': inftab,
'uuid': ud,
}
print(horsedic)
horselist.append(horsedic)
race['horses'] = horselist
#print(horselist)
print(events)
#print(formData)
#print(formData.get('raceYmd'))
##date = (formData.get('raceYmd'))
o = Country('4', 'Japan', events, fontic)
o.save()
f = open('nippon2.json', 'w')
jsonero = json.dumps(events)
f.write(jsonero)
f.close()
def get_races(events):
global fontic
formData = {'raceYmd': 20171126, 'command': 'displayRaceList'}
kk = requests.post('http://210.145.16.108/jair/SelectRace.do',
headers=headers,
data=formData)
soup = bs.BeautifulSoup(kk.text, 'lxml')
#print(soup)
#print(time.strftime("%Y/%m/%d"))
soup = soup.find('table', attrs={'width': 584})
tr = soup.find_all('tr')
lop = 0
ev = 0
for trs in tr[1:len(tr)]:
tds = trs.find_all('td')
#tds0 - vremeprva, #tds1 uputstva za slanje linka
#tds2 - vremedruga, #tds3 uputstva za slanje linka
time = tds[lop + ev].text.replace(" ", "")
inform = tds[lop + ev + 1]
if (time == ''):
print("nista zovo")
if (ev == 2 and lop == 1):
time = tds[lop + ev].text.replace(" ", "")
elif (lop == 1 and ev == 0):
time = tds[0].text.replace(" ", "")
elif (lop == 0 and ev == 2):
time = tds[lop].text.replace(" ", "")
inform = tds[lop + ev + 1 + 1]
#print(inform)
#print(lop,ev)
#print(instr)
ev = 0
a = inform.find('a') #informator za post rikvest
#print(inform)
#print(a)
kek = (a.get('href')[19:400].replace("(", "").replace(")", "").replace(
" ", "")).strip(' \t\n\r') #isto kao dolje
kek = kek.split(',')
nl = []
for word in kek: #uklanja /n i ostalo
word = word.strip(" \t\n\r ' ")
#print(word)
nl.append(word)
res = {
'command': 'dispRaceResult',
'raceY': nl[0],
'raceMd': nl[1],
'raceJoCd': nl[2],
'raceKai': nl[3],
'raceHi': nl[4],
'raceNo': nl[5],
'dataKbn': nl[6],
}
race = {
'time': time,
'instr': res,
}
if (ev == 4):
ev = 0
else:
ev += 2
events[lop]['races'].append(race)
if (lop == 0):
lop = 1
else:
lop = 0
# W#event[lop]['races'] =
#p#rint(res)
for me in events:
for race in (me['races']):
#horselist = []
#print(race['time'])
print(race['time'] + " - " + race['instr']['raceNo'])
#print(events)
#cellspacing="0" cellpadding="1" width="720" bgcolor="#ffffff" border="1">
url = 'http://210.145.16.108/jair/SelectDenma.do'
#formData = {'command': 'dispRaceResult', 'raceY': '2017', 'raceMd': '1126', 'raceJoCd': '05', 'raceKai': '05', 'raceHi': '08', 'raceNo': '01', 'dataKbn': '7'}
formData = race['instr']
req = requests.post(url, data=formData)
soup = bs.BeautifulSoup(req.text, 'lxml')
tablic = soup.find_all('table',
attrs={
'cellspacing': 0,
'cellpadding': 1,
'width': 720,
'bgcolor': '#ffffff',
'border': 1
})
#print(tablic[1])
table = soup.find('table',
attrs={
'cellspacing': 0,
'cellpadding': 0,
'width': 720,
'bgcolor': '#ffffff',
'border': 0
})
tr = table.find_all('tr')
newtr = tablic[1].find_all('tr')
length = len(tr)
eventlist = []
#print("kek", length)
horselist = []
for i in range(5, length, 1):
print(i)
tds = tr[i].find_all('td')
newtds = newtr[i - 4].find_all('td')
#print(newtds)
hor = newtds[4].find_all('font')
siredam = newtds[2].find_all('font')
print(tds[2].text + " " + tds[3].text + " Jockey: " +
hor[0].text + " Trainer: " + hor[1].text + "Sire" +
siredam[0].text + "dam" + siredam[1].text)
print("itsthis")
horseurl = 'http://www.equineline.com/Free5XPedigreeSearchResults.cfm?horse_name=' + tds[
3].text + '&page_state=LIST_HITS&foaling_year=&dam_name=&include_sire_line=Y'
print(horseurl)
try:
horsereq = requests.get(horseurl, headers=headers)
except:
tim.sleep(6)
horsereq = requests.get(horseurl, headers=headers)
soup = bs.BeautifulSoup(horsereq.text, 'lxml')
h4 = soup.find('h4')
print(h4)
if (str(h4) == '<h4><strong>No Matches Found</strong></h4>'):
print("Horse doesn't exist in DB")
inftab = 'n/a'
else:
#print(soup)
try:
horsrl = soup.find('a').get('href')
except:
print("Captcha error")
tim.sleep(6)
tim.sleep(6)
horsereq = requests.get(horseurl, headers=headers)
soup = bs.BeautifulSoup(horsereq.text, 'lxml')
try:
horsrl = soup.find('a').get('href')
except:
print("-- MENJAJ --")
tim.sleep(12)
horsereq = requests.get(horseurl, headers=headers)
soup = bs.BeautifulSoup(horsereq.text, 'lxml')
try:
horsrl = soup.find('a').get('href')
except:
print("-- MENJAJ --")
tim.sleep(12)
horsereq = requests.get(horseurl, headers=headers)
soup = bs.BeautifulSoup(horsereq.text, 'lxml')
horsrl = soup.find('a').get('href')
url = 'http://www.equineline.com/' + horsrl
start = url.find('reference_number=')
end = url.find('®istry')
refnum = url[start + 17:end]
print(refnum)
link = 'http://www.equineline.com/Free5XPedigreeNickingDisplay.cfm?page_state=DISPLAY_REPORT&reference_number=' + refnum
#print(url)
#print(link)
try:
maker = requests.get(link, headers=headers)
except:
tim.sleep(6)
maker = requests.get(link, headers=headers)
supica = bs.BeautifulSoup(maker.text, 'lxml')
#print(supica)
table = supica.find('table')
#print(table)
#print(type(table))
if (table is None):
tim.sleep(6)
print("how")
maker = requests.get(link, headers=headers)
supica = bs.BeautifulSoup(maker.text, 'lxml')
table = supica.find('table')
if (table is None):
print("how")
tim.sleep(6)
maker = requests.get(link, headers=headers)
supica = bs.BeautifulSoup(maker.text, 'lxml')
table = supica.find('table')
inftab = get_table(table)
ud = str(uuid.uuid4())
horsedic = {
'P#': tds[2].text,
'Name': tds[3].text,
'Claim': 'No claim',
'Wgt': tds[5].text,
'Jockey': hor[0].text,
'Trainer': hor[1].text,
'Sire': siredam[0].text,
'Dam': siredam[1].text,
'info': inftab,
'uuid': ud,
}
print(horsedic)
horselist.append(horsedic)
race['horses'] = horselist
#print(horselist)
print(events)
#print(formData)
#print(formData.get('raceYmd'))
##date = (formData.get('raceYmd'))
o = Country('4', 'Japan', events, fontic)
o.save()
f = open('nippon2.json', 'w')
jsonero = json.dumps(events)
f.write(jsonero)
f.close()
