def parse_infos_course(urlsource):
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
pronos_page = BeautifulSoup(html,"lxml")
boite_entete = pronos_page.find_all("div","boite4rond")[0]
num_course = urlsource[urlsource.rfind("/")+1:]
num_course = num_course[:num_course.find("_")]
nom_course = boite_entete.find_all("h1")[0].contents[0]
nom_course = sanitize.s(nom_course[:nom_course.find(' - ')])
reunion_course = boite_entete.find_all("h3")[0].contents[0]
reunion_course = sanitize.s(reunion_course[reunion_course.rfind('union')+6:])
lieu_course = boite_entete.find_all("h3")[0].contents[0]
lieu_course = lieu_course[:lieu_course.find(' | ')]
lieu_course = sanitize.s(lieu_course[lieu_course.find(' - ')+3:])
meteo_course = boite_entete.find_all("div","boite4rond")[0].find_all("img")
if not meteo_course:
meteo_course = ''
else:
meteo_course = meteo_course[0].get("src")
meteo_course = meteo_course[meteo_course.rfind('/')+1:]
meteo_course = meteo_dico[meteo_course]
temp_course = str(boite_entete.find("h4"))
if temp_course == 'None':
temp_course = ''
else :
temp_course = temp_course[temp_course.find(">")+1:temp_course.find("\xc2")] + ' - ' + temp_course[temp_course.rfind("/>")+2:temp_course.rfind("\xc2")]
type_course = boite_entete.find_all("p")[0].contents[0]
type_course = type_course[:type_course.find(' - ')]
distance_course = boite_entete.find_all("p")[0].contents[0]
distance_course = distance_course[:distance_course.find('m - ')]
distance_course = distance_course[distance_course.find(' - ')+3:]
prix_course = boite_entete.find_all("p")[0].contents[0]
prix_course = prix_course[prix_course.rfind(' - ')+3:]
prix_course = prix_course[:prix_course.find('&')]
date_course = urlsource[urlsource.find("prono")+15:urlsource.find("prono")+25]
heure_course = boite_entete.find_all("h3")[0].contents[0]
heure_course = heure_course[:heure_course.find(' - ')]
return [num_course,nom_course, reunion_course,lieu_course, meteo_course, temp_course,type_course, distance_course,prix_course, date_course,heure_course]
def find_nom_cheval(urlsource):
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
page = BeautifulSoup(html,"lxml")
try:
nom_cheval=page.find("div","ficheinfo").find("h1").contents[0].encode("ascii","ignore")
except:
nom_cheval = ''
return sanitize.s(nom_cheval)
def find_nom_cheval(urlsource):
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
page = BeautifulSoup(html, "lxml")
try:
nom_cheval = page.find("div",
"ficheinfo").find("h1").contents[0].encode(
"ascii", "ignore")
except:
nom_cheval = ''
return sanitize.s(nom_cheval)
def parse_infos_course(urlsource):
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
pronos_page = BeautifulSoup(html, "lxml")
boite_entete = pronos_page.find_all("div", "boite4rond")[0]
num_course = urlsource[urlsource.rfind("/") + 1:]
num_course = num_course[:num_course.find("_")]
nom_course = boite_entete.find_all("h1")[0].contents[0]
nom_course = sanitize.s(nom_course[:nom_course.find(' - ')])
reunion_course = boite_entete.find_all("h3")[0].contents[0]
reunion_course = sanitize.s(reunion_course[reunion_course.rfind('union') +
6:])
lieu_course = boite_entete.find_all("h3")[0].contents[0]
lieu_course = lieu_course[:lieu_course.find(' | ')]
lieu_course = sanitize.s(lieu_course[lieu_course.find(' - ') + 3:])
meteo_course = boite_entete.find_all("div",
"boite4rond")[0].find_all("img")
if not meteo_course:
meteo_course = ''
else:
meteo_course = meteo_course[0].get("src")
meteo_course = meteo_course[meteo_course.rfind('/') + 1:]
meteo_course = meteo_dico[meteo_course]
temp_course = str(boite_entete.find("h4"))
if temp_course == 'None':
temp_course = ''
else:
temp_course = temp_course[temp_course.find(">") + 1:temp_course.find(
"\xc2")] + ' - ' + temp_course[temp_course.rfind("/>") +
2:temp_course.rfind("\xc2")]
type_course = boite_entete.find_all("p")[0].contents[0]
type_course = type_course[:type_course.find(' - ')]
distance_course = boite_entete.find_all("p")[0].contents[0]
distance_course = distance_course[:distance_course.find('m - ')]
distance_course = distance_course[distance_course.find(' - ') + 3:]
prix_course = boite_entete.find_all("p")[0].contents[0]
prix_course = prix_course[prix_course.rfind(' - ') + 3:]
prix_course = prix_course[:prix_course.find('&')]
date_course = urlsource[urlsource.find("prono") +
15:urlsource.find("prono") + 25]
heure_course = boite_entete.find_all("h3")[0].contents[0]
heure_course = heure_course[:heure_course.find(' - ')]
return [
num_course, nom_course, reunion_course, lieu_course, meteo_course,
temp_course, type_course, distance_course, prix_course, date_course,
heure_course
]
def get_id_chevaux(mini,maxi):
nb_errors = 0
url_root = "http://www.canalturf.com/courses_fiche_cheval.php?idcheval="
cheval_id_table = []
for i in range(mini,maxi+1):
urlsource = url_root+str(i)
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
page = BeautifulSoup(html,"lxml").find("div","ficheinfo")
try:
cartouche = page.find_all("div")[0]
cart_infos = cartouche.find_all("div")[1]
palmares = page.find("div","fiche_bloc")
palm_infos = palmares.find("p")
except:
nb_errors = nb_errors +1
continue
num = str(i)
try:
nom = cartouche.find("h1").contents[0].encode("ascii","ignore")
nom = sanitize.s(nom[nom.find("chev")+7:])
except:
nom = ''
nb_errors = nb_errors+1
try:
sex = cart_infos.contents[0].encode("ascii","ignore")
sexe = sex[11:12]
age = sex[12:]
except:
sexe = ''
age = ''
nb_errors = nb_errors+1
try:
robe = cart_infos.contents[2].encode("ascii","ignore")[7:]
except:
robe = ''
nb_errors = nb_errors+1
try:
pere = sanitize.s(cart_infos.contents[4].encode("ascii","ignore")[6:])
except:
pere = ''
nb_errors = nb_errors+1
try:
mere = sanitize.s(cart_infos.contents[6].encode("ascii","ignore")[6:])
except:
mere = ''
nb_errors = nb_errors+1
try:
pere_mere = sanitize.s(cart_infos.contents[8].encode("ascii","ignore")[13:])
except:
pere_mere = ''
nb_errors = nb_errors+1
try:
proprio = sanitize.s(cart_infos.contents[11].encode("ascii","ignore")[14:])
except:
proprio = ''
nb_errors = nb_errors+1
try:
entraineur = sanitize.s(cart_infos.contents[13].encode("ascii","ignore")[13:])
except:
entraineur = ''
nb_errors = nb_errors+1
try:
eleveur = sanitize.s(cart_infos.contents[15].encode("ascii","ignore")[10:])
except:
eleveur = ''
nb_errors = nb_errors+1
try:
gain = palm_infos.contents[0].encode("ascii","ignore")[7:]
except:
gain = ''
nb_errors = nb_errors+1
try:
perfs = palm_infos.contents[2].encode("ascii","ignore")[8:]
except:
perfs = ''
nb_errors = nb_errors+1
try:
courus = palm_infos.contents[4].encode("ascii","ignore")[12:]
except:
courus = ''
nb_errors = nb_errors+1
try:
victoires = palm_infos.contents[6].encode("ascii","ignore")[14:]
except:
victoires = ''
nb_errors = nb_errors+1
try:
places = palm_infos.contents[8].encode("ascii","ignore")[10:]
except:
places = ''
nb_errors = nb_errors+1
cheval_id = [num,nom,sexe,age,robe,pere,mere,pere_mere,proprio,entraineur,eleveur,gain,perfs,\
courus,victoires,places]
cheval_id_table.append(cheval_id)
return (cheval_id_table,nb_errors)
def get_id_chevaux(mini, maxi):
nb_errors = 0
url_root = "http://www.canalturf.com/courses_fiche_cheval.php?idcheval="
cheval_id_table = []
for i in range(mini, maxi + 1):
urlsource = url_root + str(i)
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
page = BeautifulSoup(html, "lxml").find("div", "ficheinfo")
try:
cartouche = page.find_all("div")[0]
cart_infos = cartouche.find_all("div")[1]
palmares = page.find("div", "fiche_bloc")
palm_infos = palmares.find("p")
except:
nb_errors = nb_errors + 1
continue
num = str(i)
try:
nom = cartouche.find("h1").contents[0].encode("ascii", "ignore")
nom = sanitize.s(nom[nom.find("chev") + 7:])
except:
nom = ''
nb_errors = nb_errors + 1
try:
sex = cart_infos.contents[0].encode("ascii", "ignore")
sexe = sex[11:12]
age = sex[12:]
except:
sexe = ''
age = ''
nb_errors = nb_errors + 1
try:
robe = cart_infos.contents[2].encode("ascii", "ignore")[7:]
except:
robe = ''
nb_errors = nb_errors + 1
try:
pere = sanitize.s(cart_infos.contents[4].encode("ascii",
"ignore")[6:])
except:
pere = ''
nb_errors = nb_errors + 1
try:
mere = sanitize.s(cart_infos.contents[6].encode("ascii",
"ignore")[6:])
except:
mere = ''
nb_errors = nb_errors + 1
try:
pere_mere = sanitize.s(cart_infos.contents[8].encode(
"ascii", "ignore")[13:])
except:
pere_mere = ''
nb_errors = nb_errors + 1
try:
proprio = sanitize.s(cart_infos.contents[11].encode(
"ascii", "ignore")[14:])
except:
proprio = ''
nb_errors = nb_errors + 1
try:
entraineur = sanitize.s(cart_infos.contents[13].encode(
"ascii", "ignore")[13:])
except:
entraineur = ''
nb_errors = nb_errors + 1
try:
eleveur = sanitize.s(cart_infos.contents[15].encode(
"ascii", "ignore")[10:])
except:
eleveur = ''
nb_errors = nb_errors + 1
try:
gain = palm_infos.contents[0].encode("ascii", "ignore")[7:]
except:
gain = ''
nb_errors = nb_errors + 1
try:
perfs = palm_infos.contents[2].encode("ascii", "ignore")[8:]
except:
perfs = ''
nb_errors = nb_errors + 1
try:
courus = palm_infos.contents[4].encode("ascii", "ignore")[12:]
except:
courus = ''
nb_errors = nb_errors + 1
try:
victoires = palm_infos.contents[6].encode("ascii", "ignore")[14:]
except:
victoires = ''
nb_errors = nb_errors + 1
try:
places = palm_infos.contents[8].encode("ascii", "ignore")[10:]
except:
places = ''
nb_errors = nb_errors + 1
cheval_id = [num,nom,sexe,age,robe,pere,mere,pere_mere,proprio,entraineur,eleveur,gain,perfs,\
courus,victoires,places]
cheval_id_table.append(cheval_id)
return (cheval_id_table, nb_errors)
def parse_infos_chevaux(urlsource):
nb_errors = 0
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
pronos_page = BeautifulSoup(html, "lxml")
table_chevaux = pronos_page.find(
"table", "course").find_all("tbody")[1].find_all("tr")
label = pronos_page.find("table",
"course").find_all("tbody")[0].find_all("td")
for i in range(0, len(label)):
label[i] = str(label[i].contents)
result_cheval = []
for cheval in table_chevaux:
sstable = cheval.find_all("td")
num_course = urlsource[urlsource.rfind("/") + 1:]
num_course = num_course[:num_course.find("_")]
if sstable[0].string == "NP":
result_cheval.append([num_course,sstable[1].string,\
'',"NP",'','','','','','','','','','','',''])
continue
nom_cheval = sanitize.s(
cheval.find("strong").contents[0].encode("ascii", "ignore"))
id_cheval = cheval.find("a", "fiche").get("href")
id_cheval = id_cheval[id_cheval.find("idcheval") + 9:]
id_cheval = id_cheval[:id_cheval.find("&")]
num_cheval = sstable[0].string.encode("ascii", "ignore")
ind = find_index(label, "Def")
try:
def_cheval = sstable[ind].contents[0].encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
def_cheval = ''
ind = find_index(label, "Ec")
try:
ecurie_cheval = sstable[ind].contents[0].encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
ecurie_cheval = ''
ind = find_index(label, "Corde")
try:
corde_cheval = sstable[ind].contents[0].encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
corde_cheval = ''
ind = find_index(label, "Oeil")
try:
oeil_cheval = sstable[ind].contents[0].encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
oeil_cheval = ''
ind = find_index(label, "Entrai")
try:
jockey_cheval = sanitize.s(
sstable[ind].find_all("a")[0].contents[1].encode(
"ascii", "ignore"))
except:
nb_errors = nb_errors + 1
jockey_cheval = ''
ind = find_index(label, "Poids")
try:
poids_cheval = sstable[ind].contents[0].encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
poids_cheval = ''
ind = find_index(label, "Dist")
try:
dist_cheval = sstable[ind].contents[0].encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
dist_cheval = ''
ind = find_index(label, "10h")
try:
cote10h_cheval = sstable[ind].contents[0].string.encode(
"ascii", "ignore")
except:
nb_errors = nb_errors + 1
cote10h_cheval = ''
try:
cotepmu_cheval = sstable[ind + 1].find(
"strong").contents[0].string.encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
cotepmu_cheval = ''
try:
variation = sstable[ind + 2].contents[0].string.encode(
"ascii", "ignore")
except:
nb_errors = nb_errors + 1
variation = ''
try:
cotezeturf_cheval = sstable[ind + 3].find(
"strong").contents[0].string.encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
cotezeturf_cheval = ''
try:
cotebetclic_cheval = sstable[ind + 4].find(
"strong").contents[0].string.encode("ascii", "ignore")
except:
nb_errors = nb_errors + 1
cotebetclic_cheval = ''
cheval_infos = [num_course, nom_cheval, id_cheval, num_cheval,\
def_cheval,ecurie_cheval, corde_cheval,oeil_cheval,jockey_cheval,\
poids_cheval,dist_cheval,cote10h_cheval,cotepmu_cheval,variation,\
cotezeturf_cheval,cotebetclic_cheval]
result_cheval.append(cheval_infos)
return (result_cheval, nb_errors)
def parse_infos_chevaux(urlsource):
nb_errors = 0
req = urllib2.Request(urlsource)
html = urllib2.urlopen(req)
pronos_page = BeautifulSoup(html,"lxml")
table_chevaux = pronos_page.find("table", "course").find_all("tbody")[1].find_all("tr")
label = pronos_page.find("table", "course").find_all("tbody")[0].find_all("td")
for i in range(0,len(label)):
label[i] = str(label[i].contents)
result_cheval = []
for cheval in table_chevaux:
sstable = cheval.find_all("td")
num_course = urlsource[urlsource.rfind("/")+1:]
num_course = num_course[:num_course.find("_")]
if sstable[0].string == "NP":
result_cheval.append([num_course,sstable[1].string,\
'',"NP",'','','','','','','','','','','',''])
continue
nom_cheval = sanitize.s(cheval.find("strong").contents[0].encode("ascii","ignore"))
id_cheval = cheval.find("a","fiche").get("href")
id_cheval = id_cheval[id_cheval.find("idcheval")+9:]
id_cheval = id_cheval[:id_cheval.find("&")]
num_cheval = sstable[0].string.encode("ascii","ignore")
ind = find_index(label,"Def")
try:
def_cheval = sstable[ind].contents[0].encode("ascii","ignore")
except:
nb_errors = nb_errors+1
def_cheval = ''
ind = find_index(label,"Ec")
try:
ecurie_cheval = sstable[ind].contents[0].encode("ascii","ignore")
except:
nb_errors = nb_errors+1
ecurie_cheval = ''
ind = find_index(label,"Corde")
try:
corde_cheval = sstable[ind].contents[0].encode("ascii","ignore")
except:
nb_errors = nb_errors+1
corde_cheval = ''
ind = find_index(label,"Oeil")
try:
oeil_cheval = sstable[ind].contents[0].encode("ascii","ignore")
except:
nb_errors = nb_errors+1
oeil_cheval = ''
ind = find_index(label,"Entrai")
try:
jockey_cheval = sanitize.s(sstable[ind].find_all("a")[0].contents[1].encode("ascii","ignore"))
except:
nb_errors = nb_errors+1
jockey_cheval = ''
ind = find_index(label,"Poids")
try:
poids_cheval = sstable[ind].contents[0].encode("ascii","ignore")
except:
nb_errors = nb_errors+1
poids_cheval = ''
ind = find_index(label,"Dist")
try:
dist_cheval = sstable[ind].contents[0].encode("ascii","ignore")
except:
nb_errors = nb_errors+1
dist_cheval = ''
ind = find_index(label,"10h")
try:
cote10h_cheval = sstable[ind].contents[0].string.encode("ascii","ignore")
except:
nb_errors = nb_errors+1
cote10h_cheval = ''
try:
cotepmu_cheval = sstable[ind+1].find("strong").contents[0].string.encode("ascii","ignore")
except:
nb_errors = nb_errors+1
cotepmu_cheval = ''
try:
variation = sstable[ind+2].contents[0].string.encode("ascii","ignore")
except:
nb_errors = nb_errors+1
variation = ''
try:
cotezeturf_cheval = sstable[ind+3].find("strong").contents[0].string.encode("ascii","ignore")
except:
nb_errors = nb_errors+1
cotezeturf_cheval = ''
try:
cotebetclic_cheval = sstable[ind+4].find("strong").contents[0].string.encode("ascii","ignore")
except:
nb_errors = nb_errors+1
cotebetclic_cheval = ''
cheval_infos = [num_course, nom_cheval, id_cheval, num_cheval,\
def_cheval,ecurie_cheval, corde_cheval,oeil_cheval,jockey_cheval,\
poids_cheval,dist_cheval,cote10h_cheval,cotepmu_cheval,variation,\
cotezeturf_cheval,cotebetclic_cheval]
result_cheval.append(cheval_infos)
return (result_cheval,nb_errors)
