if you have Python, an almost full alternative solution
Code:
#!/usr/bin/env python
import urllib2,re
pat=re.compile(""".*<span class="tdBlancBold">(.*)<div align="center">.*""",re.M|re.DOTALL)
days=['lundi','mardi','mercredi','jeudi','vendredi','samedi','dimanche']
url="http://www.natureetdecouvertes.com/pages/gener/view_FO_STORE_corgen.asp?mag_cod=%s"
for num in range(101,174):
page=urllib2.urlopen(url % str(num))
data=page.read()
if not "Impossible" in data:
result = pat.findall(data)
store={}
for i in result:
for j in i.split("<br>"):
j=j.strip()
if j.startswith("le"):
j=j.split()
if j[1] in days:
t1,t2=j[-3],j[-1]
store.setdefault(j[1],[])
store[j[1]].extend([t1,t2])
for DAY in days:
try:
print "%s |" %( ' '.join(store[DAY])),
except:
print "\t\t|",
print ""
else:
print "Page not found ",url % str(num)
extract of output :
Code:
# python test.py
10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 19.00 |
10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | |
10.00 20.00 | 10.00 20.00 | 10.00 20.00 | | 10.00 21.00 | 10.00 20.00 | |
10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | |
10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | |
10.00 21.00 | 10.00 21.00 | 10.00 21.00 | 10.00 21.00 | 10.00 21.00 | 10.00 20.00 | |
10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | |
10.00 20.00 | 10.00 21.00 | 10.00 21.00 | 10.00 21.00 | 10.00 21.00 | 10.00 20.00 | |
9.30 19.30 | 9.30 19.30 | 9.30 19.30 | 9.30 19.30 | 9.30 19.30 | 9.30 19.30 | |
Page not found http://www.natureetdecouvertes.com/pages/gener/view_FO_STORE_corgen.asp?mag_cod=110
10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | |
10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | 10.00 19.30 | |
10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | |
10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | 10.00 20.00 | |
9.30 19.30 | 9.30 19.30 | 9.30 19.30 | 9.30 19.30 | 9.30 19.30 | 9.30 19.30 | |
