the python code for holyokemall/hampshiremall deal info
[code]
#!/usr/local/bin/python
import datetime
def gendatestr(diff):
today = datetime.date.today()
delta = datetime.timedelta(days=diff)
thisday = today + delta
datestr = str(thisday.month)+"/"+str(thisday.day)+"/"+str(thisday.year)
return datestr
import urllib
def crawler(baseurl, diff):
request = baseurl + gendatestr(diff)
try:
conn = urllib.urlopen(request)
except IOError:
return False
page = conn.read()
conn.close()
return page
import re
def parser(s):
#strip comments
reg = re.compile('<!--.*?-->', re.I | re.M | re.S)
s = reg.sub("",s)
#build few table list
reg = re.compile('<table border=\"0\" cellpadding=\"0\" cellspacing=\"0\" class=\"listheadertable\">.*?<\/table>', re.I | re.M | re.S)
tblist = reg.findall(s)
#build triplets
triplets = []
for ele in tblist:
reg = re.compile('(?<=<td colspan="4" class="calendarlisttitle">).*?(?=<\/td>)',re.I | re.M | re.S)
tname = reg.findall(ele)
reg = re.compile('(?<=<td colspan="4" class="upcoming_datelist">).*?(?=<\/td>)',re.I | re.M | re.S)
ttime = reg.findall(ele)
reg = re.compile('(?<=<td colspan="4">).*?(?=<\/td>)',re.I | re.M | re.S)
tcontent = reg.findall(ele)
triplets = triplets + [[tname,ttime,tcontent]]
return triplets
def writer(filename, sumlist):
b = "<?xml version=\"1.0\" encoding=\"ISO-8859-1\"?>\n<"+filename+">\n"
e = "</"+filename+">\n"
tstr = ""
for ele in sumlist:
tstr = tstr + "<"+str(ele[0])+">\n"
if len(ele[1]) != 0:
for k in ele[1]:
tstr = tstr + "<tname>\n" + str(k[0]) + "\n</tname>\n"
tstr = tstr + "<tdate>\n" + str(k[1]) + "\n</tdate>\n"
tstr = tstr + "<tcontent>\n" + str(k[2]) + "\n</tcontent>\n"
tstr = tstr + "</"+str(ele[0])+">\n"
f = open(filename+'.xml','wt')
f.write(b+tstr+e)
f.close()
def writer_html(filename, sumlist):
b = "<html>\n<table border=1>\n"
e = "</table></html>\n"
tstr = ""
for ele in sumlist:
tstr = tstr + "<tr>\n<td>\n------" + str(ele[0]) + "------<br /><br />"
if len(ele[1]) != 0:
for k in ele[1]:
tname = str(k[0])
tdate = str(k[1])
tcontent = str(k[2])
tname = tname[2:len(tname)-2]
tdate = tdate[2:len(tdate)-2]
tcontent = tcontent[2:len(tcontent)-2]
ttstr = tname + tdate + tcontent
ttstr = re.sub('\\\\t',' ',ttstr)
ttstr = re.sub('\\\\r\\\\n','<br />',ttstr)
ttstr = re.sub('<p><\/p>',' ',ttstr)
tstr = tstr + ttstr
tstr = tstr + "</td></tr>\n"
f = open(filename+'.html','wt')
f.write(b+tstr+e)
f.close()
#main function loop
http_hampshiremall = "http://www.hampshiremall.com/calendar.asp?action=detail&incDate="
http_holyokemall = "http://www.holyokemall.com/calendar.asp?action=detail&incDate="
#hampshiremall
sumlist = []
sumlist_html = []
maxdays = 7
filename = "hampshiremall"
for days in range(0, maxdays):
sdate = gendatestr(days)
s = crawler(http_hampshiremall, days)
triplets = parser(s)
sumlist = sumlist + [["M_D_Y"+sdate.replace("/","_"),triplets]]
sumlist_html = sumlist_html + [[sdate,triplets]]
writer(filename,sumlist)
writer_html(filename,sumlist_html)
#holyokemall
sumlist = []
sumlist_html = []
maxdays = 7
filename = "holyokemall"
for days in range(0, maxdays):
sdate = gendatestr(days)
s = crawler(http_holyokemall, days)
triplets = parser(s)
sumlist = sumlist + [["M_D_Y"+sdate.replace("/","_"),triplets]]
sumlist_html = sumlist_html + [[sdate,triplets]]
writer(filename,sumlist)
writer_html(filename,sumlist_html)
[/code]