def download_and_cache(self):
self.log.log("--- START DOWNLOAD AND CACHE DATA ---")
self.log.log2video_status("STARTING DOWNLOAD")
self.log.log("Removing old cached files")
scriptlib.cleanup_oldcachedfiles(self.CONF_CACHEDIR,
self.FIELD_SEPARATOR)
self.log.log("Start download XML data from \'%s\'" % self.CONF_URL)
self.log.log2video_status("downloading XML data ...")
i = self.HTTP_ERROR_RETRY
while i > 0:
try:
sock = urllib2.urlopen(self.CONF_URL)
data = sock.read()
except IOError as e:
serr = "unknown"
if hasattr(e, 'reason'):
serr = str(e.reason)
elif hasattr(e, 'code'):
serr = str(e.code)
if hasattr(e, 'msg'):
serr += " , " + str(e.msg)
self.log.log("\'" + self.CONF_URL +
"\' connection error. Reason: " + serr +
". Waiting " + str(self.HTTP_ERROR_WAIT_RETRY) +
" sec. and retry [" + str(i) + "] ...")
time.sleep(self.HTTP_ERROR_WAIT_RETRY) # add sleep
i -= 1
else:
i = -99
sock.close()
if (i != -99):
self.log.log("Cannot retrieve data from \'" + self.CONF_URL +
"\'. Abort script")
self.log.log2video_status("ERROR: cannot download XML data, abort")
time.sleep(5)
sys.exit(1)
self.log.log("end download XML data, now processing")
self.log.log2video_status("processing XML data, wait ...")
# replace malformed single end tag <.../> as <...> (SGML doesn't like "/>")
data = data.replace('/>', '></programma>')
# set max 'id' occurencies
self.SGML_PBAR_MAXVALUE = data.count('idref="')
# start SGMLLIB parsing
self.log.log2video_pbar_on()
self.log.log2video_pbar(0)
self.parse(data)
self.log.log2video_pbar(0)
self.log.log2video_pbar_off()
self.log.log("end process XML data")
def download_and_cache(self):
self.log.log("--- START DOWNLOAD AND CACHE DATA ---")
self.log.log2video_status("STARTING DOWNLOAD")
self.log.log("Removing old cached files")
scriptlib.cleanup_oldcachedfiles(self.CONF_CACHEDIR, self.FIELD_SEPARATOR)
self.log.log("Start download XML data from \'%s\'" % self.CONF_URL )
self.log.log2video_status("downloading XML data ...")
i = self.HTTP_ERROR_RETRY
while i > 0:
try:
sock = urllib2.urlopen(self.CONF_URL)
data = sock.read()
except IOError, e:
serr = "unknown"
if hasattr(e, 'reason'):
serr = str(e.reason)
elif hasattr(e, 'code'):
serr = str(e.code)
if hasattr(e, 'msg'):
serr += " , " + str(e.msg)
self.log.log("\'" + self.CONF_URL + "\' connection error. Reason: "+serr+". Waiting "+str(self.HTTP_ERROR_WAIT_RETRY)+" sec. and retry ["+str(i)+"] ...")
time.sleep(self.HTTP_ERROR_WAIT_RETRY) # add sleep
i -= 1
else:
i = -99
sock.close()
def download_and_cache(self):
self.log("--- START DOWNLOAD AND CACHE DATA ---")
self.log2video("STARTING DOWNLOAD")
self.log("Removing old cached files")
scriptlib.cleanup_oldcachedfiles(self.CONF_CACHEDIR,
self.FIELD_SEPARATOR)
self.log("Start download XML data from \'" + self.CONF_URL + "\'")
self.log2video("downloading XML data ...")
i = self.HTTP_ERROR_RETRY
while i > 0:
try:
sock = urllib2.urlopen(self.CONF_URL)
data = sock.read()
except IOError, e:
serr = "unknown"
if hasattr(e, 'reason'):
serr = str(e.reason)
elif hasattr(e, 'code'):
serr = str(e.code)
if hasattr(e, 'msg'):
serr += " , " + str(e.msg)
self.log("\'" + self.CONF_URL +
"\' connection error. Reason: " + serr +
". Waiting " + str(self.HTTP_ERROR_WAIT_RETRY) +
" sec. and retry [" + str(i) + "] ...")
time.sleep(self.HTTP_ERROR_WAIT_RETRY) # add sleep
i -= 1
else:
i = -99
sock.close()
def download_and_cache(self):
self.log.log("--- START DOWNLOAD AND CACHE DATA ---")
self.log.log2video_status("STARTING DOWNLOAD")
self.log.log("Removing old cached files")
scriptlib.cleanup_oldcachedfiles(self.CONF_CACHEDIR, self.FIELD_SEPARATOR)
#self.log("Start downloading HTML data from \'%s\'" % self.CONF_URL)
chlist = self.CHANNELLIST
# get remote XML files
# chid format: channel id , 0|1|2(,new name)
# i.e. ("101" , "1,SkyCinema1")
pbar_max = 0
for c in chlist.keys():
cacheopt = int(string.split(chlist[c],",")[0])
if cacheopt == 1:
pbar_max += 1
pbar_max *= self.CONF_MAX_DAY_EPG
pbar_max = 100.0 / pbar_max
self.log.log2video_pbar_on()
self.log.log2video_pbar(0)
pbar_value = 0
for c in sorted(chlist.keys()):
self.guidatoday = []
self.guidatomorrow = []
# get cache option
# 0 : don't download/cache
# 1 : download and cache (optional 1,new_name )
# 2 : always download overwriting existing files (optional 2,new_name )
# 3 : always download overwriting existing files only for TODAY (optional 3,new_name )
cacheopt = int(string.split(chlist[c],",")[0])
# if cacheopt == 0, do nothing
if cacheopt == 0:
continue
self.log.log2video_status("processing %s" % c)
channel_name = ''
if len(chlist[c].split(",")) > 1 :
if chlist[c].split(",")[1] != '' :
# channel renamed, new name provided by user
channel_name = chlist[c].split(",")[1].strip(' ').lower()
# if channel name is not present as option, quit with error
if channel_name == '':
self.log.log("ERROR ! ID=%s channel name not present" % c)
sys.exit(1)
channel_provider = self.CONF_DEFAULT_PROVIDER
if len(chlist[c].split(",")) > 2 :
if chlist[c].split(",")[2] != '' :
channel_provider = chlist[c].split(",")[2].strip(' ').lower()
exit_for_loop = False
for day in self.DAYCACHE:
if exit_for_loop == True:
break
pbar_value += 1
self.log.log2video_pbar(pbar_value * pbar_max)
day_get = time.strftime("%Y_%m_%d",time.strptime(day,"%Y%m%d"))
xmlfile = "%s_%s" % (c,day_get)
# download only if file doesn't exist or cacheopt == 2 (always download),
# using open(...,"w") files will be overwritten (saving a delete + create)
eventfilename = scriptlib.fn_escape(str(c) + self.FIELD_SEPARATOR + channel_name + self.FIELD_SEPARATOR + day)
eventfilepath = os.path.join(self.CONF_CACHEDIR, eventfilename)
if (cacheopt == 1) and os.path.exists(eventfilepath):
continue
if (cacheopt == 3) and os.path.exists(eventfilepath) and (day != self.TODAY):
continue
if (cacheopt != 1) and (cacheopt != 2) and (cacheopt != 3):
self.log.log("Warning: unknown cache option %s" % cacheopt)
exit_for_loop = True
continue
self.log.log("Download HTML data from \'%s/%s.html\'" % (self.CONF_URL,xmlfile))
self.log.log2video_status("downloading %s" % xmlfile)
i = self.HTTP_ERROR_RETRY
while i > 0 :
# wait randomly to avoid overloading website
time.sleep(random.uniform(self.CONF_RANDOM_MIN, self.CONF_RANDOM_MAX))
try:
sock=urllib2.urlopen(self.CONF_URL + '/' + xmlfile + '.html')
data=sock.read()
except IOError, e:
serr="unknown"
if hasattr(e, 'reason'):
serr=str(e.reason)
elif hasattr(e, 'code'):
serr=str(e.code)
if hasattr(e, 'msg'):
serr+=" , "+str(e.msg)
self.log.log("\'%s?%s\' connection error. Reason: %s. Waiting %d sec. and retry [%d] ..." % (self.CONF_URL,xmlfile, serr, self.HTTP_ERROR_WAIT_RETRY, i))
time.sleep(self.HTTP_ERROR_WAIT_RETRY) # add sleep
i -= 1
else:
i = 0 # force quit WHILE loop
sock.close()
dtparser = Titolo_parser(day)
dtparser.parse(data)
self.guida = self.guidatomorrow
(self.guidatoday, self.guidatomorrow) = dtparser.get_guida()
# if no data, quit for loop and stop downloading
if len(self.guidatoday) == 0:
exit_for_loop = True
break
self.guida = self.guida + self.guidatoday
self.log.log(" writing in cache \'%s\'" % eventfilename)
# write data in cache file using UTF-8 encoding
fd = codecs.open(eventfilepath, "w", 'utf-8')
fd.write(str(c) + self.FIELD_SEPARATOR + channel_name + self.FIELD_SEPARATOR + channel_provider + self.FIELD_SEPARATOR + day + '\n')
fd.write("Local Time (human readeable)###Unix GMT Time###Event Title###Event Description\n")
# extract all events and put in eventfile
for event in self.guida:
(dataora,titolo,sommario) = event
event_starttime = dataora
# time.mktime return Unix time inside GMT timezone
event_startime_unix_gmt = str(int(time.mktime(time.strptime(event_starttime,"%Y-%m-%d %H:%M"))) - self.DELTA_UTC )
#event_startime_unix_gmt = str(int(time.mktime(time.strptime(event_starttime,"%Y-%m-%d %H:%M"))) )
#self.log(event_starttime + " , " + str(self.DELTA_UTC) + " , " + str(int(time.mktime(time.strptime(event_starttime,"%Y-%m-%d %H:%M")))) + " , " + event_startime_unix_gmt )
# convert remote data (RAI website use UTF-8) in Python Unicode (UCS2)
event_title = unicode(titolo,self.REMOTE_EPG_CHARSET)
event_title = event_title.replace('\r','')
event_title = event_title.replace('\n',u' ')
event_title = event_title.strip(u' ')
event_description = unicode(sommario,self.REMOTE_EPG_CHARSET)
event_description = event_description.replace('\r','')
event_description = event_description.replace('\n',u' ')
event_description = event_description.strip(u' ')
fd.write(event_starttime + self.FIELD_SEPARATOR + event_startime_unix_gmt + self.FIELD_SEPARATOR + event_title + self.FIELD_SEPARATOR + event_description + '\n')
fd.close()
def download_and_cache(self):
self.log("--- START DOWNLOAD AND CACHE DATA ---")
self.log2video("STARTING DOWNLOAD")
self.log("Removing old cached files")
scriptlib.cleanup_oldcachedfiles(self.CONF_CACHEDIR,
self.FIELD_SEPARATOR)
chlist = self.CHANNELLIST
self.log("Start download XML data from \'" + self.CONF_URL + "\'")
self.log2video("downloading XML data ...")
i = self.HTTP_ERROR_RETRY
while i > 0:
try:
sock = urllib2.urlopen(self.CONF_URL)
data = sock.read()
except IOError as e:
serr = "unknown"
if hasattr(e, 'reason'):
serr = str(e.reason)
elif hasattr(e, 'code'):
serr = str(e.code)
if hasattr(e, 'msg'):
serr += " , " + str(e.msg)
self.log("\'" + self.CONF_URL +
"\' connection error. Reason: " + serr +
". Waiting " + str(self.HTTP_ERROR_WAIT_RETRY) +
" sec. and retry [" + str(i) + "] ...")
time.sleep(self.HTTP_ERROR_WAIT_RETRY) # add sleep
i -= 1
else:
i = -99
sock.close()
if (i != -99):
self.log("Cannot retrieve data from \'" + self.CONF_URL +
"\'. Abort script")
self.log2video("Error: cannot download XML data, abort")
time.sleep(5)
sys.exit(1)
self.log("End download XML data, now processing XML code.")
self.log2video("preprocessing XML data, wait ...")
try:
xmldoc = minidom.parseString(data)
except:
self.log(
"Warning ! Data are not in a valid XML format. Abort script")
self.log2video("Error: no valid XML data, abort")
time.sleep(5)
sys.exit(1)
self.log("End process XML data")
self.log2video("end process XML data")
# days list
xmlref_giorno = xmldoc.getElementsByTagName('giorno')
for xml_gg in xmlref_giorno:
gg = xml_gg.attributes["data"].value
if gg not in self.DAYCACHEMP:
continue
xmlref_canale = xml_gg.getElementsByTagName('canale')
for xml_ch in xmlref_canale:
chid = xml_ch.attributes["id"].value.strip(' \n\r').lower()
if chid not in chlist:
self.log(
"Warning: new channel \"id=%s name=%s\" found in XML data"
% (xml_ch.attributes["id"].value,
xml_ch.attributes["description"]))
continue
clist = [chid]
if chid + '+1' in self.CHANNELLIST:
clist.append(chid + '+1')
for c in clist:
# get cache option
# 0 : don't download/cache
# 1 : download and cache (optional 1,new_name )
# 2 : always download overwriting existing files (optional 2,new_name )
# 3 : always download overwriting existing files only for TODAY (optional 3,new_name )
cacheopt = int(chlist[c].split(",")[0])
# if cacheopt == 0, do nothing
if cacheopt == 0:
continue
channel_name = ''
if len(chlist[c].split(",")) > 1:
if chlist[c].split(",")[1] != '':
# channel renamed, new name provided by user
channel_name = chlist[c].split(",")[1].strip(
' \n\r').lower()
# if channel name is not present as option, quit with error
if channel_name == '':
self.log("ERROR ! ID=%s channel name not present" % c)
sys.exit(1)
channel_provider = self.CONF_DEFAULT_PROVIDER
if len(chlist[c].split(",")) > 2:
if chlist[c].split(",")[2] != '':
channel_provider = chlist[c].split(",")[2].strip(
' \n\r').lower()
# if channel name is not present as option in channel_list.conf , quit with error
if channel_name == '':
self.log("ERROR ! ID=" + str(c) +
" channel name not present. Skip !")
continue
# download only if file doesn't exist or cacheopt == 2 (always download),
# using open(...,"w") files will be overwritten (saving a delete + create)
day = str(self.convert_daymp(gg))
eventfilename = scriptlib.fn_escape(
str(c) + self.FIELD_SEPARATOR + channel_name +
self.FIELD_SEPARATOR + day)
eventfilepath = os.path.join(self.CONF_CACHEDIR,
eventfilename)
if (cacheopt == 1) and os.path.exists(eventfilepath):
continue
if (cacheopt == 3) and os.path.exists(eventfilepath) and (
gg != self.TODAYMP):
continue
if (cacheopt != 1) and (cacheopt != 2) and (cacheopt != 3):
self.log("Warning: unknown cache option " +
str(cacheopt))
exit_for_loop = True
continue
num_events = 0
self.log(" Writing in cache \'" + eventfilename + "\'", 2)
self.log2video(" extracting \"%s\" [%d] (%s)" %
(channel_name, num_events, day))
fd = codecs.open(eventfilepath, "w", 'utf-8')
fd.write(
str(c) + self.FIELD_SEPARATOR + channel_name +
self.FIELD_SEPARATOR + channel_provider +
self.FIELD_SEPARATOR + day + '\n')
fd.write(
"Local Time (human readeable)###Unix GMT Time###Event Title###Event Description\n"
)
xmlref_events = xml_ch.getElementsByTagName('prg')
for xml_ee in xmlref_events:
orainiz = xml_ee.attributes["orainizio"].value
if (orainiz >= '00:00') and (orainiz <= '05:59'):
nextdayevent = 86400
else:
nextdayevent = 0
event_starttime = gg + " " + orainiz
if c == (chid + '+1'):
# manage channel "+1"
event_startime_unix_gmt = str(
int(
time.mktime(
time.strptime(event_starttime,
"%Y/%m/%d %H:%M"))) -
self.DELTA_UTC + 3600 + nextdayevent)
else:
# normal channel, not "+1"
event_startime_unix_gmt = str(
int(
time.mktime(
time.strptime(event_starttime,
"%Y/%m/%d %H:%M"))) -
self.DELTA_UTC + nextdayevent)
event_title = unicode(
xml_ee.getElementsByTagName('titolo')
[0].firstChild.data)
event_title = event_title.replace('\r', '')
event_title = event_title.replace('\n', '')
event_title = event_title.strip(u' ')
event_description = ''
if self.CONF_DL_DESC == 1:
url_desc = xml_ee.getElementsByTagName(
'linkScheda')[0].firstChild.data
event_description = unicode(
self.get_description(url_desc.strip(' \n\r'))
[:self.CONF_DLDESCMAXCHAR])
event_description = event_description.replace(
'\r', '')
event_description = event_description.replace(
'\n', u' ')
event_description = event_description.strip(u' ')
fd.write(event_starttime + self.FIELD_SEPARATOR +
event_startime_unix_gmt +
self.FIELD_SEPARATOR + event_title +
self.FIELD_SEPARATOR + event_description +
'\n')
num_events += 1
self.log2video(" extracting \"%s\" [%d] (%s)" %
(channel_name, num_events, day))
fd.close()
del xmldoc
def download_and_cache(self):
self.log("--- START DOWNLOAD AND CACHE DATA ---")
self.log2video("STARTING DOWNLOAD")
self.log("Removing old cached files")
scriptlib.cleanup_oldcachedfiles(self.CONF_CACHEDIR,
self.FIELD_SEPARATOR)
#self.log("Start downloading HTML data from \'%s\'" % self.CONF_URL)
chlist = self.CHANNELLIST
# get remote XML files
# chid format: channel id , 0|1|2(,new name)
# i.e. ("101" , "1,SkyCinema1")
for c in sorted(chlist.keys()):
self.guidatoday = []
self.guidatomorrow = []
# get cache option
# 0 : don't download/cache
# 1 : download and cache (optional 1,new_name )
# 2 : always download overwriting existing files (optional 2,new_name )
# 3 : always download overwriting existing files only for TODAY (optional 3,new_name )
cacheopt = int(string.split(chlist[c], ",")[0])
# if cacheopt == 0, do nothing
if cacheopt == 0:
continue
channel_name = ''
if len(chlist[c].split(",")) > 1:
if chlist[c].split(",")[1] != '':
# channel renamed, new name provided by user
channel_name = chlist[c].split(",")[1].strip(' ').lower()
# if channel name is not present as option, quit with error
if channel_name == '':
self.log("ERROR ! ID=%s channel name not present" % c, 1)
sys.exit(1)
channel_provider = self.CONF_DEFAULT_PROVIDER
if len(chlist[c].split(",")) > 2:
if chlist[c].split(",")[2] != '':
channel_provider = chlist[c].split(",")[2].strip(
' ').lower()
exit_for_loop = False
for day in self.DAYCACHE:
if exit_for_loop == True:
break
day_get = time.strftime("%Y_%m_%d",
time.strptime(day, "%Y%m%d"))
xmlfile = "?%s_%s" % (c, day_get)
# download only if file doesn't exist or cacheopt == 2 (always download),
# using open(...,"w") files will be overwritten (saving a delete + create)
eventfilename = scriptlib.fn_escape(
str(c) + self.FIELD_SEPARATOR + channel_name +
self.FIELD_SEPARATOR + day)
eventfilepath = os.path.join(self.CONF_CACHEDIR, eventfilename)
if (cacheopt == 1) and os.path.exists(eventfilepath):
continue
if (cacheopt == 3) and os.path.exists(eventfilepath) and (
day != self.TODAY):
continue
if (cacheopt != 1) and (cacheopt != 2) and (cacheopt != 3):
self.log("Warning: unknown cache option " + str(cacheopt))
exit_for_loop = True
continue
self.log("Download HTML data from \'%s\'" %
(self.CONF_URL + xmlfile))
self.log2video("Download " + c)
i = self.HTTP_ERROR_RETRY
while i > 0:
# wait randomly to avoid overloading website
time.sleep(
random.uniform(self.CONF_RANDOM_MIN,
self.CONF_RANDOM_MAX))
try:
sock = urllib2.urlopen(self.CONF_URL + xmlfile)
data = sock.read()
except IOError, e:
serr = "unknown"
if hasattr(e, 'reason'):
serr = str(e.reason)
elif hasattr(e, 'code'):
serr = str(e.code)
if hasattr(e, 'msg'):
serr += " , " + str(e.msg)
self.log(
"\'%s\' connection error. Reason: %s. Waiting %d sec. and retry [%d] ..."
% (self.CONF_URL + xmlfile, serr,
self.HTTP_ERROR_WAIT_RETRY, i))
time.sleep(self.HTTP_ERROR_WAIT_RETRY) # add sleep
i -= 1
else:
i = 0 # force quit WHILE loop
sock.close()
dtparser = Titolo_parser(day)
dtparser.parse(data)
self.guida = self.guidatomorrow
(self.guidatoday,
self.guidatomorrow) = dtparser.get_guida()
# if no data, quit for loop and stop downloading
if len(self.guidatoday) == 0:
exit_for_loop = True
break
self.guida = self.guida + self.guidatoday
self.log(" writing in cache \'%s\'" % eventfilename)
# write data in cache file using UTF-8 encoding
fd = codecs.open(eventfilepath, "w", 'utf-8')
fd.write(
str(c) + self.FIELD_SEPARATOR + channel_name +
self.FIELD_SEPARATOR + channel_provider +
self.FIELD_SEPARATOR + day + '\n')
fd.write(
"Local Time (human readeable)###Unix GMT Time###Event Title###Event Description\n"
)
# extract all events and put in eventfile
for event in self.guida:
(dataora, titolo) = event
event_starttime = dataora
# time.mktime return Unix time inside GMT timezone
event_startime_unix_gmt = str(
int(
time.mktime(
time.strptime(event_starttime,
"%Y-%m-%d %H:%M"))) -
self.DELTA_UTC)
#event_startime_unix_gmt = str(int(time.mktime(time.strptime(event_starttime,"%Y-%m-%d %H:%M"))) )
#self.log(event_starttime + " , " + str(self.DELTA_UTC) + " , " + str(int(time.mktime(time.strptime(event_starttime,"%Y-%m-%d %H:%M")))) + " , " + event_startime_unix_gmt )
# convert remote data (RAI website use UTF-8) in Python Unicode (UCS2)
event_title = unicode(titolo,
self.REMOTE_EPG_CHARSET)
event_title = event_title.replace('\r', '')
event_title = event_title.replace('\n', u' ')
event_title = event_title.strip(u' ')
event_description = u''
fd.write(event_starttime + self.FIELD_SEPARATOR +
event_startime_unix_gmt +
self.FIELD_SEPARATOR + event_title +
self.FIELD_SEPARATOR + event_description +
'\n')
fd.close()
