def grab(channel, timespan):
tz = pytz.timezone("Europe/Athens")
now = datetime.datetime.now(tz)
charset = "windows-1253"
shows = []
a = 0
if now.time().hour < 7:
a = -1
for i in range(a, 14):
date = now + datetime.timedelta(days=i)
text = helper.download("https://program.ert.gr/Ert1/index.asp?id=" +
channel + "&pdate=" + date.strftime("%d/%m/%Y"),
encoding=charset)
if text is None:
continue
sections = helper.split(
text, "<td width=\"50\" align=\"center\" class=\"table\">",
"</tr></table>")
laststart = datetime.datetime.min.replace(tzinfo=tz)
for section in sections:
show = {}
temp = re.search("(\d\d):(\d\d)", section)
show["start"] = date.replace(hour=int(temp.group(1)),
minute=int(temp.group(2)),
second=0,
microsecond=0)
if show["start"] < laststart:
date += datetime.timedelta(days=1)
show["start"] += datetime.timedelta(days=1)
if (show["start"] - now).total_seconds() / 3600 > timespan:
lastshow = True
else:
lastshow = False
laststart = show["start"]
temp = re.search("<a class=\"black\".*href=\"(.*)\">(.*)</a>",
section)
show["title"] = temp.group(2)
subtitle = helper.cut(
section, "<td width=\"3\"></td><td><font color=\"#6e6868\">",
"</font>")
if subtitle is not None and subtitle:
show["sub-title"] = subtitle
link = temp.group(1)
if link[0] == "/":
link = "https://program.ert.gr" + link
if link:
show["details-url"] = link
shows.append(show)
if lastshow:
return shows
return shows
def grabdetails(url):
charset = "windows-1253"
text = helper.download(url, encoding=charset)
if text is None:
return None
show = {}
temp = helper.split(text, "<div align=\"justify\" class=\"black\">",
"</div>")
description = ""
for d in temp:
description += d
if description:
show["desc"] = helper.cleanup(description)
director = re.search("Σκηνοθεσία</b>: (.*?)(?:\n|<br>)", text)
if director is not None:
show["director"] = helper.cleanup(director.group(1))
presenter = re.search("Παρουσίαση</b>: (.*?)(?:\n|<br>)", text)
if presenter is not None:
show["presenter"] = helper.cleanup(presenter.group(1))
producer = re.search("Οργάνωση παραγωγής: (.*?)(?:\n|<br>)", text)
if producer is not None:
show["producer"] = helper.cleanup(producer.group(1))
writer = re.search("Αρχισυνταξία: (.*?)(?:\n|<br>)", text)
if writer is not None:
show["writer"] = helper.cleanup(writer.group(1))
return show
def channellist():
text = helper.download("http://programm.ard.de/")
channels = helper.split(text, "Tagesprogramm::", "</a>")
result = []
for channel in channels:
temp = re.search("Tagesprogramm::(.*?)\".*\?sender\=-?(.*?)\&", channel)
result.append((temp.group(2), temp.group(1), temp.group(1)))
return result
def channellist():
text = helper.download("http://www.ishow.gr/tvNow.asp")
channels = helper.split(text, "<b><a style=\"color:#E1D8BE\"", "</a>")
result = []
for channel in channels:
temp = re.search("\?cid=(.*?)\">(.*)</a>", channel)
result.append((temp.group(1), temp.group(2), temp.group(2)))
result.sort(key=lambda r: int(r[0]))
return result
def grab(channel, timespan):
tz = pytz.timezone("Europe/Athens")
now = datetime.datetime.now(tz)
shows = []
a = 0
if now.time().hour < 4:
a = -1
for i in range(a, 6):
date = now + datetime.timedelta(days=i)
text = helper.download(
"http://ishow.gr/showTodayChannelProgramm.asp?cid=" + channel +
"&gotoDay=" + str(i))
if text is None:
continue
sections = helper.split(text, "<tr id=\"progTr", "</tr>")
laststart = datetime.datetime.min.replace(tzinfo=tz)
for section in sections:
show = {}
temp = re.search(
"<td class=\"progTd progTdTime\".*?>(\d\d):(\d\d)", section)
show["start"] = date.replace(hour=int(temp.group(1)),
minute=int(temp.group(2)),
second=0,
microsecond=0)
if show["start"] < laststart:
date += datetime.timedelta(days=1)
show["start"] += datetime.timedelta(days=1)
if (show["start"] - now).total_seconds() / 3600 > timespan:
lastshow = True
else:
lastshow = False
laststart = show["start"]
title = re.search("<div class=\"grandTitle\".*>(.+)\s*?</div>",
section)
show["title"] = helper.cleanup(title.group(1))
subtitle = helper.cut(section, "<div class=\"subTitle\">",
"</div>")
if subtitle is not None and subtitle:
show["sub-title"] = helper.cleanup(subtitle)
temp = re.search("<div class=\"grandTitle\">.*?href=\"(.*?)\"",
section)
if temp is not None:
show["details-url"] = "http://ishow.gr" + temp.group(1)
shows.append(show)
if lastshow:
return shows
return shows
def getConstraintsForAll(dataTensor, variables, orderingNotImp):
repeatDim = ()
r = set([v for v in range(len(variables)) if v not in repeatDim])
constraints = {}
for l, (m, s) in enumerate(helper.split(r, (), repeatDim)):
newset = m + s
# this value will be used to filter max constraints
maxPossible = 1
for i in range(len(s)):
maxPossible *= len(variables[s[i]])
idTensor = helper.tensorIndicator(dataTensor, newset, variables)
sumSet = range(len(m), len(newset))
sumTensor_max, sumTensor_min = helper.tensorSum(
idTensor, sumSet,
np.array(variables)[list(newset)], 0)
if len(set(s)) == 1 and len(set(orderingNotImp) & set(s)) == 0:
(
minConsZero,
maxConsZero,
minConsNonZero,
maxConsNonZero,
) = helper.tensorConsZero(idTensor, sumSet,
np.array(variables)[list(newset)])
else:
minConsZero, maxConsZero, minConsNonZero, maxConsNonZero = (0, 0,
0, 0)
row = {}
row["minSum"] = int(
sumTensor_min) if sumTensor_min < maxPossible else 0
row["maxSum"] = int(
sumTensor_max) if sumTensor_max < maxPossible else 0
row["minConsZero"] = int(
minConsZero) if minConsZero < maxPossible else 0
row["maxConsZero"] = int(
maxConsZero) if maxConsZero < maxPossible else 0
row["minConsNonZero"] = (int(minConsNonZero)
if minConsNonZero < maxPossible else 0)
row["maxConsNonZero"] = (int(maxConsNonZero)
if maxConsNonZero < maxPossible else 0)
key = ",".join([str(i) for i in m])
key += ":"
key += ",".join([str(i) for i in s])
constraints[key] = row
return constraints
def grab(channel, timespan):
tz = pytz.timezone("Europe/Berlin")
now = datetime.datetime.now(tz)
shows = []
a = 0
if now.time().hour < 7:
a = -1
for i in range(a, 14):
date = now + datetime.timedelta(days=i)
text = helper.download("http://www.zdf.de/live-tv?airtimeDate=" + date.strftime("%Y-%m-%d"))
if text is None:
continue
text = helper.cut(text, "<section class=\"b-epg-timeline timeline-" + channel, "</section>")
sections = helper.split(text, "<li", "</li>")
laststart = datetime.datetime.min.replace(tzinfo=tz)
for section in sections:
show = {}
temp = helper.cut(section, "<span class=\"time\">", "</span>")
temp = re.search("(\d\d):(\d\d) - (\d\d):(\d\d)", temp)
show["start"] = date.replace(hour=int(temp.group(1)), minute=int(temp.group(2)), second=0, microsecond=0)
if show["start"] < laststart:
date += datetime.timedelta(days=1)
show["start"] += datetime.timedelta(days=1)
if (show["start"] - now).total_seconds() / 3600 > timespan:
return shows
laststart = show["start"]
show["stop"] = date.replace(hour=int(temp.group(3)), minute=int(temp.group(4)), second=0, microsecond=0)
if show["stop"] < show["start"]:
show["stop"] += datetime.timedelta(days=1)
temp = re.search("<span class=\"overlay-link-category\">(.*?)<span class=\"visuallyhidden\">:</span></span>\s*(?:<.*>)*\s*(.*?)\s*?</a>", section)
if temp.group(1):
show["title"] = helper.cleanup(temp.group(1) + " - " + temp.group(2))
else:
show["title"] = helper.cleanup(temp.group(2))
temp = re.search("contentUrl\": \"(.*)\"", section)
if temp is not None:
show["details-url"] = "http://www.zdf.de" + temp.group(1)
shows.append(show)
return shows
def grab(channel, timespan):
tz = pytz.timezone("Europe/Berlin")
now = datetime.datetime.now(tz)
shows = []
a = 0
if now.time().hour < 7:
a = -1
for i in range(a, 14):
date = now + datetime.timedelta(days=i)
datestring = "%s.%s.%s" % (date.day, date.month, date.year)
text = helper.download("http://programm.ard.de/TV/Programm/Sender?datum=" + date.strftime("%d.%m.%Y") + "&hour=0&sender=" + channel)
if text is None:
continue
sections = helper.split(text, "<li class=\"eid", "</li>")
laststart = datetime.datetime.min.replace(tzinfo=tz)
for section in sections:
show = {}
temp = re.search("<span class=\"date[\s\S]*?(\d\d):(\d\d)", section)
show["start"] = date.replace(hour=int(temp.group(1)), minute=int(temp.group(2)), second=0, microsecond=0)
if show["start"] < laststart:
date += datetime.timedelta(days=1)
show["start"] += datetime.timedelta(days=1)
if (show["start"] - now).total_seconds() / 3600 > timespan:
lastshow = True
else:
lastshow = False
laststart = show["start"]
show["title"] = helper.cleanup(re.search("<span class=\"title[\s\S]*?>\s*([^<]*?)[\t\n]", section).group(1))
temp = re.search("<span class=\"subtitle[\s\S]*?>\s*([^<]*?)[\t\n]", section)
if temp is not None:
subtitle = temp.group(1)
if subtitle:
show["sub-title"] = helper.cleanup(subtitle)
temp = re.search("<a class=\"sendungslink[\s\S]*?href=\"(.*?)\"", section)
if temp is not None:
show["details-url"] = "http://programm.ard.de" + temp.group(1)
shows.append(show)
if lastshow:
return shows
return shows
def grab(channel, timespan):
tz = pytz.timezone("UTC")
now = datetime.datetime.now(tz)
shows = []
laststart = datetime.datetime.min.replace(tzinfo=tz)
for i in range(1 + timespan // 4):
timestamp = int(time.time()) + i * 14400
text = helper.download("https://www.dw.com/epg/data/4765/1/" +
str(timestamp) + "000")
if text is None:
continue
channeldata = helper.cut(text, "data-channel-id=\"" + channel + "\"",
"data-channel-id")
if not channeldata:
try:
channeldata = text.split("data-channel-id=\"" + channel +
"\"")[1]
except IndexError:
continue
sections = helper.split(channeldata, "<div class=\"epgProgram\"",
"<div class=\"broadcastlinks\">")
for section in sections:
show = {}
day = helper.cut(section, "data-day=\"", "\"")
begintime = helper.cut(section, "data-begin-time=\"", "\"")
endtime = helper.cut(section, "data-end-time=\"", "\"")
show["start"] = pytz.utc.localize(
datetime.datetime.strptime(day + begintime, "%Y-%m-%d%H:%M"))
if show["start"] <= laststart:
continue
if (show["start"] - now).total_seconds() / 3600 > timespan:
return shows
laststart = show["start"]
show["stop"] = pytz.utc.localize(
datetime.datetime.strptime(day + endtime, "%Y-%m-%d%H:%M"))
if show["stop"] < show["start"]:
show["stop"] += datetime.timedelta(days=1)
show["title"] = helper.cleanup(
helper.cut(section, "<h2 class=\"title\">", "</h2>"))
url = helper.cut(section, "<a href=\"", "\">")
if url is not None and url:
show["url"] = "https://www.dw.com" + url
description = helper.cleanup(
helper.cut(section, "<ul class=\"topics\">", "</ul>"))
if description is not None and description:
show["desc"] = description
try:
icon = re.search("<img[\s\S]*?/>", section).group(0)
width = helper.cut(icon, "width=\"", "\"")
height = helper.cut(icon, "height=\"", "\"")
src = "https://www.dw.com" + helper.cut(icon, "src=\"", "\"")
show["icon"] = (src, {"width": width, "height": height})
except (AttributeError, IndexError):
pass
shows.append(show)
return shows
def split_file(path):
chunk_size = 256*1024
spl = path.split('/')
dest = 'split/{}'.format(spl[-1])
split(path,dest,chunk_size)