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):
text = helper.download(url)
if text is None:
return None
show = {}
subtitle = helper.cut(text, "<h3 class=\"overlay-subtitle\">", "</h3>")
if subtitle is not None and subtitle:
show["sub-title"] = helper.cleanup(subtitle)
description = helper.cut(text, "<p class=\"overlay-text\">", "</p>")
if description is not None and description:
show["desc"] = helper.cleanup(description)
if text.find("Untertitel für Hörgeschädigte") != -1:
show["subtitles"] = True
return show
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 grabdetails(url):
text = helper.download(url)
if text is None:
return None
show = {}
description = helper.cut(text, "<meta name=\"description\" content=\"", "\" />")
if description is not None:
show["desc"] = helper.cleanup(description)
return show
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 labellizeImage(filePath, savePath, nbFrag, client):
image = getImage(filePath)
labels = []
for n in range(1, nbFrag):
fragments = cut(image, n)
#print("Image découpée en " + str((n+1)*(n+1)))
w, h = image.size
dw = w / n
dh = h / n
x = y = 0
for fragment in fragments:
newLabels = labellize(fragment, client)
for label in newLabels:
vertices = label.bounding_poly.normalized_vertices
for vertex in vertices:
vertex.x += x
vertex.y += y
y += dh
if y >= h:
y = 0
x += dw
labels.extend(newLabels)
# print("Fragments labellisés, " + str(len(labels)) + " labels")
# lbls = []
# for label in labels:
# lbls.append(Label(label.name, label.bounding_poly, label.score))
# labels = connectLabels(labels)
# print("Fragements connectés : " + str(len(labels)) + " fragments restants")
#print (json.dumps(lbls))
# text = jsonpickle.encode(labels[0])
# print(text)
#print(dir(labels[0]))
drawn = drawImage(image, labels)
#print("Image dessinée")
saveImage(drawn, savePath)
json = listToJson(labels)
savePath = savePath[:-4]
savePath += ".json"
with open(savePath, 'w') as file:
file.write(json)
def grabdetails(url):
text = helper.download(url)
if text is None:
return None
show = {}
description = helper.cut(text,
"<meta property=\"og:description\" content=\"",
"/>")
temp = re.search(
"<meta property=\"og:description\" content=\"(.*?)(?:\"/>|<)", text)
if temp is not None:
description = temp.group(1)
if description:
show["desc"] = helper.cleanup(description)
return show
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