def get_svc_channels(self):
url = "https://search.daum.net/search?DA=B3T&w=tot&rtmaxcoll=B3T&q={}"
channelcate = ["지상파", "종합편성", "케이블", "스카이라이프", "해외위성", "라디오"]
for c in channelcate:
search_url = url.format(f"{c} 편성표")
data = self.request(search_url, None, method="GET", output="html")
soup = BeautifulSoup(data)
if not soup.find_all(attrs={"disp-attr": "B3T"}):
continue
all_channels = [
str(x.text.strip()) for x in soup.select(
'div[id="channelNaviLayer"] > div[class="layer_tv layer_all scroll"] > div > ul > li'
)
]
if not all_channels:
all_channels += [
str(x.text.strip())
for x in soup.select('div[class="wrap_sub"] > span > a')
]
svc_cate = c.replace("스카이라이프", "SKYLIFE")
self.svc_channel_list += [{
"Name": x,
"ServiceId": f"{svc_cate} {x}",
"Category": c,
} for x in all_channels]
def get_svc_channels(self):
channelcate = [
{
"name": "지상파",
"category": "00"
},
{
"name": "스포츠/취미",
"category": "01"
},
{
"name": "영화",
"category": "02"
},
{
"name": "뉴스/경제",
"category": "03"
},
{
"name": "교양/다큐",
"category": "04"
},
{
"name": "여성/오락",
"category": "05"
},
{
"name": "어린이/교육",
"category": "06"
},
{
"name": "홈쇼핑",
"category": "07"
},
{
"name": "공공/종교",
"category": "08"
},
]
p_name = re.compile(r".+(?=[(])")
p_no = re.compile(r"(?<=Ch[.])\d+")
p_svcid = re.compile(r"(?<=[('])\d+(?=[',])")
url = "https://www.uplus.co.kr/css/chgi/chgi/RetrieveTvChannel.hpi"
params = {"code": "12810"}
for c in channelcate:
params.update({"category": c["category"]})
soup = BeautifulSoup(
self.request(url, params, method="GET", output="html"))
for ch in soup.select('li > a[name="chList"]'):
ch_txt = ch.text
self.svc_channel_list.append({
"Name":
p_name.search(ch_txt).group(),
"No":
str(p_no.search(ch_txt).group()),
"ServiceId":
p_svcid.search(ch["onclick"]).group(),
"Category":
c["name"],
})
def get_svc_channels(self):
url = "https://tv.kt.com/tv/channel/pChList.asp"
params = {"ch_type": "1", "parent_menu_id": "0"}
soup = BeautifulSoup(
self.request(url, params, method="POST", output="html"))
raw_channels = [
unquote(x.find("span", {
"class": "ch"
}).text.strip()) for x in soup.select("li > a")
]
# 몇몇 채널은 (TV로만 제공, 유료채널) 웹에서 막혀있지만 실제로는 데이터가 있을 수 있다.
self.svc_channel_list = [{
"Name": " ".join(x.split()[1:]),
"No": str(x.split()[0]),
"ServiceId": x.split()[0]
} for x in raw_channels]
def get_programs(self, lazy_write=False):
url = "https://tv.kt.com/tv/channel/pSchedule.asp"
params = {
"ch_type": "1", # 1: live 2: skylife 3: uhd live 4: uhd skylife
"view_type": "1", # 1: daily 2: weekly
"service_ch_no": "SVCID",
"seldate": "EPGDATE",
}
for idx, _ch in enumerate(self.req_channels):
log.info("%03d/%03d %s", idx + 1, len(self.req_channels), _ch)
for nd in range(int(self.cfg["FETCH_LIMIT"])):
day = date.today() + timedelta(days=nd)
params.update({
"service_ch_no": _ch.svcid,
"seldate": day.strftime("%Y%m%d")
})
try:
data = self.request(url,
params,
method="POST",
output="html")
soup = BeautifulSoup(data,
parse_only=SoupStrainer("tbody"))
for row in soup.find_all("tr"):
cell = row.find_all("td")
hour = cell[0].text.strip()
for minute, program, category in zip(
cell[1].find_all("p"), cell[2].find_all("p"),
cell[3].find_all("p")):
_prog = EPGProgram(_ch.id)
_prog.stime = datetime.strptime(
f"{str(day)} {hour}:{minute.text.strip()}",
"%Y-%m-%d %H:%M")
_prog.title = program.text.replace("방송중 ",
"").strip()
_prog.category = category.text.strip()
for image in program.find_all("img", alt=True):
grade = re.match(r"([\d,]+)", image["alt"])
_prog.rating = int(
grade.group(1)) if grade else 0
_ch.programs.append(_prog)
except Exception:
log.exception("파싱 에러: %s", _ch)
if not lazy_write:
_ch.to_xml(self.cfg, no_endtime=self.no_endtime)
def get_programs(self, lazy_write=False):
url = "https://search.daum.net/search?DA=B3T&w=tot&rtmaxcoll=B3T&q={}"
for idx, _ch in enumerate(self.req_channels):
log.info("%03d/%03d %s", idx + 1, len(self.req_channels), _ch)
search_url = url.format(quote(_ch.svcid + " 편성표"))
data = self.request(search_url, None, method="GET", output="html")
soup = BeautifulSoup(data)
if not soup.find_all(attrs={"disp-attr": "B3T"}):
log.warning("EPG 정보가 없거나 없는 채널입니다: %s", _ch)
continue
days = soup.select(
'div[class="tbl_head head_type2"] > span > span[class="date"]')
# 연도 추정
currdate = datetime.now() # 언제나 basedate보다 미래
basedate = datetime.strptime(days[0].text.strip(),
"%m.%d").replace(year=currdate.year)
if (basedate - currdate).days > 0:
basedate = basedate.replace(year=basedate.year - 1)
for nd, _ in enumerate(days):
hours = soup.select(
f'[id="tvProgramListWrap"] > table > tbody > tr > td:nth-of-type({nd+1})'
)
if len(hours) != 24:
log.warning("24개의 시간 행이 있어야 합니다: %s, 현재: %d", _ch,
len(hours))
break
for nh, hour in enumerate(hours):
for dl in hour.select("dl"):
_prog = EPGProgram(_ch.id)
nm = int(dl.select("dt")[0].text.strip())
_prog.stime = basedate + timedelta(
days=nd, hours=nh, minutes=nm)
for atag in dl.select("dd > a"):
_prog.title = atag.text.strip()
# TODO: Get more details via daum search
for span in dl.select("dd > span"):
class_val = " ".join(span["class"])
if class_val == "":
_prog.title = span.text.strip()
elif "ico_re" in class_val:
_prog.rebroadcast = True
elif "ico_rate" in class_val:
_prog.rating = int(
class_val.split("ico_rate")[1].strip())
else:
# ico_live ico_hd ico_subtitle ico_hand ico_uhd ico_talk ico_st
_prog.extras.append(span.text.strip())
match = re.compile(self.title_regex).search(
_prog.title)
_prog.title = match.group("title") or None
_prog.part_num = match.group("part") or None
_prog.ep_num = match.group("epnum") or ""
_prog.title_sub = match.group("subname1") or ""
_prog.title_sub = match.group(
"subname2") or _prog.title_sub
if _prog.part_num:
_prog.title += f" {_prog.part_num}부"
_ch.programs.append(_prog)
if not lazy_write:
_ch.to_xml(self.cfg, no_endtime=self.no_endtime)
def get_programs(self, lazy_write=False):
max_ndays = 4
if int(self.cfg["FETCH_LIMIT"]) > max_ndays:
log.warning(
"""
***********************************************************************
%s는 당일포함 %d일치만 EPG를 제공하고 있습니다.
***********************************************************************
""",
self.provider_name,
max_ndays,
)
url = "http://m.skbroadband.com/content/realtime/Channel_List.do"
params = {"key_depth2": "SVCID", "key_depth3": "EPGDATE"}
for idx, _ch in enumerate(self.req_channels):
log.info("%03d/%03d %s", idx + 1, len(self.req_channels), _ch)
for nd in range(min(int(self.cfg["FETCH_LIMIT"]), max_ndays)):
day = date.today() + timedelta(days=nd)
params.update({
"key_depth2": _ch.svcid,
"key_depth3": day.strftime("%Y%m%d")
})
try:
data = self.request(url,
params,
method="GET",
output="html")
data = re.sub("EUC-KR", "utf-8", data)
data = re.sub("<!--(.*?)-->", "", data, 0, re.I | re.S)
data = re.sub(
'<span class="round_flag flag02">(.*?)</span>', "",
data)
data = re.sub(
'<span class="round_flag flag03">(.*?)</span>', "",
data)
data = re.sub(
'<span class="round_flag flag04">(.*?)</span>', "",
data)
data = re.sub(
'<span class="round_flag flag09">(.*?)</span>', "",
data)
data = re.sub(
'<span class="round_flag flag10">(.*?)</span>', "",
data)
data = re.sub(
'<span class="round_flag flag11">(.*?)</span>', "",
data)
data = re.sub(
'<span class="round_flag flag12">(.*?)</span>', "",
data)
data = re.sub('<strong class="hide">프로그램 안내</strong>', "",
data)
data = re.sub('<p class="cont">(.*)',
partial(SK.replacement, tag="p"), data)
data = re.sub('<p class="tit">(.*)',
partial(SK.replacement, tag="p"), data)
strainer = SoupStrainer("div",
{"id": "uiScheduleTabContent"})
soup = BeautifulSoup(data, parse_only=strainer)
for row in soup.find_all("li", {"class": "list"}):
_prog = EPGProgram(_ch.id)
_prog.stime = datetime.strptime(
f"{str(day)} {row.find('p', {'class': 'time'}).text}",
"%Y-%m-%d %H:%M")
for itag in row.select('i[class="hide"]'):
itxt = itag.text.strip()
if "세 이상" in itxt:
_prog.rating = int(
itxt.replace("세 이상", "").strip())
else:
_prog.extras.append(itxt)
cell = row.find("p", {"class": "cont"})
if cell:
if cell.find("span"):
cell.span.decompose()
_prog.title = cell.text.strip()
matches = re.match(self.title_regex, _prog.title)
if matches:
_prog.title = matches.group(1) or ""
_prog.title_sub = matches.group(5) or ""
_prog.rebroadcast = bool(matches.group(7))
_prog.ep_num = matches.group(3) or ""
_ch.programs.append(_prog)
except Exception:
log.exception("파싱 에러: %s", _ch)
if not lazy_write:
_ch.to_xml(self.cfg, no_endtime=self.no_endtime)
def get_programs(self, lazy_write=False):
max_ndays = 5
if int(self.cfg["FETCH_LIMIT"]) > max_ndays:
log.warning(
"""
***********************************************************************
%s는 당일포함 %d일치만 EPG를 제공하고 있습니다.
***********************************************************************
""",
self.provider_name,
max_ndays,
)
url = "http://www.uplus.co.kr/css/chgi/chgi/RetrieveTvSchedule.hpi"
params = {"chnlCd": "SVCID", "evntCmpYmd": "EPGDATE"}
for idx, _ch in enumerate(self.req_channels):
log.info("%03d/%03d %s", idx + 1, len(self.req_channels), _ch)
for nd in range(min(int(self.cfg["FETCH_LIMIT"]), max_ndays)):
day = date.today() + timedelta(days=nd)
params.update({
"chnlCd": _ch.svcid,
"evntCmpYmd": day.strftime("%Y%m%d")
})
try:
data = self.request(url,
params,
method="POST",
output="html")
data = data.replace("<재>", "<재>").replace(
" [..", "").replace(" (..", "")
soup = BeautifulSoup(data,
parse_only=SoupStrainer("table"))
if not str(soup):
log.warning("EPG 정보가 없거나 없는 채널입니다: %s", _ch)
# 오늘 없으면 내일도 없는 채널로 간주
break
for row in soup.find("table").tbody.find_all("tr"):
cell = row.find_all("td")
_prog = EPGProgram(_ch.id)
_prog.stime = datetime.strptime(
f"{str(day)} {cell[0].text}", "%Y-%m-%d %H:%M")
for span in cell[1].select("span > span[class]"):
span_txt = span.text.strip()
if "cte_all" in span["class"]:
_prog.rating = 0 if span_txt == "All" else int(
span_txt)
else:
_prog.extras.append(span_txt)
cell[1].find("span", {"class": "tagGroup"}).decompose()
_prog.title = cell[1].text.strip()
matches = re.match(self.title_regex, _prog.title)
if matches:
_prog.title = (matches.group(1) or "").strip()
_prog.title_sub = (matches.group(2) or "").strip()
_prog.ep_num = matches.group(3) or ""
_prog.rebroadcast = bool(matches.group(4))
_prog.category = cell[2].text.strip()
_ch.programs.append(_prog)
except Exception:
log.exception("파싱 에러: %s", _ch)
if not lazy_write:
_ch.to_xml(self.cfg, no_endtime=self.no_endtime)