def getCollection(url):
url = opa_url + url
response = libMediathek.getUrl(url, opa_token)
j = json.loads(response)
program_id = j['programs'][0]['programId']
l = getVideos('/zones/collection_videos?id=' + program_id)
children = j['programs'][0]['children']
topics = [item for item in children if (item['kind'] == 'TOPIC' or item['kind'] == 'TV_SERIES')]
for topic in topics:
subresponse = libMediathek.getUrl(
opa_url + '/programs?programId=' + topic['programId'] + '&language=' + current_lang +
'&fields=title,subtitle,fullDescription,shortDescription,mainImage.url', opa_token
)
topic_json = json.loads(subresponse)
program = topic_json['programs'][0]
if program['title'] in ('**', '', None):
break
d = {}
d['name'] = program['title']
if program['subtitle'] != None:
d['name'] = d['name'] + ' | ' + program['subtitle']
if program['fullDescription']:
d['plot'] = program['fullDescription']
elif program['shortDescription']:
d['plot'] = program['shortDescription']
d['thumb'] = program['mainImage']['url']
d['_type'] = 'dir'
d['mode'] = 'libArteListVideos'
d['url'] = '/zones/collection_subcollection?id=' + topic['programId']
l.append(d)
return l
def parseShows(letter):
j = _parseMain()
url = j["_links"]["broadcastSeriesAz"]["href"]
response = libMediathek.getUrl(url)
j = json.loads(response)
if not letter.lower() in j['az']['_links']:
return []
url = j['az']['_links'][letter.lower()]['href']
response = libMediathek.getUrl(url)
j = json.loads(response)
l = []
for show in j["_embedded"]["teasers"]:
d = {}
d['url'] = show["_links"]["self"]["href"]
d['_name'] = show["headline"]
d['_mediathek'] = 'BR'
d['_tvshowtitle'] = show["topline"]
if 'br-core:teaserText' in show["documentProperties"]:
d['_plot'] = show["documentProperties"]["br-core:teaserText"]
try:
d['_thumb'] = show['teaserImage']['_links']['original']['href']
except:
pass
d['_type'] = 'shows'
d['mode'] = 'libBrListVideos'
l.append(d)
return l
def parseShows(letter):
j = _parseMain()
url = j["_links"]["broadcastSeriesAz"]["href"]
response = libMediathek.getUrl(url)
j = json.loads(response)
if not letter.lower() in j['az']['_links']:
return []
url = j['az']['_links'][letter.lower()]['href']
response = libMediathek.getUrl(url)
j = json.loads(response)
l = []
for show in j["_embedded"]["teasers"]:
d = {}
d['url'] = show["_links"]["self"]["href"]
d['_name'] = show["headline"]
d['_mediathek'] = 'BR'
d['_tvshowtitle'] = show["topline"]
if 'br-core:teaserText' in show["documentProperties"]:
d['_plot'] = show["documentProperties"]["br-core:teaserText"]
try: d['_thumb'] = show['teaserImage']['_links']['original']['href']
except: pass
d['_type'] = 'shows'
d['mode'] = 'libBrListVideos'
l.append(d)
return l
def parseVideos(url, ty=False, grepShowFromVideo=False):
if grepShowFromVideo:
response = libMediathek.getUrl(url)
url = re.compile('<link rel="alternate".+?href="(.+?)"').findall(
response)[0]
url = base + url.replace('.feed', '~_variant-android.mobile')
response = libMediathek.getUrl(url)
items = re.compile('<item>(.+?)</item>', re.DOTALL).findall(response)
l = []
for item in items:
d = {}
dctype = re.compile('<dc:type>(.+?)</dc:type>',
re.DOTALL).findall(item)[0]
if 'Video' in dctype: # or (dctype == 'Sportnachricht - sportschau.de' and '<title>' in item):
d['_name'] = re.compile('<title>(.+?)</title>',
re.DOTALL).findall(item)[0]
d['url'] = re.compile('<link>(.+?)</link>',
re.DOTALL).findall(item)[0]
mediagroup = re.compile('<media:group>(.+?)</media:group>',
re.DOTALL).findall(item)[0]
try:
d['_duration'], d['m3u8'] = re.compile(
'<media:content duration="(.+?)".+?url="(.+?)"',
re.DOTALL).findall(mediagroup)[0]
except:
libMediathek.log(item)
d['_name'] = '##################' + re.compile(
'<title>(.+?)</title>', re.DOTALL).findall(item)[0]
if '<content:encoded>' in item:
d['_plot'] = re.compile(
'<content:encoded>(.+?)</content:encoded>',
re.DOTALL).findall(item)[0].replace('\n ', '\n')
d['_channel'] = re.compile('<dc:creator>(.+?)</dc:creator>',
re.DOTALL).findall(item)[0]
d['_tvshowtitle'] = re.compile('<mp:topline>(.+?)</mp:topline>',
re.DOTALL).findall(item)[0]
if '<mp:expires>' in item:
d['_ttl'] = re.compile('<mp:expires>(.+?)</mp:expires>',
re.DOTALL).findall(item)[0]
d['_thumb'] = _chooseThumb(
re.compile('<mp:image>(.+?)</mp:image>',
re.DOTALL).findall(item))
dcdate = re.compile('<dc:date>(.+?)</dc:date>',
re.DOTALL).findall(item)[0] #TODO
s = dcdate.split('T')
d['_aired'] = s[0]
t = s[1].replace('Z', '').split(':')
d['_airedtime'] = str(int(t[0]) + 2) + ':' + t[1]
d['sort'] = s[1].replace('Z', '').replace(':', '')
if len(d['_airedtime']) == 4:
d['_airedtime'] = '0' + d['_airedtime']
if ty:
d['_type'] = ty
else:
d['_type'] = 'video'
d['mode'] = 'libWdrPlay'
l.append(d)
return l
def parseDate(day='0'):
response = libMediathek.getUrl('http://www.mdr.de/mediathek/fernsehen/index.html')
url = base + re.compile('<div class="box cssBroadcastDay.+?href="(.+?)"', re.DOTALL).findall(response)[int(day)]
#url = 'http://www.mdr.de/mediathek/fernsehen/sendung-verpasst--100_date-20161004_inheritancecontext-header_numberofelements-1_zc-65ef7e36.html'
response = libMediathek.getUrl(url)
response = response.split('<div class="con">')[-1]
videos = response.split('<div data-id=')[1:]
l = []
for video in videos:
d = {}
if "mediathekUrl':''" in video:
pass
d['url'] = base + re.compile('href="(.+?)"', re.DOTALL).findall(video)[0].split('_')[0] + '-meta.xml'
d['_thumb'] = base + re.compile('src="(.+?)"', re.DOTALL).findall(video)[1]
d['_plot'] = re.compile('<a.+?>(.+?)<', re.DOTALL).findall(video)[2]
d['_airedtime'] = re.compile('<span class="startTime">(.+?)</span>', re.DOTALL).findall(video)[0]
sHH,sMM = d['_airedtime'].split(':')
eHH,eMM = re.compile('<span class="endTime">(.+?)</span>', re.DOTALL).findall(video)[0].split(':')
d['_duration'] = str((int(eHH) - int(sHH)) * 3600 + (int(eMM) - int(sMM)) * 60)
d['_name'] = re.compile('<a.+?>(.+?)<', re.DOTALL).findall(video)[1]
d['mode'] = 'libMdrPlay'
d['_type'] = 'date'
l.append(d)
return l
def getCollection(url):
response = libMediathek.getUrl(url, opa_token)
j = json.loads(response)
program_id = j['programs'][0]['programId']
topic_children = filter(lambda item: item['kind'] == 'TOPIC', j['programs'][0]['children'])
if topic_children:
l = [{'_name': 'Übersicht', '_type': 'dir', 'mode': 'libArteListListings', 'url': emac_url + '/zones/collection_videos?id=' + program_id}]
else:
return getListings(emac_url + '/zones/collection_videos?id=' + program_id)
for child in topic_children:
subresponse = libMediathek.getUrl(opa_url + '/programs?programId=' + child['programId'] + '&language=' + language + '&fields=title,subtitle,fullDescription,shortDescription,mainImage.url', headers=opa_token)
child_json = json.loads(subresponse)
program = child_json['programs'][0]
d = {}
if program['subtitle'] != None and program['title'] != None:
d['_name'] = program['title'] + ' | ' + program['subtitle']
elif program['subtitle'] != None:
d['_name'] = program['subtitle']
else:
d['_name'] = program['title']
if program['fullDescription']:
d['_plot'] = program['fullDescription']
elif program['shortDescription']:
d['_plot'] = program['shortDescription']
d['_thumb'] = program['mainImage']['url']
d['_type'] = 'dir'
d['mode'] = 'libArteListListings'
d['url'] = emac_url + '/zones/collection_subcollection?id=' + program_id + '_' + child['programId']
l.append(d)
return l
def parseVideos(id, type=None, grepShowFromVideo=False):
if grepShowFromVideo:
url = 'http://www1.wdr.de/Medien/mediathek/video/sendungen-a-z/' + id + '~_variant-android.rss'
response = libMediathek.getUrl(url)
url = re.compile('<link>(.+?)</link>').findall(response)[0]
else:
url = 'http://www1.wdr.de/' + id + '~_variant-android.mobile'
response = libMediathek.getUrl(url)
items = re.compile('<item>(.+?)</item>', re.DOTALL).findall(response)
l = []
for item in items:
d = {}
dctype = re.compile('<dc:type>(.+?)</dc:type>',
re.DOTALL).findall(item)[0]
if 'Video' in dctype: # or (dctype == 'Sportnachricht - sportschau.de' and '<title>' in item):
d['name'] = re.compile('<title>(.+?)</title>',
re.DOTALL).findall(item)[0]
d['url'] = re.compile('<link>(.+?)</link>',
re.DOTALL).findall(item)[0]
mediagroup = re.compile('<media:group>(.+?)</media:group>',
re.DOTALL).findall(item)[0]
try:
d['_duration'], d['m3u8'] = re.compile(
'<media:content duration="(.+?)".+?url="(.+?)"',
re.DOTALL).findall(mediagroup)[0]
except:
libMediathek.log(item)
d['name'] = '##################' + re.compile(
'<title>(.+?)</title>', re.DOTALL).findall(item)[0]
if '<content:encoded>' in item:
d['plot'] = re.compile(
'<content:encoded>(.+?)</content:encoded>',
re.DOTALL).findall(item)[0].replace('\n ', '\n')
d['_channel'] = re.compile('<dc:creator>(.+?)</dc:creator>',
re.DOTALL).findall(item)[0]
d['_tvshowtitle'] = re.compile('<mp:topline>(.+?)</mp:topline>',
re.DOTALL).findall(item)[0]
if '<mp:expires>' in item:
d['_ttl'] = re.compile('<mp:expires>(.+?)</mp:expires>',
re.DOTALL).findall(item)[0]
d['thumb'] = _chooseThumb(
re.compile('<mp:image>(.+?)</mp:image>',
re.DOTALL).findall(item))
dcdate = re.compile('<dc:date>(.+?)</dc:date>',
re.DOTALL).findall(item)[0] #TODO
d['_airedISO8601'] = dcdate
if type:
d['_type'] = type
else:
d['_type'] = 'date'
d['mode'] = 'libWdrPlay'
l.append(d)
l.sort(key=lambda x: x.get('_airedISO8601', None),
reverse=(type != 'date'))
return l
def getU(url,Menu=False): try: header = getHeader(Menu) response = libMediathek.getUrl(url,header) except: (tokenMenu, tokenPlayer) = libzdftokengrabber.grepToken() header = getHeader(Menu, tokenMenu, tokenPlayer) response = libMediathek.getUrl(url,header) return response
def getVideoUrl(url, documentId):
result = None
url = opa_url + url
response = libMediathek.getUrl(url, opa_token)
j = json.loads(response)
if len(j['videoStreams']) > 0:
storedLang = 0
bitrate = 0
hls_videos = [value for value in j['videoStreams'] if value['mediaType'] == 'hls']
for video in hls_videos:
voice_subtitle = video['audioCode'].split('-');
voice = voice_subtitle[0].split('[')[0]
subtitle = voice_subtitle[1].split('[')[0] if len(voice_subtitle) > 1 else '';
currentLang = voices.get(voice, lambda:0)()
# if currentLang is native language => prefer "no subtitle"
# if currentLang is foreign language => prefer subtitle in native language
currentLang = currentLang * 10 + subtitles.get(subtitle, lambda: 9 if (currentLang >= voices[nativeVoice]()) else 0)()
currentBitrate = video['bitrate']
if currentLang > storedLang or (currentLang == storedLang and currentBitrate > bitrate):
storedLang = currentLang
bitrate = currentBitrate
result = {'url':video['url'], 'type': 'video', 'stream':'hls'}
return {'media': [result]} if result else None
else:
url = 'https://api.arte.tv/api/player/v2/config/' + current_lang + '/' + documentId
response = libMediathek.getUrl(url)
j = json.loads(response)
storedLang = 0
bitrate = 0
hls_videos = [value for value in j['data']['attributes']['streams'] if value['protocol'][0:3] == 'HLS']
for video in hls_videos:
if ('versions' in video) and len(video['versions']) > 0:
voice_subtitle = video['versions'][0]['eStat']['ml5'].split('-');
voice = voice_subtitle[0].split('[')[0]
subtitle = voice_subtitle[1].split('[')[0] if len(voice_subtitle) > 1 else '';
else:
voice = ''
subtitle = ''
currentLang = voices.get(voice, lambda:0)()
# if currentLang is native language => prefer "no subtitle"
# if currentLang is foreign language => prefer subtitle in native language
currentLang = currentLang * 10 + subtitles.get(subtitle, lambda: 9 if (currentLang >= voices[nativeVoice]()) else 0)()
currentBitrate = qualities.get(video['mainQuality']['code'], 0)
if currentLang > storedLang or (currentLang == storedLang and currentBitrate > bitrate):
storedLang = currentLang
bitrate = currentBitrate
result = {'url':video['url'], 'type': 'video', 'stream':'hls'}
return {'media': [result]} if result else None
def parseVideo(id):
variables = {'clipId': id}
#variables = {'clipId':'av:5896c99cab0d0d001203ea82'}
#variables = {'clipId':'av:5a3caa4ec96563001843d591'}
p = json.dumps({'query': queries.getQueryVideo(), 'variables': variables})
libMediathek.log(p)
response = libMediathek.getUrl(graphqlUrl, header, post=p)
libMediathek.log(response)
j = json.loads(response)
l = []
x = j['data']['viewer']['clip']['videoFiles']['edges']
if x:
node = x[0]['node']
d = {}
d['media'] = []
d['media'].append({'url': node['publicLocation'], 'stream': 'hls'})
try:
sub = node['subtitles']['edges'][0]['node']['timedTextFiles'][
'edges'][0]['node']['publicLocation']
d['subtitle'] = [{'url': sub, 'type': 'ttml', 'lang': 'de'}]
except:
pass
return d
else:
return None
def parseDate(day, channel):
variables = {
"slots": ["MORNING", "NOON", "EVENING", "NIGHT"],
"day": day,
"broadcasterId": "av:http://ard.de/ontologies/ard#" + channel
}
p = json.dumps({'query': queries.getQueryDate(), 'variables': variables})
libMediathek.log(p)
response = libMediathek.getUrl(graphqlUrl, header, post=p)
libMediathek.log(response)
j = json.loads(response)
l = []
for epg in j['data']['viewer']['allLivestreams']['edges'][0]['node'][
'epg']:
broadcastEvent = epg['broadcastEvent']
publicationOf = broadcastEvent['publicationOf']
if len(publicationOf['essences']['edges']) != 0:
d = _buildVideoDict(publicationOf)
start = broadcastEvent['start'].split('+')
if (len(start) == 1):
airedtime = datetime.datetime(
*(time.strptime(start[0], "%Y-%m-%dT%H:%M:%S.%fZ")[0:6]))
tz_offset = datetime.timedelta(
minutes=(time.timezone / -60) +
(time.localtime().tm_isdst * 60))
airedtime += tz_offset
else:
airedtime = datetime.datetime(
*(time.strptime(start[0], "%Y-%m-%dT%H:%M:%S.%f")[0:6]))
d['_airedtime'] = airedtime.strftime("%H:%M")
d['_type'] = 'date'
l.append(d)
return l
def parse(pageIndex, url, partnerKey=None, channelKey=None):
result = []
response = libMediathek.getUrl(url)
j = json.loads(response)
data = j.get('data',None)
if data:
page = data.get(pageNames[pageIndex],None)
if page:
widgets = [page] if pageIndex == pageIndexShowPage else page.get('widgets',[])
for widget in widgets:
if (channelKey is None) or (channelKey == widget.get('channelKey',None)):
teasers = widget.get('teasers',None)
if teasers:
for teaser in teasers:
type = teaser['type']
publicationService = teaser.get('publicationService',None)
if (
type in ('live','ondemand','broadcastMainClip','show')
and
(type == 'live') == (pageIndex == pageIndexLivestreamPage)
and
((partnerKey is None) or (publicationService and (partnerKey == publicationService.get('partner',None))))
):
documentId = deep_get(teaser, 'links.target.id')
name = teaser['shortTitle']
if documentId and name:
d = {}
d['documentId'] = documentId
d['name'] = name
d['plot'] = teaser.get('longTitle',None)
if (pageIndex == pageIndexProgramPage) and (partnerKey is None) and publicationService:
d['name'] = d['name'] + ' | [COLOR blue]' + publicationService['name'] + '[/COLOR]'
duration = teaser.get('duration', None)
if duration:
d['_duration'] = str(duration)
thumb = deep_get(teaser, 'images.aspect16x9.src')
if not thumb:
thumb = deep_get(teaser, 'images.aspect1x1.src')
if not thumb:
thumb = deep_get(teaser, 'images.aspect16x7.src')
if thumb:
d['thumb'] = (thumb.split('?')[0]).replace('{width}','1024')
if type == 'show':
d['_type'] = 'dir'
d['mode'] = 'libArdListShow'
else:
if pageIndex == pageIndexProgramPage:
d['_airedISO8601'] = teaser.get('broadcastedOn', None)
if pageIndex == pageIndexLivestreamPage:
d['_type'] = 'live'
elif pageIndex == pageIndexProgramPage:
d['_type'] = 'date'
else:
d['_type'] = 'video'
d['mode'] = 'libArdPlay'
result.append(d)
# "Alle Sender nach Datum" ist nicht sinnvoll vorsortiert
if pageIndex == pageIndexProgramPage and partnerKey is None:
result.sort(key = lambda x: x.get('_airedISO8601',None))
return result
def parseShows(url):
response = libMediathek.getUrl(url)
uls = re.compile('<ul class="list">(.+?)</ul>',
re.DOTALL).findall(response)
l = []
for ul in uls:
lis = re.compile('<li >(.+?)</li>', re.DOTALL).findall(ul)
for li in lis:
d = {}
uri = re.compile('href="(.+?)"', re.DOTALL).findall(li)[0]
if uri != 'http://www.wdrmaus.de/':
d['url'] = base + uri
d['_name'] = re.compile('<span>(.+?)</span>',
re.DOTALL).findall(li)[0]
try:
thumb = re.compile('<img.+?src="(.+?)"',
re.DOTALL).findall(li)[0].replace(
'~_v-ARDKleinerTeaser.jpg',
'~_v-original.jpg').replace(
'http//www', 'http://www')
if thumb.startswith('http'):
d['_thumb'] = thumb
else:
d['_thumb'] = base + thumb
except:
pass
d['_channel'] = 'WDR'
d['_type'] = 'dir'
d['mode'] = 'libWdrListVideos'
l.append(d)
return l
def parseVideos(url):
response = libMediathek.getUrl(url)
typeA = re.compile(
'<div class="box".+?<a(.+?)>(.+?)</a>.+?<a(.+?)>(.+?)</a>',
re.DOTALL).findall(response)
l = []
for href, show, href2, stuff in typeA:
if '<div class="media mediaA video">' in stuff:
d = {}
d['url'] = base + re.compile('href="(.+?)"',
re.DOTALL).findall(href2)[0]
if '<h4' in stuff:
d['_name'] = re.compile(
'<h4.+?>.+?<span class="hidden">Video:</span>(.+?)<',
re.DOTALL).findall(stuff)[0].strip()
else:
d['_name'] = show.strip()
if '<img' in stuff:
d['_thumb'] = base + re.compile('<img.+?src="(.+?)"',
re.DOTALL).findall(stuff)[0]
d['_plot'] = re.compile('<p class="teasertext">(.+?)<',
re.DOTALL).findall(stuff)[0]
#TODO duration, ut
d['_type'] = 'video'
d['mode'] = 'libWdrPlay'
l.append(d)
return l
def parseLetter(pageIndex, url, letter):
result = []
response = libMediathek.getUrl(url)
j = json.loads(response)
shows = deep_get(j, 'data.' + pageNames[pageIndex] + '.glossary.shows' + letter, [])
for teaser in shows:
type = teaser['type']
documentId = deep_get(teaser, 'links.target.id')
name = teaser['shortTitle']
if type == 'show' and documentId and name:
d = {}
d['documentId'] = documentId
d['name'] = name
d['plot'] = teaser.get('longTitle',None)
thumb = deep_get(teaser, 'images.aspect16x9.src')
if not thumb:
thumb = deep_get(teaser, 'images.aspect1x1.src')
if not thumb:
thumb = deep_get(teaser, 'images.aspect16x7.src')
if thumb:
d['thumb'] = (thumb.split('?')[0]).replace('{width}','1024')
d['_type'] = 'dir'
d['mode'] = 'libArdListShow'
result.append(d)
return result
def getVideo(url):
d = {}
response = libMediathek.getUrl(url)
file = re.compile('media.push\("(.+?)"').findall(response)[0]
if file.startswith('//'):
file = 'http:' + file
if file.endswith('.m3u8'):
d['media'] = [{'url': file, 'type': 'video', 'stream': 'HLS'}]
elif file.endswith('.m.mp4'):
s = file.split('/')
video = 'http://hls-ondemand.swr.de/i/swr-fernsehen/' + s[4] + '/' + s[
5] + '/' + s[6] + '.,xl,l,ml,m,sm,s,.mp4.csmil/master.m3u8'
d['media'] = [{'url': video, 'type': 'video', 'stream': 'HLS'}]
elif file.endswith('.mp3'):
d['media'] = [{'url': file, 'type': 'audio', 'stream': 'http'}]
sub = re.compile("lucy2captionArray\((.+?)\)").findall(response)[0]
if sub != "''":
d['subtitle'] = [{
'url': sub.replace("'", ""),
'type': 'ttml',
'lang': 'de'
}]
try:
name = re.compile("title = '(.+?)'").findall(response)[-1]
plot = re.compile("descl = '(.+?)'").findall(response)[-1]
thumb = re.compile("image = '(.+?)'").findall(response)[-1]
d['metadata'] = {'name': name, 'plot': plot, 'thumb': thumb}
except:
pass
return d
def getAZ(letter):
if letter == '#':
letter = '0-9'
l = []
if letter == 'X' or letter == 'Y':
return l
content = libMediathek.getUrl(
baseUrl+"/tv/sendungen-a-z?buchstabe="+letter)
#r = requests.get(baseUrl+"/tv/sendungen-a-z?buchstabe="+letter)
#content = r.text.decode('utf-8')
spl = content.split('<div class="teaser" data-ctrl')
for i in range(1, len(spl), 1):
d = {}
entry = spl[i]
url = re.compile('href="(.+?)"', re.DOTALL).findall(entry)[0]
url = url.replace("&", "&")
d['url'] = baseUrl+url+'&m23644322=quelle.tv&rss=true'
d['name'] = re.compile('class="headline">(.+?)<',
re.DOTALL).findall(entry)[0]
d['channel'] = re.compile(
'class="subtitle">(.+?)<', re.DOTALL).findall(entry)[0]
thumbId = re.compile('/image/(.+?)/16x9/', re.DOTALL).findall(entry)[0]
d['thumb'] = baseUrl+"/image/"+thumbId+"/16x9/0"
d['fanart'] = d['thumb']
bcastId = url.split('bcastId=')[-1]
if '&' in bcastId:
bcastId = bcastId.split('&')[0]
d['plot'] = libArdBcastId2Desc.toDesc(bcastId)
d["mode"] = "libArdListVideos"
l.append(d)
return l
def parseAZ(letter='A'):
if letter == "0-9":
letter = '#'
l = []
response = libMediathek.getUrl("http://www.ardmediathek.de/appdata/servlet/tv/sendungAbisZ?json")
j = json.loads(response)
j1 = j["sections"][0]["modCons"][0]["mods"][0]["inhalte"]
for entry in j1:
#if entry["ueberschrift"] == letter.upper():
if True:
for entry in entry["inhalte"]:
d = {}
d["_name"] = entry["ueberschrift"].encode("utf-8")
d["_channel"] = entry["unterzeile"].encode("utf-8")
d["_entries"] = int(entry["dachzeile"].encode("utf-8").split(' ')[0])
#d["thumb"] = entry["bilder"][0]["schemaUrl"].replace("##width##","0").encode("utf-8")
d["_thumb"] = entry["bilder"][0]["schemaUrl"].replace("##width##","1920").encode("utf-8")
d["url"] = entry["link"]["url"].encode("utf-8")
d['mode'] = 'libArdListVideos'
#d["documentId"] = entry["link"]["url"].split("documentId=")[1].split("&")[0]
#d["pluginpath"] = pluginpath
d["_type"] = 'shows'
l.append(d)
return l
def getVideoUrl(uri):
response = libMediathek.getUrl(baseUrl+uri)
j = json.loads(response)
quality = -1
url = None
fallbacks = []
for asset in j['assets']:
if type(asset['quality']) == type(quality):
currentQuality = asset['quality']
if currentQuality > quality:
url = asset['url']
quality = currentQuality
elif asset['quality'] == 'Video 2014 | MP4 Web XL | 16:9 | 1280x720':
url = asset['url']
elif asset['quality'] == 'auto':
url = asset['url']
fallbacks.append(asset['url'])
if not url:
url = fallbacks[-1]
if url.startswith('//'):
url = 'http:' + url
if url.startswith('http://wdradaptiv') or url.endswith('.mp4'):
d = {'media':[{'url':url, 'type': 'video', 'stream':'mp4'}]}
else:
d = {'media':[{'url':url, 'type': 'video', 'stream':'HLS'}]}
return d
def getSearch(a):
libMediathek.log(a)
urlargs = json.loads(a)
i = 0
args = ''
for arg in urlargs:
if i == 0:
args += '?'
else:
args += '&'
args += arg + '=' + urlargs[arg]
i += 1
url = 'https://www.sr-mediathek.de/API/suche.json.js.php'+args
response = libMediathek.getUrl(url)
j = json.loads(response)
l = []
for item in j:
d = {}
d['name'] = item['ueberschrift']
d['plot'] = item['teasertext']
d['id'] = item['id']
if 'playtime_hh' in item:
d['_duration'] = str(int(item['playtime_hh']) * 3600 + int(item['playtime_mm']) * 60 + int(item['playtime_ss']))
d['thumb'] = item['bild']
if 'start' in item:
d['_aired'] = item['start'][:4] + '-' + item['start'][4:6] + '-' + item['start'][6:8]
d['_airedtime'] = item['start'][8:10] + ':' + item['start'][10:12]
d['mode'] = 'libSrPlay'
d['_type'] = 'video'
l.append(d)
return l
def parseSeries():
p = json.dumps({'query': queries.getQuerySeries()})
response = libMediathek.getUrl(graphqlUrl, header, post=p)
libMediathek.log(response)
j = json.loads(response)
l = []
for edge in j['data']['viewer']['allSeries']['edges']:
d = {}
node = edge['node']
d['name'] = node['title']
if node['kicker'] != None:
d['_tvshowtitle'] = node['kicker']
d['_plotoutline'] = node['kicker']
d['plot'] = node['kicker']
if node['shortDescription'] != None:
d['_plotoutline'] = node['shortDescription']
d['plot'] = node['shortDescription']
if node['description'] != None:
d['plot'] = node['description']
try:
d['thumb'] = node['defaultTeaserImage']['imageFiles']['edges'][0][
'node']['publicLocation']
except:
pass
#libMediathek.log(d['thumb'])
d['_type'] = 'dir'
d['id'] = node['id']
d['mode'] = 'libBrListEpisodes'
l.append(d)
return l
def libHrListShows():
# return libhrshows.shows
l = []
response = libMediathek.getUrl(base + '/sendungen-a-z/index.html')
soup = bs.BeautifulSoup(response, 'html.parser')
articles = soup.findAll('div', {'class': 'c-teaser__content'})
for article in articles:
name = article.find('span', {'class': 'c-teaser__headline'})
href = article.find('a', {'class': 'c-teaser__headlineLink'})
if name and href:
d = {}
href_str = href.attrs['href']
if href_str.startswith(base):
d['showid'] = href_str.replace('/index.html','/sendungen/index.html')
elif isHessenschau(href_str):
d['showid'] = href_str
else:
continue
d['name'] = name.text.strip()
d['mode'] = 'libHrListEpisodes'
d['_type'] = 'dir'
thumb = article.find('img', {'class': 'image ar__content'})
if thumb:
d['_thumb'] = thumb.attrs['src']
l.append(d)
return l
def parseNew(boardId='l:http://ard.de/ontologies/mangoLayout#mainBoard_web',
itemCount=50):
#variables = {'boardId':boardId,"itemCount":itemCount}
variables = {'boardId': boardId}
#p = json.dumps({'query': libbrgraphqlqueries.getStart(), 'variables':variables})
p = json.dumps({'query': queries.getQueryBoard(), 'variables': variables})
libMediathek.log(p)
response = libMediathek.getUrl(graphqlUrl, header, post=p)
libMediathek.log(response)
j = json.loads(response)
l = []
for edge in j['data']['viewer']['board']['sections']['edges'][1]['node'][
'contents']['edges']:
node = edge['node']['represents']
if node:
d = {}
d['name'] = node['title']
if node['kicker'] != None:
d['_tvshowtitle'] = node['kicker']
d['_plotoutline'] = node['kicker']
d['plot'] = node['kicker']
if node['shortDescription'] != None:
d['_plotoutline'] = node['shortDescription']
d['plot'] = node['shortDescription']
if node['description'] != None:
d['plot'] = node['description']
d['_duration'] = str(node['duration'])
d['thumb'] = node['defaultTeaserImage']['imageFiles']['edges'][0][
'node']['publicLocation']
#libMediathek.log(d['thumb'])
d['_type'] = 'video'
d['id'] = node['id']
d['mode'] = 'libBrPlay'
l.append(d)
return l
def getSearch(s):
l = []
url = 'http://www.arte.tv/hbbtvv2/services/web/index.php/OPA/v3/videos/search/text/'+urllib.quote_plus(s)+'/de'
response = libMediathek.getUrl(url)
j = json.loads(response)
#http://www.arte.tv/hbbtvv2/services/web/index.php/OPA/v3/videos/collection/MAGAZINE/RC-014077/de
for teaser in j['teasers']:
d = {}
d['_name'] = teaser['title']
d['_tvshowtitle'] = teaser['title']
if teaser['imageUrl'] != None:
d['_thumb'] = teaser['imageUrl']
if teaser['kind'] == 'PLAYLIST' or teaser['kind'] == 'TV_SERIES' or teaser['kind'] == 'TOPIC':
d['url'] = 'http://www.arte.tv/hbbtvv2/services/web/index.php/OPA/v3/videos/collection/MAGAZINE/'+teaser['programId']+'/de'
d['mode'] = 'libArteListVideos'
d['_type'] = 'dir'
l.append(d)
elif teaser['kind'] == 'SHOW':
d['url'] = 'https://api.arte.tv/api/player/v1/config/de/'+teaser['programId']+'?autostart=0&lifeCycle=1&lang=de_DE&config=arte_tvguide'
d['mode'] = 'libArtePlay'
d['_type'] = 'video'
l.append(d)
else:
libMediathek.log('unsupported kind found: '+teaser['kind'])
return l
def getDate(d, type, mode):
d = abs(int(d))
response = libMediathek.getUrl('http://swrmediathek.de/app-2/svp.html')
day = re.compile(
'<ul data-role="listview" data-theme="c" data-divider-theme="d">(.+?)</ul>',
re.DOTALL).findall(response)[d]
return _findLiEntries(day, type, mode)[::-1]
def getVideoUrlWeb(url):
d = {}
d['media'] = []
response = libMediathek.getUrl(url)
j = json.loads(response)
#for caption in j.get('captions',[]):
# if caption['format'] == 'ebu-tt-d-basic-de':
# d['subtitle'] = [{'url':caption['uri'], 'type':'ttml', 'lang':'de', 'colour':True}]
# #elif caption['format'] == 'webvtt':
# # d['subtitle'] = [{'url':caption['uri'], 'type':'webvtt', 'lang':'de', 'colour':False}]
storedLang = 0
for key in j['videoJsonPlayer']['VSR']:#oh, this is such bullshit. there are endless and senseless permutations of language/subtitle permutations. i'll have to rewrite this in the future for french and other languages, subtitles, hearing disabled, ... who the hell uses baked in subtitles in 2017?!?!
l = lang.get(j['videoJsonPlayer']['VSR'][key]['versionCode'].split('[')[0],'ignore').upper()
if preferences.get(l,0) > storedLang and j['videoJsonPlayer']['VSR'][key]['mediaType'] == 'hls':
storedLang = preferences.get(l,0)
result = {'url':j['videoJsonPlayer']['VSR'][key]['url'], 'type': 'video', 'stream':'HLS'}
d['media'].append(result)
d['metadata'] = {}
d['metadata']['name'] = j['videoJsonPlayer']['VTI']
if 'VDE' in j['videoJsonPlayer']:
d['metadata']['plot'] = j['videoJsonPlayer']['VDE']
elif 'V7T' in j['videoJsonPlayer']:
d['metadata']['plot'] = j['videoJsonPlayer']['V7T']
d['metadata']['thumb'] = j['videoJsonPlayer']['VTU']['IUR']
d['metadata']['duration'] = str(j['videoJsonPlayer']['videoDurationSeconds'])
return d
def parseMdrPlus(url):
response = libMediathek.getUrl(url)
root = ET.fromstring(response)
l = []
for property1 in root.find('childNodes').find('childNode').find(
'childNodes').find('childNode').find('childNodes').find(
'childNode').find('properties'):
if property1.attrib.get('name', '') == 'sophora:reference':
#for document in property1.find('property').find('document').find('customElements').find('queryResult'):
for document in property1.find('document').find(
'customElements').find('queryResult'):
d = {}
d['_duration'] = _durationToS(
document.find('customElements').find('duration').text)
d['url'] = document.find('customElements').find(
'metaxmlUrl').text
for property2 in document.find('properties'):
if property2.attrib.get('name', '') == 'mdr-core:headline':
d['_name'] = property2[0].text
if property2.attrib.get('name',
'') == 'mdr-core:teaserText':
if property2[0].text != None:
d['_plot'] = property2[0].text
for childNode in document.find('childNodes'):
if childNode.attrib.get('name',
'') == 'mdr-core:teaserImage':
d['_thumb'] = _getThumb(childNode)
d['_type'] = 'video'
d['mode'] = 'libMdrPlay'
l.append(d)
return l
def getDate(yyyymmdd):
l = []
response = libMediathek.getUrl('http://www.arte.tv/hbbtvv2/services/web/index.php/OPA/programs/'+yyyymmdd+'/de')
j = json.loads(response)
for program in j['programs']:
if program['video'] != None:
d = {}
#d['_airedtime'] = program['broadcast']['broadcastBeginRounded'].split(' ')[-2][:5]
s = program['broadcast']['broadcastBeginRounded'].split(' ')[-2].split(':')
d['_airedtime'] = str(int(s[0]) + 1) + ':' + s[1]
if len(d['_airedtime']) == 4:
d['_airedtime'] = '0' + d['_airedtime']
d['_name'] = program['program']['title']
#d['url'] = 'http://www.arte.tv/papi/tvguide/videos/stream/player/D/'+program['video']['emNumber']+'_PLUS7-D/ALL/ALL.json'
#d['url'] = 'http://www.arte.tv/hbbtvv2/services/web/index.php/OPA/streams/'+program['video']['programId']+'/SHOW/ARTEPLUS7/de/DE'
#d['url'] = 'http://www.arte.tv/hbbtvv2/services/web/index.php/OPA/streams/'+program['video']['programId']+'/'+program['video']['kind']+'/'+program['video']['platform']+'/de/DE'
d['url'] = 'https://api.arte.tv/api/player/v1/config/de/'+program['video']['programId']+'?autostart=0&lifeCycle=1&lang=de_DE&config=arte_tvguide'
#d['programId'] = program['video']['programId']
if program['video']['imageUrl'] != None:
d['_thumb'] = program['video']['imageUrl']
if program['video']['durationSeconds'] != None:
d['_duration'] = str(program['video']['durationSeconds'])
if program['video']['teaserText'] != None:
d['_plotoutline'] = program['video']['teaserText']
d['_plot'] = program['video']['teaserText']
if program['video']['fullDescription'] != None:
d['_plot'] = program['video']['fullDescription']
d['mode'] = 'libArtePlay'
d['_type'] = 'date'
l.append(d)
return l
def parseShows(letter):
l = []
if (letter in ('a', 'x', 'q')):
pass
else:
response = libMediathek.getUrl(base + '/sendungen-' + letter +
'-102~_variant-android.mobile')
items = re.compile('<mp:additionallink>(.+?)</mp:additionallink>',
re.DOTALL).findall(response)
l = []
if len(items) > 0:
creator = re.compile('<dc:creator>(.+?)</dc:creator>',
re.DOTALL).findall(response)[0]
for item in items:
d = {}
d['name'] = re.compile('<mp:label>(.+?)</mp:label>',
re.DOTALL).findall(item)[0]
if len(l) != 0 and d['name'] == l[-1]['name']: continue
tmpstr = re.compile('<mp:link>(.+?)</mp:link>',
re.DOTALL).findall(item)[0].split('/')[-1]
if '~' not in tmpstr: continue
d['id'], extension = tmpstr.split('~')
#libMediathek.log(d['id'])
#libMediathek.log(re.compile('<mp:link>(.+?)</mp:link>', re.DOTALL).findall(item)[0])
d['_channel'] = creator
d['thumb'] = _chooseThumb(
re.compile('<mp:image>(.+?)</mp:image>',
re.DOTALL).findall(item))
d['_type'] = 'dir'
if extension.endswith('rss'):
d['grepShowFromVideo'] = 'True'
d['mode'] = 'libWdrListVideos'
l.append(d)
return l
def parseVideos(id):
response = libMediathek.getUrl(base + 'vod_main_json?id=' + id)
j = json.loads(response)
l = []
if j != None:
for item in j:
d = {}
d['name'] = item['title']
if not d['name']:
d['name'] = item['smubl']
d['plot'] = item['text_vorspann']
thumbnail_item = None
if 'thumbnail_large' in item and item['thumbnail_large']:
thumbnail_item = item['thumbnail_large']
elif 'thumbnail_medium' in item and item['thumbnail_medium']:
thumbnail_item = item['thumbnail_medium']
if thumbnail_item:
if 'systemurl' in thumbnail_item and thumbnail_item[
'systemurl']:
d['thumb'] = 'https://www.phoenix.de' + thumbnail_item[
'systemurl']
elif 'systemurl_gsid' in thumbnail_item and thumbnail_item[
'systemurl_gsid']:
d['thumb'] = 'https://www.phoenix.de' + thumbnail_item[
'systemurl_gsid']
d['_type'] = 'video'
d['smubl'] = item['smubl']
d['mode'] = 'play'
l.append(d)
return l
def parseDate(url):
l = []
response = libMediathek.getUrl(url)
j = json.loads(response)
j1 = j["sections"][-1]["modCons"][0]["mods"][0]["inhalte"]
for entry in j1:
j2 = entry["inhalte"]
for entry in j2:
d = {}
d["_airedtime"] = entry["dachzeile"]
#d["_name"] = entry["dachzeile"] + ' - '
#d["_name"] += entry["ueberschrift"] + ' - '
d["_name"] = entry["ueberschrift"] + ' - '
duration = 0
for j3 in entry["inhalte"]:
if runtimeToInt(j3["unterzeile"]) > duration:
duration = runtimeToInt(j3["unterzeile"])
d["_name"] += j3["ueberschrift"]
#d["_channel"] = j3["unterzeile"]
#d["_thumb"] = j3["bilder"][0]["schemaUrl"].replace("##width##","0")
d["_thumb"] = j3["bilder"][0]["schemaUrl"].replace("##width##","384")
d["url"] = j3["link"]["url"]
d["documentId"] = j3["link"]["url"].split("player/")[1].split("?")[0]
d["_duration"] = str(runtimeToInt(j3["unterzeile"]))
#d["_pluginpath"] = pluginpath
d["_type"] = 'date'
d['mode'] = 'libArdPlay'
l.append(d)
return l
def parseVideos(url): if not 'latestVideos' in url: response = libMediathek.getUrl(url) j = json.loads(response) if "_links" in j and 'latestVideos' in j["_links"]: url = j["_links"]["latestVideos"]["href"] else: return [] return parseLinks(url)
def parseDate(date,channel='BR'):
import time
j = _parseMain()
url = j["_links"]["epg"]["href"]
response = libMediathek.getUrl(url)
j = json.loads(response)
url = j["epgDays"]["_links"][date]["href"]#date: 2016-12-30
response = libMediathek.getUrl(url)
j = json.loads(response)
l = []
broadcasts = j["channels"][chan[channel]]["broadcasts"]
for b in broadcasts:
if "_links" in b and "video" in b["_links"]:
d = {}
d["_name"] = b["headline"]
if len(b["subTitle"]) > 0:
d['_name'] += ' - ' + b["subTitle"]
d["_plot"] = b["subTitle"]
d["_tvshowtitle"] = b["hasSubtitle"]
d["url"] = b["_links"]["video"]["href"]
#2016-10-14T08:50:00+02:00
d["_epoch"] = int(time.mktime(time.strptime(b["broadcastStartDate"].split('+')[0], '%Y-%m-%dT%H:%M:%S')))
d["_epoch"] = str(d["_epoch"])
d["_time"] = startTimeToInt(b["broadcastStartDate"][11:19])
d['_date'] = b["broadcastStartDate"][11:16]
d['_duration'] = (startTimeToInt(b["broadcastEndDate"][11:19]) - startTimeToInt(b["broadcastStartDate"][11:19])) * 60
if d['_duration'] < 0:
d['_duration'] = 86400 - abs(d['_duration'])
#TODO: rest of properties
if b['hasSubtitle']:
d['_hasSubtitle'] = 'true'
#d['_plot'] += '\n\nUntertitel'
d['_type'] = 'date'
d['mode'] = 'libBrPlay'
l.append(d)
return l
def parseVideo(url):#TODO grep the plot and other metadata from here
response = libMediathek.getUrl(url)
j = json.loads(response)
d = {}
d['media'] = []
assets = j["assets"]
if 'dataTimedTextUrl' in j['_links']:
d['subtitle'] = [{'url':j['_links']['dataTimedTextUrl']['href'], 'type':'ttml', 'lang': 'de'}]
for asset in assets:
if "type" in asset and asset["type"] == "HLS_HD":
d['media'].append({'url':asset["_links"]["stream"]["href"], 'type': 'video', 'stream':'HLS'})
return d
for asset in assets:
if "type" in asset and asset["type"] == "HLS":
d['media'].append({'url':asset["_links"]["stream"]["href"], 'type': 'video', 'stream':'HLS'})
return d
def parse(url):
response = libMediathek.getUrl(url,header)
j = json.loads(response)
l = []
if 'includes' in j:
part = 'includes'
else:
part = 'data'
for item in j[part]:
if item['type'] == 'series' or item['type'] == 'format':
d = _parseSeries(item,types[item['type']])
if d:
l.append(d)
elif item['type'] == 'video':
l.append(_parseVideo(item))
else:
libMediathek.log('unkown type: '+item['type'])
return l
def parseLinks(url):
response = libMediathek.getUrl(url)
j = json.loads(response)
l = []
if not '_embedded' in j:
return l
for show in j["_embedded"]["teasers"]:
d = {}
d['url'] = show["_links"]["self"]["href"]
d['_name'] = show["topline"]
if 'headline' in show:
d['_name'] += ' - ' + show['headline']
d['_tvshowtitle'] = show['topline']
d['_subtitle'] = show["topline"]
d['_plot'] = show["teaserText"]
d['_channel'] = show["channelTitle"]
duration = show['documentProperties']["br-core:duration"].split(':')
d['_duration'] = str(int(duration[0]) * 3600 + int(duration[1]) * 60 + int(duration[2]))
if 'image512' in show["teaserImage"]["_links"]:
d['_thumb'] = show["teaserImage"]["_links"]["image512"]["href"]
elif 'image256' in show["teaserImage"]["_links"]:
d['_thumb'] = show["teaserImage"]["_links"]["image256"]["href"]
try:
if show['hasSubtitle']:
d['_hasSubtitle'] = 'true'
#d['plot'] += '\n\nUntertitel'
except:pass
d['_type'] = 'video'
d['mode'] = 'libBrPlay'
l.append(d)
try:
d = {}
d['_type'] = 'nextPage'
d['url'] = j['_embedded']['_links']['next']['href']
l.append(d)
except: pass
return l
def parse(url): l = [] response = libMediathek.getUrl(url) j = json.loads(response)
def _parseMain():
response = libMediathek.getUrl("http://www.br.de/system/halTocJson.jsp")
j = json.loads(response)
url = j["medcc"]["version"]["1"]["href"]
response = libMediathek.getUrl(url)
return json.loads(response)
