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 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 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 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 parseVideos(url):
response = libMediathek.getUrl(url)
s = response.split('<div class="pagepadding">')
s2 = s[-1].split('<div class="pagination">')
#videos = re.compile('<div class="modulepadding">.+?<img src="(.+?)".+?<span class="icon icon_video"></span>(.+?)<.+?<a href="(.+?)".+?>(.+?)</a>.+?<p>(.+?)<', re.DOTALL).findall(s2[0])
videos = re.compile(
'<div class="modulepadding">.+?<img src="(.+?)".+?<span class="icon "></span>(.+?)<.+?<a href="(.+?)".+?>(.+?)</a>.+?<p>(.+?)<',
re.DOTALL).findall(s2[0])
l = []
for thumb, duration, url, name, plot in videos:
d = {}
libMediathek.log(duration)
MM, SS = duration.split(' ')[0].split(':')
d['_duration'] = str(int(MM) * 60 + int(SS))
d['id'] = url.replace('.html', '').split(',')[-1]
d['_name'] = name
d['_thumb'] = baseUrl + thumb.replace('-einspaltig.jpg',
'-zweispaltig.jpg')
d['_plot'] = plot
d['_type'] = 'video'
d['mode'] = 'libNdrPlay'
l.append(d)
if len(s2) > 1 and '<a title="weiter" href="' in s2[1]:
d = {}
d['url'] = baseUrl + re.compile('<a title="weiter" href="(.+?)"',
re.DOTALL).findall(s2[1])[0]
d['_type'] = 'nextPage'
d['mode'] = 'libNdrListVideos'
l.append(d)
return l
def _parseVideo(j):
libMediathek.log(str(j))
d = {}
d['_name'] = j['attributes']['title']
d['_thumb'] = j['attributes']['image']['url']
if 'text' in j['attributes']:
d['_plot'] = _cleanPlot(j['attributes']['text'])
while '\n\n\n' in d['_plot']:
d['_plot'] = d['_plot'].replace('\n\n\n', '\n\n')
d['_duration'] = str(j['attributes']['duration'])
if 'season' in j['attributes']:
d['_season'] = j['attributes']['season']
if 'episode' in j['attributes']:
d['_episode'] = j['attributes']['episode']
if 'fsk' in j['attributes']:
d['_mpaa'] = 'FSK ' + j['attributes']['fsk']
d['_airedISO8601'] = j['attributes']['createdAt']
d['url'] = 'https://cdnapisec.kaltura.com/p/1985051/sp/198505100/playManifest/entryId/' + j[
'attributes'][
'rootEntryId'] + '/flavorIds/0/format/applehttp/protocol/https/a.m3u8'
#d['url'] += '?referrer=aHR0cHM6Ly93d3cuZnVuay5uZXQ='
d['entryId'] = j['attributes']['rootEntryId']
d['mode'] = 'play'
d['_type'] = 'video'
return d
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(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 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 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 getVideoUrl(entryId):
url = base
url += '&apiVersion=' + apiVersion
url += '&expiry=' + expiry
url += '&clientTag=' + clientTag
url += '&format=' + format
url += '&ignoreNull=' + ignoreNull
url += '&action=' + action
n = '1'
url += '&' + n + ':service=' + one_service
url += '&' + n + ':action=' + one_action
url += '&' + n + ':widgetId=' + one_widgetId
n = '2'
url += '&' + n + ':ks=%7B1%3Aresult%3Aks%7D'
#url += '&'+n+':contextDataParams:referrer=http%3A%2F%2Fplayer.kaltura.com%2FkWidget%2Ftests%2FkWidget.getSources.html%23__1985051%2C' + entryId
url += '&' + n + ':contextDataParams:referrer=https%3a%2f%2fwww.funk.net'
url += '&' + n + ':contextDataParams:objectType=KalturaEntryContextDataParams'
url += '&' + n + ':contextDataParams:flavorTags=all'
url += '&' + n + ':service=baseentry'
url += '&' + n + ':entryId=' + entryId
url += '&' + n + ':action=getContextData'
n = '3'
url += '&' + n + ':action=list'
url += '&' + n + ':filter:entryIdEqual=' + entryId
url += '&' + n + ':filter:objectType=KalturaAssetFilter'
url += '&' + n + ':filter:statusEqual=2'
url += '&' + n + ':ks=%7B1%3Aresult%3Aks%7D'
url += '&' + n + ':pager:pageSize=50'
url += '&' + n + ':service=caption_captionasset'
#url += '&kalsig=' + kalsig
response = libMediathek.getUrl(url)
libMediathek.log(response)
j = json.loads(response)
d = {}
flavorIds = ''
for flavorAsset in j[1]['flavorAssets']:
flavorIds += flavorAsset['id'] + ','
videoUrl = 'https://cdnapisec.kaltura.com/p/1985051/sp/198505100/playManifest/entryId/' + entryId + '/flavorIds/' + flavorIds[:
-1] + '/format/applehttp/protocol/https/a.m3u8'
videoUrl += '?referrer=aHR0cHM6Ly93d3cuZnVuay5uZXQ='
d['media'] = []
d['media'].append({'url': videoUrl, 'type': 'HLS'})
for object in j[2]['objects']:
d['subtitle'] = []
lang = object['languageCode']
subUrl = 'https://cdnsecakmi.kaltura.com/api_v3/index.php/service/caption_captionAsset/action/serve/captionAssetId/' + object[
'id']
d['subtitle'].append({'url': subUrl, 'type': 'srt', 'lang': lang})
return d
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']:
if edge['node']:
l.append(
_buildVideoDict(edge['node'],
type='dir',
mode='libBrListEpisodes'))
return l
def headUrl(url): #TODO: move to libmediathek3
libMediathek.log(url)
import urllib2
req = urllib2.Request(url)
req.get_method = lambda: 'HEAD'
req.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; rv:25.0) Gecko/20100101 Firefox/25.0')
response = urllib2.urlopen(req)
info = response.info()
response.close()
return info
def _parseAllClips(filter):
variables = {'filter': filter}
p = json.dumps({
'query': queries.getQueryAllClips(),
'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']['allClips']['edges']:
d = _buildVideoDict(edge['node'])
l.append(d)
return l
def parseSection(id):
variables = {'id': id}
p = json.dumps({
'query': queries.getQuerySection(),
'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']['section']['contents']['edges']:
d = _buildVideoDict(edge['node']['represents'])
l.append(d)
return l
def getSearch(s):
#url = 'http://www.daserste.de/dasersteapp/app/index~program_pd-'+day+'.json'
url = 'http://www.daserste.de/dasersteapp/index~search_documentTypes-video_s-broadcastDate_dir-desc_f-dateRange_fk-1YEAR%7C14DAYS_searchText-' + urllib.quote_plus(
s) + '.json'
response = libMediathek.getUrl(url)
libMediathek.log(response)
j = json.loads(response)
l = []
for r in j['result']:
if r.has_key('entries'):
for entry in r['entries']:
d = _parseVideo(entry)
l.append(d)
libMediathek.log(str(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']:
if edge['node']['represents']:
l.append(_buildVideoDict(edge['node']['represents']))
return l
def parsePage(url):
response = getU(url,True)
j = json.loads(response)
if j['profile'] == 'http://zdf.de/rels/search/result':
return _parseSearch(j)
elif j['profile'] == 'http://zdf.de/rels/search/result-page':
return _parseSearchPage(j)
elif j['profile'] == 'http://zdf.de/rels/content/page-index':
return _parsePageIndex(j)
elif j['profile'] == 'http://zdf.de/rels/content/page-index-teaser':
return _parseTeaser(j)
elif j['profile'] == 'http://zdf.de/rels/cmdm/resultpage-broadcasts':
return _parseBroadcast(j)
else:
libMediathek.log('Unknown profile: ' + j['profile'])
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':
l.append(_parseSeries(item, item['type']))
elif item['type'] == 'video':
l.append(_parseVideo(item))
else:
libMediathek.log('unkown type: ' + item['type'])
return l
def _parseBroadcast(j):
l = []
for broadcast in j['http://zdf.de/rels/cmdm/broadcasts']:
if 'http://zdf.de/rels/content/video-page-teaser' in broadcast:
target = broadcast['http://zdf.de/rels/content/video-page-teaser']
d = _grepItem(target)
if d:
#d['airedISO8601'] = broadcast['airtimeBegin']
if broadcast[
'effectiveAirtimeBegin'] != None: #TODO: find alternative for videos without this field
d['_airedISO8601'] = broadcast['effectiveAirtimeBegin']
else:
libMediathek.log('ommiting date: ' + str(broadcast))
libMediathek.log(str(broadcast['livestream']))
d['_type'] = 'date'
l.append(d)
return l
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 parsePage(url):
if url.startswith('https://api.zdf.de/search/documents'):
#response = libMediathek.getUrl(url,headerMenu)
response = getU(url, True)
else:
#response = libMediathek.getUrl(url,headerMenu)
response = getU(url, True)
j = json.loads(response)
libMediathek.log(response)
if j['profile'] == 'http://zdf.de/rels/search/result':
return _parseSearch(j)
elif j['profile'] == 'http://zdf.de/rels/search/result-page':
return _parseSearchPage(j)
elif j['profile'] == 'http://zdf.de/rels/content/page-index':
return _parsePageIndex(j)
elif j['profile'] == 'http://zdf.de/rels/content/page-index-teaser':
return _parseTeaser(j)
elif j['profile'] == 'http://zdf.de/rels/cmdm/resultpage-broadcasts':
return _parseBroadcast(j)
else:
log('Unknown profile: ' + j['profile'])
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)
d['_airedISO8601'] = broadcastEvent['start']
d['_type'] = 'date'
l.append(d)
return l
def parseBoards():
boards = [
'Board:http://ard.de/ontologies/mangoLayout#entdecken-film-krimi',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-kabarett-comedy',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-doku-reportage',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-news-politik',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-natur-tiere',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-wissen',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-berge',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-kultur',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-heimat',
'Board:http://ard.de/ontologies/mangoLayout#discover2',
'Board:http://ard.de/ontologies/mangoLayout#discover1',
'Board:http://ard.de/ontologies/mangoLayout#entdecken-kinder',
]
variables = {'nodes': boards}
p = json.dumps({
'query': libbrgraphqlqueries.getCats(),
'variables': variables
})
response = libMediathek.getUrl(graphqlUrl, header, post=p)
libMediathek.log(response)
j = json.loads(response)
l = []
for node in j['data']['nodes']:
d = {}
d['name'] = node['title'].title()
if 'shortDescription' in node and node['shortDescription'] != None:
d['_plotoutline'] = node['shortDescription']
d['plot'] = node['shortDescription']
if 'description' in node and node['description'] != None:
d['plot'] = node['description']
d['boardId'] = node['id']
d['_type'] = 'dir'
d['mode'] = 'libBrListBoard'
l.append(d)
return l
def enrichEpg(l, date):
epg = []
newL = []
response = libMediathek.getUrl(
'https://www.3sat.de/programm/?viewlong=viewlong&d=20170521')
response = response.split('<div id="EpgLongView" class="EpgBody">')[1]
response = response.split('<div id="FlagEpg" class="FlagLoaded">')[0]
response = response.split('class="EpgItemDay"')[1:]
for item in response:
time = re.compile('<div class="EpgTimeDay">(.+?)<',
re.DOTALL).findall(item)[0]
if 'class="EpgTextL"' in item:
plotS = re.compile('class="EpgTextS">.+?</a>(.+?)</div>',
re.DOTALL).findall(item)[0]
plotL = re.compile('class="EpgTextL">.+?</a>(.+?)</div>',
re.DOTALL).findall(item)[0]
else:
plotS = re.compile('<h4.+?>(.+?)</h4>', re.DOTALL).findall(item)[0]
plotL = plotS
plotS = plotS.replace('<br/><br/><br/>',
' ').replace('<br/><br/>',
' ').replace('<br/>', ' ')
plotL = plotL.replace('<br/><br/><br/>',
'\n\n').replace('<br/><br/>',
'\n\n').replace('<br/>', '\n')
libMediathek.log(plotS)
epg.append([time, plotL, plotS])
libMediathek.log(str(epg))
for item in l:
libMediathek.log('###' + item['_plot'])
d = item
for epgTime, epgPlot, epgPlotShorted in epg:
if item['_plot'][:-5] in epgPlotShorted:
d['_plot'] = '###' + epgPlot
if item['_date'] == '23:59':
d['_date'] = epgTime
newL.append(d)
return newL
def getXML(url, modePrefix, forcedType=False, channel=False):
baseUrl = url.split('/xmlservice')[0]
l = []
response = libMediathek.getUrl(url)
if not '<teasers>' in response:
return l
teasers = re.compile('<teasers>(.+?)</teasers>',
re.DOTALL).findall(response)[0]
match_teaser = re.compile('<teaser(.+?)</teaser>',
re.DOTALL).findall(teasers)
for teaser in match_teaser:
d = {}
#match_member=re.compile('member="(.+?)"', re.DOTALL).findall(teaser)
type = re.compile('<type>(.+?)</type>', re.DOTALL).findall(teaser)[0]
if type == 'video':
d['_thumb'] = chooseThumb(
re.compile('<teaserimages>(.+?)</teaserimages>',
re.DOTALL).findall(teaser)[0])
else:
d['_thumb'] = chooseThumb(
re.compile('<teaserimages>(.+?)</teaserimages>',
re.DOTALL).findall(teaser)[0], -1)
d.update(
getInfo(
re.compile('<information>(.+?)</information>',
re.DOTALL).findall(teaser)[0]))
d.update(
getDetails(
re.compile('<details>(.+?)</details>',
re.DOTALL).findall(teaser)[0]))
#title = cleanTitle(title)
if type == 'sendung':
if d['_duration'] == '0':
libMediathek.log('No videos in: ' + type)
else:
d['url'] = baseUrl + '/xmlservice/web/aktuellste?maxLength=50&id=' + d[
'_assetId']
d['_fanart'] = d['_thumb']
d['mode'] = 'xmlListPage'
if modePrefix:
d['mode'] = modePrefix + 'XmlListPage'
if channel:
d['_channel'] = channel
d['_type'] = 'shows'
l.append(d)
elif type == 'video':
d['url'] = baseUrl + '/xmlservice/web/beitragsDetails?id=' + d[
'_assetId']
d['mode'] = 'xmlPlay'
if modePrefix:
d['mode'] = modePrefix + 'XmlPlay'
if forcedType:
d['_type'] = forcedType
else:
d['_type'] = 'video'
HH, MM = d['_airtime'].split(' ')[-1].split(':')
d['_date'] = HH + ':' + MM
d['_time'] = str(int(HH) * 60 + int(MM))
if channel:
d['_channel'] = channel
l.append(d)
elif type == 'rubrik' or type == 'thema':
d['url'] = baseUrl + '/xmlservice/web/aktuellste?maxLength=50&id=' + d[
'_assetId']
d['mode'] = 'xmlListPage'
if modePrefix:
d['mode'] = modePrefix + 'XmlListPage'
if channel:
d['_channel'] = channel
d['_type'] = 'dir'
l.append(d)
else:
libMediathek.log('unsupported item type "' + type + '"')
nextPageUrl = _checkIfNextPageExists(url, response)
if nextPageUrl:
d = {}
d['url'] = nextPageUrl
d['_type'] = 'nextPage'
d['mode'] = 'xmlListPage'
l.append(d)
return l
def getIntrospection():
p = json.dumps({'query': libbrgraphqlqueries.getIntrospectionQuery()})
response = libMediathek.getUrl(graphqlUrl, header, post=p)
libMediathek.log(response)
def libDasErstePlay():
vid = libDasErsteJsonParser.getVideo(params['url'])
libMediathek.log(str(vid))
return vid
def _grepItem(target):
if target['profile'] == 'http://zdf.de/rels/not-found':
return False
if not ('contentType' in target):
return False
d = {}
d['name'] = target['teaserHeadline']
d['plot'] = target['teasertext']
d['thumb'] = _chooseImage(target['teaserImageRef'])
#d['url'] = base + target['http://zdf.de/rels/brand']['http://zdf.de/rels/target']['canonical']
if target['contentType'] == 'brand' or target['contentType'] == 'category':
try:
#d['url'] = base + target['canonical']
d['url'] = base + target['http://zdf.de/rels/search/page-video-counter-with-video']['self'].replace('&limit=0','&limit=100')
d['_type'] = 'dir'
d['mode'] = 'libZdfListPage'
except: d = False
elif target['contentType'] == 'clip':
try:
d['url'] = base + target['mainVideoContent']['http://zdf.de/rels/target']['http://zdf.de/rels/streams/ptmd-template'].replace('{playerId}',playerId)
if 'duration' in target['mainVideoContent']['http://zdf.de/rels/target']:
d['_duration'] = str(target['mainVideoContent']['http://zdf.de/rels/target']['duration'])
d['_type'] = 'clip'
#d['_type'] = 'video'
d['mode'] = 'libZdfPlay'
except: d = False
elif target['contentType'] == 'episode':# or target['contentType'] == 'clip':
try:
if not target['hasVideo']:
return False
#if target['mainVideoContent']['http://zdf.de/rels/target']['showCaption']:
# d['suburl'] = base + target['mainVideoContent']['http://zdf.de/rels/target']['captionUrl']
if 'mainVideoContent' in target:
content = target['mainVideoContent']['http://zdf.de/rels/target']
elif 'mainContent' in target:
content = target['mainContent'][0]['videoContent'][0]['http://zdf.de/rels/target']
d['url'] = base + content['http://zdf.de/rels/streams/ptmd-template'].replace('{playerId}',playerId)
if 'duration' in content:
d['_duration'] = str(content['duration'])
d['_type'] = 'video'
d['mode'] = 'libZdfPlay'
programmeItem = target.get('programmeItem', None)
if isinstance(programmeItem, list) and len(programmeItem) > 0:
episode = programmeItem[0].get('http://zdf.de/rels/target', None)
if episode:
episodeNumber = episode.get('episodeNumber', None)
if episodeNumber:
ep_nr = str(episodeNumber)
if len(ep_nr) == 1:
ep_nr = ' ' + ep_nr
d['name'] = 'Folge ' + ep_nr + ' - ' + d['name']
season = episode.get('http://zdf.de/rels/cmdm/season', None)
if season:
seasonTitle = season.get('seasonTitle', None)
if seasonTitle:
d['name'] = str(seasonTitle) + ' - ' + d['name']
series = season.get('http://zdf.de/rels/cmdm/series',None)
if series:
brand = series.get('http://zdf.de/rels/cmdm/brand',None)
if brand:
brandName = brand.get('brandName', None)
if brandName:
d['name'] = brandName + ' - ' + d['name']
else:
brand = target.get('http://zdf.de/rels/brand',None)
if brand:
title = brand.get('title',None)
if title:
d['name'] = title + ' - ' + d['name']
except:
d = False
else:
libMediathek.log('Unknown target type: ' + target['contentType'])
d = False
return d
def parseVideos(url):
l = []
response = libMediathek.getUrl(url)
j = json.loads(response)
#j1 = j["sections"][-1]["modCons"][-1]["mods"][-1]
#j1 = j["sections"][-1]["modCons"][-1]["mods"][-1]
j1 = j["sections"][-1]["modCons"][-1]["mods"][-1]
for j2 in j1["inhalte"]:
d = {}
if "ueberschrift" in j2:
d["_name"] = j2["ueberschrift"].encode("utf-8")
if 'Hörfassung' in d["_name"] or 'Audiodeskription' in d["_name"]:
d["_name"] = d["_name"].replace(' - Hörfassung','').replace(' - Audiodeskription','')
d["_name"] = d["_name"].replace(' (mit Hörfassung)','').replace(' (mit Audiodeskription)','')
d["_name"] = d["_name"].replace(' mit Hörfassung','').replace(' mit Audiodeskription','')
d["_name"] = d["_name"].replace(' (Hörfassung)','').replace(' (Audiodeskription)','')
d["_name"] = d["_name"].replace(' Hörfassung','').replace(' Audiodeskription','')
d["_name"] = d["_name"].replace('Hörfassung','').replace('Audiodeskription','')
d["_name"] = d["_name"].strip()
if d["_name"].endswith(' -'):
d["_name"] = d["_name"][:-2]
d["_name"] = d["_name"] + ' - Hörfassung'
d["_audioDesc"] = True
if "unterzeile" in j2:
d["_duration"] = str(runtimeToInt(j2["unterzeile"]))
if "bilder" in j2:
d["_thumb"] = j2["bilder"][0]["schemaUrl"].replace("##width##","384").encode("utf-8")
if "teaserTyp" in j2:
if j2["teaserTyp"] == "PermanentLivestreamClip" or j2["teaserTyp"] == "PodcastClip":
continue
elif j2["teaserTyp"] == "OnDemandClip":
d["_type"] = 'video'
d['mode'] = 'libArdPlay'
elif j2["teaserTyp"] == "Sammlung":
d["_type"] = 'dir'
d['mode'] = 'libArdListVideos'
else:
libMediathek.log('json parser: unknown item type: ' + j2["teaserTyp"])
d["_type"] = 'dir'
d['mode'] = 'libArdListVideos'
if "link" in j2:
d["url"] = j2["link"]["url"].encode("utf-8")
d["documentId"] = j2["link"]["url"].split("/player/")[-1].split("?")[0].encode("utf-8")
if "dachzeile" in j2:
d["_releasedate"] = j2["dachzeile"].encode("utf-8")
if 'ut' in j2['kennzeichen']:
d["_subtitle"] = True
if 'geo' in j2['kennzeichen']:
d['_geo'] = 'DACH'
if 'fsk6' in j2['kennzeichen']:
d['_mpaa'] = 'FSK6'
if 'fsk12' in j2['kennzeichen']:
d['_mpaa'] = 'FSK12'
if 'fsk16' in j2['kennzeichen']:
d['_mpaa'] = 'FSK16'
if 'fsk18' in j2['kennzeichen']:
d['_mpaa'] = 'FSK18'
#d["_pluginpath"] = pluginpath
l.append(d)
aktiv = False
for buttons in j1['buttons']:
if buttons["label"]["text"] == "Seiten":
for button in buttons["buttons"]:
if aktiv:
d = {}
d["url"] = button["buttonLink"]["url"]
d["type"] = 'nextPage'
d['mode'] = 'libArdListVideos'
l.append(d)
aktiv = button['aktiv']
return l
def parseVideos(url):
l = []
response = libMediathek.getUrl(url)
j = json.loads(response)
#j1 = j["sections"][-1]["modCons"][-1]["mods"][-1]
#j1 = j["sections"][-1]["modCons"][-1]["mods"][-1]
j1 = j["sections"][-1]["modCons"][-1]["mods"][-1]
for j2 in j1["inhalte"]:
d = {}
if "ueberschrift" in j2:
ueberschrift = j2["ueberschrift"]
if sys.version_info[0] < 3: # for Python 2
ueberschrift = ueberschrift.encode('utf-8')
d["name"] = ueberschrift
try:
d["plot"] = htmlParser.unescape(ueberschrift)
except UnicodeDecodeError:
d["plot"] = ueberschrift
if 'Hörfassung' in d["name"] or 'Audiodeskription' in d["name"]:
d["name"] = d["name"].replace(' - Hörfassung', '').replace(
' - Audiodeskription', '')
d["name"] = d["name"].replace(' (mit Hörfassung)', '').replace(
' (mit Audiodeskription)', '')
d["name"] = d["name"].replace(' mit Hörfassung', '').replace(
' mit Audiodeskription', '')
d["name"] = d["name"].replace(' (Hörfassung)', '').replace(
' (Audiodeskription)', '')
d["name"] = d["name"].replace(' Hörfassung', '').replace(
' Audiodeskription', '')
d["name"] = d["name"].replace('Hörfassung', '').replace(
'Audiodeskription', '')
d["name"] = d["name"].strip()
if d["name"].endswith(' -'):
d["name"] = d["name"][:-2]
d["name"] = d["name"] + ' - Hörfassung'
d["_audioDesc"] = True
if "unterzeile" in j2:
d["_duration"] = str(runtimeToInt(j2["unterzeile"]))
if "bilder" in j2:
thumb = j2["bilder"][0]["schemaUrl"].replace("##width##", "1024")
thumb = thumb.split("?")[0]
if sys.version_info[0] < 3: # for Python 2
thumb = thumb.encode('utf-8')
d["thumb"] = thumb
if "teaserTyp" in j2:
if j2["teaserTyp"] == "PermanentLivestreamClip" or j2[
"teaserTyp"] == "PodcastClip":
continue
elif j2["teaserTyp"] == "OnDemandClip":
d["_type"] = 'video'
d['mode'] = 'libArdPlayClassic'
elif j2["teaserTyp"] == "Sammlung":
d["_type"] = 'dir'
d['mode'] = 'libArdListVideos'
else:
libMediathek.log('json parser: unknown item type: ' +
j2["teaserTyp"])
d["_type"] = 'dir'
d['mode'] = 'libArdListVideos'
if "link" in j2:
url = j2["link"]["url"]
documentId = j2["link"]["url"].split("/player/")[-1].split("?")[0]
if sys.version_info[0] < 3: # for Python 2
url = url.encode('utf-8')
documentId = documentId.encode('utf-8')
d["url"] = url
d["documentId"] = documentId
if "dachzeile" in j2:
dachzeile = j2["dachzeile"]
if sys.version_info[0] < 3: # for Python 2
dachzeile = dachzeile.encode('utf-8')
d["_releasedate"] = dachzeile
if 'ut' in j2['kennzeichen']:
d["_subtitle"] = True
if 'geo' in j2['kennzeichen']:
d['_geo'] = 'DACH'
if 'fsk6' in j2['kennzeichen']:
d['_mpaa'] = 'FSK6'
if 'fsk12' in j2['kennzeichen']:
d['_mpaa'] = 'FSK12'
if 'fsk16' in j2['kennzeichen']:
d['_mpaa'] = 'FSK16'
if 'fsk18' in j2['kennzeichen']:
d['_mpaa'] = 'FSK18'
l.append(d)
aktiv = False
for buttons in j1['buttons']:
if buttons["label"]["text"] == "Seiten":
for button in buttons["buttons"]:
if aktiv:
d = {}
d["url"] = button["buttonLink"]["url"]
d["type"] = 'nextPage'
d['mode'] = 'libArdListVideos'
l.append(d)
aktiv = button['aktiv']
return l