def list(self, url, page):
""" List all episodes for a series.
https://www.npo.nl/media/series/VPWON_1247337/episodes?page=2&tilemapping=dedicated&tiletype=asset
"""
raise download_npo.Error('Dit werkt momenteel niet. Sorry :-(')
if url.startswith('http://') or url.startswith('https://'):
series_id = re.search(r'([A-Z][A-Z_]{1,8}_\d{6,9})').groups()[1]
else:
series_id = url
url = 'http://www.npo.nl/media/series/{}/episodes'.format(url)
if not url.endswith('/episodes'):
url += '/episodes'
url += '?tilemapping=dedicated&tiletype=asset&page={}'.format(page)
p = self.get_page(url)
matches = re.findall(
r'id=["\']([A-Z][A-Z_]{1,8}_\d{6,9})["\'].*?alt=["\'](.*?)["\'] onerror',
p, re.DOTALL | re.MULTILINE)
ret = []
for m in matches:
i = m[0].split('/').pop()
ret.append((i, 'http://{}'.format(i, m[0]), m[1].strip()))
return ret
def urlopen(self, url): # pylint:disable=no-self-use
""" Open a URI; return urllib.request.Request object """
if download_npo.verbose:
msg('urlopen: ' + url)
headers = {
'User-Agent':
'Mozilla/5.0 (X11; Linux x86_64; rv:51.0) Gecko/20100101 Firefox/51.0',
'Cookie': 'npo_cc=tmp; npo_cc_www.npogeschiedenis.nl=tmp',
}
req = urllib2.Request(url, headers=headers)
try:
return urllib2.urlopen(req)
except urllib2.HTTPError:
raise download_npo.Error(
'De URL {} is niet gevonden (404 error)'.format(url))
def __init__(self, url):
self.libmms = ctypes.cdll.LoadLibrary(ctypes.util.find_library('mms'))
if self.libmms._name is None: # pylint:disable=protected-access
raise download_npo.Error(
'Deze video is in het (oude) MMS/WMV formaat; om dit te'
'downloaden heb je libmms nodig, welke niet is gevonden op je'
'systeem. Zie: http://sourceforge.net/projects/libmms/')
self._libc = ctypes.cdll.LoadLibrary(ctypes.util.find_library('c'))
mmsh_connect = self.libmms.mmsh_connect
mmsh_connect.restype = ctypes.POINTER(mmsh_t)
if sys.version_info[0] > 2:
url = bytes(url, 'utf-8')
self._mms = mmsh_connect(None, None, url, 128 * 1024)
malloc = self._libc.malloc
malloc.restype = ctypes.POINTER(ctypes.c_char)
self.buf = malloc(8192)
def find_video(self, url, quality=0):
""" Find video to download
Returns (downloadurl, pagetitle, player_id, extension)"""
if not (url.startswith('http://') or url.startswith('https://')):
url = 'http://%s' % url
page = self.get_page(url)
try:
jsurl = re.search(r'data-url="(.*?)"', page).groups()[0]
player_id = re.search(r'sourceid_string:(\d+)', jsurl).groups()[0]
except AttributeError:
raise download_npo.Error('Kan player_id niet vinden')
meta = self.meta(player_id)
streams = meta['clipData']['assets']
streams.sort(key=lambda v: int(v['bandwidth']), reverse=True)
url = streams[0]['src']
return self.urlopen(url), meta['clipData'].get(
'title'), player_id, 'mp4'
def find_video(self, url, quality=0):
""" Find video to download
Returns (downloadurl, player_id, extension)"""
if not (url.startswith('http://') or url.startswith('https://')):
url = 'http://www.npostart.nl/{}'.format(url)
page = self.get_page(url)
page = unquote(page)
if download_npo.verbose >= 3:
msg('page: {}'.format(page))
player_id = None
find = re.search(self._playerid_regex, page)
if download_npo.verbose >= 2:
msg('player_id find: {}'.format(find))
if find is not None and len(find.groups()) > 0:
player_id = find.groups()[0]
if player_id is None:
raise download_npo.Error('Kan player_id niet vinden')
if download_npo.verbose:
msg('Using player_id {}'.format(player_id))
# {"token":"h4i536f2104v7aepeonjm83s51"}
try:
token = json.loads(self.get_page('{}/auth'.format(
self.base)))['token']
except AttributeError:
raise download_npo.Error('Kan token niet vinden')
if download_npo.verbose:
msg('Found token ' + token)
meta = self.meta(player_id)
if meta.get('error') and len(meta['error']) > 1:
raise download_npo.Error(
'Site geeft aan dat er iets fout is: {}'.format(meta['error']))
ext = 'mp4'
if meta.get('items') and isinstance(meta['items'][0][0], dict):
# Radiouitendingen
ext = (meta['items'][0][0].get('type')
or meta['items'][0][0].get('format') or 'mp4')
# MMS / Windows Media Speler
if meta['items'][0][0].get('formaat') == 'wmv':
return self.find_video_MMS(player_id)
# http://ida.omroep.nl/app.php/POW_03414349?adaptive=no&token=djo0nv08rdk46iq7kijrvtktr3
streams = self.get_json('{}/{}?adaptive=no&token={}'.format(
self.base, player_id, token))
url = None
errors = set()
for q, stream in enumerate(streams['items'][0][quality:]):
# Oudere afleveringen; zie #10
if stream.get('contentType') in ('url', 'audio'):
url = stream['url']
if stream.get('format'):
ext = stream.get('format')
break
else:
stream = self.get_json(stream['url'])
if stream.get('errorstring'):
# Dit is vooral voor regionale afleveringen (lijkt het ...)
if meta.get('items') and len(meta['items'][0]) > 0:
url = meta['items'][0][0]['url']
break
else:
errors.add(stream.get('errorstring'))
else:
url = stream['url']
break
if url is None:
raise download_npo.Error("Foutmelding van site:\n{}".format(
'\n'.join(['\n'.join(textwrap.wrap(e)) for e in errors])))
return (self.urlopen(url), player_id, ext)
def list(self, url, page):
raise download_npo.Error('Dit is niet ondersteund voor deze site')
def subs(self, player_id):
raise download_npo.Error('Deze site ondersteunt geen ondertitels')
def meta(self, player_id):
raise download_npo.Error('Not implemented')
def find_video(self, url, quality=0):
raise download_npo.Error('Not implemented')