import re
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_request,
+ compat_urllib_parse,
+)
from ..utils import (
fix_xml_ampersands,
parse_duration,
token_page = self._download_webpage(
'http://ida.omroep.nl/npoplayer/i.js',
video_id, note='Downloading token')
- return self._search_regex(
+ token = self._search_regex(
r'npoplayer\.token = "(.+?)"', token_page, 'token')
+ # Decryption algorithm extracted from http://npoplayer.omroep.nl/csjs/npoplayer-min.js
+ token_l = list(token)
+ first = second = None
+ for i in range(5, len(token_l) - 4):
+ if token_l[i].isdigit():
+ if first is None:
+ first = i
+ elif second is None:
+ second = i
+ if first is None or second is None:
+ first = 12
+ second = 13
+
+ token_l[first], token_l[second] = token_l[second], token_l[first]
+
+ return ''.join(token_l)
class NPOIE(NPOBaseIE):
- IE_NAME = 'npo.nl'
- _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)'
+ IE_NAME = 'npo'
+ IE_DESC = 'npo.nl and ntr.nl'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:www\.)?
+ (?:
+ npo\.nl/(?!live|radio)(?:[^/]+/){2}|
+ ntr\.nl/(?:[^/]+/){2,}|
+ omroepwnl\.nl/video/fragment/[^/]+__
+ )
+ (?P<id>[^/?#]+)
+ '''
_TESTS = [
{
'id': 'VPWON_1169289',
'ext': 'm4v',
'title': 'Tegenlicht',
- 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
+ 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
'upload_date': '20130225',
'duration': 3000,
},
'title': 'Hoe gaat Europa verder na Parijs?',
},
},
+ {
+ 'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
+ 'md5': '01c6a2841675995da1f0cf776f03a9c3',
+ 'info_dict': {
+ 'id': 'VPWON_1233944',
+ 'ext': 'm4v',
+ 'title': 'Aap, poot, pies',
+ 'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
+ 'upload_date': '20150508',
+ 'duration': 599,
+ },
+ },
+ {
+ 'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
+ 'md5': 'd30cd8417b8b9bca1fdff27428860d08',
+ 'info_dict': {
+ 'id': 'POW_00996502',
+ 'ext': 'm4v',
+ 'title': '''"Dit is wel een 'landslide'..."''',
+ 'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
+ 'upload_date': '20150508',
+ 'duration': 462,
+ },
+ }
]
def _real_extract(self, url):
def _get_info(self, video_id):
metadata = self._download_json(
- 'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
+ 'http://e.omroep.nl/metadata/%s' % video_id,
video_id,
# We have to remove the javascript callback
transform_source=strip_jsonp,
)
+ # For some videos actual video id (prid) is different (e.g. for
+ # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
+ # video id is POMS_WNL_853698 but prid is POW_00996502)
+ video_id = metadata.get('prid') or video_id
+
token = self._get_token(video_id)
formats = []
self._sort_formats(formats)
+ subtitles = {}
+ if metadata.get('tt888') == 'ja':
+ subtitles['nl'] = [{
+ 'ext': 'vtt',
+ 'url': 'http://e.omroep.nl/tt888/%s' % video_id,
+ }]
+
return {
'id': video_id,
'title': metadata['titel'],
'upload_date': unified_strdate(metadata.get('gidsdatum')),
'duration': parse_duration(metadata.get('tijdsduur')),
'formats': formats,
+ 'subtitles': subtitles,
}
class NPOLiveIE(NPOBaseIE):
IE_NAME = 'npo.nl:live'
- _VALID_URL = r'https?://www\.npo\.nl/live/(?P<id>.+)'
+ _VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>.+)'
_TEST = {
'url': 'http://www.npo.nl/live/npo-1',
if streams:
for stream in streams:
stream_type = stream.get('type').lower()
- if stream_type == 'ss':
+ # smooth streaming is not supported
+ if stream_type in ['ss', 'ms']:
continue
stream_info = self._download_json(
'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
stream_url = self._download_json(
stream_info['stream'], display_id,
'Downloading %s URL' % stream_type,
- transform_source=strip_jsonp)
+ 'Unable to download %s URL' % stream_type,
+ transform_source=strip_jsonp, fatal=False)
+ if not stream_url:
+ continue
if stream_type == 'hds':
f4m_formats = self._extract_f4m_formats(stream_url, display_id)
# f4m downloader downloads only piece of live stream
else:
formats.append({
'url': stream_url,
+ 'preference': -10,
})
self._sort_formats(formats)
}
+class NPORadioIE(InfoExtractor):
+ IE_NAME = 'npo.nl:radio'
+ _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
+
+ _TEST = {
+ 'url': 'http://www.npo.nl/radio/radio-1',
+ 'info_dict': {
+ 'id': 'radio-1',
+ 'ext': 'mp3',
+ 'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+ 'is_live': True,
+ },
+ 'params': {
+ 'skip_download': True,
+ }
+ }
+
+ @staticmethod
+ def _html_get_attribute_regex(attribute):
+ return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._html_search_regex(
+ self._html_get_attribute_regex('data-channel'), webpage, 'title')
+
+ stream = self._parse_json(
+ self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
+ video_id)
+
+ codec = stream.get('codec')
+
+ return {
+ 'id': video_id,
+ 'url': stream['url'],
+ 'title': self._live_title(title),
+ 'acodec': codec,
+ 'ext': codec,
+ 'is_live': True,
+ }
+
+
+class NPORadioFragmentIE(InfoExtractor):
+ IE_NAME = 'npo.nl:radio:fragment'
+ _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
+
+ _TEST = {
+ 'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
+ 'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
+ 'info_dict': {
+ 'id': '174356',
+ 'ext': 'mp3',
+ 'title': 'Jubileumconcert Willeke Alberti',
+ },
+ }
+
+ def _real_extract(self, url):
+ audio_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, audio_id)
+
+ title = self._html_search_regex(
+ r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
+ webpage, 'title')
+
+ audio_url = self._search_regex(
+ r"data-streams='([^']+)'", webpage, 'audio url')
+
+ return {
+ 'id': audio_id,
+ 'url': audio_url,
+ 'title': title,
+ }
+
+
class TegenlichtVproIE(NPOIE):
IE_NAME = 'tegenlicht.vpro.nl'
_VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
projects / youtube-dl.git / blobdiff