[npo:radio] Move to extractor to common npo place and add extractor for fragments

This commit is contained in:
Sergey M․ 2015-02-13 01:36:54 +06:00
parent c3d64fc1b3
commit 171ca612af
3 changed files with 83 additions and 42 deletions

View File

@ -318,9 +318,10 @@ from .nowvideo import NowVideoIE
from .npo import ( from .npo import (
NPOIE, NPOIE,
NPOLiveIE, NPOLiveIE,
NPORadioIE,
NPORadioFragmentIE,
TegenlichtVproIE, TegenlichtVproIE,
) )
from .nporadio import NPORadioIE
from .nrk import ( from .nrk import (
NRKIE, NRKIE,
NRKTVIE, NRKTVIE,

View File

@ -1,6 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .subtitles import SubtitlesInfoExtractor from .subtitles import SubtitlesInfoExtractor
from .common import InfoExtractor
from ..utils import ( from ..utils import (
fix_xml_ampersands, fix_xml_ampersands,
parse_duration, parse_duration,
@ -22,7 +23,7 @@ class NPOBaseIE(SubtitlesInfoExtractor):
class NPOIE(NPOBaseIE): class NPOIE(NPOBaseIE):
IE_NAME = 'npo.nl' IE_NAME = 'npo.nl'
_VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)' _VALID_URL = r'https?://(?:www\.)?npo\.nl/(?!live|radio)[^/]+/[^/]+/(?P<id>[^/?]+)'
_TESTS = [ _TESTS = [
{ {
@ -185,7 +186,7 @@ class NPOIE(NPOBaseIE):
class NPOLiveIE(NPOBaseIE): class NPOLiveIE(NPOBaseIE):
IE_NAME = 'npo.nl:live' 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 = { _TEST = {
'url': 'http://www.npo.nl/live/npo-1', 'url': 'http://www.npo.nl/live/npo-1',
@ -260,6 +261,84 @@ class NPOLiveIE(NPOBaseIE):
} }
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): class TegenlichtVproIE(NPOIE):
IE_NAME = 'tegenlicht.vpro.nl' IE_NAME = 'tegenlicht.vpro.nl'
_VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?' _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'

View File

@ -1,39 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
class NPORadioIE(InfoExtractor):
_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': 'NPO Radio 1',
}
}
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')
json_data = json.loads(
self._html_search_regex(
self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'))
return {
'id': video_id,
'title': title,
'ext': json_data['codec'],
'url': json_data['url']
}
def _html_get_attribute_regex(self, attribute):
return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)