youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

commit eb3680123a2f451e79e953ede5dd70fb7fb4c0ae
parent f5273890eeea6604c23367d91007fb8119768c17
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sun, 10 Aug 2014 01:21:16 +0700

[orf] Move all ORF extractors in one place

Diffstat:
Myoutube_dl/extractor/__init__.py | 8+++++---
Dyoutube_dl/extractor/fm4.py | 45---------------------------------------------
Dyoutube_dl/extractor/oe1.py | 40----------------------------------------
Myoutube_dl/extractor/orf.py | 77++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
4 files changed, 81 insertions(+), 89 deletions(-)

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py @@ -96,7 +96,6 @@ from .fktv import ( FKTVPosteckeIE, ) from .flickr import FlickrIE -from .fm4 import FM4IE from .fourtube import FourTubeIE from .franceculture import FranceCultureIE from .franceinter import FranceInterIE @@ -226,9 +225,12 @@ from .nrk import ( from .ntv import NTVIE from .nytimes import NYTimesIE from .nuvid import NuvidIE -from .oe1 import OE1IE from .ooyala import OoyalaIE -from .orf import ORFIE +from .orf import ( + ORFTVthekIE, + ORFOE1IE, + ORFFM4IE, +) from .parliamentliveuk import ParliamentLiveUKIE from .pbs import PBSIE from .photobucket import PhotobucketIE diff --git a/youtube_dl/extractor/fm4.py b/youtube_dl/extractor/fm4.py @@ -1,45 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - -# audios on fm4.orf.at are only available for 7 days, so we can't -# add tests. - - -class FM4IE(InfoExtractor): - IE_DESC = 'fm4.orf.at' - _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_date = mobj.group('date') - show_id = mobj.group('show') - - data = self._download_json( - 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id), - show_id - ) - - def extract_entry_dict(info, title, subtitle): - return { - 'id': info['loopStreamId'].replace('.mp3', ''), - 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'], - 'title': title, - 'description': subtitle, - 'duration': (info['end'] - info['start']) / 1000, - 'timestamp': info['start'] / 1000, - 'ext': 'mp3' - } - - entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] - - return { - '_type': 'playlist', - 'id': show_id, - 'title': data['title'], - 'description': data['subtitle'], - 'entries': entries - } diff --git a/youtube_dl/extractor/oe1.py b/youtube_dl/extractor/oe1.py @@ -1,40 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import calendar -import datetime -import re - -from .common import InfoExtractor - -# audios on oe1.orf.at are only available for 7 days, so we can't -# add tests. - - -class OE1IE(InfoExtractor): - IE_DESC = 'oe1.orf.at' - _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('id') - - data = self._download_json( - 'http://oe1.orf.at/programm/%s/konsole' % show_id, - show_id - ) - - timestamp = datetime.datetime.strptime('%s %s' % ( - data['item']['day_label'], - data['item']['time'] - ), '%d.%m.%Y %H:%M') - unix_timestamp = calendar.timegm(timestamp.utctimetuple()) - - return { - 'id': show_id, - 'title': data['item']['title'], - 'url': data['item']['url_stream'], - 'ext': 'mp3', - 'description': data['item'].get('info'), - 'timestamp': unix_timestamp - } diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals import json import re +import calendar +import datetime from .common import InfoExtractor from ..utils import ( @@ -12,7 +14,9 @@ from ..utils import ( ) -class ORFIE(InfoExtractor): +class ORFTVthekIE(InfoExtractor): + IE_NAME = 'orf:tvthek' + IE_DESC = 'ORF TVthek' _VALID_URL = r'https?://tvthek\.orf\.at/(?:programs/.+?/episodes|topics/.+?|program/[^/]+)/(?P<id>\d+)' _TEST = { @@ -105,3 +109,73 @@ class ORFIE(InfoExtractor): 'entries': entries, 'id': playlist_id, } + + +# Audios on ORF radio are only available for 7 days, so we can't add tests. + + +class ORFOE1IE(InfoExtractor): + IE_NAME = 'orf:oe1' + IE_DESC = 'Radio Österreich 1' + _VALID_URL = r'http://oe1\.orf\.at/programm/(?P<id>[0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_id = mobj.group('id') + + data = self._download_json( + 'http://oe1.orf.at/programm/%s/konsole' % show_id, + show_id + ) + + timestamp = datetime.datetime.strptime('%s %s' % ( + data['item']['day_label'], + data['item']['time'] + ), '%d.%m.%Y %H:%M') + unix_timestamp = calendar.timegm(timestamp.utctimetuple()) + + return { + 'id': show_id, + 'title': data['item']['title'], + 'url': data['item']['url_stream'], + 'ext': 'mp3', + 'description': data['item'].get('info'), + 'timestamp': unix_timestamp + } + + +class ORFFM4IE(InfoExtractor): + IE_DESC = 'orf:fm4' + IE_DESC = 'radio FM4' + _VALID_URL = r'http://fm4\.orf\.at/7tage/?#(?P<date>[0-9]+)/(?P<show>\w+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + show_date = mobj.group('date') + show_id = mobj.group('show') + + data = self._download_json( + 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id), + show_id + ) + + def extract_entry_dict(info, title, subtitle): + return { + 'id': info['loopStreamId'].replace('.mp3', ''), + 'url': 'http://loopstream01.apa.at/?channel=fm4&id=%s' % info['loopStreamId'], + 'title': title, + 'description': subtitle, + 'duration': (info['end'] - info['start']) / 1000, + 'timestamp': info['start'] / 1000, + 'ext': 'mp3' + } + + entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']] + + return { + '_type': 'playlist', + 'id': show_id, + 'title': data['title'], + 'description': data['subtitle'], + 'entries': entries + }+ \ No newline at end of file