From efe9316703efa5dc1561dc1c5159a77c838f5ab0 Mon Sep 17 00:00:00 2001 From: phaer Date: Sun, 8 Jan 2017 15:49:54 +0100 Subject: [orf:radio] Fix extraction Since oe1.orf.at has been updated, both ORF radios supported by youtube_dl use the same API. This commit honors this fact by merging both extractors into one. --- youtube_dl/extractor/orf.py | 113 ++++++++++++++++++++------------------------ 1 file changed, 52 insertions(+), 61 deletions(-) (limited to 'youtube_dl/extractor/orf.py') diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 1e2c54e68..10e4a2e1c 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -2,8 +2,6 @@ from __future__ import unicode_literals import re -import calendar -import datetime from .common import InfoExtractor from ..compat import compat_str @@ -144,77 +142,25 @@ class ORFTVthekIE(InfoExtractor): } -class ORFOE1IE(InfoExtractor): - IE_NAME = 'orf:oe1' - IE_DESC = 'Radio Österreich 1' - _VALID_URL = r'https?://oe1\.orf\.at/(?:programm/|konsole\?.*?\btrack_id=)(?P[0-9]+)' - - # Audios on ORF radio are only available for 7 days, so we can't add tests. - _TESTS = [{ - 'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211', - 'only_matching': True, - }, { - 'url': 'http://oe1.orf.at/konsole?show=ondemand&track_id=443608&load_day=/programm/konsole/tag/20160726', - 'only_matching': True, - }] - - def _real_extract(self, url): - show_id = self._match_id(url) - 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_NAME = 'orf:fm4' - IE_DESC = 'radio FM4' - _VALID_URL = r'https?://fm4\.orf\.at/(?:7tage/?#|player/)(?P[0-9]+)/(?P\w+)' - - _TEST = { - 'url': 'http://fm4.orf.at/player/20160110/IS/', - 'md5': '01e736e8f1cef7e13246e880a59ad298', - 'info_dict': { - 'id': '2016-01-10_2100_tl_54_7DaysSun13_11244', - 'ext': 'mp3', - 'title': 'Im Sumpf', - 'description': 'md5:384c543f866c4e422a55f66a62d669cd', - 'duration': 7173, - 'timestamp': 1452456073, - 'upload_date': '20160110', - }, - 'skip': 'Live streams on FM4 got deleted soon', - } - +class ORFRadioIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + station = mobj.group('station') show_date = mobj.group('date') show_id = mobj.group('show') + if station == 'fm4': + show_id = '4%s' % show_id + data = self._download_json( - 'http://audioapi.orf.at/fm4/json/2.0/broadcasts/%s/4%s' % (show_date, show_id), + 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date), 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'], + 'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']), 'title': title, 'description': subtitle, 'duration': (info['end'] - info['start']) / 1000, @@ -233,6 +179,51 @@ class ORFFM4IE(InfoExtractor): } +class ORFFM4IE(ORFRadioIE): + IE_NAME = 'orf:fm4' + IE_DESC = 'radio FM4' + _VALID_URL = r'https?://(?Pfm4)\.orf\.at/(?:7tage/?#|player/)(?P[0-9]+)/(?P\w+)' + + _TESTS = [ + { + 'url': 'http://fm4.orf.at/player/20170107/CC', + 'md5': '2b0be47375432a7ef104453432a19212', + 'info_dict': { + 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295', + 'ext': 'mp3', + 'title': 'Solid Steel Radioshow', + 'description': 'Die Mixshow von Coldcut und Ninja Tune.', + 'duration': 3599, + 'timestamp': 1483819257, + 'upload_date': '20170107', + }, + 'skip': 'Shows from ORF radios are only available for 7 days.' + } + ] + + +class ORFOE1IE(ORFRadioIE): + IE_NAME = 'orf:oe1' + IE_DESC = 'Radio Österreich 1' + _VALID_URL = r'https?://(?Poe1)\.orf\.at/(?:7tage/?#|player/)(?P[0-9]+)/(?P\w+)' + + _TESTS = [ + { + 'url': 'http://oe1.orf.at/player/20170108/456544', + 'md5': '34d8a6e67ea888293741c86a099b745b', + 'info_dict': { + 'id': '2017-01-08_0759_tl_51_7DaysSun6_256141', + 'ext': 'mp3', + 'title': 'Morgenjournal', + 'duration': 609, + 'timestamp': 1483858796, + 'upload_date': '20170108', + }, + 'skip': 'Shows from ORF radios are only available for 7 days.' + } + ] + + class ORFIPTVIE(InfoExtractor): IE_NAME = 'orf:iptv' IE_DESC = 'iptv.ORF.at' -- cgit 1.4.1 From 1339ecb2f8cfe96821ba6284cd470e846634f110 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Sun, 14 May 2017 04:30:29 +0700 Subject: [orf:radio] Cleanup _VALID_URLs (closes #11643) --- youtube_dl/extractor/orf.py | 62 +++++++++++++++++++++------------------------ 1 file changed, 29 insertions(+), 33 deletions(-) (limited to 'youtube_dl/extractor/orf.py') diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 10e4a2e1c..cc296eabd 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -182,46 +182,42 @@ class ORFRadioIE(InfoExtractor): class ORFFM4IE(ORFRadioIE): IE_NAME = 'orf:fm4' IE_DESC = 'radio FM4' - _VALID_URL = r'https?://(?Pfm4)\.orf\.at/(?:7tage/?#|player/)(?P[0-9]+)/(?P\w+)' + _VALID_URL = r'https?://(?Pfm4)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' - _TESTS = [ - { - 'url': 'http://fm4.orf.at/player/20170107/CC', - 'md5': '2b0be47375432a7ef104453432a19212', - 'info_dict': { - 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295', - 'ext': 'mp3', - 'title': 'Solid Steel Radioshow', - 'description': 'Die Mixshow von Coldcut und Ninja Tune.', - 'duration': 3599, - 'timestamp': 1483819257, - 'upload_date': '20170107', - }, - 'skip': 'Shows from ORF radios are only available for 7 days.' - } - ] + _TEST = { + 'url': 'http://fm4.orf.at/player/20170107/CC', + 'md5': '2b0be47375432a7ef104453432a19212', + 'info_dict': { + 'id': '2017-01-07_2100_tl_54_7DaysSat18_31295', + 'ext': 'mp3', + 'title': 'Solid Steel Radioshow', + 'description': 'Die Mixshow von Coldcut und Ninja Tune.', + 'duration': 3599, + 'timestamp': 1483819257, + 'upload_date': '20170107', + }, + 'skip': 'Shows from ORF radios are only available for 7 days.' + } class ORFOE1IE(ORFRadioIE): IE_NAME = 'orf:oe1' IE_DESC = 'Radio Österreich 1' - _VALID_URL = r'https?://(?Poe1)\.orf\.at/(?:7tage/?#|player/)(?P[0-9]+)/(?P\w+)' + _VALID_URL = r'https?://(?Poe1)\.orf\.at/player/(?P[0-9]+)/(?P\w+)' - _TESTS = [ - { - 'url': 'http://oe1.orf.at/player/20170108/456544', - 'md5': '34d8a6e67ea888293741c86a099b745b', - 'info_dict': { - 'id': '2017-01-08_0759_tl_51_7DaysSun6_256141', - 'ext': 'mp3', - 'title': 'Morgenjournal', - 'duration': 609, - 'timestamp': 1483858796, - 'upload_date': '20170108', - }, - 'skip': 'Shows from ORF radios are only available for 7 days.' - } - ] + _TEST = { + 'url': 'http://oe1.orf.at/player/20170108/456544', + 'md5': '34d8a6e67ea888293741c86a099b745b', + 'info_dict': { + 'id': '2017-01-08_0759_tl_51_7DaysSun6_256141', + 'ext': 'mp3', + 'title': 'Morgenjournal', + 'duration': 609, + 'timestamp': 1483858796, + 'upload_date': '20170108', + }, + 'skip': 'Shows from ORF radios are only available for 7 days.' + } class ORFIPTVIE(InfoExtractor): -- cgit 1.4.1 From 0732a90579091ad60b124fd693bdda8ee526e305 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 14 Sep 2017 20:37:46 +0200 Subject: [orf] Add new extractor for f4m stories --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/orf.py | 114 +++++++++++++++++++++++++++++++++++-- 2 files changed, 111 insertions(+), 4 deletions(-) (limited to 'youtube_dl/extractor/orf.py') diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index aefadc56f..a3a97e940 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -768,6 +768,7 @@ from .ora import OraTVIE from .orf import ( ORFTVthekIE, ORFFM4IE, + ORFFM4StoryIE, ORFOE1IE, ORFIPTVIE, ) diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index cc296eabd..74fe8017e 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -6,14 +6,15 @@ import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + determine_ext, + float_or_none, HEADRequest, - unified_strdate, - strip_jsonp, int_or_none, - float_or_none, - determine_ext, + orderedSet, remove_end, + strip_jsonp, unescapeHTML, + unified_strdate, ) @@ -307,3 +308,108 @@ class ORFIPTVIE(InfoExtractor): 'upload_date': upload_date, 'formats': formats, } + + +class ORFFM4StoryIE(InfoExtractor): + IE_NAME = 'orf:fm4:story' + IE_DESC = 'fm4.orf.at stories' + _VALID_URL = r'https?://fm4\.orf\.at/stories/(?P\d+)' + + _TEST = { + 'url': 'http://fm4.orf.at/stories/2865738/', + 'playlist': [{ + 'md5': 'e1c2c706c45c7b34cf478bbf409907ca', + 'info_dict': { + 'id': '547792', + 'ext': 'flv', + 'title': 'Manu Delago und Inner Tongue live', + 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.', + 'duration': 1748.52, + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20170913', + }, + }, { + 'md5': 'c6dd2179731f86f4f55a7b49899d515f', + 'info_dict': { + 'id': '547798', + 'ext': 'flv', + 'title': 'Manu Delago und Inner Tongue live (2)', + 'duration': 1504.08, + 'thumbnail': r're:^https?://.*\.jpg$', + 'upload_date': '20170913', + 'description': 'Manu Delago und Inner Tongue haben bei der FM4 Soundpark Session live alles gegeben. Hier gibt es Fotos und die gesamte Session als Video.', + }, + }], + } + + def _real_extract(self, url): + story_id = self._match_id(url) + webpage = self._download_webpage(url, story_id) + + entries = [] + all_ids = orderedSet(re.findall(r'data-video(?:id)?="(\d+)"', webpage)) + for idx, video_id in enumerate(all_ids): + data = self._download_json( + 'http://bits.orf.at/filehandler/static-api/json/current/data.json?file=%s' % video_id, + video_id)[0] + + duration = float_or_none(data['duration'], 1000) + + video = data['sources']['q8c'] + load_balancer_url = video['loadBalancerUrl'] + abr = int_or_none(video.get('audioBitrate')) + vbr = int_or_none(video.get('bitrate')) + fps = int_or_none(video.get('videoFps')) + width = int_or_none(video.get('videoWidth')) + height = int_or_none(video.get('videoHeight')) + thumbnail = video.get('preview') + + rendition = self._download_json( + load_balancer_url, video_id, transform_source=strip_jsonp) + + f = { + 'abr': abr, + 'vbr': vbr, + 'fps': fps, + 'width': width, + 'height': height, + } + + formats = [] + for format_id, format_url in rendition['redirect'].items(): + if format_id == 'rtmp': + ff = f.copy() + ff.update({ + 'url': format_url, + 'format_id': format_id, + }) + formats.append(ff) + elif determine_ext(format_url) == 'f4m': + formats.extend(self._extract_f4m_formats( + format_url, video_id, f4m_id=format_id)) + elif determine_ext(format_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', m3u8_id=format_id)) + else: + continue + self._sort_formats(formats) + + title = remove_end(self._og_search_title(webpage), ' - fm4.ORF.at') + if idx >= 1: + # Titles are duplicates, make them unique + title += ' (' + str(idx + 1) + ')' + description = self._og_search_description(webpage) + upload_date = unified_strdate(self._html_search_meta( + 'dc.date', webpage, 'upload date')) + + entries.append({ + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + 'formats': formats, + }) + + return self.playlist_result(entries) -- cgit 1.4.1 From 7512aa986f517c301fb3272584d21c8d5cec720f Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Sun, 26 Nov 2017 20:53:10 +0700 Subject: Fix some only matching tests (closes #14855) --- youtube_dl/extractor/orf.py | 6 +++--- youtube_dl/extractor/rozhlas.py | 2 +- youtube_dl/extractor/vidzi.py | 4 ++-- youtube_dl/extractor/youku.py | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'youtube_dl/extractor/orf.py') diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 74fe8017e..c1fb580ca 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -49,13 +49,13 @@ class ORFTVthekIE(InfoExtractor): 'params': { 'skip_download': True, # rtsp downloads }, - '_skip': 'Blocked outside of Austria / Germany', + 'skip': 'Blocked outside of Austria / Germany', }, { 'url': 'http://tvthek.orf.at/topic/Fluechtlingskrise/10463081/Heimat-Fremde-Heimat/13879132/Senioren-betreuen-Migrantenkinder/13879141', - 'skip_download': True, + 'only_matching': True, }, { 'url': 'http://tvthek.orf.at/profile/Universum/35429', - 'skip_download': True, + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/rozhlas.py b/youtube_dl/extractor/rozhlas.py index f8eda8dea..fccf69401 100644 --- a/youtube_dl/extractor/rozhlas.py +++ b/youtube_dl/extractor/rozhlas.py @@ -21,7 +21,7 @@ class RozhlasIE(InfoExtractor): } }, { 'url': 'http://prehravac.rozhlas.cz/audio/3421320/embed', - 'skip_download': True, + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py index e64873bce..ac35d55a9 100644 --- a/youtube_dl/extractor/vidzi.py +++ b/youtube_dl/extractor/vidzi.py @@ -28,10 +28,10 @@ class VidziIE(InfoExtractor): }, }, { 'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html', - 'skip_download': True, + 'only_matching': True, }, { 'url': 'http://vidzi.cc/cghql9yq6emu.html', - 'skip_download': True, + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index 6822a30bc..a2b3b4daf 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -240,7 +240,7 @@ class YoukuShowIE(InfoExtractor): }, { # Ongoing playlist. The initial page is the last one 'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html', - 'only_matchine': True, + 'only_matching': True, }] def _extract_entries(self, playlist_data_url, show_id, note, query): -- cgit 1.4.1