diff options
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/ndr.py | 165 |
2 files changed, 111 insertions, 56 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 2e7272931..44ab7ce3c 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -367,6 +367,8 @@ from .nbc import ( from .ndr import ( NDRIE, NJoyIE, + NDREmbedIE, + NJoyEmbedIE, ) from .ndtv import NDTVIE from .netzkino import NetzkinoIE diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 79a13958b..87f3edbbe 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -1,77 +1,92 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, qualities, - parse_duration, ) -class NDRBaseIE(InfoExtractor): - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') +preference = qualities(['xs', 's', 'm','l', 'xl']) - page = self._download_webpage(url, video_id, 'Downloading page') - title = self._og_search_title(page).strip() - description = self._og_search_description(page) - if description: - description = description.strip() - - duration = int_or_none(self._html_search_regex(r'duration: (\d+),\n', page, 'duration', default=None)) - if not duration: - duration = parse_duration(self._html_search_regex( - r'(<span class="min">\d+</span>:<span class="sec">\d+</span>)', - page, 'duration', default=None)) +class NDRBaseIE(InfoExtractor): + def extract_video_info(self, playlist, video_id): formats = [] - - mp3_url = re.search(r'''\{src:'(?P<audio>[^']+)', type:"audio/mp3"},''', page) - if mp3_url: - formats.append({ - 'url': mp3_url.group('audio'), - 'format_id': 'mp3', - }) - - thumbnail = None - - video_url = re.search(r'''3: \{src:'(?P<video>.+?)\.(lo|hi|hq)\.mp4', type:"video/mp4"},''', page) - if video_url: - thumbnails = re.findall(r'''\d+: \{src: "([^"]+)"(?: \|\| '[^']+')?, quality: '([^']+)'}''', page) - if thumbnails: - quality_key = qualities(['xs', 's', 'm', 'l', 'xl']) - largest = max(thumbnails, key=lambda thumb: quality_key(thumb[1])) - thumbnail = 'http://www.ndr.de' + largest[0] - - for format_id in 'lo', 'hi', 'hq': - formats.append({ - 'url': '%s.%s.mp4' % (video_url.group('video'), format_id), - 'format_id': format_id, - }) - - if not formats: + streamType = playlist.get('config').get('streamType') + if streamType == 'httpVideo': + for key, f in playlist.items(): + if key != 'config': + src = f['src'] + if '.f4m' in src: + formats.extend(self._extract_f4m_formats(src, video_id)) + elif '.m3u8' in src: + formats.extend(self._extract_m3u8_formats(src, video_id, fatal=False)) + else: + quality = f.get('quality') + formats.append({ + 'url': src, + 'format_id': quality, + 'preference': preference(quality), + }) + elif streamType == 'httpAudio': + for key, f in playlist.items(): + if key != 'config': + formats.append({ + 'url': f['src'], + 'format_id': 'mp3', + 'vcodec': 'none', + }) + else: raise ExtractorError('No media links available for %s' % video_id) + self._sort_formats(formats) + + config = playlist.get('config') + + title = config['title'] + duration = int_or_none(config.get('duration')) + thumbnails = [{ + 'id': thumbnail.get('quality'), + 'url': thumbnail.get('src'), + 'preference': preference(thumbnail.get('quality')) + } for thumbnail in config.get('poster').values()] + return { 'id': video_id, 'title': title, - 'description': description, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, 'duration': duration, 'formats': formats, } + def _real_extract(self, url): + video_id = self._match_id(url) + + json_data = self._download_json('http://www.ndr.de/%s-ppjson.json' % video_id, video_id, fatal=False) + + if not json_data: + webpage = self._download_webpage(url, video_id) + embed_url = self._html_search_regex(r'<iframe[^>]+id="pp_\w+"[^>]+src="(/.*)"', webpage, 'embed url', None, False) + if not embed_url: + embed_url = self._html_search_meta('embedURL', webpage, fatal=False) + if embed_url: + if embed_url.startswith('/'): + return self.url_result('http://www.ndr.de%s' % embed_url, 'NDREmbed') + else: + return self.url_result(embed_url, 'NDREmbed') + raise ExtractorError('No media links available for %s' % video_id) + + return self.extract_video_info(json_data['playlist'], video_id) + class NDRIE(NDRBaseIE): IE_NAME = 'ndr' IE_DESC = 'NDR.de - Mediathek' - _VALID_URL = r'https?://www\.ndr\.de/.+?(?P<id>\d+)\.html' + _VALID_URL = r'https?://www\.ndr\.de/.+?,(?P<id>\w+)\.html' _TESTS = [ { @@ -79,10 +94,9 @@ class NDRIE(NDRBaseIE): 'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c', 'note': 'Video file', 'info_dict': { - 'id': '25866', + 'id': 'nordmagazin25866', 'ext': 'mp4', 'title': 'Kartoffeltage in der Lewitz', - 'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8', 'duration': 166, }, 'skip': '404 Not found', @@ -91,22 +105,20 @@ class NDRIE(NDRBaseIE): 'url': 'http://www.ndr.de/fernsehen/Party-Poette-und-Parade,hafengeburtstag988.html', 'md5': 'dadc003c55ae12a5d2f6bd436cd73f59', 'info_dict': { - 'id': '988', + 'id': 'hafengeburtstag988', 'ext': 'mp4', 'title': 'Party, Pötte und Parade', - 'description': 'Hunderttausende feiern zwischen Speicherstadt und St. Pauli den 826. Hafengeburtstag. Die NDR Sondersendung zeigt die schönsten und spektakulärsten Bilder vom Auftakt.', 'duration': 3498, }, }, { - 'url': 'http://www.ndr.de/info/audio51535.html', + 'url': 'http://www.ndr.de/info/La-Valette-entgeht-der-Hinrichtung,audio51535.html', 'md5': 'bb3cd38e24fbcc866d13b50ca59307b8', 'note': 'Audio file', 'info_dict': { - 'id': '51535', + 'id': 'audio51535', 'ext': 'mp3', 'title': 'La Valette entgeht der Hinrichtung', - 'description': 'md5:22f9541913a40fe50091d5cdd7c9f536', 'duration': 884, } } @@ -115,16 +127,57 @@ class NDRIE(NDRBaseIE): class NJoyIE(NDRBaseIE): IE_NAME = 'N-JOY' - _VALID_URL = r'https?://www\.n-joy\.de/.+?(?P<id>\d+)\.html' + _VALID_URL = r'https?://www\.n-joy\.de/.+?,(?P<id>\w+)\.html' _TEST = { 'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html', 'md5': 'cb63be60cd6f9dd75218803146d8dc67', 'info_dict': { - 'id': '2480', + 'id': 'comedycontest2480', 'ext': 'mp4', 'title': 'Benaissa beim NDR Comedy Contest', - 'description': 'Von seinem sehr "behaarten" Leben lässt sich Benaissa trotz aller Schwierigkeiten nicht unterkriegen.', 'duration': 654, } } + + +class NDREmbedBaseIE(NDRBaseIE): + + def _real_extract(self, url): + video_id = self._match_id(url) + json_data = self._download_json('http://www.ndr.de/%s-ppjson.json' % video_id, video_id, fatal=False) + if not json_data: + raise ExtractorError('No media links available for %s' % video_id) + return self.extract_video_info(json_data['playlist'], video_id) + + +class NDREmbedIE(NDREmbedBaseIE): + IE_NAME = 'ndr:embed' + _VALID_URL = r'https?://www\.ndr\.de/(?:[^/]+/)+(?P<id>[a-z0-9]+)-(?:player|externalPlayer)\.html' + + _TEST = { + 'url': 'http://www.ndr.de/fernsehen/sendungen/ndr_aktuell/ndraktuell28488-player.html', + 'md5': 'cb63be60cd6f9dd75218803146d8dc67', + 'info_dict': { + 'id': 'ndraktuell28488', + 'ext': 'mp4', + 'title': 'Norddeutschland begrüßt Flüchtlinge', + 'duration': 132, + } + } + + +class NJoyEmbedIE(NDREmbedBaseIE): + IE_NAME = 'N-JOY:embed' + _VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[a-z0-9]+)-(?:player|externalPlayer)\.html' + + _TEST = { + 'url': 'http://www.n-joy.de/entertainment/film/portraet374-player_image-832d9b79-fa8a-4026-92e2-e0fd99deb2f9_theme-n-joy.html', + 'md5': 'cb63be60cd6f9dd75218803146d8dc67', + 'info_dict': { + 'id': 'portraet374', + 'ext': 'mp4', + 'title': 'Viviane Andereggen - "Schuld um Schuld"', + 'duration': 129, + } + } |