X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/47d80ec0b18245caeb97018d4c1af18d0b5b972b..8da41cd9dd1fb23ad985894740ac01fa99733936:/youtube_dl/extractor/rtl2.py?ds=inline diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py index cb4ee88..18a327d 100644 --- a/youtube_dl/extractor/rtl2.py +++ b/youtube_dl/extractor/rtl2.py @@ -2,10 +2,25 @@ from __future__ import unicode_literals import re + from .common import InfoExtractor +from ..aes import aes_cbc_decrypt +from ..compat import ( + compat_b64decode, + compat_ord, + compat_str, +) +from ..utils import ( + bytes_to_intlist, + ExtractorError, + intlist_to_bytes, + int_or_none, + strip_or_none, +) class RTL2IE(InfoExtractor): + IE_NAME = 'rtl2' _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P[^?#/]*?)(?:$|/(?:$|[?#]))' _TESTS = [{ 'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0', @@ -13,7 +28,7 @@ class RTL2IE(InfoExtractor): 'id': 'folge-203-0', 'ext': 'f4v', 'title': 'GRIP sucht den Sommerkönig', - 'description': 'Matthias, Det und Helge treten gegeneinander an.' + 'description': 'md5:e3adbb940fd3c6e76fa341b8748b562f' }, 'params': { # rtmp download @@ -25,7 +40,7 @@ class RTL2IE(InfoExtractor): 'id': '21040-anna-erwischt-alex', 'ext': 'mp4', 'title': 'Anna erwischt Alex!', - 'description': 'Anna ist Alex\' Tochter bei Köln 50667.' + 'description': 'Anna nimmt ihrem Vater nicht ab, dass er nicht spielt. Und tatsächlich erwischt sie ihn auf frischer Tat.' }, 'params': { # rtmp download @@ -52,34 +67,142 @@ class RTL2IE(InfoExtractor): r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id') vivi_id = self._html_search_regex( r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id') - info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id - info = self._download_json(info_url, video_id) + info = self._download_json( + 'http://www.rtl2.de/sites/default/modules/rtl2/mediathek/php/get_video_jw.php', + video_id, query={ + 'vico_id': vico_id, + 'vivi_id': vivi_id, + }) video_info = info['video'] title = video_info['titel'] - description = video_info.get('beschreibung') - thumbnail = video_info.get('image') - - download_url = video_info['streamurl'] - download_url = download_url.replace('\\', '') - stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL') - rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0'] - - formats = [{ - 'url': download_url, - 'play_path': stream_url, - 'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf', - 'page_url': url, - 'flash_version': 'LNX 11,2,202,429', - 'rtmp_conn': rtmp_conn, - 'no_resume': True, - }] + + formats = [] + + rtmp_url = video_info.get('streamurl') + if rtmp_url: + rtmp_url = rtmp_url.replace('\\', '') + stream_url = 'mp4:' + self._html_search_regex(r'/ondemand/(.+)', rtmp_url, 'stream URL') + rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0'] + + formats.append({ + 'format_id': 'rtmp', + 'url': rtmp_url, + 'play_path': stream_url, + 'player_url': 'http://www.rtl2.de/flashplayer/vipo_player.swf', + 'page_url': url, + 'flash_version': 'LNX 11,2,202,429', + 'rtmp_conn': rtmp_conn, + 'no_resume': True, + 'preference': 1, + }) + + m3u8_url = video_info.get('streamurl_hls') + if m3u8_url: + formats.extend(self._extract_akamai_formats(m3u8_url, video_id)) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'thumbnail': video_info.get('image'), + 'description': video_info.get('beschreibung'), + 'duration': int_or_none(video_info.get('duration')), + 'formats': formats, + } + + +class RTL2YouBaseIE(InfoExtractor): + _BACKWERK_BASE_URL = 'https://p-you-backwerk.rtl2apps.de/' + + +class RTL2YouIE(RTL2YouBaseIE): + IE_NAME = 'rtl2:you' + _VALID_URL = r'http?://you\.rtl2\.de/(?:video/\d+/|youplayer/index\.html\?.*?\bvid=)(?P\d+)' + _TESTS = [{ + 'url': 'http://you.rtl2.de/video/3002/15740/MJUNIK%20%E2%80%93%20Home%20of%20YOU/307-hirn-wo-bist-du', + 'info_dict': { + 'id': '15740', + 'ext': 'mp4', + 'title': 'MJUNIK – Home of YOU - #307 Hirn, wo bist du?!', + 'description': 'md5:ddaa95c61b372b12b66e115b2772fe01', + 'age_limit': 12, + }, + }, { + 'url': 'http://you.rtl2.de/youplayer/index.html?vid=15712', + 'only_matching': True, + }] + _AES_KEY = b'\xe9W\xe4.<*\xb8\x1a\xd2\xb6\x92\xf3C\xd3\xefL\x1b\x03*\xbbbH\xc0\x03\xffo\xc2\xf2(\xaa\xaa!' + _GEO_COUNTRIES = ['DE'] + + def _real_extract(self, url): + video_id = self._match_id(url) + + stream_data = self._download_json( + self._BACKWERK_BASE_URL + 'stream/video/' + video_id, video_id) + + data, iv = compat_b64decode(stream_data['streamUrl']).decode().split(':') + stream_url = intlist_to_bytes(aes_cbc_decrypt( + bytes_to_intlist(compat_b64decode(data)), + bytes_to_intlist(self._AES_KEY), + bytes_to_intlist(compat_b64decode(iv)) + )) + if b'rtl2_you_video_not_found' in stream_url: + raise ExtractorError('video not found', expected=True) + + formats = self._extract_m3u8_formats( + stream_url[:-compat_ord(stream_url[-1])].decode(), + video_id, 'mp4', 'm3u8_native') self._sort_formats(formats) + video_data = self._download_json( + self._BACKWERK_BASE_URL + 'video/' + video_id, video_id) + + series = video_data.get('formatTitle') + title = episode = video_data.get('title') or series + if series and series != title: + title = '%s - %s' % (series, title) + return { 'id': video_id, 'title': title, - 'thumbnail': thumbnail, - 'description': description, 'formats': formats, + 'description': strip_or_none(video_data.get('description')), + 'thumbnail': video_data.get('image'), + 'duration': int_or_none(stream_data.get('duration') or video_data.get('duration'), 1000), + 'series': series, + 'episode': episode, + 'age_limit': int_or_none(video_data.get('minimumAge')), } + + +class RTL2YouSeriesIE(RTL2YouBaseIE): + IE_NAME = 'rtl2:you:series' + _VALID_URL = r'http?://you\.rtl2\.de/videos/(?P\d+)' + _TEST = { + 'url': 'http://you.rtl2.de/videos/115/dragon-ball', + 'info_dict': { + 'id': '115', + }, + 'playlist_mincount': 5, + } + + def _real_extract(self, url): + series_id = self._match_id(url) + stream_data = self._download_json( + self._BACKWERK_BASE_URL + 'videos', + series_id, query={ + 'formatId': series_id, + 'limit': 1000000000, + }) + + entries = [] + for video in stream_data.get('videos', []): + video_id = compat_str(video['videoId']) + if not video_id: + continue + entries.append(self.url_result( + 'http://you.rtl2.de/video/%s/%s' % (series_id, video_id), + 'RTL2You', video_id)) + return self.playlist_result(entries, series_id)