[yt-dlp.git] / yt_dlp / extractor / toggle.py

import json
import re

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    float_or_none,
    int_or_none,
    parse_iso8601,
    strip_or_none,
)


class ToggleIE(InfoExtractor):
    IE_NAME = 'toggle'
    _VALID_URL = r'(?:https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}|toggle:)(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
        'info_dict': {
            'id': '343115',
            'ext': 'mp4',
            'title': 'Lion Moms Premiere',
            'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b',
            'upload_date': '20150910',
            'timestamp': 1441858274,
        },
        'params': {
            'skip_download': 'm3u8 download',
        }
    }, {
        'note': 'DRM-protected video',
        'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
        'info_dict': {
            'id': '341413',
            'ext': 'wvm',
            'title': 'Dug\'s Special Mission',
            'description': 'md5:e86c6f4458214905c1772398fabc93e0',
            'upload_date': '20150827',
            'timestamp': 1440644006,
        },
        'params': {
            'skip_download': 'DRM-protected wvm download',
        }
    }, {
        # this also tests correct video id extraction
        'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
        'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
        'info_dict': {
            'id': '332861',
            'ext': 'mp4',
            'title': '28th SEA Games (5 Show) -  Episode  11',
            'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
            'upload_date': '20150605',
            'timestamp': 1433480166,
        },
        'params': {
            'skip_download': 'DRM-protected wvm download',
        },
        'skip': 'm3u8 links are geo-restricted'
    }, {
        'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
        'only_matching': True,
    }, {
        'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
        'only_matching': True,
    }, {
        'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
        'only_matching': True,
    }, {
        'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
        'only_matching': True,
    }, {
        'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
        'only_matching': True,
    }, {
        'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
        'only_matching': True,
    }, {
        'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
        'only_matching': True,
    }]

    _API_USER = 'tvpapi_147'
    _API_PASS = '11111'

    def _real_extract(self, url):
        video_id = self._match_id(url)

        params = {
            'initObj': {
                'Locale': {
                    'LocaleLanguage': '',
                    'LocaleCountry': '',
                    'LocaleDevice': '',
                    'LocaleUserState': 0
                },
                'Platform': 0,
                'SiteGuid': 0,
                'DomainID': '0',
                'UDID': '',
                'ApiUser': self._API_USER,
                'ApiPass': self._API_PASS
            },
            'MediaID': video_id,
            'mediaType': 0,
        }

        info = self._download_json(
            'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
            video_id, 'Downloading video info json', data=json.dumps(params).encode('utf-8'))

        title = info['MediaName']

        formats = []
        for video_file in info.get('Files', []):
            video_url, vid_format = video_file.get('URL'), video_file.get('Format')
            if not video_url or video_url == 'NA' or not vid_format:
                continue
            ext = determine_ext(video_url)
            vid_format = vid_format.replace(' ', '')
            # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
            if ext == 'm3u8':
                m3u8_formats = self._extract_m3u8_formats(
                    video_url, video_id, ext='mp4', m3u8_id=vid_format,
                    note='Downloading %s m3u8 information' % vid_format,
                    errnote='Failed to download %s m3u8 information' % vid_format,
                    fatal=False)
                for f in m3u8_formats:
                    # Apple FairPlay Streaming
                    if '/fpshls/' in f['url']:
                        continue
                    formats.append(f)
            elif ext == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    video_url, video_id, mpd_id=vid_format,
                    note='Downloading %s MPD manifest' % vid_format,
                    errnote='Failed to download %s MPD manifest' % vid_format,
                    fatal=False))
            elif ext == 'ism':
                formats.extend(self._extract_ism_formats(
                    video_url, video_id, ism_id=vid_format,
                    note='Downloading %s ISM manifest' % vid_format,
                    errnote='Failed to download %s ISM manifest' % vid_format,
                    fatal=False))
            elif ext == 'mp4':
                formats.append({
                    'ext': ext,
                    'url': video_url,
                    'format_id': vid_format,
                })
        if not formats:
            for meta in (info.get('Metas') or []):
                if (not self.get_param('allow_unplayable_formats')
                        and meta.get('Key') == 'Encryption' and meta.get('Value') == '1'):
                    self.report_drm(video_id)
            # Most likely because geo-blocked if no formats and no DRM
        self._sort_formats(formats)

        thumbnails = []
        for picture in info.get('Pictures', []):
            if not isinstance(picture, dict):
                continue
            pic_url = picture.get('URL')
            if not pic_url:
                continue
            thumbnail = {
                'url': pic_url,
            }
            pic_size = picture.get('PicSize', '')
            m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
            if m:
                thumbnail.update({
                    'width': int(m.group('width')),
                    'height': int(m.group('height')),
                })
            thumbnails.append(thumbnail)

        def counter(prefix):
            return int_or_none(
                info.get(prefix + 'Counter') or info.get(prefix.lower() + '_counter'))

        return {
            'id': video_id,
            'title': title,
            'description': strip_or_none(info.get('Description')),
            'duration': int_or_none(info.get('Duration')),
            'timestamp': parse_iso8601(info.get('CreationDate') or None),
            'average_rating': float_or_none(info.get('Rating')),
            'view_count': counter('View'),
            'like_count': counter('Like'),
            'thumbnails': thumbnails,
            'formats': formats,
        }


class MeWatchIE(InfoExtractor):
    IE_NAME = 'mewatch'
    _VALID_URL = r'https?://(?:(?:www|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
    _TESTS = [{
        'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
        'info_dict': {
            'id': '1008625',
            'ext': 'mp4',
            'title': 'Recipe Of Life 味之道',
            'timestamp': 1603306526,
            'description': 'md5:6e88cde8af2068444fc8e1bc3ebf257c',
            'upload_date': '20201021',
        },
        'params': {
            'skip_download': 'm3u8 download',
        },
    }, {
        'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232',
        'only_matching': True,
    }, {
        'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232',
        'only_matching': True,
    }, {
        'url': 'https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        item_id = self._match_id(url)
        custom_id = self._download_json(
            'https://cdn.mewatch.sg/api/items/' + item_id,
            item_id, query={'segments': 'all'})['customId']
        return self.url_result(
            'toggle:' + custom_id, ToggleIE.ie_key(), custom_id)
Commit	Line	Data
ee0f0393	1	import json
c40dbb19	2	import re
ee0f0393	3
	4	from .common import InfoExtractor
	5	from ..utils import (
c82a8dd1	6	determine_ext,
8f097af4	7	float_or_none,
ee0f0393	8	int_or_none,
ee0f0393	9	parse_iso8601,
29f7c58a	10	strip_or_none,
ee0f0393	11	)
ee0f0393	12
ee0f0393	13
cc0f378d	14	class ToggleIE(InfoExtractor):
0f206ee8	15	IE_NAME = 'toggle'
29f7c58a	16	_VALID_URL = r'(?:https?://(?:(?:www\.)?mewatch\|video\.toggle)\.sg/(?:en\|zh)/(?:[^/]+/){2,}\|toggle:)(?P<id>[0-9]+)'
ee0f0393	17	_TESTS = [{
fffc618c	18	'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
ee0f0393	19	'info_dict': {
	20	'id': '343115',
	21	'ext': 'mp4',
	22	'title': 'Lion Moms Premiere',
	23	'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b',
	24	'upload_date': '20150910',
	25	'timestamp': 1441858274,
	26	},
	27	'params': {
	28	'skip_download': 'm3u8 download',
	29	}
	30	}, {
	31	'note': 'DRM-protected video',
fffc618c	32	'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
ee0f0393	33	'info_dict': {
	34	'id': '341413',
	35	'ext': 'wvm',
	36	'title': 'Dug\'s Special Mission',
	37	'description': 'md5:e86c6f4458214905c1772398fabc93e0',
	38	'upload_date': '20150827',
	39	'timestamp': 1440644006,
	40	},
	41	'params': {
	42	'skip_download': 'DRM-protected wvm download',
	43	}
	44	}, {
e33c9cba	45	# this also tests correct video id extraction
ee0f0393	46	'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
fffc618c	47	'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
ee0f0393	48	'info_dict': {
	49	'id': '332861',
	50	'ext': 'mp4',
	51	'title': '28th SEA Games (5 Show) - Episode 11',
	52	'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
	53	'upload_date': '20150605',
	54	'timestamp': 1433480166,
	55	},
	56	'params': {
	57	'skip_download': 'DRM-protected wvm download',
	58	},
	59	'skip': 'm3u8 links are geo-restricted'
	60	}, {
	61	'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
	62	'only_matching': True,
	63	}, {
fffc618c	64	'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
ee0f0393	65	'only_matching': True,
ee0f0393	66	}, {
fffc618c	67	'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
ee0f0393	68	'only_matching': True,
ee0f0393	69	}, {
fffc618c	70	'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
ee0f0393	71	'only_matching': True,
35a2d221	72	}, {
fffc618c	73	'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
35a2d221 S	74	'only_matching': True,
35a2d221 S	75	}, {
fffc618c XH	76	'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
	77	'only_matching': True,
	78	}, {
	79	'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
35a2d221	80	'only_matching': True,
ee0f0393	81	}]
ee0f0393	82
ee0f0393	83	_API_USER = 'tvpapi_147'
	84	_API_PASS = '11111'
	85
	86	def _real_extract(self, url):
	87	video_id = self._match_id(url)
	88
ee0f0393	89	params = {
	90	'initObj': {
	91	'Locale': {
74c73017 S	92	'LocaleLanguage': '',
	93	'LocaleCountry': '',
	94	'LocaleDevice': '',
	95	'LocaleUserState': 0
ee0f0393	96	},
74c73017 S	97	'Platform': 0,
	98	'SiteGuid': 0,
	99	'DomainID': '0',
	100	'UDID': '',
29f7c58a	101	'ApiUser': self._API_USER,
29f7c58a	102	'ApiPass': self._API_PASS
ee0f0393	103	},
	104	'MediaID': video_id,
	105	'mediaType': 0,
	106	}
	107
29f7c58a	108	info = self._download_json(
ee0f0393	109	'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
29f7c58a	110	video_id, 'Downloading video info json', data=json.dumps(params).encode('utf-8'))
ee0f0393	111
ee0f0393	112	title = info['MediaName']
ee0f0393	113
c40dbb19	114	formats = []
ee0f0393	115	for video_file in info.get('Files', []):
989e9f8e	116	video_url, vid_format = video_file.get('URL'), video_file.get('Format')
949faa15	117	if not video_url or video_url == 'NA' or not vid_format:
989e9f8e S	118	continue
	119	ext = determine_ext(video_url)
	120	vid_format = vid_format.replace(' ', '')
ee0f0393	121	# if geo-restricted, m3u8 is inaccessible, but mp4 is okay
ee0f0393	122	if ext == 'm3u8':
29f7c58a	123	m3u8_formats = self._extract_m3u8_formats(
989e9f8e	124	video_url, video_id, ext='mp4', m3u8_id=vid_format,
ee0f0393	125	note='Downloading %s m3u8 information' % vid_format,
ee0f0393	126	errnote='Failed to download %s m3u8 information' % vid_format,
29f7c58a	127	fatal=False)
	128	for f in m3u8_formats:
	129	# Apple FairPlay Streaming
	130	if '/fpshls/' in f['url']:
	131	continue
	132	formats.append(f)
949faa15 S	133	elif ext == 'mpd':
	134	formats.extend(self._extract_mpd_formats(
	135	video_url, video_id, mpd_id=vid_format,
	136	note='Downloading %s MPD manifest' % vid_format,
	137	errnote='Failed to download %s MPD manifest' % vid_format,
	138	fatal=False))
	139	elif ext == 'ism':
	140	formats.extend(self._extract_ism_formats(
	141	video_url, video_id, ism_id=vid_format,
	142	note='Downloading %s ISM manifest' % vid_format,
	143	errnote='Failed to download %s ISM manifest' % vid_format,
	144	fatal=False))
29f7c58a	145	elif ext == 'mp4':
ee0f0393	146	formats.append({
ee0f0393	147	'ext': ext,
989e9f8e	148	'url': video_url,
ee0f0393	149	'format_id': vid_format,
ee0f0393	150	})
ee0f0393	151	if not formats:
29f7c58a	152	for meta in (info.get('Metas') or []):
a06916d9	153	if (not self.get_param('allow_unplayable_formats')
06869367	154	and meta.get('Key') == 'Encryption' and meta.get('Value') == '1'):
88acdbc2	155	self.report_drm(video_id)
b7da73eb	156	# Most likely because geo-blocked if no formats and no DRM
ee0f0393	157	self._sort_formats(formats)
ee0f0393	158
c40dbb19 S	159	thumbnails = []
	160	for picture in info.get('Pictures', []):
	161	if not isinstance(picture, dict):
	162	continue
	163	pic_url = picture.get('URL')
	164	if not pic_url:
	165	continue
	166	thumbnail = {
	167	'url': pic_url,
	168	}
	169	pic_size = picture.get('PicSize', '')
	170	m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
	171	if m:
	172	thumbnail.update({
	173	'width': int(m.group('width')),
	174	'height': int(m.group('height')),
	175	})
	176	thumbnails.append(thumbnail)
	177
29f7c58a	178	def counter(prefix):
	179	return int_or_none(
	180	info.get(prefix + 'Counter') or info.get(prefix.lower() + '_counter'))
	181
ee0f0393	182	return {
	183	'id': video_id,
	184	'title': title,
29f7c58a	185	'description': strip_or_none(info.get('Description')),
	186	'duration': int_or_none(info.get('Duration')),
	187	'timestamp': parse_iso8601(info.get('CreationDate') or None),
	188	'average_rating': float_or_none(info.get('Rating')),
	189	'view_count': counter('View'),
	190	'like_count': counter('Like'),
c40dbb19	191	'thumbnails': thumbnails,
ee0f0393	192	'formats': formats,
ee0f0393	193	}
29f7c58a	194
	195
	196	class MeWatchIE(InfoExtractor):
	197	IE_NAME = 'mewatch'
	198	_VALID_URL = r'https?://(?:(?:www\|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
	199	_TESTS = [{
	200	'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
	201	'info_dict': {
	202	'id': '1008625',
	203	'ext': 'mp4',
	204	'title': 'Recipe Of Life 味之道',
	205	'timestamp': 1603306526,
	206	'description': 'md5:6e88cde8af2068444fc8e1bc3ebf257c',
	207	'upload_date': '20201021',
	208	},
	209	'params': {
	210	'skip_download': 'm3u8 download',
	211	},
	212	}, {
	213	'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232',
	214	'only_matching': True,
	215	}, {
	216	'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232',
	217	'only_matching': True,
	218	}, {
	219	'url': 'https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759',
	220	'only_matching': True,
	221	}]
	222
	223	def _real_extract(self, url):
	224	item_id = self._match_id(url)
	225	custom_id = self._download_json(
	226	'https://cdn.mewatch.sg/api/items/' + item_id,
	227	item_id, query={'segments': 'all'})['customId']
	228	return self.url_result(
	229	'toggle:' + custom_id, ToggleIE.ie_key(), custom_id)