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

# coding: utf-8
from __future__ import unicode_literals

import re
import uuid

from .common import InfoExtractor
from ..compat import (
    compat_str,
    compat_urlparse,
)
from ..utils import (
    ExtractorError,
    float_or_none,
    int_or_none,
    try_get,
    url_or_none,
)


class PlutoTVIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?pluto\.tv(?:/en)?/on-demand/(?P<video_type>movies|series)/(?P<slug>.*)/?$'
    _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/'
    _INFO_QUERY_PARAMS = {
        'appName': 'web',
        'appVersion': 'na',
        'clientID': compat_str(uuid.uuid1()),
        'clientModelNumber': 'na',
        'serverSideAds': 'false',
        'deviceMake': 'unknown',
        'deviceModel': 'web',
        'deviceType': 'web',
        'deviceVersion': 'unknown',
        'sid': compat_str(uuid.uuid1()),
    }
    _TESTS = [
        {
            'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3',
            'md5': 'ebcdd8ed89aaace9df37924f722fd9bd',
            'info_dict': {
                'id': '5de6c598e9379ae4912df0a8',
                'ext': 'mp4',
                'title': 'It\'s In The Cards',
                'episode': 'It\'s In The Cards',
                'description': 'The teams face off against each other in a 3-on-2 soccer showdown.  Strategy comes into play, though, as each team gets to select their opposing teams’ two defenders.',
                'series': 'I Love Money',
                'season_number': 2,
                'episode_number': 3,
                'duration': 3600,
            }
        }, {
            'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/',
            'playlist_count': 11,
            'info_dict': {
                'id': '5de6c582e9379ae4912dedbd',
                'title': 'I Love Money - Season 1',
            }
        }, {
            'url': 'https://pluto.tv/on-demand/series/i-love-money/',
            'playlist_count': 26,
            'info_dict': {
                'id': '5de6c582e9379ae4912dedbd',
                'title': 'I Love Money',
            }
        }, {
            'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1',
            'md5': '3cead001d317a018bf856a896dee1762',
            'info_dict': {
                'id': '5e83ac701fa6a9001bb9df24',
                'ext': 'mp4',
                'title': 'Arrival',
                'description': 'When mysterious spacecraft touch down across the globe, an elite team - led by expert translator Louise Banks (Academy Award® nominee Amy Adams) – races against time to decipher their intent.',
                'duration': 9000,
            }
        }, {
            'url': 'https://pluto.tv/en/on-demand/series/manhunters-fugitive-task-force/seasons/1/episode/third-times-the-charm-1-1',
            'only_matching': True,
        }
    ]

    def _to_ad_free_formats(self, video_id, formats, subtitles):
        ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set()
        for fmt in formats:
            res = self._download_webpage(
                fmt.get('url'), video_id, note='Downloading m3u8 playlist',
                fatal=False)
            if not res:
                continue
            first_segment_url = re.search(
                r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res,
                re.MULTILINE)
            if first_segment_url:
                m3u8_urls.add(
                    compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
                continue
            first_segment_url = re.search(
                r'^(https?://.*/).+\-0+\.ts$', res,
                re.MULTILINE)
            if first_segment_url:
                m3u8_urls.add(
                    compat_urlparse.urljoin(first_segment_url.group(1), 'master.m3u8'))
                continue

        for m3u8_url in m3u8_urls:
            fmts, subs = self._extract_m3u8_formats_and_subtitles(
                m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
            ad_free_formats.extend(fmts)
            ad_free_subtitles = self._merge_subtitles(ad_free_subtitles, subs)
        if ad_free_formats:
            formats, subtitles = ad_free_formats, ad_free_subtitles
        else:
            self.report_warning('Unable to find ad-free formats')
        return formats, subtitles

    def _get_video_info(self, video_json, slug, series_name=None):
        video_id = video_json.get('_id', slug)
        formats, subtitles = [], {}
        for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []:
            if video_url.get('type') != 'hls':
                continue
            url = url_or_none(video_url.get('url'))

            fmts, subs = self._extract_m3u8_formats_and_subtitles(
                url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
            formats.extend(fmts)
            subtitles = self._merge_subtitles(subtitles, subs)

        formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles)
        self._sort_formats(formats)

        info = {
            'id': video_id,
            'formats': formats,
            'subtitles': subtitles,
            'title': video_json.get('name'),
            'description': video_json.get('description'),
            'duration': float_or_none(video_json.get('duration'), scale=1000),
        }
        if series_name:
            info.update({
                'series': series_name,
                'episode': video_json.get('name'),
                'season_number': int_or_none(video_json.get('season')),
                'episode_number': int_or_none(video_json.get('number')),
            })
        return info

    def _real_extract(self, url):
        path = compat_urlparse.urlparse(url).path
        path_components = path.split('/')
        video_type = path_components[2]
        info_slug = path_components[3]
        video_json = self._download_json(self._INFO_URL + info_slug, info_slug,
                                         query=self._INFO_QUERY_PARAMS)

        if video_type == 'series':
            series_name = video_json.get('name', info_slug)
            season_number = int_or_none(try_get(path_components, lambda x: x[5]))
            episode_slug = try_get(path_components, lambda x: x[7])

            videos = []
            for season in video_json['seasons']:
                if season_number is not None and season_number != int_or_none(season.get('number')):
                    continue
                for episode in season['episodes']:
                    if episode_slug is not None and episode_slug != episode.get('slug'):
                        continue
                    videos.append(self._get_video_info(episode, episode_slug, series_name))
            if not videos:
                raise ExtractorError('Failed to find any videos to extract')
            if episode_slug is not None and len(videos) == 1:
                return videos[0]
            playlist_title = series_name
            if season_number is not None:
                playlist_title += ' - Season %d' % season_number
            return self.playlist_result(videos,
                                        playlist_id=video_json.get('_id', info_slug),
                                        playlist_title=playlist_title)
        return self._get_video_info(video_json, info_slug)
Commit	Line	Data
ea3a012d C	1	# coding: utf-8
	2	from __future__ import unicode_literals
	3
	4	import re
	5	import uuid
	6
	7	from .common import InfoExtractor
	8	from ..compat import (
	9	compat_str,
	10	compat_urlparse,
	11	)
	12	from ..utils import (
	13	ExtractorError,
	14	float_or_none,
	15	int_or_none,
	16	try_get,
	17	url_or_none,
	18	)
	19
	20
	21	class PlutoTVIE(InfoExtractor):
2b18a8c5	22	_VALID_URL = r'https?://(?:www\.)?pluto\.tv(?:/en)?/on-demand/(?P<video_type>movies\|series)/(?P<slug>.*)/?$'
ea3a012d C	23	_INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/'
	24	_INFO_QUERY_PARAMS = {
	25	'appName': 'web',
	26	'appVersion': 'na',
	27	'clientID': compat_str(uuid.uuid1()),
	28	'clientModelNumber': 'na',
	29	'serverSideAds': 'false',
	30	'deviceMake': 'unknown',
	31	'deviceModel': 'web',
	32	'deviceType': 'web',
	33	'deviceVersion': 'unknown',
	34	'sid': compat_str(uuid.uuid1()),
	35	}
	36	_TESTS = [
	37	{
	38	'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3',
	39	'md5': 'ebcdd8ed89aaace9df37924f722fd9bd',
	40	'info_dict': {
	41	'id': '5de6c598e9379ae4912df0a8',
	42	'ext': 'mp4',
	43	'title': 'It\'s In The Cards',
	44	'episode': 'It\'s In The Cards',
	45	'description': 'The teams face off against each other in a 3-on-2 soccer showdown. Strategy comes into play, though, as each team gets to select their opposing teams’ two defenders.',
	46	'series': 'I Love Money',
	47	'season_number': 2,
	48	'episode_number': 3,
	49	'duration': 3600,
	50	}
2b18a8c5	51	}, {
ea3a012d C	52	'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/',
	53	'playlist_count': 11,
	54	'info_dict': {
	55	'id': '5de6c582e9379ae4912dedbd',
	56	'title': 'I Love Money - Season 1',
	57	}
2b18a8c5	58	}, {
ea3a012d C	59	'url': 'https://pluto.tv/on-demand/series/i-love-money/',
	60	'playlist_count': 26,
	61	'info_dict': {
	62	'id': '5de6c582e9379ae4912dedbd',
	63	'title': 'I Love Money',
	64	}
2b18a8c5	65	}, {
ea3a012d C	66	'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1',
	67	'md5': '3cead001d317a018bf856a896dee1762',
	68	'info_dict': {
	69	'id': '5e83ac701fa6a9001bb9df24',
	70	'ext': 'mp4',
	71	'title': 'Arrival',
	72	'description': 'When mysterious spacecraft touch down across the globe, an elite team - led by expert translator Louise Banks (Academy Award® nominee Amy Adams) – races against time to decipher their intent.',
	73	'duration': 9000,
	74	}
2b18a8c5	75	}, {
	76	'url': 'https://pluto.tv/en/on-demand/series/manhunters-fugitive-task-force/seasons/1/episode/third-times-the-charm-1-1',
	77	'only_matching': True,
	78	}
ea3a012d C	79	]
ea3a012d C	80
7700b37f	81	def _to_ad_free_formats(self, video_id, formats, subtitles):
7700b37f	82	ad_free_formats, ad_free_subtitles, m3u8_urls = [], {}, set()
12e73423	83	for fmt in formats:
ea3a012d	84	res = self._download_webpage(
12e73423	85	fmt.get('url'), video_id, note='Downloading m3u8 playlist',
ea3a012d C	86	fatal=False)
	87	if not res:
	88	continue
	89	first_segment_url = re.search(
	90	r'^(https?://.*/)0\-(end\|[0-9]+)/[^/]+\.ts$', res,
	91	re.MULTILINE)
12e73423	92	if first_segment_url:
	93	m3u8_urls.add(
	94	compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
	95	continue
	96	first_segment_url = re.search(
	97	r'^(https?://.*/).+\-0+\.ts$', res,
	98	re.MULTILINE)
	99	if first_segment_url:
	100	m3u8_urls.add(
	101	compat_urlparse.urljoin(first_segment_url.group(1), 'master.m3u8'))
ea3a012d	102	continue
ea3a012d C	103
ea3a012d C	104	for m3u8_url in m3u8_urls:
7700b37f	105	fmts, subs = self._extract_m3u8_formats_and_subtitles(
	106	m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
	107	ad_free_formats.extend(fmts)
	108	ad_free_subtitles = self._merge_subtitles(ad_free_subtitles, subs)
12e73423	109	if ad_free_formats:
	110	formats, subtitles = ad_free_formats, ad_free_subtitles
	111	else:
a06916d9	112	self.report_warning('Unable to find ad-free formats')
12e73423	113	return formats, subtitles
ea3a012d C	114
	115	def _get_video_info(self, video_json, slug, series_name=None):
	116	video_id = video_json.get('_id', slug)
7700b37f	117	formats, subtitles = [], {}
ea3a012d C	118	for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []:
	119	if video_url.get('type') != 'hls':
	120	continue
	121	url = url_or_none(video_url.get('url'))
7700b37f	122
	123	fmts, subs = self._extract_m3u8_formats_and_subtitles(
	124	url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
	125	formats.extend(fmts)
	126	subtitles = self._merge_subtitles(subtitles, subs)
	127
	128	formats, subtitles = self._to_ad_free_formats(video_id, formats, subtitles)
	129	self._sort_formats(formats)
	130
ea3a012d C	131	info = {
ea3a012d C	132	'id': video_id,
7700b37f	133	'formats': formats,
7700b37f	134	'subtitles': subtitles,
ea3a012d C	135	'title': video_json.get('name'),
	136	'description': video_json.get('description'),
	137	'duration': float_or_none(video_json.get('duration'), scale=1000),
	138	}
	139	if series_name:
	140	info.update({
	141	'series': series_name,
	142	'episode': video_json.get('name'),
	143	'season_number': int_or_none(video_json.get('season')),
	144	'episode_number': int_or_none(video_json.get('number')),
	145	})
	146	return info
	147
	148	def _real_extract(self, url):
	149	path = compat_urlparse.urlparse(url).path
	150	path_components = path.split('/')
	151	video_type = path_components[2]
	152	info_slug = path_components[3]
	153	video_json = self._download_json(self._INFO_URL + info_slug, info_slug,
	154	query=self._INFO_QUERY_PARAMS)
	155
	156	if video_type == 'series':
	157	series_name = video_json.get('name', info_slug)
	158	season_number = int_or_none(try_get(path_components, lambda x: x[5]))
	159	episode_slug = try_get(path_components, lambda x: x[7])
	160
	161	videos = []
	162	for season in video_json['seasons']:
	163	if season_number is not None and season_number != int_or_none(season.get('number')):
	164	continue
	165	for episode in season['episodes']:
	166	if episode_slug is not None and episode_slug != episode.get('slug'):
	167	continue
	168	videos.append(self._get_video_info(episode, episode_slug, series_name))
	169	if not videos:
	170	raise ExtractorError('Failed to find any videos to extract')
	171	if episode_slug is not None and len(videos) == 1:
	172	return videos[0]
	173	playlist_title = series_name
	174	if season_number is not None:
	175	playlist_title += ' - Season %d' % season_number
	176	return self.playlist_result(videos,
	177	playlist_id=video_json.get('_id', info_slug),
	178	playlist_title=playlist_title)
	179	return self._get_video_info(video_json, info_slug)