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

# coding: utf-8
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    clean_html,
    determine_ext,
    ExtractorError,
    extract_attributes,
    get_element_by_class,
    get_element_html_by_id,
    HEADRequest,
    parse_qs,
    unescapeHTML,
    unified_timestamp,
)


class MegaTVComBaseIE(InfoExtractor):
    _PLAYER_DIV_ID = 'player_div_id'

    def _extract_player_attrs(self, webpage):
        player_el = get_element_html_by_id(self._PLAYER_DIV_ID, webpage)
        return {
            re.sub(r'^data-(?:kwik_)?', '', k): v
            for k, v in extract_attributes(player_el).items()
            if k not in ('id',)
        }


class MegaTVComIE(MegaTVComBaseIE):
    IE_NAME = 'megatvcom'
    IE_DESC = 'megatv.com videos'
    _VALID_URL = r'https?://(?:www\.)?megatv\.com/(?:\d{4}/\d{2}/\d{2}|[^/]+/(?P<id>\d+))/(?P<slug>[^/]+)'

    _TESTS = [{
        'url': 'https://www.megatv.com/2021/10/23/egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia/',
        'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
        'info_dict': {
            'id': '520979',
            'ext': 'mp4',
            'title': 'md5:70eef71a9cd2c1ecff7ee428354dded2',
            'description': 'md5:0209fa8d318128569c0d256a5c404db1',
            'timestamp': 1634975747,
            'upload_date': '20211023',
            'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
            'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
        },
    }, {
        'url': 'https://www.megatv.com/tvshows/527800/epeisodio-65-12/',
        'md5': 'cba2085d45c1abeb8e7e9b7e1d6c0072',
        'info_dict': {
            'id': '527800',
            'ext': 'mp4',
            'title': 'md5:fc322cb51f682eecfe2f54cd5ab3a157',
            'description': 'md5:b2b7ed3690a78f2a0156eb790fdc00df',
            'timestamp': 1636048859,
            'upload_date': '20211104',
            'display_id': 'epeisodio-65-12',
            'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/16-1-1.jpg',
        },
    }]

    def _real_extract(self, url):
        video_id, display_id = self._match_valid_url(url).group('id', 'slug')
        _is_article = video_id is None
        webpage = self._download_webpage(url, video_id or display_id)
        if _is_article:
            video_id = self._search_regex(
                r'<article[^>]*\sid=["\']Article_(\d+)["\']', webpage, 'article id')
        player_attrs = self._extract_player_attrs(webpage)
        title = player_attrs.get('label') or self._og_search_title(webpage)
        description = get_element_by_class(
            'article-wrapper' if _is_article else 'story_content',
            webpage)
        description = clean_html(re.sub(r'<script[^>]*>[^<]+</script>', '', description))
        if not description:
            description = self._og_search_description(webpage)
        thumbnail = player_attrs.get('image') or self._og_search_thumbnail(webpage)
        timestamp = unified_timestamp(self._html_search_meta(
            'article:published_time', webpage))
        source = player_attrs.get('source')
        if not source:
            raise ExtractorError('No source found', video_id=video_id)
        if determine_ext(source) == 'm3u8':
            formats, subs = self._extract_m3u8_formats_and_subtitles(source, video_id, 'mp4')
        else:
            formats, subs = [{'url': source}], {}
        if player_attrs.get('subs'):
            self._merge_subtitles({'und': [{'url': player_attrs['subs']}]}, target=subs)
        self._sort_formats(formats)
        return {
            'id': video_id,
            'display_id': display_id,
            'title': title,
            'description': description,
            'thumbnail': thumbnail,
            'timestamp': timestamp,
            'formats': formats,
            'subtitles': subs,
        }


class MegaTVComEmbedIE(MegaTVComBaseIE):
    IE_NAME = 'megatvcom:embed'
    IE_DESC = 'megatv.com embedded videos'
    _VALID_URL = r'(?:https?:)?//(?:www\.)?megatv\.com/embed/?\?p=(?P<id>\d+)'
    _EMBED_RE = re.compile(rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''')

    _TESTS = [{
        'url': 'https://www.megatv.com/embed/?p=2020520979',
        'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
        'info_dict': {
            'id': '520979',
            'ext': 'mp4',
            'title': 'md5:70eef71a9cd2c1ecff7ee428354dded2',
            'description': 'md5:0209fa8d318128569c0d256a5c404db1',
            'timestamp': 1634975747,
            'upload_date': '20211023',
            'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
            'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
        },
    }, {
        'url': 'https://www.megatv.com/embed/?p=2020534081',
        'md5': '6ac8b3ce4dc6120c802f780a1e6b3812',
        'info_dict': {
            'id': '534081',
            'ext': 'mp4',
            'title': 'md5:062e9d5976ef854d8bdc1f5724d9b2d0',
            'description': 'md5:36dbe4c3762d2ede9513eea8d07f6d52',
            'timestamp': 1636376351,
            'upload_date': '20211108',
            'display_id': 'neo-rekor-stin-timi-tou-ilektrikou-reymatos-pano-apo-ta-200e-i-xondriki-timi-tou-ilektrikou',
            'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/Capture-266.jpg',
        },
    }]

    @classmethod
    def _extract_urls(cls, webpage):
        for mobj in cls._EMBED_RE.finditer(webpage):
            yield unescapeHTML(mobj.group('url'))

    def _match_canonical_url(self, webpage):
        LINK_RE = r'''(?x)
        <link(?:
            rel=(?P<_q1>["'])(?P<canonical>canonical)(?P=_q1)|
            href=(?P<_q2>["'])(?P<href>(?:(?!(?P=_q2)).)+)(?P=_q2)|
            [^>]*?
        )+>
        '''
        for mobj in re.finditer(LINK_RE, webpage):
            canonical, href = mobj.group('canonical', 'href')
            if canonical and href:
                return unescapeHTML(href)

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)
        player_attrs = self._extract_player_attrs(webpage)
        canonical_url = player_attrs.get('share_url') or self._match_canonical_url(webpage)
        if not canonical_url:
            raise ExtractorError('canonical URL not found')
        video_id = parse_qs(canonical_url)['p'][0]

        # Defer to megatvcom as the metadata extracted from the embeddable page some
        # times are slightly different, for the same video
        canonical_url = self._request_webpage(
            HEADRequest(canonical_url), video_id,
            note='Resolve canonical URL',
            errnote='Could not resolve canonical URL').geturl()
        return self.url_result(canonical_url, MegaTVComIE.ie_key(), video_id)
Commit	Line	Data
32b95bb6 ZM	1	# coding: utf-8
	2	from __future__ import unicode_literals
	3
	4	import re
	5
	6	from .common import InfoExtractor
	7	from ..utils import (
	8	clean_html,
	9	determine_ext,
	10	ExtractorError,
	11	extract_attributes,
	12	get_element_by_class,
	13	get_element_html_by_id,
	14	HEADRequest,
	15	parse_qs,
	16	unescapeHTML,
	17	unified_timestamp,
	18	)
	19
	20
	21	class MegaTVComBaseIE(InfoExtractor):
	22	_PLAYER_DIV_ID = 'player_div_id'
	23
	24	def _extract_player_attrs(self, webpage):
	25	player_el = get_element_html_by_id(self._PLAYER_DIV_ID, webpage)
	26	return {
	27	re.sub(r'^data-(?:kwik_)?', '', k): v
	28	for k, v in extract_attributes(player_el).items()
	29	if k not in ('id',)
	30	}
	31
	32
	33	class MegaTVComIE(MegaTVComBaseIE):
	34	IE_NAME = 'megatvcom'
	35	IE_DESC = 'megatv.com videos'
	36	_VALID_URL = r'https?://(?:www\.)?megatv\.com/(?:\d{4}/\d{2}/\d{2}\|[^/]+/(?P<id>\d+))/(?P<slug>[^/]+)'
	37
	38	_TESTS = [{
	39	'url': 'https://www.megatv.com/2021/10/23/egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia/',
	40	'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
	41	'info_dict': {
	42	'id': '520979',
	43	'ext': 'mp4',
	44	'title': 'md5:70eef71a9cd2c1ecff7ee428354dded2',
	45	'description': 'md5:0209fa8d318128569c0d256a5c404db1',
	46	'timestamp': 1634975747,
	47	'upload_date': '20211023',
	48	'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
	49	'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
	50	},
	51	}, {
	52	'url': 'https://www.megatv.com/tvshows/527800/epeisodio-65-12/',
	53	'md5': 'cba2085d45c1abeb8e7e9b7e1d6c0072',
	54	'info_dict': {
	55	'id': '527800',
	56	'ext': 'mp4',
	57	'title': 'md5:fc322cb51f682eecfe2f54cd5ab3a157',
	58	'description': 'md5:b2b7ed3690a78f2a0156eb790fdc00df',
	59	'timestamp': 1636048859,
	60	'upload_date': '20211104',
	61	'display_id': 'epeisodio-65-12',
	62	'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/16-1-1.jpg',
	63	},
	64	}]
65
66	def _real_extract(self, url):
67	video_id, display_id = self._match_valid_url(url).group('id', 'slug')
68	_is_article = video_id is None
69	webpage = self._download_webpage(url, video_id or display_id)
70	if _is_article:
71	video_id = self._search_regex(
72	r'<article[^>]*\sid=["\']Article_(\d+)["\']', webpage, 'article id')
73	player_attrs = self._extract_player_attrs(webpage)
74	title = player_attrs.get('label') or self._og_search_title(webpage)
75	description = get_element_by_class(
76	'article-wrapper' if _is_article else 'story_content',
77	webpage)
78	description = clean_html(re.sub(r'<script[^>]*>[^<]+</script>', '', description))
79	if not description:
80	description = self._og_search_description(webpage)
81	thumbnail = player_attrs.get('image') or self._og_search_thumbnail(webpage)
82	timestamp = unified_timestamp(self._html_search_meta(
83	'article:published_time', webpage))
84	source = player_attrs.get('source')
85	if not source:
86	raise ExtractorError('No source found', video_id=video_id)
87	if determine_ext(source) == 'm3u8':
88	formats, subs = self._extract_m3u8_formats_and_subtitles(source, video_id, 'mp4')
89	else:
90	formats, subs = [{'url': source}], {}
91	if player_attrs.get('subs'):
92	self._merge_subtitles({'und': [{'url': player_attrs['subs']}]}, target=subs)
93	self._sort_formats(formats)
94	return {
95	'id': video_id,
96	'display_id': display_id,
97	'title': title,
98	'description': description,
99	'thumbnail': thumbnail,
100	'timestamp': timestamp,
101	'formats': formats,
102	'subtitles': subs,
103	}
104
105
106	class MegaTVComEmbedIE(MegaTVComBaseIE):
107	IE_NAME = 'megatvcom:embed'
108	IE_DESC = 'megatv.com embedded videos'
109	_VALID_URL = r'(?:https?:)?//(?:www\.)?megatv\.com/embed/?\?p=(?P<id>\d+)'
110	_EMBED_RE = re.compile(rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''')
111
112	_TESTS = [{
113	'url': 'https://www.megatv.com/embed/?p=2020520979',
114	'md5': '6546a1a37fff0dd51c9dce5f490b7d7d',
115	'info_dict': {
116	'id': '520979',
117	'ext': 'mp4',
118	'title': 'md5:70eef71a9cd2c1ecff7ee428354dded2',
119	'description': 'md5:0209fa8d318128569c0d256a5c404db1',
120	'timestamp': 1634975747,
121	'upload_date': '20211023',
122	'display_id': 'egkainia-gia-ti-nea-skini-omega-tou-dimotikou-theatrou-peiraia',
123	'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/10/ΠΕΙΡΑΙΑΣ-1024x450.jpg',
124	},
125	}, {
126	'url': 'https://www.megatv.com/embed/?p=2020534081',
127	'md5': '6ac8b3ce4dc6120c802f780a1e6b3812',
128	'info_dict': {
129	'id': '534081',
130	'ext': 'mp4',
131	'title': 'md5:062e9d5976ef854d8bdc1f5724d9b2d0',
132	'description': 'md5:36dbe4c3762d2ede9513eea8d07f6d52',
133	'timestamp': 1636376351,
134	'upload_date': '20211108',
135	'display_id': 'neo-rekor-stin-timi-tou-ilektrikou-reymatos-pano-apo-ta-200e-i-xondriki-timi-tou-ilektrikou',
136	'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/11/Capture-266.jpg',
137	},
138	}]
139
140	@classmethod
141	def _extract_urls(cls, webpage):
142	for mobj in cls._EMBED_RE.finditer(webpage):
143	yield unescapeHTML(mobj.group('url'))
144
145	def _match_canonical_url(self, webpage):
146	LINK_RE = r'''(?x)
147	<link(?:
148	rel=(?P<_q1>["'])(?P<canonical>canonical)(?P=_q1)\|
149	href=(?P<_q2>["'])(?P<href>(?:(?!(?P=_q2)).)+)(?P=_q2)\|
150	[^>]*?
151	)+>
152	'''
153	for mobj in re.finditer(LINK_RE, webpage):
154	canonical, href = mobj.group('canonical', 'href')
155	if canonical and href:
156	return unescapeHTML(href)
157
158	def _real_extract(self, url):
159	video_id = self._match_id(url)
160	webpage = self._download_webpage(url, video_id)
161	player_attrs = self._extract_player_attrs(webpage)
162	canonical_url = player_attrs.get('share_url') or self._match_canonical_url(webpage)
163	if not canonical_url:
164	raise ExtractorError('canonical URL not found')
165	video_id = parse_qs(canonical_url)['p'][0]
166
167	# Defer to megatvcom as the metadata extracted from the embeddable page some
168	# times are slightly different, for the same video
169	canonical_url = self._request_webpage(
170	HEADRequest(canonical_url), video_id,
171	note='Resolve canonical URL',
172	errnote='Could not resolve canonical URL').geturl()
173	return self.url_result(canonical_url, MegaTVComIE.ie_key(), video_id)