-# coding: utf-8
-from __future__ import unicode_literals
-
import re
import time
from ..utils import (
determine_ext,
js_to_json,
+ urlencode_postdata,
+ ExtractorError,
+ parse_qs
)
class IPrimaIE(InfoExtractor):
- _VALID_URL = r'https?://(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+ _VALID_URL = r'https?://(?!cnn)(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_GEO_BYPASS = False
+ _NETRC_MACHINE = 'iprima'
+ _LOGIN_URL = 'https://auth.iprima.cz/oauth2/login'
+ _TOKEN_URL = 'https://auth.iprima.cz/oauth2/token'
+ access_token = None
_TESTS = [{
'url': 'https://prima.iprima.cz/particka/92-epizoda',
'ext': 'mp4',
'title': 'Partička (92)',
'description': 'md5:859d53beae4609e6dd7796413f1b6cac',
- },
- 'params': {
- 'skip_download': True, # m3u8 download
- },
- }, {
- 'url': 'https://cnn.iprima.cz/videa/70-epizoda',
- 'info_dict': {
- 'id': 'p681554',
- 'ext': 'mp4',
- 'title': 'HLAVNÍ ZPRÁVY 3.5.2020',
+ 'upload_date': '20201103',
+ 'timestamp': 1604437480,
},
'params': {
'skip_download': True, # m3u8 download
'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
'only_matching': True,
}, {
- # iframe api.play-backend.iprima.cz
'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2',
'only_matching': True,
}, {
- # iframe prima.iprima.cz
'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
'only_matching': True,
}, {
}, {
'url': 'https://love.iprima.cz/laska-az-za-hrob/slib-dany-bratrovi',
'only_matching': True,
- }, {
- 'url': 'https://autosalon.iprima.cz/motorsport/7-epizoda-1',
- 'only_matching': True,
+ }]
+
+ def _perform_login(self, username, password):
+ if self.access_token:
+ return
+
+ login_page = self._download_webpage(
+ self._LOGIN_URL, None, note='Downloading login page',
+ errnote='Downloading login page failed')
+
+ login_form = self._hidden_inputs(login_page)
+
+ login_form.update({
+ '_email': username,
+ '_password': password})
+
+ _, login_handle = self._download_webpage_handle(
+ self._LOGIN_URL, None, data=urlencode_postdata(login_form),
+ note='Logging in')
+
+ code = parse_qs(login_handle.geturl()).get('code')[0]
+ if not code:
+ raise ExtractorError('Login failed', expected=True)
+
+ token_request_data = {
+ 'scope': 'openid+email+profile+phone+address+offline_access',
+ 'client_id': 'prima_sso',
+ 'grant_type': 'authorization_code',
+ 'code': code,
+ 'redirect_uri': 'https://auth.iprima.cz/sso/auth-check'}
+
+ token_data = self._download_json(
+ self._TOKEN_URL, None,
+ note='Downloading token', errnote='Downloading token failed',
+ data=urlencode_postdata(token_request_data))
+
+ self.access_token = token_data.get('access_token')
+ if self.access_token is None:
+ raise ExtractorError('Getting token failed', expected=True)
+
+ def _real_initialize(self):
+ if not self.access_token:
+ self.raise_login_required('Login is required to access any iPrima content', method='password')
+
+ def _raise_access_error(self, error_code):
+ if error_code == 'PLAY_GEOIP_DENIED':
+ self.raise_geo_restricted(countries=['CZ'], metadata_available=True)
+ elif error_code is not None:
+ self.raise_no_formats('Access to stream infos forbidden', expected=True)
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._html_search_meta(
+ ['og:title', 'twitter:title'],
+ webpage, 'title', default=None)
+
+ video_id = self._search_regex((
+ r'productId\s*=\s*([\'"])(?P<id>p\d+)\1',
+ r'pproduct_id\s*=\s*([\'"])(?P<id>p\d+)\1'),
+ webpage, 'real id', group='id')
+
+ metadata = self._download_json(
+ f'https://api.play-backend.iprima.cz/api/v1//products/id-{video_id}/play',
+ video_id, note='Getting manifest URLs', errnote='Failed to get manifest URLs',
+ headers={'X-OTT-Access-Token': self.access_token},
+ expected_status=403)
+
+ self._raise_access_error(metadata.get('errorCode'))
+
+ stream_infos = metadata.get('streamInfos')
+ formats = []
+ if stream_infos is None:
+ self.raise_no_formats('Reading stream infos failed', expected=True)
+ else:
+ for manifest in stream_infos:
+ manifest_type = manifest.get('type')
+ manifest_url = manifest.get('url')
+ ext = determine_ext(manifest_url)
+ if manifest_type == 'HLS' or ext == 'm3u8':
+ formats += self._extract_m3u8_formats(
+ manifest_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False)
+ elif manifest_type == 'DASH' or ext == 'mpd':
+ formats += self._extract_mpd_formats(
+ manifest_url, video_id, mpd_id='dash', fatal=False)
+
+ final_result = self._search_json_ld(webpage, video_id, default={})
+ final_result.update({
+ 'id': video_id,
+ 'title': title,
+ 'thumbnail': self._html_search_meta(
+ ['thumbnail', 'og:image', 'twitter:image'],
+ webpage, 'thumbnail', default=None),
+ 'formats': formats,
+ 'description': self._html_search_meta(
+ ['description', 'og:description', 'twitter:description'],
+ webpage, 'description', default=None)})
+
+ return final_result
+
+
+class IPrimaCNNIE(InfoExtractor):
+ _VALID_URL = r'https?://cnn\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+ _GEO_BYPASS = False
+
+ _TESTS = [{
+ 'url': 'https://cnn.iprima.cz/porady/strunc/24072020-koronaviru-mam-plne-zuby-strasit-druhou-vlnou-je-absurdni-rika-senatorka-dernerova',
+ 'info_dict': {
+ 'id': 'p716177',
+ 'ext': 'mp4',
+ 'title': 'md5:277c6b1ed0577e51b40ddd35602ff43e',
+ },
+ 'params': {
+ 'skip_download': 'm3u8'
+ }
}]
def _real_extract(self, url):
extract_formats(src)
if not formats and '>GEO_IP_NOT_ALLOWED<' in playerpage:
- self.raise_geo_restricted(countries=['CZ'])
-
- self._sort_formats(formats)
+ self.raise_geo_restricted(countries=['CZ'], metadata_available=True)
return {
'id': video_id,
projects / yt-dlp.git / blobdiff