-# coding: utf-8
-from __future__ import unicode_literals
-
import base64
import hashlib
import json
import re
from .common import InfoExtractor
-from ..compat import (
- compat_str,
-)
+from ..networking import HEADRequest
from ..utils import (
ExtractorError,
float_or_none,
}, {
'url': 'globo:3607726',
'only_matching': True,
+ }, {
+ 'url': 'https://globoplay.globo.com/v/10248083/',
+ 'info_dict': {
+ 'id': '10248083',
+ 'ext': 'mp4',
+ 'title': 'Melhores momentos: Equador 1 x 1 Brasil pelas Eliminatórias da Copa do Mundo 2022',
+ 'duration': 530.964,
+ 'uploader': 'SporTV',
+ 'uploader_id': '698',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}]
def _real_extract(self, url):
video_id = self._match_id(url)
+ self._request_webpage(
+ HEADRequest('https://globo-ab.globo.com/v2/selected-alternatives?experiments=player-isolated-experiment-02&skipImpressions=true'),
+ video_id, 'Getting cookies')
+
video = self._download_json(
- 'http://api.globovideos.com/videos/%s/playlist' % video_id,
+ f'http://api.globovideos.com/videos/{video_id}/playlist',
video_id)['videos'][0]
if not self.get_param('allow_unplayable_formats') and video.get('encrypted') is True:
self.report_drm(video_id)
formats = []
security = self._download_json(
- 'https://playback.video.globo.com/v1/video-session', video_id, 'Downloading security hash for %s' % video_id,
+ 'https://playback.video.globo.com/v2/video-session', video_id, f'Downloading security hash for {video_id}',
headers={'content-type': 'application/json'}, data=json.dumps({
- "player_type": "desktop",
- "video_id": video_id,
- "quality": "max",
- "content_protection": "widevine",
- "vsid": "581b986b-4c40-71f0-5a58-803e579d5fa2",
- "tz": "-3.0:00"
+ 'player_type': 'desktop',
+ 'video_id': video_id,
+ 'quality': 'max',
+ 'content_protection': 'widevine',
+ 'vsid': '581b986b-4c40-71f0-5a58-803e579d5fa2',
+ 'tz': '-3.0:00',
}).encode())
- security_hash = security['source']['token']
+ self._request_webpage(HEADRequest(security['sources'][0]['url_template']), video_id, 'Getting locksession cookie')
+
+ security_hash = security['sources'][0]['token']
if not security_hash:
message = security.get('message')
if message:
raise ExtractorError(
- '%s returned error: %s' % (self.IE_NAME, message), expected=True)
+ f'{self.IE_NAME} returned error: {message}', expected=True)
hash_code = security_hash[:2]
padding = '%010d' % random.randint(1, 10000000000)
padding += '1'
hash_prefix = '05' + security_hash[:22]
- padded_sign_time = compat_str(int(received_time) + 86400) + padding
+ padded_sign_time = str(int(received_time) + 86400) + padding
md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode()
signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=')
signed_hash = hash_prefix + padded_sign_time + signed_md5
- source = security['source']['url_parts']
+ source = security['sources'][0]['url_parts']
resource_url = source['scheme'] + '://' + source['domain'] + source['path']
- signed_url = '%s?h=%s&k=html5&a=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A')
+ signed_url = '{}?h={}&k=html5&a={}'.format(resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A')
- formats.extend(self._extract_m3u8_formats(
- signed_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
- self._sort_formats(formats)
+ fmts, subtitles = self._extract_m3u8_formats_and_subtitles(
+ signed_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+ formats.extend(fmts)
- subtitles = {}
for resource in video['resources']:
if resource.get('type') == 'subtitle':
subtitles.setdefault(resource.get('language') or 'por', []).append({
_VALID_URL = r'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/.]+)(?:\.html)?'
_VIDEOID_REGEXES = [
- r'\bdata-video-id=["\'](\d{7,})',
- r'\bdata-player-videosids=["\'](\d{7,})',
+ r'\bdata-video-id=["\'](\d{7,})["\']',
+ r'\bdata-player-videosids=["\'](\d{7,})["\']',
r'\bvideosIDs\s*:\s*["\']?(\d{7,})',
- r'\bdata-id=["\'](\d{7,})',
- r'<div[^>]+\bid=["\'](\d{7,})',
+ r'\bdata-id=["\'](\d{7,})["\']',
+ r'<div[^>]+\bid=["\'](\d{7,})["\']',
+ r'<bs-player[^>]+\bvideoid=["\'](\d{8,})["\']',
]
_TESTS = [{
}, {
'url': 'http://oglobo.globo.com/rio/a-amizade-entre-um-entregador-de-farmacia-um-piano-19946271',
'only_matching': True,
+ }, {
+ 'url': 'https://ge.globo.com/video/ta-na-area-como-foi-assistir-ao-jogo-do-palmeiras-que-a-globo-nao-passou-10287094.ghtml',
+ 'info_dict': {
+ 'id': 'ta-na-area-como-foi-assistir-ao-jogo-do-palmeiras-que-a-globo-nao-passou-10287094',
+ 'title': 'Tá na Área: como foi assistir ao jogo do Palmeiras que a Globo não passou',
+ 'description': 'md5:2d089d036c4c9675117d3a56f8c61739',
+ },
+ 'playlist_count': 1,
+ }, {
+ 'url': 'https://redeglobo.globo.com/rpc/meuparana/noticia/a-producao-de-chocolates-no-parana.ghtml',
+ 'info_dict': {
+ 'id': 'a-producao-de-chocolates-no-parana',
+ 'title': 'A produção de chocolates no Paraná',
+ 'description': 'md5:f2e3daf00ffd1dc0e9a8a6c7cfb0a89e',
+ },
+ 'playlist_count': 2,
}]
@classmethod
def suitable(cls, url):
- return False if GloboIE.suitable(url) else super(GloboArticleIE, cls).suitable(url)
+ return False if GloboIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)
for video_regex in self._VIDEOID_REGEXES:
video_ids.extend(re.findall(video_regex, webpage))
entries = [
- self.url_result('globo:%s' % video_id, GloboIE.ie_key())
+ self.url_result(f'globo:{video_id}', GloboIE.ie_key())
for video_id in orderedSet(video_ids)]
- title = self._og_search_title(webpage, fatal=False)
+ title = self._og_search_title(webpage).strip()
description = self._html_search_meta('description', webpage)
return self.playlist_result(entries, display_id, title, description)