yt-dlp/yt_dlp/extractor/noovo.py

101 lines
3.5 KiB
Python
Raw Normal View History

from .brightcove import BrightcoveNewIE
2017-04-19 23:43:32 +02:00
from .common import InfoExtractor
from ..utils import (
int_or_none,
2017-09-15 18:12:19 +02:00
js_to_json,
smuggle_url,
try_get,
)
2017-04-19 23:43:32 +02:00
class NoovoIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?noovo\.ca/videos/(?P<id>[^/]+/[^/?#&]+)'
2017-04-19 23:43:32 +02:00
_TESTS = [{
# clip
2017-04-19 23:43:32 +02:00
'url': 'http://noovo.ca/videos/rpm-plus/chrysler-imperial',
'info_dict': {
'id': '5386045029001',
'ext': 'mp4',
'title': 'Chrysler Imperial',
'description': 'md5:de3c898d1eb810f3e6243e08c8b4a056',
'timestamp': 1491399228,
2017-04-19 23:43:32 +02:00
'upload_date': '20170405',
'uploader_id': '618566855001',
'series': 'RPM+',
},
'params': {
'skip_download': True,
},
2017-04-19 23:43:32 +02:00
}, {
# episode
2017-04-19 23:43:32 +02:00
'url': 'http://noovo.ca/videos/l-amour-est-dans-le-pre/episode-13-8',
'info_dict': {
'id': '5395865725001',
'title': 'Épisode 13 : Les retrouvailles',
2017-09-15 18:12:19 +02:00
'description': 'md5:888c3330f0c1b4476c5bc99a1c040473',
2017-04-19 23:43:32 +02:00
'ext': 'mp4',
'timestamp': 1492019320,
'upload_date': '20170412',
'uploader_id': '618566855001',
'series': "L'amour est dans le pré",
'season_number': 5,
'episode': 'Épisode 13',
'episode_number': 13,
},
'params': {
'skip_download': True,
},
2017-04-19 23:43:32 +02:00
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/618566855001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
2017-09-15 18:12:19 +02:00
webpage = self._download_webpage(url, video_id)
2017-04-19 23:43:32 +02:00
2019-02-16 16:45:53 +01:00
brightcove_id = self._search_regex(
r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
2017-09-15 18:12:19 +02:00
data = self._parse_json(
self._search_regex(
r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data',
default='{}'),
video_id, transform_source=js_to_json, fatal=False)
title = try_get(
data, lambda x: x['video']['nom'],
str) or self._html_search_meta(
2017-09-15 18:12:19 +02:00
'dcterms.Title', webpage, 'title', fatal=True)
description = self._html_search_meta(
('dcterms.Description', 'description'), webpage, 'description')
series = try_get(
2017-09-15 18:12:19 +02:00
data, lambda x: x['emission']['nom']) or self._search_regex(
r'<div[^>]+class="banner-card__subtitle h4"[^>]*>([^<]+)',
webpage, 'series', default=None)
2017-09-15 18:12:19 +02:00
season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {}
season = try_get(season_el, lambda x: x['nom'], str)
2017-09-15 18:12:19 +02:00
season_number = int_or_none(try_get(season_el, lambda x: x['numero']))
2017-09-15 18:12:19 +02:00
episode_el = try_get(season_el, lambda x: x['episode'], dict) or {}
episode = try_get(episode_el, lambda x: x['nom'], str)
2017-09-15 18:12:19 +02:00
episode_number = int_or_none(try_get(episode_el, lambda x: x['numero']))
return {
'_type': 'url_transparent',
'ie_key': BrightcoveNewIE.ie_key(),
2019-02-16 16:45:53 +01:00
'url': smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
{'geo_countries': ['CA']}),
'id': brightcove_id,
2017-09-15 18:12:19 +02:00
'title': title,
'description': description,
'series': series,
2017-09-15 18:12:19 +02:00
'season': season,
'season_number': season_number,
'episode': episode,
2017-09-15 18:12:19 +02:00
'episode_number': episode_number,
}