You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
yt-dlp/yt_dlp/extractor/tbs.py

87 lines
3.4 KiB
Python

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

import re
import urllib.parse
from .turner import TurnerBaseIE
from ..utils import (
float_or_none,
int_or_none,
strip_or_none,
)
class TBSIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com(?P<path>/(?:movies|watchtnt|watchtbs|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+))'
_TESTS = [{
'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster',
'info_dict': {
'id': '8d384cde33b89f3a43ce5329de42903ed5099887',
'ext': 'mp4',
'title': 'Monster',
'description': 'Get a first look at the theatrical trailer for TNTs highly anticipated new psychological thriller The Alienist, which premieres January 22 on TNT.',
'timestamp': 1508175329,
'upload_date': '20171016',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.tbs.com/shows/search-party/season-1/episode-1/explicit-the-mysterious-disappearance-of-the-girl-no-one-knew',
'only_matching': True,
}, {
'url': 'http://www.tntdrama.com/movies/star-wars-a-new-hope',
'only_matching': True,
}]
def _real_extract(self, url):
site, path, display_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, display_id)
drupal_settings = self._parse_json(self._search_regex(
r'<script[^>]+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})</script>',
webpage, 'drupal setting'), display_id)
is_live = 'watchtnt' in path or 'watchtbs' in path
video_data = next(v for v in drupal_settings['turner_playlist'] if is_live or v.get('url') == path)
media_id = video_data['mediaID']
title = video_data['title']
tokenizer_query = urllib.parse.parse_qs(urllib.parse.urlparse(
drupal_settings['ngtv_token_url']).query)
info = self._extract_ngtv_info(
media_id, tokenizer_query, {
'url': url,
'site_name': site[:3].upper(),
'auth_required': video_data.get('authRequired') == '1' or is_live,
'is_live': is_live,
})
thumbnails = []
for image_id, image in video_data.get('images', {}).items():
image_url = image.get('url')
if not image_url or image.get('type') != 'video':
continue
i = {
'id': image_id,
'url': image_url,
}
mobj = re.search(r'(\d+)x(\d+)', image_url)
if mobj:
i.update({
'width': int(mobj.group(1)),
'height': int(mobj.group(2)),
})
thumbnails.append(i)
info.update({
'id': media_id,
'title': title,
'description': strip_or_none(video_data.get('descriptionNoTags') or video_data.get('shortDescriptionNoTags')),
'duration': float_or_none(video_data.get('duration')) or info.get('duration'),
'timestamp': int_or_none(video_data.get('created')),
'season_number': int_or_none(video_data.get('season')),
'episode_number': int_or_none(video_data.get('episode')),
'thumbnails': thumbnails,
'is_live': is_live,
})
return info