yt-dlp/yt_dlp/extractor/watchertv.py

216 lines
9.1 KiB
Python
Raw Normal View History

2024-04-20 17:07:02 +00:00
import functools
from .common import InfoExtractor
from .vimeo import VHXEmbedIE
from ..utils import (
ExtractorError,
OnDemandPagedList,
clean_html,
extract_attributes,
get_element_by_class,
get_element_by_id,
get_elements_html_by_class,
int_or_none,
traverse_obj,
unified_strdate,
urlencode_postdata,
)
class WatcherTVIE(InfoExtractor):
_LOGIN_URL = 'https://www.watchertv.com/login'
_NETRC_MACHINE = 'watchertv'
_VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
_TESTS = [
{
'url': 'https://www.watchertv.com/ghost-files/season:2/videos/gf-201',
'note': 'Episode in a series',
'md5': '99c9aab2cb62157467b7ef5e37266e4e',
'info_dict': {
'id': '3129338',
'display_id': 'gf-201',
'ext': 'mp4',
'title': 'The Death Row Poltergeists of Missouri State Penitentiary',
'description': 'Where Curiosity Meets Comedy',
'release_date': '20230825',
'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/92c02f39-2ed6-4b51-9e63-1a907b82e2bc.png',
'series': 'Ghost Files',
'season_number': 2,
'season': 'Season 2',
'episode_number': 1,
'episode': 'The Death Row Poltergeists of Missouri State Penitentiary',
'duration': 3853,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos'
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
},
{
'url': 'https://www.watchertv.com/road-files/season:1/videos/rf101',
'note': 'Episode in a series (missing release_date)',
'md5': '02f9aaafc8ad9bd1be366cf6a61a68d8',
'info_dict': {
'id': '3187312',
'display_id': 'rf101',
'ext': 'mp4',
'title': 'Road Files: Haunted Hill House',
'description': 'Where Curiosity Meets Comedy',
'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/7445f23c-a3e7-47fb-835a-d288273e2698.png',
'series': 'Road Files',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'Road Files: Haunted Hill House',
'duration': 516,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos'
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
},
{
'url': 'https://www.watchertv.com/videos/welcome-beta-users',
'note': 'Episode not in a series',
'md5': 'fd1db805f9adc442c38d706bba21ad03',
'info_dict': {
'id': '3187107',
'display_id': 'welcome-beta-users',
'ext': 'mp4',
'title': 'Welcome to Watcher!',
'description': 'Where Curiosity Meets Comedy',
'release_date': '20240419',
'thumbnail': 'https://vhx.imgix.net/watcherentertainment/assets/fbb90dc8-ebb0-4597-9a83-95729e234030.jpg',
'duration': 92,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos'
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest']
}
]
def _get_authenticity_token(self, display_id):
signin_page = self._download_webpage(
self._LOGIN_URL, display_id, note='Getting authenticity token')
return self._html_search_regex(
r'name=["\']authenticity_token["\'] value=["\'](.+?)["\']',
signin_page, 'authenticity_token')
def _login(self, display_id):
username, password = self._get_login_info()
if not username:
return True
response = self._download_webpage(
self._LOGIN_URL, display_id, note='Logging in', fatal=False,
data=urlencode_postdata({
'email': username,
'password': password,
'authenticity_token': self._get_authenticity_token(display_id),
'utf8': True
}))
user_has_subscription = self._search_regex(
r'user_has_subscription:\s*["\'](.+?)["\']', response, 'subscription status', default='none')
if user_has_subscription.lower() == 'true':
return
elif user_has_subscription.lower() == 'false':
return 'Account is not subscribed'
else:
return 'Incorrect username/password'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = None
if self._get_cookies('https://www.watchertv.com').get('_session'):
webpage = self._download_webpage(url, display_id)
if not webpage or '<div id="watch-unauthorized"' in webpage:
login_err = self._login(display_id)
webpage = self._download_webpage(url, display_id)
if login_err and '<div id="watch-unauthorized"' in webpage:
if login_err is True:
self.raise_login_required(method='any')
raise ExtractorError(login_err, expected=True)
embed_url = self._search_regex(r'embed_url:\s*["\'](.+?)["\']', webpage, 'embed url')
thumbnail = self._og_search_thumbnail(webpage)
watch_info = get_element_by_id('watch-info', webpage) or ''
title = clean_html(get_element_by_class('video-title', watch_info))
season_episode = get_element_by_class(
'site-font-secondary-color', get_element_by_class('text', watch_info))
episode_number = int_or_none(self._search_regex(
r'Episode (\d+)', season_episode or '', 'episode', default=None))
return {
'_type': 'url_transparent',
'ie_key': VHXEmbedIE.ie_key(),
'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.watchertv.com'),
'id': self._search_regex(r'embed\.vhx\.tv/videos/(.+?)\?', embed_url, 'id'),
'display_id': display_id,
'title': title,
'description': self._html_search_meta('description', webpage, fatal=False),
'thumbnail': thumbnail.split('?')[0] if thumbnail else None, # Ignore crop/downscale
'series': clean_html(get_element_by_class('series-title', watch_info)),
'episode_number': episode_number,
'episode': title if episode_number else None,
'season_number': int_or_none(self._search_regex(
r'Season (\d+),', season_episode or '', 'season', default=None)),
'release_date': unified_strdate(self._search_regex(
r'data-meta-field-name=["\']release_dates["\'] data-meta-field-value=["\'](.+?)["\']',
watch_info, 'release date', default=None)),
}
class WatcherTVSeasonIE(InfoExtractor):
_PAGE_SIZE = 24
_VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_TESTS = [
{
'url': 'https://www.watchertv.com/ghost-files/season:1',
'note': 'Multi-season series with the season in the url',
'playlist_count': 8,
'info_dict': {
'id': 'ghost-files-season-1',
'title': 'Ghost Files - Season 1'
}
},
{
'url': 'https://www.watchertv.com/are-you-scared',
'note': 'Multi-season series with the season not in the url',
'playlist_count': 3,
'info_dict': {
'id': 'are-you-scared-season-1',
'title': 'Are You Scared - Season 1'
}
},
{
'url': 'https://www.watchertv.com/watcher-one-offs',
'note': 'Single-season series',
'playlist_count': 16,
'info_dict': {
'id': 'watcher-one-offs-season-1',
'title': 'Watcher One Offs - Season 1'
}
}
]
def _fetch_page(self, url, season_id, page):
page += 1
webpage = self._download_webpage(
f'{url}?page={page}', season_id, note=f'Downloading page {page}', expected_status={400})
yield from [self.url_result(item_url, WatcherTVIE) for item_url in traverse_obj(
get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
def _real_extract(self, url):
season_id = self._match_id(url)
season_num = self._match_valid_url(url).group('season') or 1
season_title = season_id.replace('-', ' ').title()
return self.playlist_result(
OnDemandPagedList(functools.partial(self._fetch_page, url, season_id), self._PAGE_SIZE),
f'{season_id}-season-{season_num}', f'{season_title} - Season {season_num}')