Archives
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
2
0
Fork 0
Code Issues Projects Releases Wiki Activity

[watchertv] create DropoutBase IEs for Dropout and WatcherTV to extend

Browse Source
pull/9748/head
McSwindler 1 month ago
parent dd41cc4ade
commit 123ac3301c
2 changed files with 96 additions and 90 deletions
Show Stats Download Patch File Download Diff File

179
yt_dlp/extractor/dropout.py
Unescape Escape View File

@ -17,7 +17,84 @@ from ..utils import (
)
class DropoutIE(InfoExtractor):
class DropoutBaseIE(InfoExtractor):
_HOST = None
def _get_authenticity_token(self, display_id):
signin_page = self._download_webpage(
f'{self._HOST}/login', 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(
f'{self._HOST}/login', 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(self._HOST).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, self._HOST),
'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 DropoutIE(DropoutBaseIE):
_HOST = 'https://www.dropout.tv'
_NETRC_MACHINE = 'dropout'
@ -91,82 +168,28 @@ class DropoutIE(InfoExtractor):
}
]
def _get_authenticity_token(self, display_id):
signin_page = self._download_webpage(
f'{self._HOST}/login', 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(
f'{self._HOST}/login', display_id, note='Logging in', fatal=False,
data=urlencode_postdata({
'email': username,
'password': password,
'authenticity_token': self._get_authenticity_token(display_id),
'utf8': True
}))
class DropoutSeasonBaseIE(InfoExtractor):
_PAGE_SIZE = 24
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 _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, self._VIDEO_IE) for item_url in traverse_obj(
get_elements_html_by_class('browse-item-link', webpage), (..., {extract_attributes}, 'href'))]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = None
if self._get_cookies(self._HOST).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))
season_id = self._match_id(url)
season_num = self._match_valid_url(url).group('season') or 1
season_title = season_id.replace('-', ' ').title()
return {
'_type': 'url_transparent',
'ie_key': VHXEmbedIE.ie_key(),
'url': VHXEmbedIE._smuggle_referrer(embed_url, self._HOST),
'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)),
}
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}')
class DropoutSeasonIE(InfoExtractor):
_PAGE_SIZE = 24
class DropoutSeasonIE(DropoutSeasonBaseIE):
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_VIDEO_IE = DropoutIE
_TESTS = [
@ -207,19 +230,3 @@ class DropoutSeasonIE(InfoExtractor):
}
}
]
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, self._VIDEO_IE) 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}')

7
yt_dlp/extractor/watchertv.py
Unescape Escape View File

@ -1,7 +1,7 @@
from .dropout import DropoutIE, DropoutSeasonIE
from .dropout import DropoutBaseIE, DropoutSeasonBaseIE
class WatcherTVIE(DropoutIE):
class WatcherTVIE(DropoutBaseIE):
_HOST = 'https://www.watchertv.com'
_NETRC_MACHINE = 'watchertv'
@ -76,8 +76,7 @@ class WatcherTVIE(DropoutIE):
]
class WatcherTVSeasonIE(DropoutSeasonIE):
_PAGE_SIZE = 24
class WatcherTVSeasonIE(DropoutSeasonBaseIE):
_VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_VIDEO_IE = WatcherTVIE
_TESTS = [

Write Preview
Loading…
Cancel
Save