Mirroring
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp
1
0
Fork 0
Code Issues Releases Wiki Activity

[watchertv] update extractor to extend dropout instead of duplicating

Browse Source
pull/9748/head
McSwindler 1 year ago
parent c1e92ef0fe
commit f1dc2a32f0
2 changed files with 24 additions and 127 deletions
Show Stats Download Patch File Download Diff File

37
yt_dlp/extractor/dropout.py
Unescape Escape View File

@ -18,7 +18,7 @@ from ..utils import (
class DropoutIE(InfoExtractor):
_LOGIN_URL = 'https://www.dropout.tv/login'
_HOST = 'https://www.dropout.tv'
_NETRC_MACHINE = 'dropout'
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
@ -26,7 +26,7 @@ class DropoutIE(InfoExtractor):
{
'url': 'https://www.dropout.tv/game-changer/season:2/videos/yes-or-no',
'note': 'Episode in a series',
'md5': '5e000fdfd8d8fa46ff40456f1c2af04a',
'md5': 'fc55805bac60b1ce2ffdc35fb9c51195',
'info_dict': {
'id': '738153',
'display_id': 'yes-or-no',
@ -48,22 +48,22 @@ class DropoutIE(InfoExtractor):
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
},
{
'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1/videos/episode-1',
'url': 'https://www.dropout.tv/ch-shorts/season:1/videos/post-apocalyptic-dane-cook',
'note': 'Episode in a series (missing release_date)',
'md5': '712caf7c191f1c47c8f1879520c2fa5c',
'md5': 'f260b8d7d0fdbaceae713c9196dac07f',
'info_dict': {
'id': '320562',
'display_id': 'episode-1',
'id': '449042',
'display_id': 'post-apocalyptic-dane-cook',
'ext': 'mp4',
'title': 'The Beginning Begins',
'description': 'The cast introduces their PCs, including a neurotic elf, a goblin PI, and a corn-worshipping cleric.',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/4421ed0d-f630-4c88-9004-5251b2b8adfa.jpg',
'series': 'Dimension 20: Fantasy High',
'title': 'Post-Apocalyptic Dane Cook',
'description': 'Dane Cook is back with his all new special. Don\'t worry, it\'s not the end of the world.',
'thumbnail': 'https://vhx.imgix.net/chuncensoredstaging/assets/5b0678df-d9c3-4864-b811-24db03072f4a.jpg',
'series': 'CH Shorts',
'season_number': 1,
'season': 'Season 1',
'episode_number': 1,
'episode': 'The Beginning Begins',
'duration': 6838,
'episode': 'Post-Apocalyptic Dane Cook',
'duration': 135,
'uploader_id': 'user80538407',
'uploader_url': 'https://vimeo.com/user80538407',
'uploader': 'OTT Videos',
@ -73,7 +73,7 @@ class DropoutIE(InfoExtractor):
{
'url': 'https://www.dropout.tv/videos/misfits-magic-holiday-special',
'note': 'Episode not in a series',
'md5': 'c30fa18999c5880d156339f13c953a26',
'md5': '147e0607bd877a791665c0b7219b512c',
'info_dict': {
'id': '1915774',
'display_id': 'misfits-magic-holiday-special',
@ -93,7 +93,7 @@ class DropoutIE(InfoExtractor):
def _get_authenticity_token(self, display_id):
signin_page = self._download_webpage(
self._LOGIN_URL, display_id, note='Getting authenticity token')
f'{self._HOST}/login', display_id, note='Getting authenticity token')
return self._html_search_regex(
r'name=["\']authenticity_token["\'] value=["\'](.+?)["\']',
signin_page, 'authenticity_token')
@ -104,7 +104,7 @@ class DropoutIE(InfoExtractor):
return True
response = self._download_webpage(
self._LOGIN_URL, display_id, note='Logging in', fatal=False,
f'{self._HOST}/login', display_id, note='Logging in', fatal=False,
data=urlencode_postdata({
'email': username,
'password': password,
@ -125,7 +125,7 @@ class DropoutIE(InfoExtractor):
display_id = self._match_id(url)
webpage = None
if self._get_cookies('https://www.dropout.tv').get('_session'):
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)
@ -148,7 +148,7 @@ class DropoutIE(InfoExtractor):
return {
'_type': 'url_transparent',
'ie_key': VHXEmbedIE.ie_key(),
'url': VHXEmbedIE._smuggle_referrer(embed_url, 'https://www.dropout.tv'),
'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,
@ -168,6 +168,7 @@ class DropoutIE(InfoExtractor):
class DropoutSeasonIE(InfoExtractor):
_PAGE_SIZE = 24
_VALID_URL = r'https?://(?:www\.)?dropout\.tv/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_VIDEO_IE = DropoutIE
_TESTS = [
{
'url': 'https://www.dropout.tv/dimension-20-fantasy-high/season:1',
@ -211,7 +212,7 @@ class DropoutSeasonIE(InfoExtractor):
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, DropoutIE) for item_url in traverse_obj(
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):

114
yt_dlp/extractor/watchertv.py
Unescape Escape View File

@ -1,24 +1,8 @@
import functools
from .dropout import DropoutIE, DropoutSeasonIE
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'
class WatcherTVIE(DropoutIE):
_HOST = 'https://www.watchertv.com'
_NETRC_MACHINE = 'watchertv'
_VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?:[^/]+/)*videos/(?P<id>[^/]+)/?$'
@ -91,83 +75,11 @@ class WatcherTVIE(InfoExtractor):
}
]
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):
class WatcherTVSeasonIE(DropoutSeasonIE):
_PAGE_SIZE = 24
_VALID_URL = r'https?://(?:www\.)?watchertv\.com/(?P<id>[^\/$&?#]+)(?:/?$|/season:(?P<season>[0-9]+)/?$)'
_VIDEO_IE = WatcherTVIE
_TESTS = [
{
'url': 'https://www.watchertv.com/ghost-files/season:1',
@ -197,19 +109,3 @@ class WatcherTVSeasonIE(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, 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}')

Write Preview
Loading…
Cancel
Save