itdominator/SolarFM
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Plugin cleanup and tweaks

Browse Source
This commit is contained in:
itdominator
2023-02-20 19:18:45 -06:00
parent 372e4ff3dc
commit 3ad9e1c7bb
1138 changed files with 48878 additions and 40445 deletions
Download Patch File Download Diff File Expand all files Collapse all files

329
plugins/youtube_download/yt_dlp/extractor/vk.py
View File

@@ -1,39 +1,51 @@
# coding: utf-8
from __future__ import unicode_literals
import collections
import hashlib
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
clean_html,
ExtractorError,
get_element_by_class,
int_or_none,
orderedSet,
str_or_none,
str_to_int,
unescapeHTML,
unified_timestamp,
url_or_none,
urlencode_postdata,
)
from .dailymotion import DailymotionIE
from .odnoklassniki import OdnoklassnikiIE
from .pladform import PladformIE
from .sibnet import SibnetEmbedIE
from .vimeo import VimeoIE
from .youtube import YoutubeIE
from ..utils import (
ExtractorError,
clean_html,
get_element_by_class,
get_element_html_by_id,
int_or_none,
join_nonempty,
str_or_none,
str_to_int,
try_call,
unescapeHTML,
unified_timestamp,
update_url_query,
url_or_none,
urlencode_postdata,
urljoin,
)
class VKBaseIE(InfoExtractor):
_NETRC_MACHINE = 'vk'
def _login(self):
username, password = self._get_login_info()
if username is None:
return
def _download_webpage_handle(self, url_or_request, video_id, *args, fatal=True, **kwargs):
response = super()._download_webpage_handle(url_or_request, video_id, *args, fatal=fatal, **kwargs)
challenge_url, cookie = response[1].geturl() if response else '', None
if challenge_url.startswith('https://vk.com/429.html?'):
cookie = self._get_cookies(challenge_url).get('hash429')
if not cookie:
return response
hash429 = hashlib.md5(cookie.value.encode('ascii')).hexdigest()
self._request_webpage(
update_url_query(challenge_url, {'key': hash429}), video_id, fatal=fatal,
note='Resolving WAF challenge', errnote='Failed to bypass WAF challenge')
return super()._download_webpage_handle(url_or_request, video_id, *args, fatal=True, **kwargs)
def _perform_login(self, username, password):
login_page, url_handle = self._download_webpage_handle(
'https://vk.com', None, 'Downloading login page')
@@ -57,15 +69,15 @@ class VKBaseIE(InfoExtractor):
raise ExtractorError(
'Unable to login, incorrect username and/or password', expected=True)
def _real_initialize(self):
self._login()
def _download_payload(self, path, video_id, data, fatal=True):
endpoint = f'https://vk.com/{path}.php'
data['al'] = 1
code, payload = self._download_json(
'https://vk.com/%s.php' % path, video_id,
data=urlencode_postdata(data), fatal=fatal,
headers={'X-Requested-With': 'XMLHttpRequest'})['payload']
endpoint, video_id, data=urlencode_postdata(data), fatal=fatal,
headers={
'Referer': endpoint,
'X-Requested-With': 'XMLHttpRequest',
})['payload']
if code == '3':
self.raise_login_required()
elif code == '8':
@@ -76,6 +88,7 @@ class VKBaseIE(InfoExtractor):
class VKIE(VKBaseIE):
IE_NAME = 'vk'
IE_DESC = 'VK'
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://vk\.com/video_ext\.php.+?)\1']
_VALID_URL = r'''(?x)
https?://
(?:
@@ -91,20 +104,24 @@ class VKIE(VKBaseIE):
(?P<videoid>-?\d+_\d+)(?:.*\blist=(?P<list_id>([\da-f]+)|(ln-[\da-zA-Z]+)))?
)
'''
_TESTS = [
{
'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
'md5': '7babad3b85ea2e91948005b1b8b0cb84',
'info_dict': {
'id': '-77521_162222515',
'ext': 'mp4',
'title': 'ProtivoGunz - Хуёвая песня',
'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
'uploader_id': '-77521',
'uploader_id': '39545378',
'duration': 195,
'timestamp': 1329049880,
'upload_date': '20120212',
'comment_count': int,
'like_count': int,
'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$',
},
'params': {'skip_download': 'm3u8'},
},
{
'url': 'http://vk.com/video205387401_165548505',
@@ -117,12 +134,14 @@ class VKIE(VKBaseIE):
'duration': 9,
'timestamp': 1374364108,
'upload_date': '20130720',
'comment_count': int,
'like_count': int,
'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$',
}
},
{
'note': 'Embedded video',
'url': 'https://vk.com/video_ext.php?oid=-77521&id=162222515&hash=87b046504ccd8bfa',
'md5': '7babad3b85ea2e91948005b1b8b0cb84',
'info_dict': {
'id': '-77521_162222515',
'ext': 'mp4',
@@ -131,53 +150,10 @@ class VKIE(VKBaseIE):
'duration': 195,
'upload_date': '20120212',
'timestamp': 1329049880,
'uploader_id': '-77521',
'uploader_id': '39545378',
'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$',
},
},
{
# VIDEO NOW REMOVED
# please update if you find a video whose URL follows the same pattern
'url': 'http://vk.com/video-8871596_164049491',
'md5': 'a590bcaf3d543576c9bd162812387666',
'note': 'Only available for registered users',
'info_dict': {
'id': '-8871596_164049491',
'ext': 'mp4',
'uploader': 'Триллеры',
'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
'duration': 8352,
'upload_date': '20121218',
'view_count': int,
},
'skip': 'Removed',
},
{
'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
'info_dict': {
'id': '-43215063_168067957',
'ext': 'mp4',
'uploader': 'Bro Mazter',
'title': ' ',
'duration': 7291,
'upload_date': '20140328',
'uploader_id': '223413403',
'timestamp': 1396018030,
},
'skip': 'Requires vk account credentials',
},
{
'url': 'http://m.vk.com/video-43215063_169084319?list=125c627d1aa1cebb83&from=wall-43215063_2566540',
'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
'note': 'ivi.ru embed',
'info_dict': {
'id': '-43215063_169084319',
'ext': 'mp4',
'title': 'Книга Илая',
'duration': 6771,
'upload_date': '20140626',
'view_count': int,
},
'skip': 'Removed',
'params': {'skip_download': 'm3u8'},
},
{
'url': 'https://vk.com/video-93049196_456239755?list=ln-cBjJ7S4jYYx3ADnmDT',
@@ -186,27 +162,17 @@ class VKIE(VKBaseIE):
'ext': 'mp4',
'title': '8 серия (озвучка)',
'duration': 8383,
'comment_count': int,
'uploader': 'Dizi2021',
'like_count': int,
'timestamp': 1640162189,
'upload_date': '20211222',
'view_count': int,
'uploader_id': '-93049196',
'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$',
},
},
{
# video (removed?) only available with list id
'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
'md5': '091287af5402239a1051c37ec7b92913',
'info_dict': {
'id': '30481095_171201961',
'ext': 'mp4',
'title': 'ТюменцевВВ_09.07.2015',
'uploader': 'Anton Ivanov',
'duration': 109,
'upload_date': '20150709',
'view_count': int,
},
'skip': 'Removed',
},
{
# youtube embed
'note': 'youtube embed',
'url': 'https://vk.com/video276849682_170681728',
'info_dict': {
'id': 'V3K4mi0SYkc',
@@ -214,27 +180,60 @@ class VKIE(VKBaseIE):
'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',
'duration': 178,
'upload_date': '20130116',
'upload_date': '20130117',
'uploader': "Children's Joy Foundation Inc.",
'uploader_id': 'thecjf',
'view_count': int,
'channel_id': 'UCgzCNQ11TmR9V97ECnhi3gw',
'availability': 'public',
'like_count': int,
'live_status': 'not_live',
'playable_in_embed': True,
'channel': 'Children\'s Joy Foundation Inc.',
'uploader_url': 'http://www.youtube.com/user/thecjf',
'thumbnail': r're:https?://.+\.jpg$',
'tags': 'count:27',
'start_time': 0.0,
'categories': ['Nonprofits & Activism'],
'channel_url': 'https://www.youtube.com/channel/UCgzCNQ11TmR9V97ECnhi3gw',
'channel_follower_count': int,
'age_limit': 0,
},
},
{
# dailymotion embed
'url': 'https://vk.com/video-37468416_456239855',
'note': 'dailymotion embed',
'url': 'https://vk.com/video-95168827_456239103?list=cca524a0f0d5557e16',
'info_dict': {
'id': 'k3lz2cmXyRuJQSjGHUv',
'id': 'x8gfli0',
'ext': 'mp4',
'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
'description': 'md5:424b8e88cc873217f520e582ba28bb36',
'uploader': 'AniLibria.Tv',
'upload_date': '20160914',
'uploader_id': 'x1p5vl5',
'timestamp': 1473877246,
'title': 'md5:45410f60ccd4b2760da98cb5fc777d70',
'description': 'md5:2e71c5c9413735cfa06cf1a166f16c84',
'uploader': 'Movies and cinema.',
'upload_date': '20221218',
'uploader_id': 'x1jdavv',
'timestamp': 1671387617,
'age_limit': 0,
'duration': 2918,
'like_count': int,
'view_count': int,
'thumbnail': r're:https?://.+x1080$',
'tags': list
},
'params': {
'skip_download': True,
},
{
'url': 'https://vk.com/clips-74006511?z=clip-74006511_456247211',
'info_dict': {
'id': '-74006511_456247211',
'ext': 'mp4',
'comment_count': int,
'duration': 9,
'like_count': int,
'thumbnail': r're:https?://.+(?:\.jpg|getVideoPreview.*)$',
'timestamp': 1664995597,
'title': 'Clip by @madempress',
'upload_date': '20221005',
'uploader': 'Шальная императрица',
'uploader_id': '-74006511',
},
},
{
@@ -250,12 +249,10 @@ class VKIE(VKBaseIE):
'timestamp': 1454859345,
'upload_date': '20160207',
},
'params': {
'skip_download': True,
},
'skip': 'Removed',
},
{
# finished live stream, postlive_mp4
'note': 'finished live stream, postlive_mp4',
'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
'info_dict': {
'id': '-387766_456242764',
@@ -263,11 +260,12 @@ class VKIE(VKBaseIE):
'title': 'ИгроМир 2016 День 1 — Игромания Утром',
'uploader': 'Игромания',
'duration': 5239,
# TODO: use act=show to extract view_count
# 'view_count': int,
'upload_date': '20160929',
'uploader_id': '-387766',
'timestamp': 1475137527,
'thumbnail': r're:https?://.+\.jpg$',
'comment_count': int,
'like_count': int,
},
'params': {
'skip_download': True,
@@ -313,13 +311,6 @@ class VKIE(VKBaseIE):
'only_matching': True,
}]
@staticmethod
def _extract_sibnet_urls(webpage):
# https://help.sibnet.ru/?sibnet_video_embed
return [unescapeHTML(mobj.group('url')) for mobj in re.finditer(
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.sibnet\.ru/shell\.php\?.*?\bvideoid=\d+.*?)\1',
webpage)]
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('videoid')
@@ -327,7 +318,7 @@ class VKIE(VKBaseIE):
mv_data = {}
if video_id:
data = {
'act': 'show_inline',
'act': 'show',
'video': video_id,
}
# Some videos (removed?) can only be downloaded with list id specified
@@ -420,17 +411,17 @@ class VKIE(VKBaseIE):
m_rutube.group(1).replace('\\', ''))
return self.url_result(rutube_url)
dailymotion_urls = DailymotionIE._extract_urls(info_page)
if dailymotion_urls:
return self.url_result(dailymotion_urls[0], DailymotionIE.ie_key())
dailymotion_url = next(DailymotionIE._extract_embed_urls(url, info_page), None)
if dailymotion_url:
return self.url_result(dailymotion_url, DailymotionIE.ie_key())
odnoklassniki_url = OdnoklassnikiIE._extract_url(info_page)
if odnoklassniki_url:
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
sibnet_urls = self._extract_sibnet_urls(info_page)
if sibnet_urls:
return self.url_result(sibnet_urls[0])
sibnet_url = next(SibnetEmbedIE._extract_embed_urls(url, info_page), None)
if sibnet_url:
return self.url_result(sibnet_url)
m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page)
if m_opts:
@@ -480,7 +471,6 @@ class VKIE(VKBaseIE):
'url': format_url,
'ext': 'flv',
})
self._sort_formats(formats)
subtitles = {}
for sub in data.get('subs') or {}:
@@ -509,7 +499,7 @@ class VKIE(VKBaseIE):
class VKUserVideosIE(VKBaseIE):
IE_NAME = 'vk:uservideos'
IE_DESC = "VK - User's Videos"
_VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/@(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
_VALID_URL = r'https?://(?:(?:m|new)\.)?vk\.com/video/(?:playlist/)?(?P<id>[^?$#/&]+)(?!\?.*\bz=video)(?:[/?#&](?:.*?\bsection=(?P<section>\w+))?|$)'
_TEMPLATE_URL = 'https://vk.com/videos'
_TESTS = [{
'url': 'https://vk.com/video/@mobidevices',
@@ -523,6 +513,13 @@ class VKUserVideosIE(VKBaseIE):
'id': '-17892518_uploaded',
},
'playlist_mincount': 182,
}, {
'url': 'https://vk.com/video/playlist/-174476437_2',
'info_dict': {
'id': '-174476437_playlist_2',
'title': 'Анонсы'
},
'playlist_mincount': 108,
}]
_VIDEO = collections.namedtuple('Video', ['owner_id', 'id'])
@@ -557,11 +554,20 @@ class VKUserVideosIE(VKBaseIE):
def _real_extract(self, url):
u_id, section = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, u_id)
page_id = self._search_regex(r'data-owner-id\s?=\s?"([^"]+)"', webpage, 'page_id')
if u_id.startswith('@'):
page_id = self._search_regex(r'data-owner-id\s?=\s?"([^"]+)"', webpage, 'page_id')
elif '_' in u_id:
page_id, section = u_id.split('_', 1)
section = f'playlist_{section}'
else:
raise ExtractorError('Invalid URL', expected=True)
if not section:
section = 'all'
return self.playlist_result(self._entries(page_id, section), '%s_%s' % (page_id, section))
playlist_title = clean_html(get_element_by_class('VideoInfoPanel__title', webpage))
return self.playlist_result(self._entries(page_id, section), '%s_%s' % (page_id, section), playlist_title)
class VKWallPostIE(VKBaseIE):
@@ -573,13 +579,13 @@ class VKWallPostIE(VKBaseIE):
'info_dict': {
'id': '-23538238_35',
'title': 'Black Shadow - Wall post -23538238_35',
'description': 'md5:3f84b9c4f9ef499731cf1ced9998cc0c',
'description': 'md5:190c78f905a53e0de793d83933c6e67f',
},
'playlist': [{
'md5': '5ba93864ec5b85f7ce19a9af4af080f6',
'info_dict': {
'id': '135220665_111806521',
'ext': 'mp4',
'ext': 'm4a',
'title': 'Black Shadow - Слепое Верование',
'duration': 370,
'uploader': 'Black Shadow',
@@ -590,7 +596,7 @@ class VKWallPostIE(VKBaseIE):
'md5': '4cc7e804579122b17ea95af7834c9233',
'info_dict': {
'id': '135220665_111802303',
'ext': 'mp4',
'ext': 'm4a',
'title': 'Black Shadow - Война - Негасимое Бездны Пламя!',
'duration': 423,
'uploader': 'Black Shadow',
@@ -600,21 +606,16 @@ class VKWallPostIE(VKBaseIE):
}],
'params': {
'skip_download': True,
'usenetrc': True,
},
'skip': 'Requires vk account credentials',
}, {
# single YouTube embed, no leading -
'url': 'https://vk.com/wall85155021_6319',
# single YouTube embed with irrelevant reaction videos
'url': 'https://vk.com/wall-32370614_7173954',
'info_dict': {
'id': '85155021_6319',
'title': 'Сергей Горбунов - Wall post 85155021_6319',
'id': '-32370614_7173954',
'title': 'md5:9f93c405bbc00061d34007d78c75e3bc',
'description': 'md5:953b811f26fa9f21ee5856e2ea8e68fc',
},
'playlist_count': 1,
'params': {
'usenetrc': True,
},
'skip': 'Requires vk account credentials',
}, {
# wall page URL
'url': 'https://vk.com/wall-23538238_35',
@@ -666,39 +667,37 @@ class VKWallPostIE(VKBaseIE):
'w': 'wall' + post_id,
})[1]
description = clean_html(get_element_by_class('wall_post_text', webpage))
uploader = clean_html(get_element_by_class('author', webpage))
uploader = clean_html(get_element_by_class('PostHeaderTitle__authorName', webpage))
entries = []
for audio in re.findall(r'data-audio="([^"]+)', webpage):
audio = self._parse_json(unescapeHTML(audio), post_id)
a = self._AUDIO._make(audio[:16])
if not a.url:
if not audio['url']:
continue
title = unescapeHTML(a.title)
performer = unescapeHTML(a.performer)
title = unescapeHTML(audio.get('title'))
artist = unescapeHTML(audio.get('artist'))
entries.append({
'id': '%s_%s' % (a.owner_id, a.id),
'url': self._unmask_url(a.url, a.ads['vk_id']),
'title': '%s - %s' % (performer, title) if performer else title,
'thumbnails': [{'url': c_url} for c_url in a.cover_url.split(',')] if a.cover_url else None,
'duration': int_or_none(a.duration),
'id': f'{audio["owner_id"]}_{audio["id"]}',
'title': join_nonempty(artist, title, delim=' - '),
'thumbnails': try_call(lambda: [{'url': u} for u in audio['coverUrl'].split(',')]),
'duration': int_or_none(audio.get('duration')),
'uploader': uploader,
'artist': performer,
'artist': artist,
'track': title,
'ext': 'mp4',
'protocol': 'm3u8',
'formats': [{
'url': audio['url'],
'ext': 'm4a',
'vcodec': 'none',
'acodec': 'mp3',
'container': 'm4a_dash',
}],
})
for video in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>/video(?:-?[\d_]+).*?)\1', webpage):
entries.append(self.url_result(
compat_urlparse.urljoin(url, video.group('url')), VKIE.ie_key()))
title = 'Wall post %s' % post_id
entries.extend(self.url_result(urljoin(url, entry), VKIE) for entry in set(re.findall(
r'<a[^>]+href=(?:["\'])(/video(?:-?[\d_]+)[^"\']*)',
get_element_html_by_id('wl_post_body', webpage))))
return self.playlist_result(
orderedSet(entries), post_id,
'%s - %s' % (uploader, title) if uploader else title,
description)
entries, post_id, join_nonempty(uploader, f'Wall post {post_id}', delim=' - '),
clean_html(get_element_by_class('wall_post_text', webpage)))