From 1a4fbe8462f5e531a891aeac7db6c0bde49c5536 Mon Sep 17 00:00:00 2001 From: FraFraFra-LongD <85188920+FraFraFra-LongD@users.noreply.github.com> Date: Sun, 13 Nov 2022 14:22:04 +0100 Subject: [PATCH] Added ThisVid.com support (#29187) * add ThisVidIE, ThisVidMemberIE, ThisVidPlaylistIE * redirect embed to main page for more metadata * use KVS extraction newly added to GenericIE and remove duplicate tests * also add MrDeepFake etc compat to GenericIE (closes #22390) Co-authored-by: dirkf --- youtube_dl/extractor/extractors.py | 5 + youtube_dl/extractor/generic.py | 54 ++++--- youtube_dl/extractor/thisvid.py | 218 +++++++++++++++++++++++++++++ 3 files changed, 249 insertions(+), 28 deletions(-) create mode 100644 youtube_dl/extractor/thisvid.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 4d9f37424..947cbe8fd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1265,6 +1265,11 @@ from .theweatherchannel import TheWeatherChannelIE from .thisamericanlife import ThisAmericanLifeIE from .thisav import ThisAVIE from .thisoldhouse import ThisOldHouseIE +from .thisvid import ( + ThisVidIE, + ThisVidMemberIE, + ThisVidPlaylistIE, +) from .threeqsdn import ThreeQSDNIE from .tiktok import ( TikTokIE, diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 01e406750..597611157 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2252,31 +2252,7 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, { - # KVS Player - 'url': 'https://thisvid.com/videos/fruit-is-healthy/', - 'md5': 'f83e52f409b9139a7efee58ef926a72e', - 'info_dict': { - 'id': '7079579', - 'display_id': 'fruit-is-healthy', - 'ext': 'mp4', - 'title': 'Fruit is healthy - ThisVid.com', - 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/7079000/7079579/preview.jpg', - } - }, { - # KVS Player - 'url': 'https://thisvid.com/embed/7079579/', - 'info_dict': { - 'id': '7079579', - 'display_id': 'fruit-is-healthy', - 'ext': 'mp4', - 'title': 'Fruit is healthy - ThisVid.com', - 'thumbnail': 'https://media.thisvid.com/contents/videos_screenshots/7079000/7079579/preview.jpg', - }, - 'params': { - 'skip_download': True, - }, - }, { - # KVS Player + # KVS Player (tested also in thisvid.py) 'url': 'https://youix.com/video/leningrad-zoj/', 'md5': '94f96ba95706dc3880812b27b7d8a2b8', 'info_dict': { @@ -2306,6 +2282,7 @@ class GenericIE(InfoExtractor): 'display_id': '40-nochey-2016', 'ext': 'mp4', 'title': '40 ночей (2016) - BogMedia.org', + 'description': 'md5:4e6d7d622636eb7948275432eb256dc3', 'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg', }, }, { @@ -2319,6 +2296,18 @@ class GenericIE(InfoExtractor): 'title': 'Syren De Mer onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер', 'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg', }, + }, { + 'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes', + 'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4', + 'info_dict': { + 'id': '5', + 'display_id': 'selena-gomez-pov-deep-fakes', + 'ext': 'mp4', + 'title': 'Selena Gomez POV (Deep Fakes) DeepFake Porn - MrDeepFakes', + 'description': 'md5:17d1f84b578c9c26875ac5ef9a932354', + 'height': 720, + 'age_limit': 18, + }, }, ] @@ -2491,6 +2480,7 @@ class GenericIE(InfoExtractor): 'url': getrealurl(flashvars[key], flashvars['license_code']), 'format_id': format_id, 'ext': 'mp4', + 'http_headers': {'Referer': url}, })) if not formats[-1].get('height'): formats[-1]['quality'] = 1 @@ -2713,9 +2703,15 @@ class GenericIE(InfoExtractor): # but actually don't. AGE_LIMIT_MARKERS = [ r'Proudly Labeled RTA', + r'>[^<]*you acknowledge you are at least (\d+) years old', ] - if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS): - age_limit = 18 + for marker in AGE_LIMIT_MARKERS: + m = re.search(marker, webpage) + if not m: + continue + age_limit = max( + age_limit or 0, + int_or_none(m.groups() and m.group(1), default=18)) # video uploader is domain name video_uploader = self._search_regex( @@ -3570,7 +3566,9 @@ class GenericIE(InfoExtractor): self.report_extraction('KVS Player') if found.group('maj_ver') not in ('4', '5', '6'): self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found.group('ver'), )) - return self._extract_kvs(url, webpage, video_id) + return merge_dicts( + self._extract_kvs(url, webpage, video_id), + info_dict) # Looking for http://schema.org/VideoObject json_ld = self._search_json_ld( diff --git a/youtube_dl/extractor/thisvid.py b/youtube_dl/extractor/thisvid.py new file mode 100644 index 000000000..bc4bcb2d1 --- /dev/null +++ b/youtube_dl/extractor/thisvid.py @@ -0,0 +1,218 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import itertools + +from .common import InfoExtractor +from ..compat import ( + compat_urlparse, +) +from ..utils import ( + clean_html, + get_element_by_class, + int_or_none, + merge_dicts, + url_or_none, + urljoin, +) + + +class ThisVidIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?thisvid\.com/(?Pvideos|embed)/(?P[A-Za-z0-9-]+)' + _TESTS = [{ + 'url': 'https://thisvid.com/videos/sitting-on-ball-tight-jeans/', + 'md5': '839becb572995687e11a69dc4358a386', + 'info_dict': { + 'id': '3533241', + 'ext': 'mp4', + 'title': 'Sitting on ball tight jeans', + 'description': 'md5:372353bb995883d1b65fddf507489acd', + 'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg', + 'uploader_id': '150629', + 'uploader': 'jeanslevisjeans', + 'age_limit': 18, + } + }, { + 'url': 'https://thisvid.com/embed/3533241/', + 'md5': '839becb572995687e11a69dc4358a386', + 'info_dict': { + 'id': '3533241', + 'ext': 'mp4', + 'title': 'Sitting on ball tight jeans', + 'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg', + 'uploader_id': '150629', + 'uploader': 'jeanslevisjeans', + 'age_limit': 18, + } + }] + + def _real_extract(self, url): + main_id, type_ = re.match(self._VALID_URL, url).group('id', 'type') + webpage = self._download_webpage(url, main_id) + + title = self._html_search_regex( + r']*?>(?:Video:\s+)?(.+?)(?:\s+-\s+ThisVid(?:\.com| tube))?', + webpage, 'title') + + if type_ == 'embed': + # look for more metadata + video_alt_url = url_or_none(self._search_regex( + r'''video_alt_url\s*:\s+'(%s/)',''' % (self._VALID_URL, ), + webpage, 'video_alt_url', default=None)) + if video_alt_url and video_alt_url != url: + webpage = self._download_webpage( + video_alt_url, main_id, + note='Redirecting embed to main page', fatal=False) or webpage + + video_holder = get_element_by_class('video-holder', webpage) or '' + if '>This video is a private video' in video_holder: + self.raise_login_required( + (clean_html(video_holder) or 'Private video').split('\n', 1)[0]) + + uploader = self._html_search_regex( + r'''(?s)]*>Added by:\s*]+\bclass\s*=\s*["']author\b[^>]+\bhref\s*=\s*["']https://thisvid\.com/members/([0-9]+/.{3,}?)\s*''', + webpage, 'uploader', default='') + uploader = re.split(r'''/["'][^>]*>\s*''', uploader) + if len(uploader) == 2: + # id must be non-empty, uploader could be '' + uploader_id, uploader = uploader + uploader = uploader or None + else: + uploader_id = uploader = None + + return merge_dicts({ + '_type': 'url_transparent', + 'title': title, + 'age_limit': 18, + 'uploader': uploader, + 'uploader_id': uploader_id, + }, self.url_result(url, ie='Generic')) + + +class ThisVidMemberIE(InfoExtractor): + _VALID_URL = r'https?://thisvid\.com/members/(?P\d+)' + _TESTS = [{ + 'url': 'https://thisvid.com/members/2140501/', + 'info_dict': { + 'id': '2140501', + 'title': 'Rafflesia\'s Profile', + }, + 'playlist_mincount': 16, + }, { + 'url': 'https://thisvid.com/members/2140501/favourite_videos/', + 'info_dict': { + 'id': '2140501', + 'title': 'Rafflesia\'s Favourite Videos', + }, + 'playlist_mincount': 15, + }, { + 'url': 'https://thisvid.com/members/636468/public_videos/', + 'info_dict': { + 'id': '636468', + 'title': 'Happymouth\'s Public Videos', + }, + 'playlist_mincount': 196, + }, + ] + + def _urls(self, html): + for m in re.finditer(r''']+\bhref\s*=\s*["'](?P%s\b)[^>]+>''' % (ThisVidIE._VALID_URL, ), html): + yield m.group('url') + + def _real_extract(self, url): + pl_id = self._match_id(url) + webpage = self._download_webpage(url, pl_id) + + title = re.split( + r'(?i)\s*\|\s*ThisVid\.com\s*$', + self._og_search_title(webpage, default=None) or self._html_search_regex(r'(?s)]*>(.+?)]+\bhref\s*=\s*("|')(?P(?!#)(?:(?!\1).)+)''', + next_page, 'next page link', group='url', default=None)) + # in case a member page should have pagination-next with empty link, not just `else:` + if next_page is None: + # playlist page + parsed_url = compat_urlparse.urlparse(page_url) + base_path, num = parsed_url.path.rsplit('/', 1) + num = int_or_none(num) + if num is None: + base_path, num = parsed_url.path.rstrip('/'), 1 + parsed_url = parsed_url._replace(path=base_path + ('/%d' % (num + 1, ))) + next_page = compat_urlparse.urlunparse(parsed_url) + if page_url == next_page: + next_page = None + if not next_page: + break + page_url, html = next_page, None + + return self.playlist_from_matches( + entries(url, webpage), playlist_id=pl_id, playlist_title=title, ie='ThisVid') + + +class ThisVidPlaylistIE(ThisVidMemberIE): + _VALID_URL = r'https?://thisvid\.com/playlist/(?P\d+)/video/(?P[A-Za-z0-9-]+)' + _TESTS = [{ + 'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/', + 'info_dict': { + 'id': '6615', + 'title': 'Underwear Stuff', + }, + 'playlist_mincount': 200, + }, { + 'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/', + 'info_dict': { + 'id': '1072387', + 'ext': 'mp4', + 'title': 'Big Italian Booty 28', + 'description': 'md5:1bccf7b13765e18fb27bf764dba7ede2', + 'uploader_id': '367912', + 'uploader': 'Jcmusclefun', + 'age_limit': 18, + }, + 'params': { + 'noplaylist': True, + }, + }] + + def _get_video_url(self, pl_url): + video_id = re.match(self._VALID_URL, pl_url).group('video_id') + return urljoin(pl_url, '/videos/%s/' % (video_id, )) + + def _urls(self, html): + for m in re.finditer(r''']+\bhref\s*=\s*["'](?P%s\b)[^>]+>''' % (self._VALID_URL, ), html): + yield self._get_video_url(m.group('url')) + + def _real_extract(self, url): + pl_id = self._match_id(url) + + if self._downloader.params.get('noplaylist'): + self.to_screen('Downloading just the featured video because of --no-playlist') + return self.url_result(self._get_video_url(url), 'ThisVid') + + self.to_screen( + 'Downloading playlist %s - add --no-playlist to download just the featured video' % (pl_id, )) + result = super(ThisVidPlaylistIE, self)._real_extract(url) + + # rework title returned as `the title - the title` + title = result['title'] + t_len = len(title) + if t_len > 5 and t_len % 2 != 0: + t_len = t_len // 2 + if title[t_len] == '-': + title = [t.strip() for t in (title[:t_len], title[t_len + 1:])] + if title[0] and title[0] == title[1]: + result['title'] = title[0] + return result