diff --git a/yt_dlp/extractor/facebook.py b/yt_dlp/extractor/facebook.py index d29b9aab9..f55845720 100644 --- a/yt_dlp/extractor/facebook.py +++ b/yt_dlp/extractor/facebook.py @@ -519,7 +519,10 @@ class FacebookIE(InfoExtractor): raise ExtractorError( 'The video is not available, Facebook said: "%s"' % m_msg.group(1), expected=True) - elif '>You must log in to continue' in webpage: + elif any(p in webpage for p in ( + '>You must log in to continue', + 'id="login_form"', + 'id="loginbutton"')): self.raise_login_required() if not video_data and '/watchparty/' in url: diff --git a/yt_dlp/extractor/formula1.py b/yt_dlp/extractor/formula1.py index fecfc28ae..67662e6de 100644 --- a/yt_dlp/extractor/formula1.py +++ b/yt_dlp/extractor/formula1.py @@ -5,29 +5,23 @@ from .common import InfoExtractor class Formula1IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?formula1\.com/(?:content/fom-website/)?en/video/\d{4}/\d{1,2}/(?P.+?)\.html' - _TESTS = [{ - 'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html', - 'md5': '8c79e54be72078b26b89e0e111c0502b', + _VALID_URL = r'https?://(?:www\.)?formula1\.com/en/latest/video\.[^.]+\.(?P\d+)\.html' + _TEST = { + 'url': 'https://www.formula1.com/en/latest/video.race-highlights-spain-2016.6060988138001.html', + 'md5': 'be7d3a8c2f804eb2ab2aa5d941c359f8', 'info_dict': { - 'id': 'JvYXJpMzE6pArfHWm5ARp5AiUmD-gibV', + 'id': '6060988138001', 'ext': 'mp4', 'title': 'Race highlights - Spain 2016', + 'timestamp': 1463332814, + 'upload_date': '20160515', + 'uploader_id': '6057949432001', }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'add_ie': ['Ooyala'], - }, { - 'url': 'http://www.formula1.com/en/video/2016/5/Race_highlights_-_Spain_2016.html', - 'only_matching': True, - }] + 'add_ie': ['BrightcoveNew'], + } + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/6057949432001/S1WMrhjlh_default/index.html?videoId=%s' def _real_extract(self, url): - display_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - ooyala_embed_code = self._search_regex( - r'data-videoid="([^"]+)"', webpage, 'ooyala embed code') + bc_id = self._match_id(url) return self.url_result( - 'ooyala:%s' % ooyala_embed_code, 'Ooyala', ooyala_embed_code) + self.BRIGHTCOVE_URL_TEMPLATE % bc_id, 'BrightcoveNew', bc_id) diff --git a/yt_dlp/extractor/orf.py b/yt_dlp/extractor/orf.py index 3fadbcbea..ed8a9a841 100644 --- a/yt_dlp/extractor/orf.py +++ b/yt_dlp/extractor/orf.py @@ -140,6 +140,25 @@ class ORFTVthekIE(InfoExtractor): }) upload_date = unified_strdate(sd.get('created_date')) + + thumbnails = [] + preview = sd.get('preview_image_url') + if preview: + thumbnails.append({ + 'id': 'preview', + 'url': preview, + 'preference': 0, + }) + image = sd.get('image_full_url') + if not image and len(data_jsb) == 1: + image = self._og_search_thumbnail(webpage) + if image: + thumbnails.append({ + 'id': 'full', + 'url': image, + 'preference': 1, + }) + entries.append({ '_type': 'video', 'id': video_id, @@ -149,7 +168,7 @@ class ORFTVthekIE(InfoExtractor): 'description': sd.get('description'), 'duration': int_or_none(sd.get('duration_in_seconds')), 'upload_date': upload_date, - 'thumbnail': sd.get('image_full_url'), + 'thumbnails': thumbnails, }) return { diff --git a/yt_dlp/extractor/youporn.py b/yt_dlp/extractor/youporn.py index 33114363d..7084d3d12 100644 --- a/yt_dlp/extractor/youporn.py +++ b/yt_dlp/extractor/youporn.py @@ -4,13 +4,12 @@ import re from .common import InfoExtractor from ..utils import ( + extract_attributes, int_or_none, str_to_int, - unescapeHTML, unified_strdate, url_or_none, ) -from ..aes import aes_decrypt_text class YouPornIE(InfoExtractor): @@ -34,6 +33,7 @@ class YouPornIE(InfoExtractor): 'tags': list, 'age_limit': 18, }, + 'skip': 'This video has been disabled', }, { # Unknown uploader 'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4', @@ -78,58 +78,22 @@ class YouPornIE(InfoExtractor): video_id = mobj.group('id') display_id = mobj.group('display_id') or video_id - webpage = self._download_webpage( - 'http://www.youporn.com/watch/%s' % video_id, display_id, - headers={'Cookie': 'age_verified=1'}) - - title = self._html_search_regex( - r'(?s)]+class=["\']watchVideoTitle[^>]+>(.+?)', - webpage, 'title', default=None) or self._og_search_title( - webpage, default=None) or self._html_search_meta( - 'title', webpage, fatal=True) - - links = [] - - # Main source - definitions = self._parse_json( - self._search_regex( - r'mediaDefinition\s*[=:]\s*(\[.+?\])\s*[;,]', webpage, - 'media definitions', default='[]'), - video_id, fatal=False) - if definitions: - for definition in definitions: - if not isinstance(definition, dict): - continue - video_url = url_or_none(definition.get('videoUrl')) - if video_url: - links.append(video_url) - - # Fallback #1, this also contains extra low quality 180p format - for _, link in re.findall(r']+href=(["\'])(http(?:(?!\1).)+\.mp4(?:(?!\1).)*)\1[^>]+title=["\']Download [Vv]ideo', webpage): - links.append(link) - - # Fallback #2 (unavailable as at 22.06.2017) - sources = self._search_regex( - r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None) - if sources: - for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources): - links.append(link) - - # Fallback #3 (unavailable as at 22.06.2017) - for _, link in re.findall( - r'(?:videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage): - links.append(link) - - # Fallback #4, encrypted links (unavailable as at 22.06.2017) - for _, encrypted_link in re.findall( - r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage): - links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8')) + definitions = self._download_json( + 'https://www.youporn.com/api/video/media_definitions/%s/' % video_id, + display_id) formats = [] - for video_url in set(unescapeHTML(link) for link in links): + for definition in definitions: + if not isinstance(definition, dict): + continue + video_url = url_or_none(definition.get('videoUrl')) + if not video_url: + continue f = { 'url': video_url, + 'filesize': int_or_none(definition.get('videoSize')), } + height = int_or_none(definition.get('quality')) # Video URL's path looks like this: # /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 # /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4 @@ -137,16 +101,27 @@ class YouPornIE(InfoExtractor): # We will benefit from it by extracting some metadata mobj = re.search(r'(?P\d{3,4})[pP]_(?P\d+)[kK]_\d+', video_url) if mobj: - height = int(mobj.group('height')) + if not height: + height = int(mobj.group('height')) bitrate = int(mobj.group('bitrate')) f.update({ 'format_id': '%dp-%dk' % (height, bitrate), - 'height': height, 'tbr': bitrate, }) + f['height'] = height formats.append(f) self._sort_formats(formats) + webpage = self._download_webpage( + 'http://www.youporn.com/watch/%s' % video_id, display_id, + headers={'Cookie': 'age_verified=1'}) + + title = self._html_search_regex( + r'(?s)]+class=["\']watchVideoTitle[^>]+>(.+?)', + webpage, 'title', default=None) or self._og_search_title( + webpage, default=None) or self._html_search_meta( + 'title', webpage, fatal=True) + description = self._html_search_regex( r'(?s)]+\bid=["\']description["\'][^>]*>(.+?)', webpage, 'description', @@ -169,13 +144,12 @@ class YouPornIE(InfoExtractor): age_limit = self._rta_search(webpage) - average_rating = int_or_none(self._search_regex( - r']+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%', - webpage, 'average rating', fatal=False)) - - view_count = str_to_int(self._search_regex( - r'(?s)]+class=(["\']).*?\bvideoInfoViews\b.*?\1[^>]*>.*?(?P[\d,.]+)<', - webpage, 'view count', fatal=False, group='count')) + view_count = None + views = self._search_regex( + r'(]+\bclass=["\']js_videoInfoViews["\']>)', webpage, + 'views', default=None) + if views: + view_count = str_to_int(extract_attributes(views).get('data-value')) comment_count = str_to_int(self._search_regex( r'>All [Cc]omments? \(([\d,.]+)\)', webpage, 'comment count', default=None)) @@ -201,7 +175,6 @@ class YouPornIE(InfoExtractor): 'duration': duration, 'uploader': uploader, 'upload_date': upload_date, - 'average_rating': average_rating, 'view_count': view_count, 'comment_count': comment_count, 'categories': categories,