diff options
Diffstat (limited to 'youtube_dl')
54 files changed, 1610 insertions, 1111 deletions
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 68721e9ab..ace80f14b 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -975,6 +975,8 @@ class YoutubeDL(object): 'playlist': playlist, 'playlist_id': ie_result.get('id'), 'playlist_title': ie_result.get('title'), + 'playlist_uploader': ie_result.get('uploader'), + 'playlist_uploader_id': ie_result.get('uploader_id'), 'playlist_index': i + playliststart, 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index 7bb61a541..ea5e3a4b5 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -112,7 +112,7 @@ class FragmentFD(FileDownloader): if self.__do_ytdl_file(ctx): self._write_ytdl_file(ctx) if not self.params.get('keep_fragments', False): - os.remove(ctx['fragment_filename_sanitized']) + os.remove(encodeFilename(ctx['fragment_filename_sanitized'])) del ctx['fragment_filename_sanitized'] def _prepare_frag_download(self, ctx): diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 8a6638cc2..3ff26ff70 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -284,8 +284,7 @@ class HttpFD(FileDownloader): while count <= retries: try: establish_connection() - download() - return True + return download() except RetryDownload as e: count += 1 if count <= retries: diff --git a/youtube_dl/extractor/afreecatv.py b/youtube_dl/extractor/afreecatv.py index e6513c7a4..513dd81df 100644 --- a/youtube_dl/extractor/afreecatv.py +++ b/youtube_dl/extractor/afreecatv.py @@ -228,10 +228,19 @@ class AfreecaTVIE(InfoExtractor): r'^(\d{8})_', key, 'upload date', default=None) file_duration = int_or_none(file_element.get('duration')) format_id = key if key else '%s_%s' % (video_id, file_num) - formats = self._extract_m3u8_formats( - file_url, video_id, 'mp4', entry_protocol='m3u8_native', - m3u8_id='hls', - note='Downloading part %d m3u8 information' % file_num) + if determine_ext(file_url) == 'm3u8': + formats = self._extract_m3u8_formats( + file_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', + note='Downloading part %d m3u8 information' % file_num) + else: + formats = [{ + 'url': file_url, + 'format_id': 'http', + }] + if not formats: + continue + self._sort_formats(formats) file_info = common_entry.copy() file_info.update({ 'id': format_id, diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py index 34c2b363e..e4fa72f46 100644 --- a/youtube_dl/extractor/animeondemand.py +++ b/youtube_dl/extractor/animeondemand.py @@ -85,8 +85,8 @@ class AnimeOnDemandIE(InfoExtractor): if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')): error = self._search_regex( - r'<p class="alert alert-danger">(.+?)</p>', - response, 'error', default=None) + r'<p[^>]+\bclass=(["\'])(?:(?!\1).)*\balert\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</p>', + response, 'error', default=None, group='error') if error: raise ExtractorError('Unable to login: %s' % error, expected=True) raise ExtractorError('Unable to log in') diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 915f8862e..ef73d5a93 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from .generic import GenericIE +from ..compat import compat_str from ..utils import ( determine_ext, ExtractorError, @@ -126,6 +127,8 @@ class ARDMediathekIE(InfoExtractor): quality = stream.get('_quality') server = stream.get('_server') for stream_url in stream_urls: + if not isinstance(stream_url, compat_str) or '//' not in stream_url: + continue ext = determine_ext(stream_url) if quality != 'auto' and ext in ('f4m', 'm3u8'): continue @@ -146,13 +149,11 @@ class ARDMediathekIE(InfoExtractor): 'play_path': stream_url, 'format_id': 'a%s-rtmp-%s' % (num, quality), } - elif stream_url.startswith('http'): + else: f = { 'url': stream_url, 'format_id': 'a%s-%s-%s' % (num, ext, quality) } - else: - continue m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url) if m: f.update({ diff --git a/youtube_dl/extractor/aws.py b/youtube_dl/extractor/aws.py new file mode 100644 index 000000000..670abce0c --- /dev/null +++ b/youtube_dl/extractor/aws.py @@ -0,0 +1,78 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import datetime +import hashlib +import hmac + +from .common import InfoExtractor +from ..compat import compat_urllib_parse_urlencode + + +class AWSIE(InfoExtractor): + _AWS_ALGORITHM = 'AWS4-HMAC-SHA256' + _AWS_REGION = 'us-east-1' + + def _aws_execute_api(self, aws_dict, video_id, query=None): + query = query or {} + amz_date = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ') + date = amz_date[:8] + headers = { + 'Accept': 'application/json', + 'Host': self._AWS_PROXY_HOST, + 'X-Amz-Date': amz_date, + } + session_token = aws_dict.get('session_token') + if session_token: + headers['X-Amz-Security-Token'] = session_token + headers['X-Api-Key'] = self._AWS_API_KEY + + def aws_hash(s): + return hashlib.sha256(s.encode('utf-8')).hexdigest() + + # Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html + canonical_querystring = compat_urllib_parse_urlencode(query) + canonical_headers = '' + for header_name, header_value in headers.items(): + canonical_headers += '%s:%s\n' % (header_name.lower(), header_value) + signed_headers = ';'.join([header.lower() for header in headers.keys()]) + canonical_request = '\n'.join([ + 'GET', + aws_dict['uri'], + canonical_querystring, + canonical_headers, + signed_headers, + aws_hash('') + ]) + + # Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html + credential_scope_list = [date, self._AWS_REGION, 'execute-api', 'aws4_request'] + credential_scope = '/'.join(credential_scope_list) + string_to_sign = '\n'.join([self._AWS_ALGORITHM, amz_date, credential_scope, aws_hash(canonical_request)]) + + # Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html + def aws_hmac(key, msg): + return hmac.new(key, msg.encode('utf-8'), hashlib.sha256) + + def aws_hmac_digest(key, msg): + return aws_hmac(key, msg).digest() + + def aws_hmac_hexdigest(key, msg): + return aws_hmac(key, msg).hexdigest() + + k_signing = ('AWS4' + aws_dict['secret_key']).encode('utf-8') + for value in credential_scope_list: + k_signing = aws_hmac_digest(k_signing, value) + + signature = aws_hmac_hexdigest(k_signing, string_to_sign) + + # Task 4: http://docs.aws.amazon.com/general/latest/gr/sigv4-add-signature-to-request.html + headers['Authorization'] = ', '.join([ + '%s Credential=%s/%s' % (self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope), + 'SignedHeaders=%s' % signed_headers, + 'Signature=%s' % signature, + ]) + + return self._download_json( + 'https://%s%s%s' % (self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''), + video_id, headers=headers) diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 5525f7c9b..8b20c03d6 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -386,7 +386,7 @@ class BBCCoUkIE(InfoExtractor): m3u8_id=format_id, fatal=False)) if re.search(self._USP_RE, href): usp_formats = self._extract_m3u8_formats( - re.sub(self._USP_RE, r'/\1\.ism/\1\.m3u8', href), + re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href), programme_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id=format_id, fatal=False) for f in usp_formats: diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 0ed59bcbc..f04505011 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -464,7 +464,7 @@ class BrightcoveNewIE(AdobePassIE): 'timestamp': 1441391203, 'upload_date': '20150904', 'uploader_id': '929656772001', - 'formats': 'mincount:22', + 'formats': 'mincount:20', }, }, { # with rtmp streams @@ -478,7 +478,7 @@ class BrightcoveNewIE(AdobePassIE): 'timestamp': 1433556729, 'upload_date': '20150606', 'uploader_id': '4036320279001', - 'formats': 'mincount:41', + 'formats': 'mincount:39', }, 'params': { # m3u8 download @@ -564,59 +564,7 @@ class BrightcoveNewIE(AdobePassIE): return entries - def _real_extract(self, url): - url, smuggled_data = unsmuggle_url(url, {}) - self._initialize_geo_bypass(smuggled_data.get('geo_countries')) - - account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups() - - webpage = self._download_webpage( - 'http://players.brightcove.net/%s/%s_%s/index.min.js' - % (account_id, player_id, embed), video_id) - - policy_key = None - - catalog = self._search_regex( - r'catalog\(({.+?})\);', webpage, 'catalog', default=None) - if catalog: - catalog = self._parse_json( - js_to_json(catalog), video_id, fatal=False) - if catalog: - policy_key = catalog.get('policyKey') - - if not policy_key: - policy_key = self._search_regex( - r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1', - webpage, 'policy key', group='pk') - - api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id) - try: - json_data = self._download_json(api_url, video_id, headers={ - 'Accept': 'application/json;pk=%s' % policy_key - }) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - json_data = self._parse_json(e.cause.read().decode(), video_id)[0] - message = json_data.get('message') or json_data['error_code'] - if json_data.get('error_subcode') == 'CLIENT_GEO': - self.raise_geo_restricted(msg=message) - raise ExtractorError(message, expected=True) - raise - - errors = json_data.get('errors') - if errors and errors[0].get('error_subcode') == 'TVE_AUTH': - custom_fields = json_data['custom_fields'] - tve_token = self._extract_mvpd_auth( - smuggled_data['source_url'], video_id, - custom_fields['bcadobepassrequestorid'], - custom_fields['bcadobepassresourceid']) - json_data = self._download_json( - api_url, video_id, headers={ - 'Accept': 'application/json;pk=%s' % policy_key - }, query={ - 'tveToken': tve_token, - }) - + def _parse_brightcove_metadata(self, json_data, video_id): title = json_data['name'].strip() formats = [] @@ -682,6 +630,7 @@ class BrightcoveNewIE(AdobePassIE): }) formats.append(f) + errors = json_data.get('errors') if not formats and errors: error = errors[0] raise ExtractorError( @@ -708,9 +657,64 @@ class BrightcoveNewIE(AdobePassIE): 'thumbnail': json_data.get('thumbnail') or json_data.get('poster'), 'duration': duration, 'timestamp': parse_iso8601(json_data.get('published_at')), - 'uploader_id': account_id, + 'uploader_id': json_data.get('account_id'), 'formats': formats, 'subtitles': subtitles, 'tags': json_data.get('tags', []), 'is_live': is_live, } + + def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + self._initialize_geo_bypass(smuggled_data.get('geo_countries')) + + account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups() + + webpage = self._download_webpage( + 'http://players.brightcove.net/%s/%s_%s/index.min.js' + % (account_id, player_id, embed), video_id) + + policy_key = None + + catalog = self._search_regex( + r'catalog\(({.+?})\);', webpage, 'catalog', default=None) + if catalog: + catalog = self._parse_json( + js_to_json(catalog), video_id, fatal=False) + if catalog: + policy_key = catalog.get('policyKey') + + if not policy_key: + policy_key = self._search_regex( + r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1', + webpage, 'policy key', group='pk') + + api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id) + try: + json_data = self._download_json(api_url, video_id, headers={ + 'Accept': 'application/json;pk=%s' % policy_key + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + json_data = self._parse_json(e.cause.read().decode(), video_id)[0] + message = json_data.get('message') or json_data['error_code'] + if json_data.get('error_subcode') == 'CLIENT_GEO': + self.raise_geo_restricted(msg=message) + raise ExtractorError(message, expected=True) + raise + + errors = json_data.get('errors') + if errors and errors[0].get('error_subcode') == 'TVE_AUTH': + custom_fields = json_data['custom_fields'] + tve_token = self._extract_mvpd_auth( + smuggled_data['source_url'], video_id, + custom_fields['bcadobepassrequestorid'], + custom_fields['bcadobepassresourceid']) + json_data = self._download_json( + api_url, video_id, headers={ + 'Accept': 'application/json;pk=%s' % policy_key + }, query={ + 'tveToken': tve_token, + }) + + return self._parse_brightcove_metadata(json_data, video_id) diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 8ef089653..4bf4efe1f 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -3,20 +3,19 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError class BYUtvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?' + _VALID_URL = r'https?://(?:www\.)?byutv\.org/(?:watch|player)/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?' _TESTS = [{ 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5', 'info_dict': { - 'id': '6587b9a3-89d2-42a6-a7f7-fd2f81840a7d', + 'id': 'ZvanRocTpW-G5_yZFeltTAMv6jxOU9KH', 'display_id': 'studio-c-season-5-episode-5', 'ext': 'mp4', 'title': 'Season 5 Episode 5', - 'description': 'md5:e07269172baff037f8e8bf9956bc9747', - 'thumbnail': r're:^https?://.*\.jpg$', + 'description': 'md5:1d31dc18ef4f075b28f6a65937d22c65', + 'thumbnail': r're:^https?://.*', 'duration': 1486.486, }, 'params': { @@ -26,6 +25,9 @@ class BYUtvIE(InfoExtractor): }, { 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d', 'only_matching': True, + }, { + 'url': 'https://www.byutv.org/player/27741493-dc83-40b0-8420-e7ae38a2ae98/byu-football-toledo-vs-byu-93016?listid=4fe0fee5-0d3c-4a29-b725-e4948627f472&listindex=0&q=toledo', + 'only_matching': True, }] def _real_extract(self, url): @@ -33,16 +35,16 @@ class BYUtvIE(InfoExtractor): video_id = mobj.group('id') display_id = mobj.group('display_id') or video_id - webpage = self._download_webpage(url, display_id) - episode_code = self._search_regex( - r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information') - - ep = self._parse_json( - episode_code, display_id, transform_source=lambda s: - re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s)) - - if ep['providerType'] != 'Ooyala': - raise ExtractorError('Unsupported provider %s' % ep['provider']) + ep = self._download_json( + 'https://api.byutv.org/api3/catalog/getvideosforcontent', video_id, + query={ + 'contentid': video_id, + 'channel': 'byutv', + 'x-byutv-context': 'web$US', + }, headers={ + 'x-byutv-context': 'web$US', + 'x-byutv-platformkey': 'xsaaw9c7y5', + })['ooyalaVOD'] return { '_type': 'url_transparent', @@ -50,44 +52,7 @@ class BYUtvIE(InfoExtractor): 'url': 'ooyala:%s' % ep['providerId'], 'id': video_id, 'display_id': display_id, - 'title': ep['title'], + 'title': ep.get('title'), 'description': ep.get('description'), 'thumbnail': ep.get('imageThumbnail'), } - - -class BYUtvEventIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/event/(?P<id>[0-9a-f-]+)' - _TEST = { - 'url': 'http://www.byutv.org/watch/event/29941b9b-8bf6-48d2-aebf-7a87add9e34b', - 'info_dict': { - 'id': '29941b9b-8bf6-48d2-aebf-7a87add9e34b', - 'ext': 'mp4', - 'title': 'Toledo vs. BYU (9/30/16)', - }, - 'params': { - 'skip_download': True, - }, - 'add_ie': ['Ooyala'], - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - ooyala_id = self._search_regex( - r'providerId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', - webpage, 'ooyala id', group='id') - - title = self._search_regex( - r'class=["\']description["\'][^>]*>\s*<h1>([^<]+)</h1>', webpage, - 'title').strip() - - return { - '_type': 'url_transparent', - 'ie_key': 'Ooyala', - 'url': 'ooyala:%s' % ooyala_id, - 'id': video_id, - 'title': title, - } diff --git a/youtube_dl/extractor/cbslocal.py b/youtube_dl/extractor/cbslocal.py index 7d78e3aae..90852a9ef 100644 --- a/youtube_dl/extractor/cbslocal.py +++ b/youtube_dl/extractor/cbslocal.py @@ -91,12 +91,10 @@ class CBSLocalIE(AnvatoIE): info_dict = self._extract_anvato_videos(webpage, display_id) - time_str = self._html_search_regex( - r'class="entry-date">([^<]+)<', webpage, 'released date', default=None) - if time_str: - timestamp = unified_timestamp(time_str) - else: - timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage)) + timestamp = unified_timestamp(self._html_search_regex( + r'class="(?:entry|post)-date"[^>]*>([^<]+)', webpage, + 'released date', default=None)) or parse_iso8601( + self._html_search_meta('uploadDate', webpage)) info_dict.update({ 'display_id': display_id, diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 80a9c982f..3b79b8cb4 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -301,8 +301,9 @@ class InfoExtractor(object): There must be a key "entries", which is a list, an iterable, or a PagedList object, each element of which is a valid dictionary by this specification. - Additionally, playlists can have "title", "description" and "id" attributes - with the same semantics as videos (see above). + Additionally, playlists can have "id", "title", "description", "uploader", + "uploader_id", "uploader_url" attributes with the same semantics as videos + (see above). _type "multi_video" indicates that there are multiple videos that @@ -494,6 +495,16 @@ class InfoExtractor(object): self.to_screen('%s' % (note,)) else: self.to_screen('%s: %s' % (video_id, note)) + + # Some sites check X-Forwarded-For HTTP header in order to figure out + # the origin of the client behind proxy. This allows bypassing geo + # restriction by faking this header's value to IP that belongs to some + # geo unrestricted country. We will do so once we encounter any + # geo restriction error. + if self._x_forwarded_for_ip: + if 'X-Forwarded-For' not in headers: + headers['X-Forwarded-For'] = self._x_forwarded_for_ip + if isinstance(url_or_request, compat_urllib_request.Request): url_or_request = update_Request( url_or_request, data=data, headers=headers, query=query) @@ -523,15 +534,6 @@ class InfoExtractor(object): if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - # Some sites check X-Forwarded-For HTTP header in order to figure out - # the origin of the client behind proxy. This allows bypassing geo - # restriction by faking this header's value to IP that belongs to some - # geo unrestricted country. We will do so once we encounter any - # geo restriction error. - if self._x_forwarded_for_ip: - if 'X-Forwarded-For' not in headers: - headers['X-Forwarded-For'] = self._x_forwarded_for_ip - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) if urlh is False: assert not fatal diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index b53f2d705..b92f25447 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -392,7 +392,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'Downloading subtitles for ' + sub_name, data={ 'subtitle_script_id': sub_id, }) - if not sub_doc: + if sub_doc is None: continue sid = sub_doc.get('id') iv = xpath_text(sub_doc, 'iv', 'subtitle iv') @@ -479,9 +479,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_quality': stream_quality, 'current_page': url, }) - if streamdata: + if streamdata is not None: stream_info = streamdata.find('./{default}preload/stream_info') - if stream_info: + if stream_info is not None: stream_infos.append(stream_info) stream_info = self._call_rpc_api( 'VideoEncode_GetStreamInfo', video_id, @@ -490,7 +490,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text 'video_format': stream_format, 'video_encode_quality': stream_quality, }) - if stream_info: + if stream_info is not None: stream_infos.append(stream_info) for stream_info in stream_infos: video_encode_id = xpath_text(stream_info, './video_encode_id') diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 171820e27..67d6df4b0 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -4,13 +4,14 @@ import re from .common import InfoExtractor from ..utils import ( - int_or_none, - unescapeHTML, - find_xpath_attr, - smuggle_url, determine_ext, ExtractorError, extract_attributes, + find_xpath_attr, + get_element_by_class, + int_or_none, + smuggle_url, + unescapeHTML, ) from .senateisvp import SenateISVPIE from .ustream import UstreamIE @@ -68,6 +69,10 @@ class CSpanIE(InfoExtractor): 'uploader': 'HouseCommittee', 'uploader_id': '12987475', }, + }, { + # Audio Only + 'url': 'https://www.c-span.org/video/?437336-1/judiciary-antitrust-competition-policy-consumer-rights', + 'only_matching': True, }] BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s' @@ -111,7 +116,15 @@ class CSpanIE(InfoExtractor): title = self._og_search_title(webpage) surl = smuggle_url(senate_isvp_url, {'force_title': title}) return self.url_result(surl, 'SenateISVP', video_id, title) + video_id = self._search_regex( + r'jwsetup\.clipprog\s*=\s*(\d+);', + webpage, 'jwsetup program id', default=None) + if video_id: + video_type = 'program' if video_type is None or video_id is None: + error_message = get_element_by_class('VLplayer-error-message', webpage) + if error_message: + raise ExtractorError(error_message) raise ExtractorError('unable to find video id and type') def get_text_attr(d, attr): @@ -138,7 +151,7 @@ class CSpanIE(InfoExtractor): entries = [] for partnum, f in enumerate(files): formats = [] - for quality in f['qualities']: + for quality in f.get('qualities', []): formats.append({ 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')), 'url': unescapeHTML(get_text_attr(quality, 'file')), diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 21a2d0239..0e7d587dd 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -413,52 +413,3 @@ class DailymotionUserIE(DailymotionPlaylistIE): 'title': full_user, 'entries': self._extract_entries(user), } - - -class DailymotionCloudIE(DailymotionBaseInfoExtractor): - _VALID_URL_PREFIX = r'https?://api\.dmcloud\.net/(?:player/)?embed/' - _VALID_URL = r'%s[^/]+/(?P<id>[^/?]+)' % _VALID_URL_PREFIX - _VALID_EMBED_URL = r'%s[^/]+/[^\'"]+' % _VALID_URL_PREFIX - - _TESTS = [{ - # From http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html - # Tested at FranceTvInfo_2 - 'url': 'http://api.dmcloud.net/embed/4e7343f894a6f677b10006b4/556e03339473995ee145930c?auth=1464865870-0-jyhsm84b-ead4c701fb750cf9367bf4447167a3db&autoplay=1', - 'only_matching': True, - }, { - # http://www.francetvinfo.fr/societe/larguez-les-amarres-le-cobaturage-se-developpe_980101.html - 'url': 'http://api.dmcloud.net/player/embed/4e7343f894a6f677b10006b4/559545469473996d31429f06?auth=1467430263-0-90tglw2l-a3a4b64ed41efe48d7fccad85b8b8fda&autoplay=1', - 'only_matching': True, - }] - - @classmethod - def _extract_dmcloud_url(cls, webpage): - mobj = re.search(r'<iframe[^>]+src=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, webpage) - if mobj: - return mobj.group(1) - - mobj = re.search( - r'<input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=[\'"](%s)[\'"]' % cls._VALID_EMBED_URL, - webpage) - if mobj: - return mobj.group(1) - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage_no_ff(url, video_id) - - title = self._html_search_regex(r'<title>([^>]+)</title>', webpage, 'title') - - video_info = self._parse_json(self._search_regex( - r'var\s+info\s*=\s*([^;]+);', webpage, 'video info'), video_id) - - # TODO: parse ios_url, which is in fact a manifest - video_url = video_info['mp4_url'] - - return { - 'id': video_id, - 'url': video_url, - 'title': title, - 'thumbnail': video_info.get('thumbnail_url'), - } diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 55853f76f..f9cec1d23 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -1,14 +1,18 @@ from __future__ import unicode_literals -from .common import InfoExtractor +import random +import re +import string + +from .discoverygo import DiscoveryGoBaseIE from ..utils import ( - parse_duration, - parse_iso8601, + ExtractorError, + update_url_query, ) -from ..compat import compat_str +from ..compat import compat_HTTPError -class DiscoveryIE(InfoExtractor): +class DiscoveryIE(DiscoveryGoBaseIE): _VALID_URL = r'''(?x)https?://(?:www\.)?(?: discovery| investigationdiscovery| @@ -19,79 +23,65 @@ class DiscoveryIE(InfoExtractor): sciencechannel| tlc| velocity - )\.com/(?:[^/]+/)*(?P<id>[^./?#]+)''' + )\.com(?P<path>/tv-shows/[^/]+/(?:video|full-episode)s/(?P<id>[^./?#]+))''' _TESTS = [{ - 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', + 'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley', 'info_dict': { - 'id': '20769', + 'id': '5a2d9b4d6b66d17a5026e1fd', 'ext': 'mp4', - 'title': 'Mission Impossible Outtakes', - 'description': ('Watch Jamie Hyneman and Adam Savage practice being' - ' each other -- to the point of confusing Jamie\'s dog -- and ' - 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' - ' back.'), - 'duration': 156, - 'timestamp': 1302032462, - 'upload_date': '20110405', - 'uploader_id': '103207', + 'title': 'Dave Foley', + 'description': 'md5:4b39bcafccf9167ca42810eb5f28b01f', + 'duration': 608, }, 'params': { 'skip_download': True, # requires ffmpeg } }, { - 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mythbusters-the-simpsons', - 'info_dict': { - 'id': 'mythbusters-the-simpsons', - 'title': 'MythBusters: The Simpsons', - }, - 'playlist_mincount': 10, - }, { - 'url': 'http://www.animalplanet.com/longfin-eels-maneaters/', - 'info_dict': { - 'id': '78326', - 'ext': 'mp4', - 'title': 'Longfin Eels: Maneaters?', - 'description': 'Jeremy Wade tests whether or not New Zealand\'s longfin eels are man-eaters by covering himself in fish guts and getting in the water with them.', - 'upload_date': '20140725', - 'timestamp': 1406246400, - 'duration': 116, - 'uploader_id': '103207', - }, - 'params': { - 'skip_download': True, # requires ffmpeg - } + 'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision', + 'only_matching': True, }] + _GEO_COUNTRIES = ['US'] + _GEO_BYPASS = False def _real_extract(self, url): - display_id = self._match_id(url) - info = self._download_json(url + '?flat=1', display_id) - - video_title = info.get('playlist_title') or info.get('video_title') + path, display_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, display_id) - entries = [] + react_data = self._parse_json(self._search_regex( + r'window\.__reactTransmitPacket\s*=\s*({.+?});', + webpage, 'react data'), display_id) + content_blocks = react_data['layout'][path]['contentBlocks'] + video = next(cb for cb in content_blocks if cb.get('type') == 'video')['content']['items'][0] + video_id = video['id'] - for idx, video_info in enumerate(info['playlist']): - subtitles = {} - caption_url = video_info.get('captionsUrl') - if caption_url: - subtitles = { - 'en': [{ - 'url': caption_url, - }] - } + access_token = self._download_json( + 'https://www.discovery.com/anonymous', display_id, query={ + 'authLink': update_url_query( + 'https://login.discovery.com/v1/oauth2/authorize', { + 'client_id': react_data['application']['apiClientId'], + 'redirect_uri': 'https://fusion.ddmcdn.com/app/mercury-sdk/180/redirectHandler.html', + 'response_type': 'anonymous', + 'state': 'nonce,' + ''.join([random.choice(string.ascii_letters) for _ in range(32)]), + }) + })['access_token'] - entries.append({ - '_type': 'url_transparent', - 'url': 'http://players.brightcove.net/103207/default_default/index.html?videoId=ref:%s' % video_info['referenceId'], - 'id': compat_str(video_info['id']), - 'title': video_info['title'], - 'description': video_info.get('description'), - 'duration': parse_duration(video_info.get('video_length')), - 'webpage_url': video_info.get('href') or video_info.get('url'), - 'thumbnail': video_info.get('thumbnailURL'), - 'alt_title': video_info.get('secondary_title'), - 'timestamp': parse_iso8601(video_info.get('publishedDate')), - 'subtitles': subtitles, - }) + try: + stream = self._download_json( + 'https://api.discovery.com/v1/streaming/video/' + video_id, + display_id, headers={ + 'Authorization': 'Bearer ' + access_token, + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + e_description = self._parse_json( + e.cause.read().decode(), display_id)['description'] + if 'resource not available for country' in e_description: + self.raise_geo_restricted(countries=self._GEO_COUNTRIES) + if 'Authorized Networks' in e_description: + raise ExtractorError( + 'This video is only available via cable service provider subscription that' + ' is not currently supported. You may want to use --cookies.', expected=True) + raise ExtractorError(e_description) + raise - return self.playlist_result(entries, display_id, video_title) + return self._extract_video_info(video, stream, display_id) diff --git a/youtube_dl/extractor/discoverygo.py b/youtube_dl/extractor/discoverygo.py index 7cd5d4291..3368c4c07 100644 --- a/youtube_dl/extractor/discoverygo.py +++ b/youtube_dl/extractor/discoverygo.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + determine_ext, extract_attributes, ExtractorError, int_or_none, @@ -27,42 +28,9 @@ class DiscoveryGoBaseIE(InfoExtractor): velocitychannel )go\.com/%s(?P<id>[^/?#&]+)''' - -class DiscoveryGoIE(DiscoveryGoBaseIE): - _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+' - _GEO_COUNTRIES = ['US'] - _TEST = { - 'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/', - 'info_dict': { - 'id': '58c167d86b66d12f2addeb01', - 'ext': 'mp4', - 'title': 'Reaper Madness', - 'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78', - 'duration': 2519, - 'series': 'Bering Sea Gold', - 'season_number': 8, - 'episode_number': 6, - 'age_limit': 14, - }, - } - - def _real_extract(self, url): - display_id = self._match_id(url) - - webpage = self._download_webpage(url, display_id) - - container = extract_attributes( - self._search_regex( - r'(<div[^>]+class=["\']video-player-container[^>]+>)', - webpage, 'video container')) - - video = self._parse_json( - container.get('data-video') or container.get('data-json'), - display_id) - + def _extract_video_info(self, video, stream, display_id): title = video['name'] - stream = video.get('stream') if not stream: if video.get('authenticated') is True: raise ExtractorError( @@ -106,7 +74,11 @@ class DiscoveryGoIE(DiscoveryGoBaseIE): not subtitle_url.startswith('http')): continue lang = caption.get('fileLang', 'en') - subtitles.setdefault(lang, []).append({'url': subtitle_url}) + ext = determine_ext(subtitle_url) + subtitles.setdefault(lang, []).append({ + 'url': subtitle_url, + 'ext': 'ttml' if ext == 'xml' else ext, + }) return { 'id': video_id, @@ -124,6 +96,43 @@ class DiscoveryGoIE(DiscoveryGoBaseIE): } +class DiscoveryGoIE(DiscoveryGoBaseIE): + _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+' + _GEO_COUNTRIES = ['US'] + _TEST = { + 'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/', + 'info_dict': { + 'id': '58c167d86b66d12f2addeb01', + 'ext': 'mp4', + 'title': 'Reaper Madness', + 'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78', + 'duration': 2519, + 'series': 'Bering Sea Gold', + 'season_number': 8, + 'episode_number': 6, + 'age_limit': 14, + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + container = extract_attributes( + self._search_regex( + r'(<div[^>]+class=["\']video-player-container[^>]+>)', + webpage, 'video container')) + + video = self._parse_json( + container.get('data-video') or container.get('data-json'), + display_id) + + stream = video.get('stream') + + return self._extract_video_info(video, stream, display_id) + + class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE): _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % '' _TEST = { diff --git a/youtube_dl/extractor/disney.py b/youtube_dl/extractor/disney.py index 968c4c7fd..0eee82fd6 100644 --- a/youtube_dl/extractor/disney.py +++ b/youtube_dl/extractor/disney.py @@ -10,6 +10,7 @@ from ..utils import ( compat_str, determine_ext, ExtractorError, + update_url_query, ) @@ -108,9 +109,16 @@ class DisneyIE(InfoExtractor): continue tbr = int_or_none(flavor.get('bitrate')) if tbr == 99999: - formats.extend(self._extract_m3u8_formats( + # wrong ks(Kaltura Signature) causes 404 Error + flavor_url = update_url_query(flavor_url, {'ks': ''}) + m3u8_formats = self._extract_m3u8_formats( flavor_url, video_id, 'mp4', - m3u8_id=flavor_format, fatal=False)) + m3u8_id=flavor_format, fatal=False) + for f in m3u8_formats: + # Apple FairPlay + if '/fpshls/' in f['url']: + continue + formats.append(f) continue format_id = [] if flavor_format: diff --git a/youtube_dl/extractor/ellentube.py b/youtube_dl/extractor/ellentube.py new file mode 100644 index 000000000..544473274 --- /dev/null +++ b/youtube_dl/extractor/ellentube.py @@ -0,0 +1,133 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + clean_html, + extract_attributes, + float_or_none, + int_or_none, + try_get, +) + + +class EllenTubeBaseIE(InfoExtractor): + def _extract_data_config(self, webpage, video_id): + details = self._search_regex( + r'(<[^>]+\bdata-component=(["\'])[Dd]etails.+?></div>)', webpage, + 'details') + return self._parse_json( + extract_attributes(details)['data-config'], video_id) + + def _extract_video(self, data, video_id): + title = data['title'] + + formats = [] + duration = None + for entry in data.get('media'): + if entry.get('id') == 'm3u8': + formats = self._extract_m3u8_formats( + entry['url'], video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls') + duration = int_or_none(entry.get('duration')) + break + self._sort_formats(formats) + + def get_insight(kind): + return int_or_none(try_get( + data, lambda x: x['insight']['%ss' % kind])) + + return { + 'extractor_key': EllenTubeIE.ie_key(), + 'id': video_id, + 'title': title, + 'description': data.get('description'), + 'duration': duration, + 'thumbnail': data.get('thumbnail'), + 'timestamp': float_or_none(data.get('publishTime'), scale=1000), + 'view_count': get_insight('view'), + 'like_count': get_insight('like'), + 'formats': formats, + } + + +class EllenTubeIE(EllenTubeBaseIE): + _VALID_URL = r'''(?x) + (?: + ellentube:| + https://api-prod\.ellentube\.com/ellenapi/api/item/ + ) + (?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}) + ''' + _TESTS = [{ + 'url': 'https://api-prod.ellentube.com/ellenapi/api/item/0822171c-3829-43bf-b99f-d77358ae75e3', + 'md5': '2fabc277131bddafdd120e0fc0f974c9', + 'info_dict': { + 'id': '0822171c-3829-43bf-b99f-d77358ae75e3', + 'ext': 'mp4', + 'title': 'Ellen Meets Las Vegas Survivors Jesus Campos and Stephen Schuck', + 'description': 'md5:76e3355e2242a78ad9e3858e5616923f', + 'thumbnail': r're:^https?://.+?', + 'duration': 514, + 'timestamp': 1508505120, + 'upload_date': '20171020', + 'view_count': int, + 'like_count': int, + } + }, { + 'url': 'ellentube:734a3353-f697-4e79-9ca9-bfc3002dc1e0', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + data = self._download_json( + 'https://api-prod.ellentube.com/ellenapi/api/item/%s' % video_id, + video_id) + return self._extract_video(data, video_id) + + +class EllenTubeVideoIE(EllenTubeBaseIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/video/(?P<id>.+?)\.html' + _TEST = { + 'url': 'https://www.ellentube.com/video/ellen-meets-las-vegas-survivors-jesus-campos-and-stephen-schuck.html', + 'only_matching': True, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._extract_data_config(webpage, display_id)['id'] + return self.url_result( + 'ellentube:%s' % video_id, ie=EllenTubeIE.ie_key(), + video_id=video_id) + + +class EllenTubePlaylistIE(EllenTubeBaseIE): + _VALID_URL = r'https?://(?:www\.)?ellentube\.com/(?:episode|studios)/(?P<id>.+?)\.html' + _TESTS = [{ + 'url': 'https://www.ellentube.com/episode/dax-shepard-jordan-fisher-haim.html', + 'info_dict': { + 'id': 'dax-shepard-jordan-fisher-haim', + 'title': "Dax Shepard, 'DWTS' Team Jordan Fisher & Lindsay Arnold, HAIM", + 'description': 'md5:bfc982194dabb3f4e325e43aa6b2e21c', + }, + 'playlist_count': 6, + }, { + 'url': 'https://www.ellentube.com/studios/macey-goes-rving0.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + data = self._extract_data_config(webpage, display_id)['data'] + feed = self._download_json( + 'https://api-prod.ellentube.com/ellenapi/api/feed/?%s' + % data['filter'], display_id) + entries = [ + self._extract_video(elem, elem['id']) + for elem in feed if elem.get('type') == 'VIDEO' and elem.get('id')] + return self.playlist_result( + entries, display_id, data.get('title'), + clean_html(data.get('description'))) diff --git a/youtube_dl/extractor/ellentv.py b/youtube_dl/extractor/ellentv.py deleted file mode 100644 index e0a13dd76..000000000 --- a/youtube_dl/extractor/ellentv.py +++ /dev/null @@ -1,101 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .common import InfoExtractor -from .kaltura import KalturaIE -from ..utils import NO_DEFAULT - - -class EllenTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)' - _TESTS = [{ - 'url': 'http://www.ellentv.com/videos/0-ipq1gsai/', - 'md5': '4294cf98bc165f218aaa0b89e0fd8042', - 'info_dict': { - 'id': '0_ipq1gsai', - 'ext': 'mov', - 'title': 'Fast Fingers of Fate', - 'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a', - 'timestamp': 1428035648, - 'upload_date': '20150403', - 'uploader_id': 'batchUser', - }, - }, { - # not available via http://widgets.ellentube.com/ - 'url': 'http://www.ellentv.com/videos/1-szkgu2m2/', - 'info_dict': { - 'id': '1_szkgu2m2', - 'ext': 'flv', - 'title': "Ellen's Amazingly Talented Audience", - 'description': 'md5:86ff1e376ff0d717d7171590e273f0a5', - 'timestamp': 1255140900, - 'upload_date': '20091010', - 'uploader_id': 'ellenkaltura@gmail.com', - }, - 'params': { - 'skip_download': True, - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - - URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url) - - for num, url_ in enumerate(URLS, 1): - webpage = self._download_webpage( - url_, video_id, fatal=num == len(URLS)) - - default = NO_DEFAULT if num == len(URLS) else None - - partner_id = self._search_regex( - r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id', - default=default) - - kaltura_id = self._search_regex( - [r'id="kaltura_player_([^"]+)"', - r"_wb_entry_id\s*:\s*'([^']+)", - r'data-kaltura-entry-id="([^"]+)'], - webpage, 'kaltura id', default=default) - - if partner_id and kaltura_id: - break - - return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key()) - - -class EllenTVClipsIE(InfoExtractor): - IE_NAME = 'EllenTV:clips' - _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)' - _TEST = { - 'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/', - 'info_dict': { - 'id': 'meryl-streep-vanessa-hudgens', - 'title': 'Meryl Streep, Vanessa Hudgens', - }, - 'playlist_mincount': 5, - } - - def _real_extract(self, url): - playlist_id = self._match_id(url) - - webpage = self._download_webpage(url, playlist_id) - playlist = self._extract_playlist(webpage, playlist_id) - - return { - '_type': 'playlist', - 'id': playlist_id, - 'title': self._og_search_title(webpage), - 'entries': self._extract_entries(playlist) - } - - def _extract_playlist(self, webpage, playlist_id): - json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json') - return self._parse_json('[{' + json_string + '}]', playlist_id) - - def _extract_entries(self, playlist): - return [ - self.url_result( - 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']), - KalturaIE.ie_key(), video_id=item['kaltura_entry_id']) - for item in playlist] diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index 7a7436068..127c69b2e 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -1,6 +1,9 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from .once import OnceIE from ..compat import compat_str from ..utils import ( determine_ext, @@ -9,22 +12,27 @@ from ..utils import ( ) -class ESPNIE(InfoExtractor): +class ESPNIE(OnceIE): _VALID_URL = r'''(?x) https?:// (?: - (?:(?:\w+\.)+)?espn\.go| - (?:www\.)?espn - )\.com/ - (?: - (?: - video/clip| - watch/player - ) (?: - \?.*?\bid=| - /_/id/ - ) + (?: + (?:(?:\w+\.)+)?espn\.go| + (?:www\.)?espn + )\.com/ + (?: + (?: + video/(?:clip|iframe/twitter)| + watch/player + ) + (?: + .*?\?.*?\bid=| + /_/id/ + ) + ) + )| + (?:www\.)espnfc\.(?:com|us)/(?:video/)?[^/]+/\d+/video/ ) (?P<id>\d+) ''' @@ -77,6 +85,15 @@ class ESPNIE(InfoExtractor): }, { 'url': 'http://www.espn.com/video/clip/_/id/17989860', 'only_matching': True, + }, { + 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', + 'only_matching': True, + }, { + 'url': 'http://www.espnfc.us/video/espn-fc-tv/86/video/3319154/nashville-unveiled-as-the-newest-club-in-mls', + 'only_matching': True, + }, { + 'url': 'http://www.espnfc.com/english-premier-league/23/video/3324163/premier-league-in-90-seconds-golden-tweets', + 'only_matching': True, }] def _real_extract(self, url): @@ -93,7 +110,9 @@ class ESPNIE(InfoExtractor): def traverse_source(source, base_source_id=None): for source_id, source in source.items(): - if isinstance(source, compat_str): + if source_id == 'alert': + continue + elif isinstance(source, compat_str): extract_source(source, base_source_id) elif isinstance(source, dict): traverse_source( @@ -106,7 +125,9 @@ class ESPNIE(InfoExtractor): return format_urls.add(source_url) ext = determine_ext(source_url) - if ext == 'smil': + if OnceIE.suitable(source_url): + formats.extend(self._extract_once_formats(source_url)) + elif ext == 'smil': formats.extend(self._extract_smil_formats( source_url, video_id, fatal=False)) elif ext == 'f4m': @@ -117,12 +138,24 @@ class ESPNIE(InfoExtractor): source_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id=source_id, fatal=False)) else: - formats.append({ + f = { 'url': source_url, 'format_id': source_id, - }) - - traverse_source(clip['links']['source']) + } + mobj = re.search(r'(\d+)p(\d+)_(\d+)k\.', source_url) + if mobj: + f.update({ + 'height': int(mobj.group(1)), + 'fps': int(mobj.group(2)), + 'tbr': int(mobj.group(3)), + }) + if source_id == 'mezzanine': + f['preference'] = 1 + formats.append(f) + + links = clip.get('links', {}) + traverse_source(links.get('source', {})) + traverse_source(links.get('mobile', {})) self._sort_formats(formats) description = clip.get('caption') or clip.get('description') @@ -144,9 +177,6 @@ class ESPNIE(InfoExtractor): class ESPNArticleIE(InfoExtractor): _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)' _TESTS = [{ - 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', - 'only_matching': True, - }, { 'url': 'http://espn.go.com/nba/recap?gameId=400793786', 'only_matching': True, }, { @@ -175,3 +205,34 @@ class ESPNArticleIE(InfoExtractor): return self.url_result( 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key()) + + +class FiveThirtyEightIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fivethirtyeight\.com/features/(?P<id>[^/?#]+)' + _TEST = { + 'url': 'http://fivethirtyeight.com/features/how-the-6-8-raiders-can-still-make-the-playoffs/', + 'info_dict': { + 'id': '21846851', + 'ext': 'mp4', + 'title': 'FiveThirtyEight: The Raiders can still make the playoffs', + 'description': 'Neil Paine breaks down the simplest scenario that will put the Raiders into the playoffs at 8-8.', + 'timestamp': 1513960621, + 'upload_date': '20171222', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Unable to download f4m manifest'], + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_id = self._search_regex( + r'data-video-id=["\'](?P<id>\d+)', + webpage, 'video id', group='id') + + return self.url_result( + 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key()) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f1ea735b5..e863f03ab 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -138,10 +138,7 @@ from .brightcove import ( BrightcoveNewIE, ) from .buzzfeed import BuzzFeedIE -from .byutv import ( - BYUtvIE, - BYUtvEventIE, -) +from .byutv import BYUtvIE from .c56 import C56IE from .camdemy import ( CamdemyIE, @@ -246,7 +243,6 @@ from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, DailymotionUserIE, - DailymotionCloudIE, ) from .daisuki import ( DaisukiMottoIE, @@ -312,9 +308,10 @@ from .ehow import EHowIE from .eighttracks import EightTracksIE from .einthusan import EinthusanIE from .eitb import EitbIE -from .ellentv import ( - EllenTVIE, - EllenTVClipsIE, +from .ellentube import ( + EllenTubeIE, + EllenTubeVideoIE, + EllenTubePlaylistIE, ) from .elpais import ElPaisIE from .embedly import EmbedlyIE @@ -325,6 +322,7 @@ from .escapist import EscapistIE from .espn import ( ESPNIE, ESPNArticleIE, + FiveThirtyEightIE, ) from .esri import EsriVideoIE from .etonline import ETOnlineIE @@ -689,6 +687,7 @@ from .nhl import ( ) from .nick import ( NickIE, + NickBrIE, NickDeIE, NickNightIE, NickRuIE, @@ -721,10 +720,6 @@ from .nowness import ( NownessPlaylistIE, NownessSeriesIE, ) -from .nowtv import ( - NowTVIE, - NowTVListIE, -) from .noz import NozIE from .npo import ( AndereTijdenIE, @@ -857,6 +852,7 @@ from .radiofrance import RadioFranceIE from .rai import ( RaiPlayIE, RaiPlayLiveIE, + RaiPlayPlaylistIE, RaiIE, ) from .rbmaradio import RBMARadioIE @@ -931,8 +927,12 @@ from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE from .servingsys import ServingSysIE from .servus import ServusIE +from .sevenplus import SevenPlusIE from .sexu import SexuIE -from .shahid import ShahidIE +from .shahid import ( + ShahidIE, + ShahidShowIE, +) from .shared import ( SharedIE, VivoIE, @@ -1000,6 +1000,7 @@ from .streamango import StreamangoIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE from .streetvoice import StreetVoiceIE +from .stretchinternet import StretchInternetIE from .sunporno import SunPornoIE from .svt import ( SVTIE, @@ -1102,6 +1103,10 @@ from .tvigle import TvigleIE from .tvland import TVLandIE from .tvn24 import TVN24IE from .tvnoe import TVNoeIE +from .tvnow import ( + TVNowIE, + TVNowListIE, +) from .tvp import ( TVPEmbedIE, TVPIE, @@ -1139,6 +1144,7 @@ from .udemy import ( from .udn import UDNEmbedIE from .uktvplay import UKTVPlayIE from .digiteka import DigitekaIE +from .umg import UMGDeIE from .unistra import UnistraIE from .unity import UnityIE from .uol import UOLIE diff --git a/youtube_dl/extractor/fox.py b/youtube_dl/extractor/fox.py index 5f98d017b..11d6c9c32 100644 --- a/youtube_dl/extractor/fox.py +++ b/youtube_dl/extractor/fox.py @@ -11,6 +11,7 @@ from ..utils import ( parse_duration, try_get, unified_timestamp, + update_url_query, ) @@ -62,7 +63,8 @@ class FOXIE(AdobePassIE): duration = int_or_none(video.get('durationInSeconds')) or int_or_none( video.get('duration')) or parse_duration(video.get('duration')) timestamp = unified_timestamp(video.get('datePublished')) - age_limit = parse_age_limit(video.get('contentRating')) + rating = video.get('contentRating') + age_limit = parse_age_limit(rating) data = try_get( video, lambda x: x['trackingData']['properties'], dict) or {} @@ -77,8 +79,24 @@ class FOXIE(AdobePassIE): release_year = int_or_none(video.get('releaseYear')) if data.get('authRequired'): - # TODO: AP - pass + resource = self._get_mvpd_resource( + 'fbc-fox', title, video.get('guid'), rating) + release_url = update_url_query( + release_url, { + 'auth': self._extract_mvpd_auth( + url, video_id, 'fbc-fox', resource) + }) + + subtitles = {} + for doc_rel in video.get('documentReleases', []): + rel_url = doc_rel.get('url') + if not url or doc_rel.get('format') != 'SCC': + continue + subtitles['en'] = [{ + 'url': rel_url, + 'ext': 'scc', + }] + break info = { 'id': video_id, @@ -93,6 +111,7 @@ class FOXIE(AdobePassIE): 'episode': episode, 'episode_number': episode_number, 'release_year': release_year, + 'subtitles': subtitles, } urlh = self._request_webpage(HEADRequest(release_url), video_id) diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 5a3abeaff..095bb3954 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -13,10 +13,7 @@ from ..utils import ( parse_duration, determine_ext, ) -from .dailymotion import ( - DailymotionIE, - DailymotionCloudIE, -) +from .dailymotion import DailymotionIE class FranceTVBaseInfoExtractor(InfoExtractor): @@ -290,10 +287,6 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor): page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) - dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) - if dmcloud_url: - return self.url_result(dmcloud_url, DailymotionCloudIE.ie_key()) - dailymotion_urls = DailymotionIE._extract_urls(webpage) if dailymotion_urls: return self.playlist_result([ @@ -363,6 +356,7 @@ class CultureboxIE(FranceTVBaseInfoExtractor): raise ExtractorError('Video %s is not available' % name, expected=True) video_id, catalogue = self._search_regex( - r'"https?://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@') + r'["\'>]https?://videos\.francetv\.fr/video/([^@]+@.+?)["\'<]', + webpage, 'video id').split('@') return self._extract_video(video_id, catalogue) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 56df2ab47..c7b609215 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -59,10 +59,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE from .drtuber import DrTuberIE from .redtube import RedTubeIE from .vimeo import VimeoIE -from .dailymotion import ( - DailymotionIE, - DailymotionCloudIE, -) +from .dailymotion import DailymotionIE from .dailymail import DailyMailIE from .onionstudios import OnionStudiosIE from .viewlift import ViewLiftEmbedIE @@ -1472,23 +1469,6 @@ class GenericIE(InfoExtractor): 'timestamp': 1432570283, }, }, - # Dailymotion Cloud video - { - 'url': 'http://replay.publicsenat.fr/vod/le-debat/florent-kolandjian,dominique-cena,axel-decourtye,laurence-abeille,bruno-parmentier/175910', - 'md5': 'dcaf23ad0c67a256f4278bce6e0bae38', - 'info_dict': { - 'id': 'x2uy8t3', - 'ext': 'mp4', - 'title': 'Sauvons les abeilles ! - Le débat', - 'description': 'md5:d9082128b1c5277987825d684939ca26', - 'thumbnail': r're:^https?://.*\.jpe?g$', - 'timestamp': 1434970506, - 'upload_date': '20150622', - 'uploader': 'Public Sénat', - 'uploader_id': 'xa9gza', - }, - 'skip': 'File not found.', - }, # OnionStudios embed { 'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537', @@ -2195,7 +2175,7 @@ class GenericIE(InfoExtractor): return self.playlist_result(self._parse_xspf(doc, video_id), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'] = self._parse_mpd_formats( - doc, video_id, + doc, mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0], mpd_url=url) self._sort_formats(info_dict['formats']) @@ -2704,11 +2684,6 @@ class GenericIE(InfoExtractor): if senate_isvp_url: return self.url_result(senate_isvp_url, 'SenateISVP') - # Look for Dailymotion Cloud videos - dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage) - if dmcloud_url: - return self.url_result(dmcloud_url, 'DailymotionCloud') - # Look for OnionStudios embeds onionstudios_url = OnionStudiosIE._extract_url(webpage) if onionstudios_url: diff --git a/youtube_dl/extractor/itv.py b/youtube_dl/extractor/itv.py index 413a219dc..18a7d7f8c 100644 --- a/youtube_dl/extractor/itv.py +++ b/youtube_dl/extractor/itv.py @@ -26,7 +26,7 @@ from ..utils import ( class ITVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)' _GEO_COUNTRIES = ['GB'] - _TEST = { + _TESTS = [{ 'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053', 'info_dict': { 'id': '2a2936a0053', @@ -37,7 +37,11 @@ class ITVIE(InfoExtractor): # rtmp download 'skip_download': True, }, - } + }, { + # unavailable via data-playlist-url + 'url': 'https://www.itv.com/hub/through-the-keyhole/2a2271a0033', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -101,6 +105,18 @@ class ITVIE(InfoExtractor): 'Content-Type': 'text/xml; charset=utf-8', 'SOAPAction': 'http://tempuri.org/PlaylistService/GetPlaylist', }) + + info = self._search_json_ld(webpage, video_id, default={}) + formats = [] + subtitles = {} + + def extract_subtitle(sub_url): + ext = determine_ext(sub_url, 'ttml') + subtitles.setdefault('en', []).append({ + 'url': sub_url, + 'ext': 'ttml' if ext == 'xml' else ext, + }) + resp_env = self._download_xml( params['data-playlist-url'], video_id, headers=headers, data=etree.tostring(req_env)) @@ -111,37 +127,55 @@ class ITVIE(InfoExtractor): if fault_code == 'InvalidGeoRegion': self.raise_geo_restricted( msg=fault_string, countries=self._GEO_COUNTRIES) - raise ExtractorError('%s said: %s' % (self.IE_NAME, fault_string)) - title = xpath_text(playlist, 'EpisodeTitle', fatal=True) - video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True) - media_files = xpath_element(video_element, 'MediaFiles', fatal=True) - rtmp_url = media_files.attrib['base'] + elif fault_code != 'InvalidEntity': + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, fault_string), expected=True) + info.update({ + 'title': self._og_search_title(webpage), + 'episode_title': params.get('data-video-episode'), + 'series': params.get('data-video-title'), + }) + else: + title = xpath_text(playlist, 'EpisodeTitle', default=None) + info.update({ + 'title': title, + 'episode_title': title, + 'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')), + 'series': xpath_text(playlist, 'ProgrammeTitle'), + 'duration': parse_duration(xpath_text(playlist, 'Duration')), + }) + video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True) + media_files = xpath_element(video_element, 'MediaFiles', fatal=True) + rtmp_url = media_files.attrib['base'] - formats = [] - for media_file in media_files.findall('MediaFile'): - play_path = xpath_text(media_file, 'URL') - if not play_path: - continue - tbr = int_or_none(media_file.get('bitrate'), 1000) - f = { - 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''), - 'play_path': play_path, - # Providing this swfVfy allows to avoid truncated downloads - 'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf', - 'page_url': url, - 'tbr': tbr, - 'ext': 'flv', - } - app = self._search_regex( - 'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None) - if app: - f.update({ - 'url': rtmp_url.split('?', 1)[0], - 'app': app, - }) - else: - f['url'] = rtmp_url - formats.append(f) + for media_file in media_files.findall('MediaFile'): + play_path = xpath_text(media_file, 'URL') + if not play_path: + continue + tbr = int_or_none(media_file.get('bitrate'), 1000) + f = { + 'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''), + 'play_path': play_path, + # Providing this swfVfy allows to avoid truncated downloads + 'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf', + 'page_url': url, + 'tbr': tbr, + 'ext': 'flv', + } + app = self._search_regex( + 'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None) + if app: + f.update({ + 'url': rtmp_url.split('?', 1)[0], + 'app': app, + }) + else: + f['url'] = rtmp_url + formats.append(f) + + for caption_url in video_element.findall('ClosedCaptioningURIs/URL'): + if caption_url.text: + extract_subtitle(caption_url.text) ios_playlist_url = params.get('data-video-playlist') or params.get('data-video-id') hmac = params.get('data-video-hmac') @@ -198,27 +232,22 @@ class ITVIE(InfoExtractor): formats.append({ 'url': href, }) - self._sort_formats(formats) + subs = video_data.get('Subtitles') + if isinstance(subs, list): + for sub in subs: + if not isinstance(sub, dict): + continue + href = sub.get('Href') + if isinstance(href, compat_str): + extract_subtitle(href) + if not info.get('duration'): + info['duration'] = parse_duration(video_data.get('Duration')) - subtitles = {} - for caption_url in video_element.findall('ClosedCaptioningURIs/URL'): - if not caption_url.text: - continue - ext = determine_ext(caption_url.text, 'ttml') - subtitles.setdefault('en', []).append({ - 'url': caption_url.text, - 'ext': 'ttml' if ext == 'xml' else ext, - }) + self._sort_formats(formats) - info = self._search_json_ld(webpage, video_id, default={}) info.update({ 'id': video_id, - 'title': title, 'formats': formats, 'subtitles': subtitles, - 'episode_title': title, - 'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')), - 'series': xpath_text(playlist, 'ProgrammeTitle'), - 'duartion': parse_duration(xpath_text(playlist, 'Duration')), }) return info diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index bdac2df3e..562e25f6d 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -125,9 +125,12 @@ class KalturaIE(InfoExtractor): (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)* (?P=q1).*? (?: - entry_?[Ii]d| - (?P<q2>["'])entry_?[Ii]d(?P=q2) - )\s*:\s* + (?: + entry_?[Ii]d| + (?P<q2>["'])entry_?[Ii]d(?P=q2) + )\s*:\s*| + \[\s*(?P<q2_1>["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s* + ) (?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3) ''', webpage) or re.search( diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index f7cc3c832..6b7c5e3e0 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -13,8 +13,15 @@ from ..utils import ( class MailRuIE(InfoExtractor): IE_NAME = 'mailru' IE_DESC = 'Видео@Mail.Ru' - _VALID_URL = r'https?://(?:(?:www|m)\.)?my\.mail\.ru/(?:video/.*#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html)' - + _VALID_URL = r'''(?x) + https?:// + (?:(?:www|m)\.)?my\.mail\.ru/ + (?: + video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)| + (?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html| + (?:video/embed|\+/video/meta)/(?P<metaid>\d+) + ) + ''' _TESTS = [ { 'url': 'http://my.mail.ru/video/top#video=/mail/sonypicturesrus/75/76', @@ -23,7 +30,7 @@ class MailRuIE(InfoExtractor): 'id': '46301138_76', 'ext': 'mp4', 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', - 'timestamp': 1393232740, + 'timestamp': 1393235077, 'upload_date': '20140224', 'uploader': 'sonypicturesrus', 'uploader_id': 'sonypicturesrus@mail.ru', @@ -40,7 +47,7 @@ class MailRuIE(InfoExtractor): 'title': 'Samsung Galaxy S5 Hammer Smash Fail Battery Explosion', 'timestamp': 1397039888, 'upload_date': '20140409', - 'uploader': 'hitech@corp.mail.ru', + 'uploader': 'hitech', 'uploader_id': 'hitech@corp.mail.ru', 'duration': 245, }, @@ -65,28 +72,42 @@ class MailRuIE(InfoExtractor): { 'url': 'http://m.my.mail.ru/mail/3sktvtr/video/_myvideo/138.html', 'only_matching': True, + }, + { + 'url': 'https://my.mail.ru/video/embed/7949340477499637815', + 'only_matching': True, + }, + { + 'url': 'http://my.mail.ru/+/video/meta/7949340477499637815', + 'only_matching': True, } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('idv1') - - if not video_id: - video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix') - - webpage = self._download_webpage(url, video_id) + meta_id = mobj.group('metaid') + + video_id = None + if meta_id: + meta_url = 'https://my.mail.ru/+/video/meta/%s' % meta_id + else: + video_id = mobj.group('idv1') + if not video_id: + video_id = mobj.group('idv2prefix') + mobj.group('idv2suffix') + webpage = self._download_webpage(url, video_id) + page_config = self._parse_json(self._search_regex( + r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>', + webpage, 'page config', default='{}'), video_id, fatal=False) + if page_config: + meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') + else: + meta_url = None video_data = None - - page_config = self._parse_json(self._search_regex( - r'(?s)<script[^>]+class="sp-video__page-config"[^>]*>(.+?)</script>', - webpage, 'page config', default='{}'), video_id, fatal=False) - if page_config: - meta_url = page_config.get('metaUrl') or page_config.get('video', {}).get('metaUrl') - if meta_url: - video_data = self._download_json( - meta_url, video_id, 'Downloading video meta JSON', fatal=False) + if meta_url: + video_data = self._download_json( + meta_url, video_id or meta_id, 'Downloading video meta JSON', + fatal=not video_id) # Fallback old approach if not video_data: diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py index 310eea2cf..7edd68472 100644 --- a/youtube_dl/extractor/nick.py +++ b/youtube_dl/extractor/nick.py @@ -10,7 +10,7 @@ from ..utils import update_url_query class NickIE(MTVServicesInfoExtractor): # None of videos on the website are still alive? IE_NAME = 'nick.com' - _VALID_URL = r'https?://(?:(?:www|beta)\.)?nick(?:jr)?\.com/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)' + _VALID_URL = r'https?://(?P<domain>(?:(?:www|beta)\.)?nick(?:jr)?\.com)/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)' _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm' _GEO_COUNTRIES = ['US'] _TESTS = [{ @@ -69,8 +69,59 @@ class NickIE(MTVServicesInfoExtractor): 'mgid': uri, } - def _extract_mgid(self, webpage): - return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid') + def _real_extract(self, url): + domain, display_id = re.match(self._VALID_URL, url).groups() + video_data = self._download_json( + 'http://%s/data/video.endLevel.json' % domain, + display_id, query={ + 'urlKey': display_id, + }) + return self._get_videos_info(video_data['player'] + video_data['id']) + + +class NickBrIE(MTVServicesInfoExtractor): + IE_NAME = 'nickelodeon:br' + _VALID_URL = r'https?://(?P<domain>(?:www\.)?nickjr|mundonick\.uol)\.com\.br/(?:programas/)?[^/]+/videos/(?:episodios/)?(?P<id>[^/?#.]+)' + _TESTS = [{ + 'url': 'http://www.nickjr.com.br/patrulha-canina/videos/210-labirinto-de-pipoca/', + 'only_matching': True, + }, { + 'url': 'http://mundonick.uol.com.br/programas/the-loud-house/videos/muitas-irmas/7ljo9j', + 'only_matching': True, + }] + + def _real_extract(self, url): + domain, display_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, display_id) + uri = self._search_regex( + r'data-(?:contenturi|mgid)="([^"]+)', webpage, 'mgid') + video_id = self._id_from_uri(uri) + config = self._download_json( + 'http://media.mtvnservices.com/pmt/e1/access/index.html', + video_id, query={ + 'uri': uri, + 'configtype': 'edge', + }, headers={ + 'Referer': url, + }) + info_url = self._remove_template_parameter(config['feedWithQueryParams']) + if info_url == 'None': + if domain.startswith('www.'): + domain = domain[4:] + content_domain = { + 'mundonick.uol': 'mundonick.com.br', + 'nickjr': 'br.nickelodeonjunior.tv', + }[domain] + query = { + 'mgid': uri, + 'imageEp': content_domain, + 'arcEp': content_domain, + } + if domain == 'nickjr.com.br': + query['ep'] = 'c4b16088' + info_url = update_url_query( + 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed', query) + return self._get_videos_info_from_url(info_url, video_id) class NickDeIE(MTVServicesInfoExtractor): diff --git a/youtube_dl/extractor/nowtv.py b/youtube_dl/extractor/nowtv.py deleted file mode 100644 index e43b37136..000000000 --- a/youtube_dl/extractor/nowtv.py +++ /dev/null @@ -1,261 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - ExtractorError, - determine_ext, - int_or_none, - parse_iso8601, - parse_duration, - remove_start, -) - - -class NowTVBaseIE(InfoExtractor): - _VIDEO_FIELDS = ( - 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', - 'broadcastStartDate', 'seoUrl', 'duration', 'files', - 'format.defaultImage169Format', 'format.defaultImage169Logo') - - def _extract_video(self, info, display_id=None): - video_id = compat_str(info['id']) - - files = info['files'] - if not files: - if info.get('geoblocked', False): - raise ExtractorError( - 'Video %s is not available from your location due to geo restriction' % video_id, - expected=True) - if not info.get('free', True): - raise ExtractorError( - 'Video %s is not available for free' % video_id, expected=True) - - formats = [] - for item in files['items']: - if determine_ext(item['path']) != 'f4v': - continue - app, play_path = remove_start(item['path'], '/').split('/', 1) - formats.append({ - 'url': 'rtmpe://fms.rtl.de', - 'app': app, - 'play_path': 'mp4:%s' % play_path, - 'ext': 'flv', - 'page_url': 'http://rtlnow.rtl.de', - 'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf', - 'tbr': int_or_none(item.get('bitrate')), - }) - self._sort_formats(formats) - - title = info['title'] - description = info.get('articleLong') or info.get('articleShort') - timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') - duration = parse_duration(info.get('duration')) - - f = info.get('format', {}) - thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') - - return { - 'id': video_id, - 'display_id': display_id or info.get('seoUrl'), - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, - } - - -class NowTVIE(NowTVBaseIE): - _WORKING = False - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)' - - _TESTS = [{ - # rtl - 'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player', - 'info_dict': { - 'id': '203519', - 'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', - 'ext': 'flv', - 'title': 'Inka Bause stellt die neuen Bauern vor', - 'description': 'md5:e234e1ed6d63cf06be5c070442612e7e', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432580700, - 'upload_date': '20150525', - 'duration': 2786, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # rtl2 - 'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player', - 'info_dict': { - 'id': '203481', - 'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934', - 'ext': 'flv', - 'title': 'Berlin - Tag & Nacht (Folge 934)', - 'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432666800, - 'upload_date': '20150526', - 'duration': 2641, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # rtlnitro - 'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player', - 'info_dict': { - 'id': '165780', - 'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00', - 'ext': 'flv', - 'title': 'Hals- und Beinbruch', - 'description': 'md5:b50d248efffe244e6f56737f0911ca57', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432415400, - 'upload_date': '20150523', - 'duration': 2742, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # superrtl - 'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player', - 'info_dict': { - 'id': '99205', - 'display_id': 'medicopter-117/angst', - 'ext': 'flv', - 'title': 'Angst!', - 'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1222632900, - 'upload_date': '20080928', - 'duration': 3025, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # ntv - 'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player', - 'info_dict': { - 'id': '203521', - 'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch', - 'ext': 'flv', - 'title': 'Thema u.a.: Der erste Blick: Die Apple Watch', - 'description': 'md5:4312b6c9d839ffe7d8caf03865a531af', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432751700, - 'upload_date': '20150527', - 'duration': 1083, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - # vox - 'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player', - 'info_dict': { - 'id': '128953', - 'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel', - 'ext': 'flv', - 'title': "Büro-Fall / Chihuahua 'Joel'", - 'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d', - 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1432408200, - 'upload_date': '20150523', - 'duration': 3092, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - }, { - 'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.at/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview?return=/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player', - 'only_matching': True, - }, { - 'url': 'http://www.nowtv.de/rtl2/zuhause-im-glueck/jahr/2015/11/eine-erschuetternde-diagnose/player', - 'only_matching': True, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = '%s/%s' % (mobj.group('show_id'), mobj.group('id')) - - info = self._download_json( - 'https://api.nowtv.de/v3/movies/%s?fields=%s' - % (display_id, ','.join(self._VIDEO_FIELDS)), display_id) - - return self._extract_video(info, display_id) - - -class NowTVListIE(NowTVBaseIE): - _VALID_URL = r'https?://(?:www\.)?nowtv\.(?:de|at|ch)/(?:rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/list/(?P<id>[^?/#&]+)$' - - _SHOW_FIELDS = ('title', ) - _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) - - _TESTS = [{ - 'url': 'http://www.nowtv.at/rtl/stern-tv/list/aktuell', - 'info_dict': { - 'id': '17006', - 'title': 'stern TV - Aktuell', - }, - 'playlist_count': 1, - }, { - 'url': 'http://www.nowtv.at/rtl/das-supertalent/list/free-staffel-8', - 'info_dict': { - 'id': '20716', - 'title': 'Das Supertalent - FREE Staffel 8', - }, - 'playlist_count': 14, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - show_id = mobj.group('show_id') - season_id = mobj.group('id') - - fields = [] - fields.extend(self._SHOW_FIELDS) - fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) - fields.extend( - 'formatTabs.formatTabPages.container.movies.%s' % field - for field in self._VIDEO_FIELDS) - - list_info = self._download_json( - 'https://api.nowtv.de/v3/formats/seo?fields=%s&name=%s.php' - % (','.join(fields), show_id), - season_id) - - season = next( - season for season in list_info['formatTabs']['items'] - if season.get('seoheadline') == season_id) - - title = '%s - %s' % (list_info['title'], season['headline']) - - entries = [] - for container in season['formatTabPages']['items']: - for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []: - entries.append(self._extract_video(info)) - - return self.playlist_result( - entries, compat_str(season.get('id') or season_id), title) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index a99af12a4..d1eb3be25 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -112,6 +112,8 @@ class PhantomJSwrapper(object): return get_exe_version('phantomjs', version_re=r'([0-9.]+)') def __init__(self, extractor, required_version=None, timeout=10000): + self._TMP_FILES = {} + self.exe = check_executable('phantomjs', ['-v']) if not self.exe: raise ExtractorError('PhantomJS executable not found in PATH, ' @@ -130,7 +132,6 @@ class PhantomJSwrapper(object): self.options = { 'timeout': timeout, } - self._TMP_FILES = {} for name in self._TMP_FILE_NAMES: tmp = tempfile.NamedTemporaryFile(delete=False) tmp.close() @@ -140,7 +141,7 @@ class PhantomJSwrapper(object): for name in self._TMP_FILE_NAMES: try: os.remove(self._TMP_FILES[name].name) - except (IOError, OSError): + except (IOError, OSError, KeyError): pass def _save_cookies(self, url): @@ -242,7 +243,7 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' + _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -289,6 +290,9 @@ class OpenloadIE(InfoExtractor): }, { 'url': 'http://www.openload.link/f/KnG-kKZdcfY', 'only_matching': True, + }, { + 'url': 'https://oload.stream/f/KnG-kKZdcfY', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 4bf0aa786..597b11218 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -131,6 +131,13 @@ class PluralsightIE(PluralsightBaseIE): if BLOCKED in response: raise ExtractorError( 'Unable to login: %s' % BLOCKED, expected=True) + MUST_AGREE = 'To continue using Pluralsight, you must agree to' + if any(p in response for p in (MUST_AGREE, '>Disagree<', '>Agree<')): + raise ExtractorError( + 'Unable to login: %s some documents. Go to pluralsight.com, ' + 'log in and agree with what Pluralsight requires.' + % MUST_AGREE, expected=True) + raise ExtractorError('Unable to log in') def _get_subtitles(self, author, clip_id, lang, name, duration, video_id): diff --git a/youtube_dl/extractor/porncom.py b/youtube_dl/extractor/porncom.py index 8218c7d3b..60ade06da 100644 --- a/youtube_dl/extractor/porncom.py +++ b/youtube_dl/extractor/porncom.py @@ -77,12 +77,14 @@ class PornComIE(InfoExtractor): self._sort_formats(formats) view_count = str_to_int(self._search_regex( - r'class=["\']views["\'][^>]*><p>([\d,.]+)', webpage, + (r'Views:\s*</span>\s*<span>\s*([\d,.]+)', + r'class=["\']views["\'][^>]*><p>([\d,.]+)'), webpage, 'view count', fatal=False)) def extract_list(kind): s = self._search_regex( - r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize(), + (r'(?s)%s:\s*</span>\s*<span>(.+?)</span>' % kind.capitalize(), + r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize()), webpage, kind, fatal=False) return re.findall(r'<a[^>]+>([^<]+)</a>', s or '') diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index 5bf64a56b..d22311031 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -17,6 +17,7 @@ from ..utils import ( parse_duration, strip_or_none, try_get, + unescapeHTML, unified_strdate, unified_timestamp, update_url_query, @@ -249,6 +250,41 @@ class RaiPlayLiveIE(RaiBaseIE): } +class RaiPlayPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?raiplay\.it/programmi/(?P<id>[^/?#&]+)' + _TESTS = [{ + 'url': 'http://www.raiplay.it/programmi/nondirloalmiocapo/', + 'info_dict': { + 'id': 'nondirloalmiocapo', + 'title': 'Non dirlo al mio capo', + 'description': 'md5:9f3d603b2947c1c7abb098f3b14fac86', + }, + 'playlist_mincount': 12, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + title = self._html_search_meta( + ('programma', 'nomeProgramma'), webpage, 'title') + description = unescapeHTML(self._html_search_meta( + ('description', 'og:description'), webpage, 'description')) + print(description) + + entries = [] + for mobj in re.finditer( + r'<a\b[^>]+\bhref=(["\'])(?P<path>/raiplay/video/.+?)\1', + webpage): + video_url = urljoin(url, mobj.group('path')) + entries.append(self.url_result( + video_url, ie=RaiPlayIE.ie_key(), + video_id=RaiPlayIE._match_id(video_url))) + + return self.playlist_result(entries, playlist_id, title, description) + + class RaiIE(RaiBaseIE): _VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE _TESTS = [{ diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py index b446a02ba..4023aeef8 100644 --- a/youtube_dl/extractor/scrippsnetworks.py +++ b/youtube_dl/extractor/scrippsnetworks.py @@ -1,13 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import datetime import json import hashlib -import hmac import re -from .common import InfoExtractor +from .aws import AWSIE from .anvato import AnvatoIE from ..utils import ( smuggle_url, @@ -16,7 +14,7 @@ from ..utils import ( ) -class ScrippsNetworksWatchIE(InfoExtractor): +class ScrippsNetworksWatchIE(AWSIE): IE_NAME = 'scrippsnetworks:watch' _VALID_URL = r'''(?x) https?:// @@ -64,44 +62,27 @@ class ScrippsNetworksWatchIE(InfoExtractor): 'travelchannel': 'trav', 'geniuskitchen': 'genius', } - _SNI_HOST = 'web.api.video.snidigital.com' - _AWS_REGION = 'us-east-1' - _AWS_IDENTITY_ID_JSON = json.dumps({ - 'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % _AWS_REGION - }) - _AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback' _AWS_API_KEY = 'E7wSQmq0qK6xPrF13WmzKiHo4BQ7tip4pQcSXVl1' - _AWS_SERVICE = 'execute-api' - _AWS_REQUEST = 'aws4_request' - _AWS_SIGNED_HEADERS = ';'.join([ - 'host', 'x-amz-date', 'x-amz-security-token', 'x-api-key']) - _AWS_CANONICAL_REQUEST_TEMPLATE = '''GET -%(uri)s - -host:%(host)s -x-amz-date:%(date)s -x-amz-security-token:%(token)s -x-api-key:%(key)s + _AWS_PROXY_HOST = 'web.api.video.snidigital.com' -%(signed_headers)s -%(payload_hash)s''' + _AWS_USER_AGENT = 'aws-sdk-js/2.80.0 callback' def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) site_id, video_id = mobj.group('site', 'id') - def aws_hash(s): - return hashlib.sha256(s.encode('utf-8')).hexdigest() - + aws_identity_id_json = json.dumps({ + 'IdentityId': '%s:7655847c-0ae7-4d9b-80d6-56c062927eb3' % self._AWS_REGION + }).encode('utf-8') token = self._download_json( - 'https://cognito-identity.us-east-1.amazonaws.com/', video_id, - data=self._AWS_IDENTITY_ID_JSON.encode('utf-8'), + 'https://cognito-identity.%s.amazonaws.com/' % self._AWS_REGION, video_id, + data=aws_identity_id_json, headers={ 'Accept': '*/*', 'Content-Type': 'application/x-amz-json-1.1', 'Referer': url, - 'X-Amz-Content-Sha256': aws_hash(self._AWS_IDENTITY_ID_JSON), + 'X-Amz-Content-Sha256': hashlib.sha256(aws_identity_id_json).hexdigest(), 'X-Amz-Target': 'AWSCognitoIdentityService.GetOpenIdToken', 'X-Amz-User-Agent': self._AWS_USER_AGENT, })['Token'] @@ -124,64 +105,12 @@ x-api-key:%(key)s sts, './/{https://sts.amazonaws.com/doc/2011-06-15/}%s' % key, fatal=True) - access_key_id = get('AccessKeyId') - secret_access_key = get('SecretAccessKey') - session_token = get('SessionToken') - - # Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html - uri = '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id) - datetime_now = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ') - date = datetime_now[:8] - canonical_string = self._AWS_CANONICAL_REQUEST_TEMPLATE % { - 'uri': uri, - 'host': self._SNI_HOST, - 'date': datetime_now, - 'token': session_token, - 'key': self._AWS_API_KEY, - 'signed_headers': self._AWS_SIGNED_HEADERS, - 'payload_hash': aws_hash(''), - } - - # Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html - credential_string = '/'.join([date, self._AWS_REGION, self._AWS_SERVICE, self._AWS_REQUEST]) - string_to_sign = '\n'.join([ - 'AWS4-HMAC-SHA256', datetime_now, credential_string, - aws_hash(canonical_string)]) - - # Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html - def aws_hmac(key, msg): - return hmac.new(key, msg.encode('utf-8'), hashlib.sha256) - - def aws_hmac_digest(key, msg): - return aws_hmac(key, msg).digest() - - def aws_hmac_hexdigest(key, msg): - return aws_hmac(key, msg).hexdigest() - - k_secret = 'AWS4' + secret_access_key - k_date = aws_hmac_digest(k_secret.encode('utf-8'), date) - k_region = aws_hmac_digest(k_date, self._AWS_REGION) - k_service = aws_hmac_digest(k_region, self._AWS_SERVICE) - k_signing = aws_hmac_digest(k_service, self._AWS_REQUEST) - - signature = aws_hmac_hexdigest(k_signing, string_to_sign) - - auth_header = ', '.join([ - 'AWS4-HMAC-SHA256 Credential=%s' % '/'.join( - [access_key_id, date, self._AWS_REGION, self._AWS_SERVICE, self._AWS_REQUEST]), - 'SignedHeaders=%s' % self._AWS_SIGNED_HEADERS, - 'Signature=%s' % signature, - ]) - - mcp_id = self._download_json( - 'https://%s%s' % (self._SNI_HOST, uri), video_id, headers={ - 'Accept': '*/*', - 'Referer': url, - 'Authorization': auth_header, - 'X-Amz-Date': datetime_now, - 'X-Amz-Security-Token': session_token, - 'X-Api-Key': self._AWS_API_KEY, - })['results'][0]['mcpId'] + mcp_id = self._aws_execute_api({ + 'uri': '/1/web/brands/%s/episodes/scrid/%s' % (self._SNI_TABLE[site_id], video_id), + 'access_key': get('AccessKeyId'), + 'secret_key': get('SecretAccessKey'), + 'session_token': get('SessionToken'), + }, video_id)['results'][0]['mcpId'] return self.url_result( smuggle_url( diff --git a/youtube_dl/extractor/sevenplus.py b/youtube_dl/extractor/sevenplus.py new file mode 100644 index 000000000..9792f820a --- /dev/null +++ b/youtube_dl/extractor/sevenplus.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .brightcove import BrightcoveNewIE +from ..utils import update_url_query + + +class SevenPlusIE(BrightcoveNewIE): + IE_NAME = '7plus' + _VALID_URL = r'https?://(?:www\.)?7plus\.com\.au/(?P<path>[^?]+\?.*?\bepisode-id=(?P<id>[^&#]+))' + _TESTS = [{ + 'url': 'https://7plus.com.au/BEAT?episode-id=BEAT-001', + 'info_dict': { + 'id': 'BEAT-001', + 'ext': 'mp4', + 'title': 'S1 E1 - Help / Lucy In The Sky With Diamonds', + 'description': 'md5:37718bea20a8eedaca7f7361af566131', + 'uploader_id': '5303576322001', + 'upload_date': '20171031', + 'timestamp': 1509440068, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + } + }, { + 'url': 'https://7plus.com.au/UUUU?episode-id=AUMS43-001', + 'only_matching': True, + }] + + def _real_extract(self, url): + path, episode_id = re.match(self._VALID_URL, url).groups() + + media = self._download_json( + 'https://videoservice.swm.digital/playback', episode_id, query={ + 'appId': '7plus', + 'deviceType': 'web', + 'platformType': 'web', + 'accountId': 5303576322001, + 'referenceId': 'ref:' + episode_id, + 'deliveryId': 'csai', + 'videoType': 'vod', + })['media'] + + for source in media.get('sources', {}): + src = source.get('src') + if not src: + continue + source['src'] = update_url_query(src, {'rule': ''}) + + info = self._parse_brightcove_metadata(media, episode_id) + + content = self._download_json( + 'https://component-cdn.swm.digital/content/' + path, + episode_id, headers={ + 'market-id': 4, + }, fatal=False) or {} + for item in content.get('items', {}): + if item.get('componentData', {}).get('componentType') == 'infoPanel': + for src_key, dst_key in [('title', 'title'), ('shortSynopsis', 'description')]: + value = item.get(src_key) + if value: + info[dst_key] = value + + return info diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py index 374f7faf9..5c2a6206b 100644 --- a/youtube_dl/extractor/shahid.py +++ b/youtube_dl/extractor/shahid.py @@ -1,22 +1,53 @@ # coding: utf-8 from __future__ import unicode_literals -import re import json +import math +import re -from .common import InfoExtractor +from .aws import AWSIE from ..compat import compat_HTTPError from ..utils import ( + clean_html, ExtractorError, + InAdvancePagedList, int_or_none, parse_iso8601, str_or_none, urlencode_postdata, - clean_html, ) -class ShahidIE(InfoExtractor): +class ShahidBaseIE(AWSIE): + _AWS_PROXY_HOST = 'api2.shahid.net' + _AWS_API_KEY = '2RRtuMHx95aNI1Kvtn2rChEuwsCogUd4samGPjLh' + + def _handle_error(self, e): + fail_data = self._parse_json( + e.cause.read().decode('utf-8'), None, fatal=False) + if fail_data: + faults = fail_data.get('faults', []) + faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')]) + if faults_message: + raise ExtractorError(faults_message, expected=True) + + def _call_api(self, path, video_id, request=None): + query = {} + if request: + query['request'] = json.dumps(request) + try: + return self._aws_execute_api({ + 'uri': '/proxy/v2/' + path, + 'access_key': 'AKIAI6X4TYCIXM2B7MUQ', + 'secret_key': '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', + }, video_id, query) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError): + self._handle_error(e) + raise + + +class ShahidIE(ShahidBaseIE): _NETRC_MACHINE = 'shahid' _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)' _TESTS = [{ @@ -41,34 +72,25 @@ class ShahidIE(InfoExtractor): 'only_matching': True }] - def _api2_request(self, *args, **kwargs): - try: - return self._download_json(*args, **kwargs) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError): - fail_data = self._parse_json( - e.cause.read().decode('utf-8'), None, fatal=False) - if fail_data: - faults = fail_data.get('faults', []) - faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')]) - if faults_message: - raise ExtractorError(faults_message, expected=True) - raise - def _real_initialize(self): email, password = self._get_login_info() if email is None: return - user_data = self._api2_request( - 'https://shahid.mbc.net/wd/service/users/login', - None, 'Logging in', data=json.dumps({ - 'email': email, - 'password': password, - 'basic': 'false', - }).encode('utf-8'), headers={ - 'Content-Type': 'application/json; charset=UTF-8', - })['user'] + try: + user_data = self._download_json( + 'https://shahid.mbc.net/wd/service/users/login', + None, 'Logging in', data=json.dumps({ + 'email': email, + 'password': password, + 'basic': 'false', + }).encode('utf-8'), headers={ + 'Content-Type': 'application/json; charset=UTF-8', + })['user'] + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError): + self._handle_error(e) + raise self._download_webpage( 'https://shahid.mbc.net/populateContext', @@ -81,25 +103,13 @@ class ShahidIE(InfoExtractor): 'sessionId': user_data['sessionId'], })) - def _get_api_data(self, response): - data = response.get('data', {}) - - error = data.get('error') - if error: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())), - expected=True) - - return data - def _real_extract(self, url): page_type, video_id = re.match(self._VALID_URL, url).groups() if page_type == 'clip': page_type = 'episode' - playout = self._api2_request( - 'https://api2.shahid.net/proxy/v2/playout/url/' + video_id, - video_id, 'Downloading player JSON')['playout'] + playout = self._call_api( + 'playout/url/' + video_id, video_id)['playout'] if playout.get('drm'): raise ExtractorError('This video is DRM protected.', expected=True) @@ -107,13 +117,27 @@ class ShahidIE(InfoExtractor): formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4') self._sort_formats(formats) - video = self._get_api_data(self._download_json( + # video = self._call_api( + # 'product/id', video_id, { + # 'id': video_id, + # 'productType': 'ASSET', + # 'productSubType': page_type.upper() + # })['productModel'] + + response = self._download_json( 'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id), video_id, 'Downloading video JSON', query={ 'apiKey': 'sh@hid0nlin3', 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=', - }))[page_type] + }) + data = response.get('data', {}) + error = data.get('error') + if error: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())), + expected=True) + video = data[page_type] title = video['title'] categories = [ category['name'] @@ -135,3 +159,57 @@ class ShahidIE(InfoExtractor): 'episode_id': video_id, 'formats': formats, } + + +class ShahidShowIE(ShahidBaseIE): + _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:show|serie)s/[^/]+/(?:show|series)-(?P<id>\d+)' + _TESTS = [{ + 'url': 'https://shahid.mbc.net/ar/shows/%D8%B1%D8%A7%D9%85%D8%B2-%D9%82%D8%B1%D8%B4-%D8%A7%D9%84%D8%A8%D8%AD%D8%B1/show-79187', + 'info_dict': { + 'id': '79187', + 'title': 'رامز قرش البحر', + 'description': 'md5:c88fa7e0f02b0abd39d417aee0d046ff', + }, + 'playlist_mincount': 32, + }, { + 'url': 'https://shahid.mbc.net/ar/series/How-to-live-Longer-(The-Big-Think)/series-291861', + 'only_matching': True + }] + _PAGE_SIZE = 30 + + def _real_extract(self, url): + show_id = self._match_id(url) + + product = self._call_api( + 'playableAsset', show_id, {'showId': show_id})['productModel'] + playlist = product['playlist'] + playlist_id = playlist['id'] + show = product.get('show', {}) + + def page_func(page_num): + playlist = self._call_api( + 'product/playlist', show_id, { + 'playListId': playlist_id, + 'pageNumber': page_num, + 'pageSize': 30, + 'sorts': [{ + 'order': 'DESC', + 'type': 'SORTDATE' + }], + }) + for product in playlist.get('productList', {}).get('products', []): + product_url = product.get('productUrl', []).get('url') + if not product_url: + continue + yield self.url_result( + product_url, 'Shahid', + str_or_none(product.get('id')), + product.get('title')) + + entries = InAdvancePagedList( + page_func, + math.ceil(playlist['count'] / self._PAGE_SIZE), + self._PAGE_SIZE) + + return self.playlist_result( + entries, show_id, show.get('title'), show.get('description')) diff --git a/youtube_dl/extractor/sonyliv.py b/youtube_dl/extractor/sonyliv.py index accd112aa..c3078e285 100644 --- a/youtube_dl/extractor/sonyliv.py +++ b/youtube_dl/extractor/sonyliv.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import smuggle_url class SonyLIVIE(InfoExtractor): @@ -10,12 +11,12 @@ class SonyLIVIE(InfoExtractor): 'url': "http://www.sonyliv.com/details/episodes/5024612095001/Ep.-1---Achaari-Cheese-Toast---Bachelor's-Delight", 'info_dict': { 'title': "Ep. 1 - Achaari Cheese Toast - Bachelor's Delight", - 'id': '5024612095001', + 'id': 'ref:5024612095001', 'ext': 'mp4', - 'upload_date': '20160707', + 'upload_date': '20170923', 'description': 'md5:7f28509a148d5be9d0782b4d5106410d', - 'uploader_id': '4338955589001', - 'timestamp': 1467870968, + 'uploader_id': '5182475815001', + 'timestamp': 1506200547, }, 'params': { 'skip_download': True, @@ -26,9 +27,11 @@ class SonyLIVIE(InfoExtractor): 'only_matching': True, }] - BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s' + # BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4338955589001/default_default/index.html?videoId=%s' + BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5182475815001/default_default/index.html?videoId=ref:%s' def _real_extract(self, url): brightcove_id = self._match_id(url) return self.url_result( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) + smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['IN']}), + 'BrightcoveNew', brightcove_id) diff --git a/youtube_dl/extractor/stretchinternet.py b/youtube_dl/extractor/stretchinternet.py new file mode 100644 index 000000000..ae2ac1b42 --- /dev/null +++ b/youtube_dl/extractor/stretchinternet.py @@ -0,0 +1,48 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none + + +class StretchInternetIE(InfoExtractor): + _VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/portal\.htm\?.*?\beventId=(?P<id>\d+)' + _TEST = { + 'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=313900&streamType=video', + 'info_dict': { + 'id': '313900', + 'ext': 'mp4', + 'title': 'Augustana (S.D.) Baseball vs University of Mary', + 'description': 'md5:7578478614aae3bdd4a90f578f787438', + 'timestamp': 1490468400, + 'upload_date': '20170325', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + stream = self._download_json( + 'https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s' + % video_id, video_id) + + video_url = 'https://%s' % stream['source'] + + event = self._download_json( + 'https://neo-client.stretchinternet.com/portal-ws/getEvent.json', + video_id, query={ + 'clientID': 99997, + 'eventID': video_id, + 'token': 'asdf', + })['event'] + + title = event.get('title') or event['mobileTitle'] + description = event.get('customText') + timestamp = int_or_none(event.get('longtime')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'url': video_url, + } diff --git a/youtube_dl/extractor/tbs.py b/youtube_dl/extractor/tbs.py index e9474533f..eab22c38f 100644 --- a/youtube_dl/extractor/tbs.py +++ b/youtube_dl/extractor/tbs.py @@ -4,58 +4,109 @@ from __future__ import unicode_literals import re from .turner import TurnerBaseIE -from ..utils import extract_attributes +from ..utils import ( + float_or_none, + int_or_none, + strip_or_none, +) class TBSIE(TurnerBaseIE): - # https://github.com/rg3/youtube-dl/issues/13658 - _WORKING = False - - _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com/videos/(?:[^/]+/)+(?P<id>[^/?#]+)\.html' + _VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com/(?:movies|shows/[^/]+/(?:clips|season-\d+/episode-\d+))/(?P<id>[^/?#]+)' _TESTS = [{ - 'url': 'http://www.tbs.com/videos/people-of-earth/season-1/extras/2007318/theatrical-trailer.html', - 'md5': '9e61d680e2285066ade7199e6408b2ee', + 'url': 'http://www.tntdrama.com/shows/the-alienist/clips/monster', 'info_dict': { - 'id': '2007318', + 'id': '8d384cde33b89f3a43ce5329de42903ed5099887', 'ext': 'mp4', - 'title': 'Theatrical Trailer', - 'description': 'Catch the latest comedy from TBS, People of Earth, premiering Halloween night--Monday, October 31, at 9/8c.', + 'title': 'Monster', + 'description': 'Get a first look at the theatrical trailer for TNT’s highly anticipated new psychological thriller The Alienist, which premieres January 22 on TNT.', + 'timestamp': 1508175329, + 'upload_date': '20171016', }, - 'skip': 'TBS videos are deleted after a while', + 'params': { + # m3u8 download + 'skip_download': True, + } }, { - 'url': 'http://www.tntdrama.com/videos/good-behavior/season-1/extras/1538823/you-better-run.html', - 'md5': 'ce53c6ead5e9f3280b4ad2031a6fab56', - 'info_dict': { - 'id': '1538823', - 'ext': 'mp4', - 'title': 'You Better Run', - 'description': 'Letty Raines must figure out what she\'s running toward while running away from her past. Good Behavior premieres November 15 at 9/8c.', - }, - 'skip': 'TBS videos are deleted after a while', + 'url': 'http://www.tbs.com/shows/search-party/season-1/episode-1/explicit-the-mysterious-disappearance-of-the-girl-no-one-knew', + 'only_matching': True, + }, { + 'url': 'http://www.tntdrama.com/movies/star-wars-a-new-hope', + 'only_matching': True, }] def _real_extract(self, url): - domain, display_id = re.match(self._VALID_URL, url).groups() - site = domain[:3] + site, display_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) - video_params = extract_attributes(self._search_regex(r'(<[^>]+id="page-video"[^>]*>)', webpage, 'video params')) - query = None - clip_id = video_params.get('clipid') - if clip_id: - query = 'id=' + clip_id - else: - query = 'titleId=' + video_params['titleid'] - return self._extract_cvp_info( - 'http://www.%s.com/service/cvpXml?%s' % (domain, query), display_id, { - 'default': { - 'media_src': 'http://ht.cdn.turner.com/%s/big' % site, - }, - 'secure': { - 'media_src': 'http://androidhls-secure.cdn.turner.com/%s/big' % site, - 'tokenizer_src': 'http://www.%s.com/video/processors/services/token_ipadAdobe.do' % domain, - }, - }, { - 'url': url, - 'site_name': site.upper(), - 'auth_required': video_params.get('isAuthRequired') != 'false', - }) + video_data = self._parse_json(self._search_regex( + r'<script[^>]+?data-drupal-selector="drupal-settings-json"[^>]*?>({.+?})</script>', + webpage, 'drupal setting'), display_id)['turner_playlist'][0] + + media_id = video_data['mediaID'] + title = video_data['title'] + + streams_data = self._download_json( + 'http://medium.ngtv.io/media/%s/tv' % media_id, + media_id)['media']['tv'] + duration = None + chapters = [] + formats = [] + for supported_type in ('unprotected', 'bulkaes'): + stream_data = streams_data.get(supported_type, {}) + m3u8_url = stream_data.get('secureUrl') or stream_data.get('url') + if not m3u8_url: + continue + if stream_data.get('playlistProtection') == 'spe': + m3u8_url = self._add_akamai_spe_token( + 'http://www.%s.com/service/token_spe' % site, + m3u8_url, media_id, { + 'url': url, + 'site_name': site[:3].upper(), + 'auth_required': video_data.get('authRequired') == '1', + }) + formats.extend(self._extract_m3u8_formats( + m3u8_url, media_id, 'mp4', m3u8_id='hls', fatal=False)) + + duration = float_or_none(stream_data.get('totalRuntime') or video_data.get('duration')) + + if not chapters: + for chapter in stream_data.get('contentSegments', []): + start_time = float_or_none(chapter.get('start')) + duration = float_or_none(chapter.get('duration')) + if start_time is None or duration is None: + continue + chapters.append({ + 'start_time': start_time, + 'end_time': start_time + duration, + }) + self._sort_formats(formats) + + thumbnails = [] + for image_id, image in video_data.get('images', {}).items(): + image_url = image.get('url') + if not image_url or image.get('type') != 'video': + continue + i = { + 'id': image_id, + 'url': image_url, + } + mobj = re.search(r'(\d+)x(\d+)', image_url) + if mobj: + i.update({ + 'width': int(mobj.group(1)), + 'height': int(mobj.group(2)), + }) + thumbnails.append(i) + + return { + 'id': media_id, + 'title': title, + 'description': strip_or_none(video_data.get('descriptionNoTags') or video_data.get('shortDescriptionNoTags')), + 'duration': duration, + 'timestamp': int_or_none(video_data.get('created')), + 'season_number': int_or_none(video_data.get('season')), + 'episode_number': int_or_none(video_data.get('episode')), + 'cahpters': chapters, + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/toutv.py b/youtube_dl/extractor/toutv.py index 17c0adc15..2e7876cc5 100644 --- a/youtube_dl/extractor/toutv.py +++ b/youtube_dl/extractor/toutv.py @@ -16,7 +16,7 @@ from ..utils import ( class TouTvIE(InfoExtractor): _NETRC_MACHINE = 'toutv' IE_NAME = 'tou.tv' - _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+E[0-9]+)?)' + _VALID_URL = r'https?://ici\.tou\.tv/(?P<id>[a-zA-Z0-9_-]+(?:/S[0-9]+[EC][0-9]+)?)' _access_token = None _claims = None @@ -37,6 +37,9 @@ class TouTvIE(InfoExtractor): }, { 'url': 'http://ici.tou.tv/hackers', 'only_matching': True, + }, { + 'url': 'https://ici.tou.tv/l-age-adulte/S01C501', + 'only_matching': True, }] def _real_initialize(self): diff --git a/youtube_dl/extractor/turner.py b/youtube_dl/extractor/turner.py index efeb677ee..e73b64aeb 100644 --- a/youtube_dl/extractor/turner.py +++ b/youtube_dl/extractor/turner.py @@ -18,9 +18,32 @@ from ..utils import ( class TurnerBaseIE(AdobePassIE): + _AKAMAI_SPE_TOKEN_CACHE = {} + def _extract_timestamp(self, video_data): return int_or_none(xpath_attr(video_data, 'dateCreated', 'uts')) + def _add_akamai_spe_token(self, tokenizer_src, video_url, content_id, ap_data): + secure_path = self._search_regex(r'https?://[^/]+(.+/)', video_url, 'secure path') + '*' + token = self._AKAMAI_SPE_TOKEN_CACHE.get(secure_path) + if not token: + query = { + 'path': secure_path, + 'videoId': content_id, + } + if ap_data.get('auth_required'): + query['accessToken'] = self._extract_mvpd_auth(ap_data['url'], content_id, ap_data['site_name'], ap_data['site_name']) + auth = self._download_xml( + tokenizer_src, content_id, query=query) + error_msg = xpath_text(auth, 'error/msg') + if error_msg: + raise ExtractorError(error_msg, expected=True) + token = xpath_text(auth, 'token') + if not token: + return video_url + self._AKAMAI_SPE_TOKEN_CACHE[secure_path] = token + return video_url + '?hdnea=' + token + def _extract_cvp_info(self, data_src, video_id, path_data={}, ap_data={}): video_data = self._download_xml(data_src, video_id) video_id = video_data.attrib['id'] @@ -33,7 +56,6 @@ class TurnerBaseIE(AdobePassIE): # rtmp_src = splited_rtmp_src[1] # aifp = xpath_text(video_data, 'akamai/aifp', default='') - tokens = {} urls = [] formats = [] rex = re.compile( @@ -67,26 +89,10 @@ class TurnerBaseIE(AdobePassIE): secure_path_data = path_data.get('secure') if not secure_path_data: continue - video_url = secure_path_data['media_src'] + video_url - secure_path = self._search_regex(r'https?://[^/]+(.+/)', video_url, 'secure path') + '*' - token = tokens.get(secure_path) - if not token: - query = { - 'path': secure_path, - 'videoId': content_id, - } - if ap_data.get('auth_required'): - query['accessToken'] = self._extract_mvpd_auth(ap_data['url'], video_id, ap_data['site_name'], ap_data['site_name']) - auth = self._download_xml( - secure_path_data['tokenizer_src'], video_id, query=query) - error_msg = xpath_text(auth, 'error/msg') - if error_msg: - raise ExtractorError(error_msg, expected=True) - token = xpath_text(auth, 'token') - if not token: - continue - tokens[secure_path] = token - video_url = video_url + '?hdnea=' + token + video_url = self._add_akamai_spe_token( + secure_path_data['tokenizer_src'], + secure_path_data['media_src'] + video_url, + content_id, ap_data) elif not re.match('https?://', video_url): base_path_data = path_data.get(ext, path_data.get('default', {})) media_src = base_path_data.get('media_src') diff --git a/youtube_dl/extractor/tvnow.py b/youtube_dl/extractor/tvnow.py new file mode 100644 index 000000000..e2169f2bc --- /dev/null +++ b/youtube_dl/extractor/tvnow.py @@ -0,0 +1,175 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + ExtractorError, + parse_iso8601, + parse_duration, + update_url_query, +) + + +class TVNowBaseIE(InfoExtractor): + _VIDEO_FIELDS = ( + 'id', 'title', 'free', 'geoblocked', 'articleLong', 'articleShort', + 'broadcastStartDate', 'isDrm', 'duration', 'manifest.dashclear', + 'format.defaultImage169Format', 'format.defaultImage169Logo') + + def _call_api(self, path, video_id, query): + return self._download_json( + 'https://api.tvnow.de/v3/' + path, + video_id, query=query) + + def _extract_video(self, info, display_id): + video_id = compat_str(info['id']) + title = info['title'] + + mpd_url = info['manifest']['dashclear'] + if not mpd_url: + if info.get('isDrm'): + raise ExtractorError( + 'Video %s is DRM protected' % video_id, expected=True) + if info.get('geoblocked'): + raise ExtractorError( + 'Video %s is not available from your location due to geo restriction' % video_id, + expected=True) + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + + mpd_url = update_url_query(mpd_url, {'filter': ''}) + formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False) + formats.extend(self._extract_ism_formats( + mpd_url.replace('dash.', 'hss.').replace('/.mpd', '/Manifest'), + video_id, ism_id='mss', fatal=False)) + formats.extend(self._extract_m3u8_formats( + mpd_url.replace('dash.', 'hls.').replace('/.mpd', '/.m3u8'), + video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + self._sort_formats(formats) + + description = info.get('articleLong') or info.get('articleShort') + timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') + duration = parse_duration(info.get('duration')) + + f = info.get('format', {}) + thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } + + +class TVNowIE(TVNowBaseIE): + _VALID_URL = r'https?://(?:www\.)?tvnow\.(?:de|at|ch)/(?:rtl(?:2|plus)?|nitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/(?:(?:list/[^/]+|jahr/\d{4}/\d{1,2})/)?(?P<id>[^/]+)/(?:player|preview)' + + _TESTS = [{ + # rtl + 'url': 'https://www.tvnow.de/rtl/alarm-fuer-cobra-11/freier-fall/player?return=/rtl', + 'info_dict': { + 'id': '385314', + 'display_id': 'alarm-fuer-cobra-11/freier-fall', + 'ext': 'mp4', + 'title': 'Freier Fall', + 'description': 'md5:8c2d8f727261adf7e0dc18366124ca02', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1512677700, + 'upload_date': '20171207', + 'duration': 2862.0, + }, + }, { + # rtl2 + 'url': 'https://www.tvnow.de/rtl2/armes-deutschland/episode-0008/player', + 'only_matching': 'True', + }, { + # rtlnitro + 'url': 'https://www.tvnow.de/nitro/alarm-fuer-cobra-11-die-autobahnpolizei/auf-eigene-faust-pilot/player', + 'only_matching': 'True', + }, { + # superrtl + 'url': 'https://www.tvnow.de/superrtl/die-lustigsten-schlamassel-der-welt/u-a-ketchup-effekt/player', + 'only_matching': 'True', + }, { + # ntv + 'url': 'https://www.tvnow.de/ntv/startup-news/goetter-in-weiss/player', + 'only_matching': 'True', + }, { + # vox + 'url': 'https://www.tvnow.de/vox/auto-mobil/neues-vom-automobilmarkt-2017-11-19-17-00-00/player', + 'only_matching': 'True', + }, { + # rtlplus + 'url': 'https://www.tvnow.de/rtlplus/op-ruft-dr-bruckner/die-vernaehte-frau/player', + 'only_matching': 'True', + }] + + def _real_extract(self, url): + display_id = '%s/%s' % re.match(self._VALID_URL, url).groups() + + info = self._call_api( + 'movies/' + display_id, display_id, query={ + 'fields': ','.join(self._VIDEO_FIELDS), + }) + + return self._extract_video(info, display_id) + + +class TVNowListIE(TVNowBaseIE): + _VALID_URL = r'(?P<base_url>https?://(?:www\.)?tvnow\.(?:de|at|ch)/(?:rtl(?:2|plus)?|nitro|superrtl|ntv|vox)/(?P<show_id>[^/]+)/)list/(?P<id>[^?/#&]+)$' + + _SHOW_FIELDS = ('title', ) + _SEASON_FIELDS = ('id', 'headline', 'seoheadline', ) + _VIDEO_FIELDS = ('id', 'headline', 'seoUrl', ) + + _TESTS = [{ + 'url': 'https://www.tvnow.de/rtl/30-minuten-deutschland/list/aktuell', + 'info_dict': { + 'id': '28296', + 'title': '30 Minuten Deutschland - Aktuell', + }, + 'playlist_mincount': 1, + }] + + def _real_extract(self, url): + base_url, show_id, season_id = re.match(self._VALID_URL, url).groups() + + fields = [] + fields.extend(self._SHOW_FIELDS) + fields.extend('formatTabs.%s' % field for field in self._SEASON_FIELDS) + fields.extend( + 'formatTabs.formatTabPages.container.movies.%s' % field + for field in self._VIDEO_FIELDS) + + list_info = self._call_api( + 'formats/seo', season_id, query={ + 'fields': ','.join(fields), + 'name': show_id + '.php' + }) + + season = next( + season for season in list_info['formatTabs']['items'] + if season.get('seoheadline') == season_id) + + title = '%s - %s' % (list_info['title'], season['headline']) + + entries = [] + for container in season['formatTabPages']['items']: + for info in ((container.get('container') or {}).get('movies') or {}).get('items') or []: + seo_url = info.get('seoUrl') + if not seo_url: + continue + entries.append(self.url_result( + base_url + seo_url + '/player', 'TVNow', info.get('id'))) + + return self.playlist_result( + entries, compat_str(season.get('id') or season_id), title) diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py index 1b0b96371..d7e425041 100644 --- a/youtube_dl/extractor/twitter.py +++ b/youtube_dl/extractor/twitter.py @@ -43,7 +43,7 @@ class TwitterBaseIE(InfoExtractor): class TwitterCardIE(TwitterBaseIE): IE_NAME = 'twitter:card' - _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?P<path>cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)' _TESTS = [ { 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889', @@ -51,11 +51,10 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '560070183650213889', 'ext': 'mp4', - 'title': 'Twitter Card', + 'title': 'Twitter web player', 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 30.033, }, - 'skip': 'Video gone', }, { 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768', @@ -63,11 +62,9 @@ class TwitterCardIE(TwitterBaseIE): 'info_dict': { 'id': '623160978427936768', 'ext': 'mp4', - 'title': 'Twitter Card', - 'thumbnail': r're:^https?://.*\.jpg', - 'duration': 80.155, + 'title': 'Twitter web player', + 'thumbnail': r're:^https?://.*(?:\bformat=|\.)jpg', }, - 'skip': 'Video gone', }, { 'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977', @@ -120,15 +117,15 @@ class TwitterCardIE(TwitterBaseIE): elif media_url.endswith('.mpd'): formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash')) else: - vbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000) + tbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000) a_format = { 'url': media_url, - 'format_id': 'http-%d' % vbr if vbr else 'http', - 'vbr': vbr, + 'format_id': 'http-%d' % tbr if tbr else 'http', + 'tbr': tbr, } # Reported bitRate may be zero - if not a_format['vbr']: - del a_format['vbr'] + if not a_format['tbr']: + del a_format['tbr'] self._search_dimensions_in_video_url(a_format, media_url) @@ -150,79 +147,83 @@ class TwitterCardIE(TwitterBaseIE): bearer_token = self._search_regex( r'BEARER_TOKEN\s*:\s*"([^"]+)"', main_script, 'bearer token') - guest_token = self._search_regex( - r'document\.cookie\s*=\s*decodeURIComponent\("gt=(\d+)', - webpage, 'guest token') + # https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id api_data = self._download_json( - 'https://api.twitter.com/2/timeline/conversation/%s.json' % video_id, - video_id, 'Downloading mobile API data', + 'https://api.twitter.com/1.1/statuses/show/%s.json' % video_id, + video_id, 'Downloading API data', headers={ 'Authorization': 'Bearer ' + bearer_token, - 'x-guest-token': guest_token, }) - media_info = try_get(api_data, lambda o: o['globalObjects']['tweets'][video_id] - ['extended_entities']['media'][0]['video_info']) or {} + media_info = try_get(api_data, lambda o: o['extended_entities']['media'][0]['video_info']) or {} return self._parse_media_info(media_info, video_id) def _real_extract(self, url): - video_id = self._match_id(url) + path, video_id = re.search(self._VALID_URL, url).groups() config = None formats = [] duration = None - webpage = self._download_webpage(url, video_id) + urls = [url] + if path.startswith('cards/'): + urls.append('https://twitter.com/i/videos/' + video_id) - iframe_url = self._html_search_regex( - r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', - webpage, 'video iframe', default=None) - if iframe_url: - return self.url_result(iframe_url) + for u in urls: + webpage = self._download_webpage(u, video_id) - config = self._parse_json(self._html_search_regex( - r'data-(?:player-)?config="([^"]+)"', webpage, - 'data player config', default='{}'), - video_id) + iframe_url = self._html_search_regex( + r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"', + webpage, 'video iframe', default=None) + if iframe_url: + return self.url_result(iframe_url) - if config.get('source_type') == 'vine': - return self.url_result(config['player_url'], 'Vine') + config = self._parse_json(self._html_search_regex( + r'data-(?:player-)?config="([^"]+)"', webpage, + 'data player config', default='{}'), + video_id) - periscope_url = PeriscopeIE._extract_url(webpage) - if periscope_url: - return self.url_result(periscope_url, PeriscopeIE.ie_key()) + if config.get('source_type') == 'vine': + return self.url_result(config['player_url'], 'Vine') - video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source') + periscope_url = PeriscopeIE._extract_url(webpage) + if periscope_url: + return self.url_result(periscope_url, PeriscopeIE.ie_key()) - if video_url: - if determine_ext(video_url) == 'm3u8': - formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls')) - else: - f = { - 'url': video_url, - } + video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source') + + if video_url: + if determine_ext(video_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls')) + else: + f = { + 'url': video_url, + } + + self._search_dimensions_in_video_url(f, video_url) - self._search_dimensions_in_video_url(f, video_url) + formats.append(f) - formats.append(f) + vmap_url = config.get('vmapUrl') or config.get('vmap_url') + if vmap_url: + formats.extend( + self._extract_formats_from_vmap_url(vmap_url, video_id)) - vmap_url = config.get('vmapUrl') or config.get('vmap_url') - if vmap_url: - formats.extend( - self._extract_formats_from_vmap_url(vmap_url, video_id)) + media_info = None - media_info = None + for entity in config.get('status', {}).get('entities', []): + if 'mediaInfo' in entity: + media_info = entity['mediaInfo'] - for entity in config.get('status', {}).get('entities', []): - if 'mediaInfo' in entity: - media_info = entity['mediaInfo'] + if media_info: + formats.extend(self._parse_media_info(media_info, video_id)) + duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) - if media_info: - formats.extend(self._parse_media_info(media_info, video_id)) - duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9) + username = config.get('user', {}).get('screen_name') + if username: + formats.extend(self._extract_mobile_formats(username, video_id)) - username = config.get('user', {}).get('screen_name') - if username: - formats.extend(self._extract_mobile_formats(username, video_id)) + if formats: + break self._remove_duplicate_formats(formats) self._sort_formats(formats) @@ -258,9 +259,6 @@ class TwitterIE(InfoExtractor): 'uploader_id': 'freethenipple', 'duration': 12.922, }, - 'params': { - 'skip_download': True, # requires ffmpeg - }, }, { 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1', 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42', @@ -277,7 +275,6 @@ class TwitterIE(InfoExtractor): 'skip': 'Account suspended', }, { 'url': 'https://twitter.com/starwars/status/665052190608723968', - 'md5': '39b7199856dee6cd4432e72c74bc69d4', 'info_dict': { 'id': '665052190608723968', 'ext': 'mp4', @@ -303,20 +300,16 @@ class TwitterIE(InfoExtractor): }, }, { 'url': 'https://twitter.com/jaydingeer/status/700207533655363584', - 'md5': '', 'info_dict': { 'id': '700207533655363584', 'ext': 'mp4', - 'title': 'あかさ - BEAT PROD: @suhmeduh #Damndaniel', - 'description': 'あかさ on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"', + 'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel', + 'description': 'JG on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"', 'thumbnail': r're:^https?://.*\.jpg', - 'uploader': 'あかさ', + 'uploader': 'JG', 'uploader_id': 'jaydingeer', 'duration': 30.0, }, - 'params': { - 'skip_download': True, # requires ffmpeg - }, }, { 'url': 'https://twitter.com/Filmdrunk/status/713801302971588609', 'md5': '89a15ed345d13b86e9a5a5e051fa308a', @@ -342,9 +335,6 @@ class TwitterIE(InfoExtractor): 'uploader': 'Captain America', 'duration': 3.17, }, - 'params': { - 'skip_download': True, # requires ffmpeg - }, }, { 'url': 'https://twitter.com/OPP_HSD/status/779210622571536384', 'info_dict': { @@ -370,9 +360,6 @@ class TwitterIE(InfoExtractor): 'uploader_id': 'news_al3alm', 'duration': 277.4, }, - 'params': { - 'format': 'best[format_id^=http-]', - }, }, { 'url': 'https://twitter.com/i/web/status/910031516746514432', 'info_dict': { diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index c248ea727..195f5ce78 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -62,11 +62,11 @@ class UdemyIE(InfoExtractor): def _extract_course_info(self, webpage, video_id): course = self._parse_json( unescapeHTML(self._search_regex( - r'ng-init=["\'].*\bcourse=({.+?});', webpage, 'course', default='{}')), + r'ng-init=["\'].*\bcourse=({.+?})[;"\']', + webpage, 'course', default='{}')), video_id, fatal=False) or {} course_id = course.get('id') or self._search_regex( - (r'"id"\s*:\s*(\d+)', r'data-course-id=["\'](\d+)'), - webpage, 'course id') + r'data-course-id=["\'](\d+)', webpage, 'course id') return course_id, course.get('title') def _enroll_course(self, base_url, webpage, course_id): @@ -257,6 +257,11 @@ class UdemyIE(InfoExtractor): video_url = source.get('file') or source.get('src') if not video_url or not isinstance(video_url, compat_str): continue + if source.get('type') == 'application/x-mpegURL' or determine_ext(video_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + continue format_id = source.get('label') f = { 'url': video_url, diff --git a/youtube_dl/extractor/umg.py b/youtube_dl/extractor/umg.py new file mode 100644 index 000000000..d815cd9a6 --- /dev/null +++ b/youtube_dl/extractor/umg.py @@ -0,0 +1,103 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_filesize, + parse_iso8601, +) + + +class UMGDeIE(InfoExtractor): + IE_NAME = 'umg:de' + IE_DESC = 'Universal Music Deutschland' + _VALID_URL = r'https?://(?:www\.)?universal-music\.de/[^/]+/videos/[^/?#]+-(?P<id>\d+)' + _TEST = { + 'url': 'https://www.universal-music.de/sido/videos/jedes-wort-ist-gold-wert-457803', + 'md5': 'ebd90f48c80dcc82f77251eb1902634f', + 'info_dict': { + 'id': '457803', + 'ext': 'mp4', + 'title': 'Jedes Wort ist Gold wert', + 'timestamp': 1513591800, + 'upload_date': '20171218', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._download_json( + 'https://api.universal-music.de/graphql', + video_id, query={ + 'query': '''{ + universalMusic(channel:16) { + video(id:%s) { + headline + formats { + formatId + url + type + width + height + mimeType + fileSize + } + duration + createdDate + } + } +}''' % video_id})['data']['universalMusic']['video'] + + title = video_data['headline'] + hls_url_template = 'http://mediadelivery.universal-music-services.de/vod/mp4:autofill/storage/' + '/'.join(list(video_id)) + '/content/%s/file/playlist.m3u8' + + thumbnails = [] + formats = [] + + def add_m3u8_format(format_id): + m3u8_formats = self._extract_m3u8_formats( + hls_url_template % format_id, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal='False') + if m3u8_formats and m3u8_formats[0].get('height'): + formats.extend(m3u8_formats) + + for f in video_data.get('formats', []): + f_url = f.get('url') + mime_type = f.get('mimeType') + if not f_url or mime_type == 'application/mxf': + continue + fmt = { + 'url': f_url, + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'filesize': parse_filesize(f.get('fileSize')), + } + f_type = f.get('type') + if f_type == 'Image': + thumbnails.append(fmt) + elif f_type == 'Video': + format_id = f.get('formatId') + if format_id: + fmt['format_id'] = format_id + if mime_type == 'video/mp4': + add_m3u8_format(format_id) + urlh = self._request_webpage(f_url, video_id, fatal=False) + if urlh: + first_byte = urlh.read(1) + if first_byte not in (b'F', b'\x00'): + continue + formats.append(fmt) + if not formats: + for format_id in (867, 836, 940): + add_m3u8_format(format_id) + self._sort_formats(formats, ('width', 'height', 'filesize', 'tbr')) + + return { + 'id': video_id, + 'title': title, + 'duration': int_or_none(video_data.get('duration')), + 'timestamp': parse_iso8601(video_data.get('createdDate'), ' '), + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index 0d8376522..d4838b3e5 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -414,7 +414,7 @@ class VKIE(VKBaseIE): view_count = str_to_int(self._search_regex( r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)', - info_page, 'view count', fatal=False)) + info_page, 'view count', default=None)) formats = [] for format_id, format_url in data.items(): diff --git a/youtube_dl/extractor/voot.py b/youtube_dl/extractor/voot.py index 5de3deb8c..751b21ee5 100644 --- a/youtube_dl/extractor/voot.py +++ b/youtube_dl/extractor/voot.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals from .common import InfoExtractor -from .kaltura import KalturaIE from ..utils import ( ExtractorError, int_or_none, @@ -21,7 +20,6 @@ class VootIE(InfoExtractor): 'ext': 'mp4', 'title': 'Ishq Ka Rang Safed - Season 01 - Episode 340', 'description': 'md5:06291fbbbc4dcbe21235c40c262507c1', - 'uploader_id': 'batchUser', 'timestamp': 1472162937, 'upload_date': '20160825', 'duration': 1146, @@ -63,6 +61,10 @@ class VootIE(InfoExtractor): entry_id = media['EntryId'] title = media['MediaName'] + formats = self._extract_m3u8_formats( + 'https://cdnapisec.kaltura.com/p/1982551/playManifest/pt/https/f/applehttp/t/web/e/' + entry_id, + video_id, 'mp4', m3u8_id='hls') + self._sort_formats(formats) description, series, season_number, episode, episode_number = [None] * 5 @@ -82,9 +84,8 @@ class VootIE(InfoExtractor): episode_number = int_or_none(value) return { - '_type': 'url_transparent', - 'url': 'kaltura:1982551:%s' % entry_id, - 'ie_key': KalturaIE.ie_key(), + 'extractor_key': 'Kaltura', + 'id': entry_id, 'title': title, 'description': description, 'series': series, @@ -95,4 +96,5 @@ class VootIE(InfoExtractor): 'duration': int_or_none(media.get('Duration')), 'view_count': int_or_none(media.get('ViewCounter')), 'like_count': int_or_none(media.get('like_counter')), + 'formats': formats, } diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 52f8ded2f..68652a22f 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -76,6 +76,10 @@ class XHamsterIE(InfoExtractor): 'skip_download': True, }, }, { + # mobile site + 'url': 'https://m.xhamster.com/videos/cute-teen-jacqueline-solo-masturbation-8559111', + 'only_matching': True, + }, { 'url': 'https://xhamster.com/movies/2272726/amber_slayed_by_the_knight.html', 'only_matching': True, }, { @@ -93,7 +97,8 @@ class XHamsterIE(InfoExtractor): video_id = mobj.group('id') or mobj.group('id_2') display_id = mobj.group('display_id') or mobj.group('display_id_2') - webpage = self._download_webpage(url, video_id) + desktop_url = re.sub(r'^(https?://(?:.+?\.)?)m\.', r'\1', url) + webpage = self._download_webpage(desktop_url, video_id) error = self._html_search_regex( r'<div[^>]+id=["\']videoClosed["\'][^>]*>(.+?)</div>', @@ -229,8 +234,8 @@ class XHamsterIE(InfoExtractor): webpage, 'uploader', default='anonymous') thumbnail = self._search_regex( - [r'''thumb\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''', - r'''<video[^>]+poster=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''], + [r'''["']thumbUrl["']\s*:\s*(?P<q>["'])(?P<thumbnail>.+?)(?P=q)''', + r'''<video[^>]+"poster"=(?P<q>["'])(?P<thumbnail>.+?)(?P=q)[^>]*>'''], webpage, 'thumbnail', fatal=False, group='thumbnail') duration = parse_duration(self._search_regex( @@ -274,15 +279,16 @@ class XHamsterIE(InfoExtractor): class XHamsterEmbedIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)' + _VALID_URL = r'https?://(?:.+?\.)?xhamster\.com/xembed\.php\?video=(?P<id>\d+)' _TEST = { 'url': 'http://xhamster.com/xembed.php?video=3328539', 'info_dict': { 'id': '3328539', 'ext': 'mp4', 'title': 'Pen Masturbation', + 'timestamp': 1406581861, 'upload_date': '20140728', - 'uploader_id': 'anonymous', + 'uploader': 'ManyakisArt', 'duration': 5, 'age_limit': 18, } diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index f0ba01197..c7947d4a1 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -154,7 +154,7 @@ class YoukuIE(InfoExtractor): # request basic data basic_data_params = { 'vid': video_id, - 'ccode': '0501', + 'ccode': '0507', 'client_ip': '192.168.1.1', 'utid': cna, 'client_ts': time.time() / 1000, @@ -241,6 +241,10 @@ class YoukuShowIE(InfoExtractor): # Ongoing playlist. The initial page is the last one 'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html', 'only_matching': True, + }, { + # No data-id value. + 'url': 'http://list.youku.com/show/id_zefbfbd61237fefbfbdef.html', + 'only_matching': True, }] def _extract_entries(self, playlist_data_url, show_id, note, query): @@ -276,9 +280,9 @@ class YoukuShowIE(InfoExtractor): r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id') # The first reload_id has the same items as first_page reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page) + entries.extend(initial_entries) for idx, reload_id in enumerate(reload_ids): if reload_id == first_page_reload_id: - entries.extend(initial_entries) continue _, new_entries = self._extract_entries( 'http://list.youku.com/show/episode', show_id, diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 9943dddc1..0919bef0e 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -2270,6 +2270,19 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', page, 'title', default=None) + _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref=' + uploader = self._search_regex( + r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE, + page, 'uploader', default=None) + mobj = re.search( + r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE, + page) + if mobj: + uploader_id = mobj.group('uploader_id') + uploader_url = compat_urlparse.urljoin(url, mobj.group('path')) + else: + uploader_id = uploader_url = None + has_videos = True if not playlist_title: @@ -2280,8 +2293,15 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): except StopIteration: has_videos = False - return has_videos, self.playlist_result( + playlist = self.playlist_result( self._entries(page, playlist_id), playlist_id, playlist_title) + playlist.update({ + 'uploader': uploader, + 'uploader_id': uploader_id, + 'uploader_url': uploader_url, + }) + + return has_videos, playlist def _check_download_just_video(self, url, playlist_id): # Check if it's a video-specific URL diff --git a/youtube_dl/postprocessor/xattrpp.py b/youtube_dl/postprocessor/xattrpp.py index fbdfa02ac..b0aed9ca7 100644 --- a/youtube_dl/postprocessor/xattrpp.py +++ b/youtube_dl/postprocessor/xattrpp.py @@ -42,6 +42,7 @@ class XAttrMetadataPP(PostProcessor): 'user.dublincore.format': 'format', } + num_written = 0 for xattrname, infoname in xattr_mapping.items(): value = info.get(infoname) @@ -52,6 +53,7 @@ class XAttrMetadataPP(PostProcessor): byte_value = value.encode('utf-8') write_xattr(filename, xattrname, byte_value) + num_written += 1 return [], info @@ -62,8 +64,8 @@ class XAttrMetadataPP(PostProcessor): except XAttrMetadataError as e: if e.reason == 'NO_SPACE': self._downloader.report_warning( - 'There\'s no disk space left or disk quota exceeded. ' + - 'Extended attributes are not written.') + 'There\'s no disk space left, disk quota exceeded or filesystem xattr limit exceeded. ' + + (('Some ' if num_written else '') + 'extended attributes are not written.').capitalize()) elif e.reason == 'VALUE_TOO_LONG': self._downloader.report_warning( 'Unable to write extended attributes due to too long values.') diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index eccbc0b1f..2843a3dc0 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -159,6 +159,8 @@ DATE_FORMATS = ( '%Y-%m-%dT%H:%M', '%b %d %Y at %H:%M', '%b %d %Y at %H:%M:%S', + '%B %d %Y at %H:%M', + '%B %d %Y at %H:%M:%S', ) DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 88bf1d652..f999584d7 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2017.12.02' +__version__ = '2017.12.23' |