diff options
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 12 | ||||
| -rw-r--r-- | youtube_dl/extractor/audioboom.py | 66 | ||||
| -rw-r--r-- | youtube_dl/extractor/bbc.py | 30 | ||||
| -rw-r--r-- | youtube_dl/extractor/common.py | 49 | ||||
| -rw-r--r-- | youtube_dl/extractor/dw.py | 85 | ||||
| -rw-r--r-- | youtube_dl/extractor/facebook.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 39 | ||||
| -rw-r--r-- | youtube_dl/extractor/googledrive.py | 12 | ||||
| -rw-r--r-- | youtube_dl/extractor/kaltura.py | 67 | ||||
| -rw-r--r-- | youtube_dl/extractor/makerschannel.py | 40 | ||||
| -rw-r--r-- | youtube_dl/extractor/minoto.py | 56 | ||||
| -rw-r--r-- | youtube_dl/extractor/mixcloud.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/safari.py | 59 | ||||
| -rw-r--r-- | youtube_dl/extractor/vice.py | 78 | ||||
| -rw-r--r-- | youtube_dl/utils.py | 38 |
15 files changed, 527 insertions, 115 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 98de5ddff..c5b80f4aa 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -54,6 +54,7 @@ from .arte import ( from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE from .audimedia import AudiMediaIE +from .audioboom import AudioBoomIE from .audiomack import AudiomackIE, AudiomackAlbumIE from .azubu import AzubuIE, AzubuLiveIE from .baidu import BaiduVideoIE @@ -188,6 +189,10 @@ from .dumpert import DumpertIE from .defense import DefenseGouvFrIE from .discovery import DiscoveryIE from .dropbox import DropboxIE +from .dw import ( + DWIE, + DWArticleIE, +) from .eagleplatform import EaglePlatformIE from .ebaumsworld import EbaumsWorldIE from .echomsk import EchoMskIE @@ -384,6 +389,7 @@ from .lynda import ( from .m6 import M6IE from .macgamestore import MacGameStoreIE from .mailru import MailRuIE +from .makerschannel import MakersChannelIE from .makertv import MakerTVIE from .malemotion import MalemotionIE from .matchtv import MatchTVIE @@ -393,6 +399,7 @@ from .metacritic import MetacriticIE from .mgoon import MgoonIE from .minhateca import MinhatecaIE from .ministrygrid import MinistryGridIE +from .minoto import MinotoIE from .miomio import MioMioIE from .mit import TechTVMITIE, MITIE, OCWMITIE from .mitele import MiTeleIE @@ -829,7 +836,10 @@ from .vgtv import ( VGTVIE, ) from .vh1 import VH1IE -from .vice import ViceIE +from .vice import ( + ViceIE, + ViceShowIE, +) from .viddler import ViddlerIE from .videodetective import VideoDetectiveIE from .videofyme import VideofyMeIE diff --git a/youtube_dl/extractor/audioboom.py b/youtube_dl/extractor/audioboom.py new file mode 100644 index 000000000..2ec2d7092 --- /dev/null +++ b/youtube_dl/extractor/audioboom.py @@ -0,0 +1,66 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import float_or_none + + +class AudioBoomIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audioboom\.com/boos/(?P<id>[0-9]+)' + _TEST = { + 'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0', + 'md5': '63a8d73a055c6ed0f1e51921a10a5a76', + 'info_dict': { + 'id': '4279833', + 'ext': 'mp3', + 'title': '3/09/2016 Czaban Hour 3', + 'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans', + 'duration': 2245.72, + 'uploader': 'Steve Czaban', + 'uploader_url': 're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + clip = None + + clip_store = self._parse_json( + self._search_regex( + r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id, + webpage, 'clip store', default='{}', group='json'), + video_id, fatal=False) + if clip_store: + clips = clip_store.get('clips') + if clips and isinstance(clips, list) and isinstance(clips[0], dict): + clip = clips[0] + + def from_clip(field): + if clip: + clip.get(field) + + audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property( + 'audio', webpage, 'audio url') + title = from_clip('title') or self._og_search_title(webpage) + description = from_clip('description') or self._og_search_description(webpage) + + duration = float_or_none(from_clip('duration') or self._html_search_meta( + 'weibo:audio:duration', webpage)) + + uploader = from_clip('author') or self._og_search_property( + 'audio:artist', webpage, 'uploader', fatal=False) + uploader_url = from_clip('author_url') or self._html_search_meta( + 'audioboo:channel', webpage, 'uploader url') + + return { + 'id': video_id, + 'url': audio_url, + 'title': title, + 'description': description, + 'duration': duration, + 'uploader': uploader, + 'uploader_url': uploader_url, + } diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 9d0dfb961..e62b3860e 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -10,7 +10,6 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, - remove_end, unescapeHTML, ) from ..compat import ( @@ -561,7 +560,7 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', 'info_dict': { 'id': '3662a707-0af9-3149-963f-47bea720b460', - 'title': 'BBC Blogs - Adam Curtis - BUGGER', + 'title': 'BUGGER', }, 'playlist_count': 18, }, { @@ -670,10 +669,18 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.com/sport/0/football/34475836', 'info_dict': { 'id': '34475836', - 'title': 'What Liverpool can expect from Klopp', + 'title': 'Jurgen Klopp: Furious football from a witty and winning coach', }, 'playlist_count': 3, }, { + # school report article with single video + 'url': 'http://www.bbc.co.uk/schoolreport/35744779', + 'info_dict': { + 'id': '35744779', + 'title': 'School which breaks down barriers in Jerusalem', + }, + 'playlist_count': 1, + }, { # single video with playlist URL from weather section 'url': 'http://www.bbc.com/weather/features/33601775', 'only_matching': True, @@ -735,8 +742,17 @@ class BBCIE(BBCCoUkIE): json_ld_info = self._search_json_ld(webpage, playlist_id, default=None) timestamp = json_ld_info.get('timestamp') + playlist_title = json_ld_info.get('title') - playlist_description = json_ld_info.get('description') + if not playlist_title: + playlist_title = self._og_search_title( + webpage, default=None) or self._html_search_regex( + r'<title>(.+?)</title>', webpage, 'playlist title', default=None) + if playlist_title: + playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip() + + playlist_description = json_ld_info.get( + 'description') or self._og_search_description(webpage, default=None) if not timestamp: timestamp = parse_iso8601(self._search_regex( @@ -797,8 +813,6 @@ class BBCIE(BBCCoUkIE): playlist.get('progressiveDownloadUrl'), playlist_id, timestamp)) if entries: - playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News') - playlist_description = playlist_description or self._og_search_description(webpage, default=None) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) @@ -829,10 +843,6 @@ class BBCIE(BBCCoUkIE): 'subtitles': subtitles, } - playlist_title = self._html_search_regex( - r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') - playlist_description = self._og_search_description(webpage, default=None) - def extract_all(pattern): return list(filter(None, map( lambda s: self._parse_json(s, playlist_id, fatal=False), diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index bfa9c82f6..ecd7da767 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -48,6 +48,7 @@ from ..utils import ( determine_protocol, parse_duration, mimetype2ext, + update_url_query, ) @@ -345,7 +346,7 @@ class InfoExtractor(object): def IE_NAME(self): return compat_str(type(self).__name__[:-2]) - def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True): + def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers=None, query=None): """ Returns the response handle """ if note is None: self.report_download_webpage(video_id) @@ -354,6 +355,12 @@ class InfoExtractor(object): self.to_screen('%s' % (note,)) else: self.to_screen('%s: %s' % (video_id, note)) + # data, headers and query params will be ignored for `Request` objects + if isinstance(url_or_request, compat_str): + if query: + url_or_request = update_url_query(url_or_request, query) + if data or headers: + url_or_request = sanitized_Request(url_or_request, data, headers or {}) try: return self._downloader.urlopen(url_or_request) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: @@ -369,13 +376,13 @@ class InfoExtractor(object): self._downloader.report_warning(errmsg) return False - def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None): + def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers=None, query=None): """ Returns a tuple (page content as string, URL handle) """ # Strip hashes from the URL (#1038) if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal) + 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 return False @@ -462,13 +469,13 @@ class InfoExtractor(object): return content - def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None): + def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers=None, query=None): """ Returns the data of the page as a string """ success = False try_count = 0 while success is False: try: - res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding) + res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query) success = True except compat_http_client.IncompleteRead as e: try_count += 1 @@ -483,10 +490,10 @@ class InfoExtractor(object): def _download_xml(self, url_or_request, video_id, note='Downloading XML', errnote='Unable to download XML', - transform_source=None, fatal=True, encoding=None): + transform_source=None, fatal=True, encoding=None, data=None, headers=None, query=None): """Return the xml as an xml.etree.ElementTree.Element""" xml_string = self._download_webpage( - url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding) + url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query) if xml_string is False: return xml_string if transform_source: @@ -497,10 +504,10 @@ class InfoExtractor(object): note='Downloading JSON metadata', errnote='Unable to download JSON metadata', transform_source=None, - fatal=True, encoding=None): + fatal=True, encoding=None, data=None, headers=None, query=None): json_string = self._download_webpage( url_or_request, video_id, note, errnote, fatal=fatal, - encoding=encoding) + encoding=encoding, data=data, headers=headers, query=query) if (not fatal) and json_string is False: return None return self._parse_json( @@ -966,6 +973,13 @@ class InfoExtractor(object): if manifest is False: return [] + return self._parse_f4m_formats( + manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id, + transform_source=transform_source, fatal=fatal) + + def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None, + transform_source=lambda s: fix_xml_ampersands(s).strip(), + fatal=True): formats = [] manifest_version = '1.0' media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media') @@ -991,7 +1005,8 @@ class InfoExtractor(object): # bitrate in f4m downloader if determine_ext(manifest_url) == 'f4m': formats.extend(self._extract_f4m_formats( - manifest_url, video_id, preference, f4m_id, fatal=fatal)) + manifest_url, video_id, preference=preference, f4m_id=f4m_id, + transform_source=transform_source, fatal=fatal)) continue tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ @@ -1140,8 +1155,8 @@ class InfoExtractor(object): out.append('{%s}%s' % (namespace, c)) return '/'.join(out) - def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None): - smil = self._download_smil(smil_url, video_id, fatal=fatal) + def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None, transform_source=None): + smil = self._download_smil(smil_url, video_id, fatal=fatal, transform_source=transform_source) if smil is False: assert not fatal @@ -1158,10 +1173,10 @@ class InfoExtractor(object): return {} return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params) - def _download_smil(self, smil_url, video_id, fatal=True): + def _download_smil(self, smil_url, video_id, fatal=True, transform_source=None): return self._download_xml( smil_url, video_id, 'Downloading SMIL file', - 'Unable to download SMIL file', fatal=fatal) + 'Unable to download SMIL file', fatal=fatal, transform_source=transform_source) def _parse_smil(self, smil, smil_url, video_id, f4m_params=None): namespace = self._parse_smil_namespace(smil) @@ -1447,8 +1462,9 @@ class InfoExtractor(object): continue representation_attrib = adaptation_set.attrib.copy() representation_attrib.update(representation.attrib) - mime_type = representation_attrib.get('mimeType') - content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType') + # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory + mime_type = representation_attrib['mimeType'] + content_type = mime_type.split('/')[0] if content_type == 'text': # TODO implement WebVTT downloading pass @@ -1471,6 +1487,7 @@ class InfoExtractor(object): f = { 'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id, 'url': base_url, + 'ext': mimetype2ext(mime_type), 'width': int_or_none(representation_attrib.get('width')), 'height': int_or_none(representation_attrib.get('height')), 'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000), diff --git a/youtube_dl/extractor/dw.py b/youtube_dl/extractor/dw.py new file mode 100644 index 000000000..b6c985547 --- /dev/null +++ b/youtube_dl/extractor/dw.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import int_or_none +from ..compat import compat_urlparse + + +class DWIE(InfoExtractor): + IE_NAME = 'dw' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)' + _TESTS = [{ + # video + 'url': 'http://www.dw.com/en/intelligent-light/av-19112290', + 'md5': '7372046e1815c5a534b43f3c3c36e6e9', + 'info_dict': { + 'id': '19112290', + 'ext': 'mp4', + 'title': 'Intelligent light', + 'description': 'md5:90e00d5881719f2a6a5827cb74985af1', + 'upload_date': '20160311', + } + }, { + # audio + 'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941', + 'md5': '2814c9a1321c3a51f8a7aeb067a360dd', + 'info_dict': { + 'id': '19111941', + 'ext': 'mp3', + 'title': 'WorldLink: My business', + 'description': 'md5:bc9ca6e4e063361e21c920c53af12405', + 'upload_date': '20160311', + } + }] + + def _real_extract(self, url): + media_id = self._match_id(url) + webpage = self._download_webpage(url, media_id) + hidden_inputs = self._hidden_inputs(webpage) + title = hidden_inputs['media_title'] + + formats = [] + if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1': + formats = self._extract_smil_formats( + 'http://www.dw.com/smil/v-%s' % media_id, media_id, + transform_source=lambda s: s.replace( + 'rtmp://tv-od.dw.de/flash/', + 'http://tv-download.dw.de/dwtv_video/flv/')) + else: + formats = [{'url': hidden_inputs['file_name']}] + + return { + 'id': media_id, + 'title': title, + 'description': self._og_search_description(webpage), + 'thumbnail': hidden_inputs.get('preview_image'), + 'duration': int_or_none(hidden_inputs.get('file_duration')), + 'upload_date': hidden_inputs.get('display_date'), + 'formats': formats, + } + + +class DWArticleIE(InfoExtractor): + IE_NAME = 'dw:article' + _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)' + _TEST = { + 'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009', + 'md5': '8ca657f9d068bbef74d6fc38b97fc869', + 'info_dict': { + 'id': '19105868', + 'ext': 'mp4', + 'title': 'The harsh life of refugees in Idomeni', + 'description': 'md5:196015cc7e48ebf474db9399420043c7', + 'upload_date': '20160310', + } + } + + def _real_extract(self, url): + article_id = self._match_id(url) + webpage = self._download_webpage(url, article_id) + hidden_inputs = self._hidden_inputs(webpage) + media_id = hidden_inputs['media_id'] + media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url') + media_url = compat_urlparse.urljoin(url, media_path) + return self.url_result(media_url, 'DW', media_id) diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 5e8589479..f5bbd39d2 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -38,7 +38,8 @@ class FacebookIE(InfoExtractor): story\.php )\?(?:.*?)(?:v|video_id|story_fbid)=| [^/]+/videos/(?:[^/]+/)?| - [^/]+/posts/ + [^/]+/posts/| + groups/[^/]+/permalink/ )| facebook: ) @@ -123,6 +124,9 @@ class FacebookIE(InfoExtractor): }, { 'url': 'facebook:544765982287235', 'only_matching': True, + }, { + 'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/', + 'only_matching': True, }] def _login(self): diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index ca745ae41..8121f04a5 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1242,28 +1242,34 @@ class GenericIE(InfoExtractor): full_response = self._request_webpage(request, video_id) head_response = full_response + info_dict = { + 'id': video_id, + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + } + # Check for direct link to a video content_type = head_response.headers.get('Content-Type', '') m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>.+)$', content_type) if m: upload_date = unified_strdate( head_response.headers.get('Last-Modified')) - formats = [] - if m.group('format_id').endswith('mpegurl'): + format_id = m.group('format_id') + if format_id.endswith('mpegurl'): formats = self._extract_m3u8_formats(url, video_id, 'mp4') + elif format_id == 'f4m': + formats = self._extract_f4m_formats(url, video_id) else: formats = [{ 'format_id': m.group('format_id'), 'url': url, 'vcodec': 'none' if m.group('type') == 'audio' else None }] - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + info_dict.update({ 'direct': True, 'formats': formats, 'upload_date': upload_date, - } + }) + return info_dict if not self._downloader.params.get('test', False) and not is_intentional: force = self._downloader.params.get('force_generic_extractor', False) @@ -1291,13 +1297,12 @@ class GenericIE(InfoExtractor): 'URL could be a direct video link, returning it as such.') upload_date = unified_strdate( head_response.headers.get('Last-Modified')) - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), + info_dict.update({ 'direct': True, 'url': url, 'upload_date': upload_date, - } + }) + return info_dict webpage = self._webpage_read_content( full_response, url, video_id, prefix=first_bytes) @@ -1314,12 +1319,12 @@ class GenericIE(InfoExtractor): elif doc.tag == '{http://xspf.org/ns/0/}playlist': return self.playlist_result(self._parse_xspf(doc, video_id), video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): - return { - 'id': video_id, - 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), - 'formats': self._parse_mpd_formats( - doc, video_id, mpd_base_url=url.rpartition('/')[0]), - } + info_dict['formats'] = self._parse_mpd_formats( + doc, video_id, mpd_base_url=url.rpartition('/')[0]) + return info_dict + elif re.match(r'^{http://ns\.adobe\.com/f4m/[12]\.0}manifest$', doc.tag): + info_dict['formats'] = self._parse_f4m_formats(doc, url, video_id) + return info_dict except compat_xml_parse_error: pass @@ -1985,6 +1990,8 @@ class GenericIE(InfoExtractor): entry_info_dict['formats'] = self._extract_m3u8_formats(video_url, video_id, ext='mp4') elif ext == 'mpd': entry_info_dict['formats'] = self._extract_mpd_formats(video_url, video_id) + elif ext == 'f4m': + entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id) else: entry_info_dict['url'] = video_url diff --git a/youtube_dl/extractor/googledrive.py b/youtube_dl/extractor/googledrive.py index 37be34091..766fc26d0 100644 --- a/youtube_dl/extractor/googledrive.py +++ b/youtube_dl/extractor/googledrive.py @@ -10,8 +10,8 @@ from ..utils import ( class GoogleDriveIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28})' - _TEST = { + _VALID_URL = r'https?://(?:(?:docs|drive)\.google\.com/(?:uc\?.*?id=|file/d/)|video\.google\.com/get_player\?.*?docid=)(?P<id>[a-zA-Z0-9_-]{28,})' + _TESTS = [{ 'url': 'https://drive.google.com/file/d/0ByeS4oOUV-49Zzh4R1J6R09zazQ/edit?pli=1', 'md5': '881f7700aec4f538571fa1e0eed4a7b6', 'info_dict': { @@ -20,7 +20,11 @@ class GoogleDriveIE(InfoExtractor): 'title': 'Big Buck Bunny.mp4', 'duration': 46, } - } + }, { + # video id is longer than 28 characters + 'url': 'https://drive.google.com/file/d/1ENcQ_jeCuj7y19s66_Ou9dRP4GKGsodiDQ/edit', + 'only_matching': True, + }] _FORMATS_EXT = { '5': 'flv', '6': 'flv', @@ -43,7 +47,7 @@ class GoogleDriveIE(InfoExtractor): @staticmethod def _extract_url(webpage): mobj = re.search( - r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28})', + r'<iframe[^>]+src="https?://(?:video\.google\.com/get_player\?.*?docid=|(?:docs|drive)\.google\.com/file/d/)(?P<id>[a-zA-Z0-9_-]{28,})', webpage) if mobj: return 'https://drive.google.com/file/d/%s' % mobj.group('id') diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index ccbc39c66..44d7c84a1 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -8,6 +8,7 @@ from .common import InfoExtractor from ..compat import ( compat_urllib_parse, compat_urlparse, + compat_parse_qs, ) from ..utils import ( clean_html, @@ -20,21 +21,17 @@ from ..utils import ( class KalturaIE(InfoExtractor): _VALID_URL = r'''(?x) (?: - kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)| + kaltura:(?P<partner_id>\d+):(?P<id>[0-9a-z_]+)| https?:// (:?(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/ (?: (?: # flash player - index\.php/kwidget/ - (?:[^/]+/)*?wid/_(?P<partner_id>\d+)/ - (?:[^/]+/)*?entry_id/(?P<id>[0-9a-z_]+)| + index\.php/kwidget| # html5 player - html5/html5lib/ - (?:[^/]+/)*?entry_id/(?P<id_html5>[0-9a-z_]+) - .*\?.*\bwid=_(?P<partner_id_html5>\d+) + html5/html5lib/[^/]+/mwEmbedFrame\.php ) - ) + )(?:/(?P<path>[^?]+))?(?:\?(?P<query>.*))? ) ''' _API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?' @@ -127,10 +124,41 @@ class KalturaIE(InfoExtractor): url, smuggled_data = unsmuggle_url(url, {}) mobj = re.match(self._VALID_URL, url) - partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5') - entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5') - - info, flavor_assets = self._get_video_info(entry_id, partner_id) + partner_id, entry_id = mobj.group('partner_id', 'id') + ks = None + if partner_id and entry_id: + info, flavor_assets = self._get_video_info(entry_id, partner_id) + else: + path, query = mobj.group('path', 'query') + if not path and not query: + raise ExtractorError('Invalid URL', expected=True) + params = {} + if query: + params = compat_parse_qs(query) + if path: + splitted_path = path.split('/') + params.update(dict((zip(splitted_path[::2], [[v] for v in splitted_path[1::2]])))) + if 'wid' in params: + partner_id = params['wid'][0][1:] + elif 'p' in params: + partner_id = params['p'][0] + else: + raise ExtractorError('Invalid URL', expected=True) + if 'entry_id' in params: + entry_id = params['entry_id'][0] + info, flavor_assets = self._get_video_info(entry_id, partner_id) + elif 'uiconf_id' in params and 'flashvars[referenceId]' in params: + reference_id = params['flashvars[referenceId]'][0] + webpage = self._download_webpage(url, reference_id) + entry_data = self._parse_json(self._search_regex( + r'window\.kalturaIframePackageData\s*=\s*({.*});', + webpage, 'kalturaIframePackageData'), + reference_id)['entryResult'] + info, flavor_assets = entry_data['meta'], entry_data['contextData']['flavorAssets'] + entry_id = info['id'] + else: + raise ExtractorError('Invalid URL', expected=True) + ks = params.get('flashvars[ks]', [None])[0] source_url = smuggled_data.get('source_url') if source_url: @@ -140,14 +168,19 @@ class KalturaIE(InfoExtractor): else: referrer = None + def sign_url(unsigned_url): + if ks: + unsigned_url += '/ks/%s' % ks + if referrer: + unsigned_url += '?referrer=%s' % referrer + return unsigned_url + formats = [] for f in flavor_assets: # Continue if asset is not ready if f['status'] != 2: continue - video_url = '%s/flavorId/%s' % (info['dataUrl'], f['id']) - if referrer: - video_url += '?referrer=%s' % referrer + video_url = sign_url('%s/flavorId/%s' % (info['dataUrl'], f['id'])) formats.append({ 'format_id': '%(fileExt)s-%(bitrate)s' % f, 'ext': f.get('fileExt'), @@ -160,9 +193,7 @@ class KalturaIE(InfoExtractor): 'width': int_or_none(f.get('width')), 'url': video_url, }) - m3u8_url = info['dataUrl'].replace('format/url', 'format/applehttp') - if referrer: - m3u8_url += '?referrer=%s' % referrer + m3u8_url = sign_url(info['dataUrl'].replace('format/url', 'format/applehttp')) formats.extend(self._extract_m3u8_formats( m3u8_url, entry_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) diff --git a/youtube_dl/extractor/makerschannel.py b/youtube_dl/extractor/makerschannel.py new file mode 100644 index 000000000..f5d00e61d --- /dev/null +++ b/youtube_dl/extractor/makerschannel.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class MakersChannelIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?makerschannel\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://makerschannel.com/en/zoomin/community-highlights?video_id=849', + 'md5': '624a512c6969236b5967bf9286345ad1', + 'info_dict': { + 'id': '849', + 'ext': 'mp4', + 'title': 'Landing a bus on a plane is an epic win', + 'uploader': 'ZoomIn', + 'description': 'md5:cd9cca2ea7b69b78be81d07020c97139', + } + } + + def _real_extract(self, url): + id_type, url_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, url_id) + video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data') + + def extract_data_val(attr, fatal=False): + return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal) + minoto_id = self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id') + + return { + '_type': 'url_transparent', + 'url': 'minoto:%s' % minoto_id, + 'id': extract_data_val('video-id', True), + 'title': extract_data_val('title', True), + 'description': extract_data_val('description'), + 'thumbnail': extract_data_val('image'), + 'uploader': extract_data_val('channel'), + } diff --git a/youtube_dl/extractor/minoto.py b/youtube_dl/extractor/minoto.py new file mode 100644 index 000000000..959a10589 --- /dev/null +++ b/youtube_dl/extractor/minoto.py @@ -0,0 +1,56 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class MinotoIE(InfoExtractor): + _VALID_URL = r'(?:minoto:|https?://(?:play|iframe|embed)\.minoto-video\.com/(?P<player_id>[0-9]+)/)(?P<id>[a-zA-Z0-9]+)' + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + player_id = mobj.group('player_id') or '1' + video_id = mobj.group('id') + video_data = self._download_json('http://play.minoto-video.com/%s/%s.js' % (player_id, video_id), video_id) + video_metadata = video_data['video-metadata'] + formats = [] + for fmt in video_data['video-files']: + fmt_url = fmt.get('url') + if not fmt_url: + continue + container = fmt.get('container') + if container == 'hls': + formats.extend(fmt_url, video_id, 'mp4', m3u8_id='hls', fatal=False) + else: + fmt_profile = fmt.get('profile') or {} + f = { + 'format_id': fmt_profile.get('name-short'), + 'format_note': fmt_profile.get('name'), + 'url': fmt_url, + 'container': container, + 'tbr': int_or_none(fmt.get('bitrate')), + 'filesize': int_or_none(fmt.get('filesize')), + 'width': int_or_none(fmt.get('width')), + 'height': int_or_none(fmt.get('height')), + } + codecs = fmt.get('codecs') + if codecs: + codecs = codecs.split(',') + if len(codecs) == 2: + f.update({ + 'vcodec': codecs[0], + 'acodec': codecs[1], + }) + formats.append(f) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': video_metadata['title'], + 'description': video_metadata.get('description'), + 'thumbnail': video_metadata.get('video-poster', {}).get('url'), + 'formats': formats, + } diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index c2b7ed9ab..101497118 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -7,6 +7,7 @@ from ..compat import compat_urllib_parse_unquote from ..utils import ( ExtractorError, HEADRequest, + parse_count, str_to_int, ) @@ -85,8 +86,8 @@ class MixcloudIE(InfoExtractor): uploader_id = self._search_regex( r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) description = self._og_search_description(webpage) - like_count = str_to_int(self._search_regex( - r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"', + like_count = parse_count(self._search_regex( + r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)', webpage, 'like count', fatal=False)) view_count = str_to_int(self._search_regex( [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"', diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index a65fc8ed7..256396bb8 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -4,14 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .brightcove import BrightcoveLegacyIE from ..utils import ( ExtractorError, sanitized_Request, - smuggle_url, std_headers, urlencode_postdata, + update_url_query, ) @@ -20,21 +19,22 @@ class SafariBaseIE(InfoExtractor): _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>' _NETRC_MACHINE = 'safari' - _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' + _API_BASE = 'https://www.safaribooksonline.com/api/v1' _API_FORMAT = 'json' LOGGED_IN = False def _real_initialize(self): - # We only need to log in once for courses or individual videos - if not self.LOGGED_IN: - self._login() - SafariBaseIE.LOGGED_IN = True + self._login() def _login(self): + # We only need to log in once for courses or individual videos + if self.LOGGED_IN: + return + (username, password) = self._get_login_info() if username is None: - self.raise_login_required('safaribooksonline.com account is required') + return headers = std_headers.copy() if 'Referer' not in headers: @@ -67,6 +67,8 @@ class SafariBaseIE(InfoExtractor): 'Login failed; make sure your credentials are correct and try again.', expected=True) + SafariBaseIE.LOGGED_IN = True + self.to_screen('Login successful') @@ -86,13 +88,15 @@ class SafariIE(SafariBaseIE): _TESTS = [{ 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html', - 'md5': '5b0c4cc1b3c1ba15dda7344085aa5592', + 'md5': 'dcc5a425e79f2564148652616af1f2a3', 'info_dict': { - 'id': '2842601850001', + 'id': '0_qbqx90ic', 'ext': 'mp4', - 'title': 'Introduction', + 'title': 'Introduction to Hadoop Fundamentals LiveLessons', + 'timestamp': 1437758058, + 'upload_date': '20150724', + 'uploader_id': 'stork', }, - 'skip': 'Requires safaribooksonline account credentials', }, { 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', 'only_matching': True, @@ -107,15 +111,30 @@ class SafariIE(SafariBaseIE): course_id = mobj.group('course_id') part = mobj.group('part') - webpage = self._download_webpage( - '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part), - part) + webpage = self._download_webpage(url, '%s/%s' % (course_id, part)) + reference_id = self._search_regex(r'data-reference-id="([^"]+)"', webpage, 'kaltura reference id') + partner_id = self._search_regex(r'data-partner-id="([^"]+)"', webpage, 'kaltura widget id') + ui_id = self._search_regex(r'data-ui-id="([^"]+)"', webpage, 'kaltura uiconf id') + + query = { + 'wid': '_%s' % partner_id, + 'uiconf_id': ui_id, + 'flashvars[referenceId]': reference_id, + } - bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage) - if not bc_url: - raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True) + if self.LOGGED_IN: + kaltura_session = self._download_json( + '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id), + course_id, 'Downloading kaltura session JSON', + 'Unable to download kaltura session JSON', fatal=False) + if kaltura_session: + session = kaltura_session.get('session') + if session: + query['flashvars[ks]'] = session - return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy') + return self.url_result(update_url_query( + 'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query), + 'Kaltura') class SafariCourseIE(SafariBaseIE): @@ -141,7 +160,7 @@ class SafariCourseIE(SafariBaseIE): course_id = self._match_id(url) course_json = self._download_json( - '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), + '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT), course_id, 'Downloading course JSON') if 'chapters' not in course_json: diff --git a/youtube_dl/extractor/vice.py b/youtube_dl/extractor/vice.py index 3db6286e4..46c785ae1 100644 --- a/youtube_dl/extractor/vice.py +++ b/youtube_dl/extractor/vice.py @@ -1,31 +1,37 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from .ooyala import OoyalaIE from ..utils import ExtractorError class ViceIE(InfoExtractor): - _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)+(?P<id>.+)' - - _TESTS = [ - { - 'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1', - 'info_dict': { - 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', - 'ext': 'mp4', - 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', - 'duration': 725.983, - }, - 'params': { - # Requires ffmpeg (m3u8 manifest) - 'skip_download': True, - }, - }, { - 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', - 'only_matching': True, - } - ] + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?videos?/(?P<id>[^/?#&]+)' + + _TESTS = [{ + 'url': 'http://www.vice.com/video/cowboy-capitalists-part-1', + 'info_dict': { + 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', + 'ext': 'mp4', + 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + 'duration': 725.983, + }, + 'params': { + # Requires ffmpeg (m3u8 manifest) + 'skip_download': True, + }, + }, { + 'url': 'https://news.vice.com/video/experimenting-on-animals-inside-the-monkey-lab', + 'only_matching': True, + }, { + 'url': 'http://www.vice.com/ru/video/big-night-out-ibiza-clive-martin-229', + 'only_matching': True, + }, { + 'url': 'https://munchies.vice.com/en/videos/watch-the-trailer-for-our-new-series-the-pizza-show', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -38,3 +44,35 @@ class ViceIE(InfoExtractor): except ExtractorError: raise ExtractorError('The page doesn\'t contain a video', expected=True) return self.url_result(ooyala_url, ie='Ooyala') + + +class ViceShowIE(InfoExtractor): + _VALID_URL = r'https?://(?:.+?\.)?vice\.com/(?:[^/]+/)?show/(?P<id>[^/?#&]+)' + + _TEST = { + 'url': 'https://munchies.vice.com/en/show/fuck-thats-delicious-2', + 'info_dict': { + 'id': 'fuck-thats-delicious-2', + 'title': "Fuck, That's Delicious", + 'description': 'Follow the culinary adventures of rapper Action Bronson during his ongoing world tour.', + }, + 'playlist_count': 17, + } + + def _real_extract(self, url): + show_id = self._match_id(url) + webpage = self._download_webpage(url, show_id) + + entries = [ + self.url_result(video_url, ViceIE.ie_key()) + for video_url, _ in re.findall( + r'<h2[^>]+class="article-title"[^>]+data-id="\d+"[^>]*>\s*<a[^>]+href="(%s.*?)"' + % ViceIE._VALID_URL, webpage)] + + title = self._search_regex( + r'<title>(.+?)</title>', webpage, 'title', default=None) + if title: + title = re.sub(r'(.+)\s*\|\s*.+$', r'\1', title).strip() + description = self._html_search_meta('description', webpage, 'description') + + return self.playlist_result(entries, show_id, title, description) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 22a39a0ab..9fd0ec8d5 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1316,6 +1316,17 @@ def format_bytes(bytes): return '%.2f%s' % (converted, suffix) +def lookup_unit_table(unit_table, s): + units_re = '|'.join(re.escape(u) for u in unit_table) + m = re.match( + r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)' % units_re, s) + if not m: + return None + num_str = m.group('num').replace(',', '.') + mult = unit_table[m.group('unit')] + return int(float(num_str) * mult) + + def parse_filesize(s): if s is None: return None @@ -1359,15 +1370,28 @@ def parse_filesize(s): 'Yb': 1000 ** 8, } - units_re = '|'.join(re.escape(u) for u in _UNIT_TABLE) - m = re.match( - r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)' % units_re, s) - if not m: + return lookup_unit_table(_UNIT_TABLE, s) + + +def parse_count(s): + if s is None: return None - num_str = m.group('num').replace(',', '.') - mult = _UNIT_TABLE[m.group('unit')] - return int(float(num_str) * mult) + s = s.strip() + + if re.match(r'^[\d,.]+$', s): + return str_to_int(s) + + _UNIT_TABLE = { + 'k': 1000, + 'K': 1000, + 'm': 1000 ** 2, + 'M': 1000 ** 2, + 'kk': 1000 ** 2, + 'KK': 1000 ** 2, + } + + return lookup_unit_table(_UNIT_TABLE, s) def month_by_name(name): |