diff options
-rwxr-xr-x | youtube_dl/YoutubeDL.py | 9 | ||||
-rw-r--r-- | youtube_dl/__init__.py | 8 | ||||
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/kaltura.py | 6 | ||||
-rw-r--r-- | youtube_dl/extractor/lynda.py | 11 | ||||
-rw-r--r-- | youtube_dl/extractor/odnoklassniki.py | 85 | ||||
-rw-r--r-- | youtube_dl/extractor/svtplay.py | 42 | ||||
-rw-r--r-- | youtube_dl/options.py | 4 | ||||
-rw-r--r-- | youtube_dl/postprocessor/__init__.py | 2 | ||||
-rw-r--r-- | youtube_dl/postprocessor/ffmpeg.py | 38 |
10 files changed, 189 insertions, 17 deletions
diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 76fc394bc..74e426168 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -1300,17 +1300,18 @@ class YoutubeDL(object): # subtitles download errors are already managed as troubles in relevant IE # that way it will silently go on when used with unsupporting IE subtitles = info_dict['requested_subtitles'] + ie = self.get_info_extractor(info_dict['extractor_key']) for sub_lang, sub_info in subtitles.items(): sub_format = sub_info['ext'] if sub_info.get('data') is not None: sub_data = sub_info['data'] else: try: - uf = self.urlopen(sub_info['url']) - sub_data = uf.read().decode('utf-8') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + sub_data = ie._download_webpage( + sub_info['url'], info_dict['id'], note=False) + except ExtractorError as err: self.report_warning('Unable to download subtitle for "%s": %s' % - (sub_lang, compat_str(err))) + (sub_lang, compat_str(err.cause))) continue try: sub_filename = subtitles_filename(filename, sub_lang, sub_format) diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 5ce201800..49f382695 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -170,6 +170,9 @@ def _real_main(argv=None): if opts.recodevideo is not None: if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: parser.error('invalid video recode format specified') + if opts.convertsubtitles is not None: + if opts.convertsubtitles not in ['srt', 'vtt', 'ass']: + parser.error('invalid subtitle format specified') if opts.date is not None: date = DateRange.day(opts.date) @@ -223,6 +226,11 @@ def _real_main(argv=None): 'key': 'FFmpegVideoConvertor', 'preferedformat': opts.recodevideo, }) + if opts.convertsubtitles: + postprocessors.append({ + 'key': 'FFmpegSubtitlesConvertor', + 'format': opts.convertsubtitles, + }) if opts.embedsubtitles: postprocessors.append({ 'key': 'FFmpegEmbedSubtitle', diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index d137e1104..ffcc7d9ab 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -346,6 +346,7 @@ from .ntvde import NTVDeIE from .ntvru import NTVRuIE from .nytimes import NYTimesIE from .nuvid import NuvidIE +from .odnoklassniki import OdnoklassnikiIE from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE from .openfilm import OpenFilmIE diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index 2aff410c5..d28730492 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -14,7 +14,7 @@ from ..utils import ( class KalturaIE(InfoExtractor): _VALID_URL = r'''(?x) (?:kaltura:| - https?://(:?www\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_ + https?://(:?(?:www|cdnapisec)\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_ )(?P<partner_id>\d+) (?::| /(?:[^/]+/)*?entry_id/ @@ -39,6 +39,10 @@ class KalturaIE(InfoExtractor): 'url': 'http://www.kaltura.com/index.php/kwidget/cache_st/1300318621/wid/_269692/uiconf_id/3873291/entry_id/1_1jc2y3e4', 'only_matching': True, }, + { + 'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3', + 'only_matching': True, + }, ] def _kaltura_api_call(self, video_id, actions, *args, **kwargs): diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 109055e72..5dc22da22 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -18,7 +18,7 @@ from ..utils import ( class LyndaIE(InfoExtractor): IE_NAME = 'lynda' IE_DESC = 'lynda.com videos' - _VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html' + _VALID_URL = r'https?://www\.lynda\.com/(?:[^/]+/[^/]+/\d+|player/embed)/(\d+)' _LOGIN_URL = 'https://www.lynda.com/login/login.aspx' _NETRC_MACHINE = 'lynda' @@ -27,7 +27,7 @@ class LyndaIE(InfoExtractor): ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to provide lynda.com account credentials.' - _TEST = { + _TESTS = [{ 'url': 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html', 'md5': 'ecfc6862da89489161fb9cd5f5a6fac1', 'info_dict': { @@ -36,7 +36,10 @@ class LyndaIE(InfoExtractor): 'title': 'Using the exercise files', 'duration': 68 } - } + }, { + 'url': 'https://www.lynda.com/player/embed/133770?tr=foo=1;bar=g;fizz=rt&fs=0', + 'only_matching': True, + }] def _real_initialize(self): self._login() @@ -152,7 +155,7 @@ class LyndaIE(InfoExtractor): continue appear_time = m_current.group('timecode') disappear_time = m_next.group('timecode') - text = seq_current['Caption'] + text = seq_current['Caption'].lstrip() srt += '%s\r\n%s --> %s\r\n%s' % (str(pos), appear_time, disappear_time, text) if srt: return srt diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py new file mode 100644 index 000000000..155d0ee6a --- /dev/null +++ b/youtube_dl/extractor/odnoklassniki.py @@ -0,0 +1,85 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + int_or_none, + qualities, +) + + +class OdnoklassnikiIE(InfoExtractor): + _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://ok.ru/video/20079905452', + 'md5': '8e24ad2da6f387948e7a7d44eb8668fe', + 'info_dict': { + 'id': '20079905452', + 'ext': 'mp4', + 'title': 'Культура меняет нас (прекрасный ролик!))', + 'duration': 100, + 'upload_date': '20141207', + 'uploader_id': '330537914540', + 'uploader': 'Виталий Добровольский', + 'like_count': int, + 'age_limit': 0, + }, + }, { + 'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + player = self._parse_json( + self._search_regex( + r"OKVideo\.start\(({.+?})\s*,\s*'VideoAutoplay_player'", webpage, 'player'), + video_id) + + metadata = self._parse_json(player['flashvars']['metadata'], video_id) + + movie = metadata['movie'] + title = movie['title'] + thumbnail = movie.get('poster') + duration = int_or_none(movie.get('duration')) + + author = metadata.get('author', {}) + uploader_id = author.get('id') + uploader = author.get('name') + + upload_date = unified_strdate(self._html_search_meta( + 'ya:ovs:upload_date', webpage, 'upload date')) + + age_limit = None + adult = self._html_search_meta( + 'ya:ovs:adult', webpage, 'age limit') + if adult: + age_limit = 18 if adult == 'true' else 0 + + like_count = int_or_none(metadata.get('likeCount')) + + quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd')) + + formats = [{ + 'url': f['url'], + 'ext': 'mp4', + 'format_id': f['name'], + 'quality': quality(f['name']), + } for f in metadata['videos']] + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, + 'duration': duration, + 'upload_date': upload_date, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'like_count': like_count, + 'age_limit': age_limit, + 'formats': formats, + } diff --git a/youtube_dl/extractor/svtplay.py b/youtube_dl/extractor/svtplay.py index eadb9ccb4..433dfd1cb 100644 --- a/youtube_dl/extractor/svtplay.py +++ b/youtube_dl/extractor/svtplay.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( determine_ext, @@ -8,23 +10,40 @@ from ..utils import ( class SVTPlayIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?svtplay\.se/video/(?P<id>[0-9]+)' - _TEST = { + IE_DESC = 'SVT Play and Öppet arkiv' + _VALID_URL = r'https?://(?:www\.)?(?P<host>svtplay|oppetarkiv)\.se/video/(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'http://www.svtplay.se/video/2609989/sm-veckan/sm-veckan-rally-final-sasong-1-sm-veckan-rally-final', - 'md5': 'f4a184968bc9c802a9b41316657aaa80', + 'md5': 'ade3def0643fa1c40587a422f98edfd9', 'info_dict': { 'id': '2609989', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'SM veckan vinter, Örebro - Rally, final', 'duration': 4500, 'thumbnail': 're:^https?://.*[\.-]jpg$', + 'age_limit': 0, }, - } + }, { + 'url': 'http://www.oppetarkiv.se/video/1058509/rederiet-sasong-1-avsnitt-1-av-318', + 'md5': 'c3101a17ce9634f4c1f9800f0746c187', + 'info_dict': { + 'id': '1058509', + 'ext': 'flv', + 'title': 'Farlig kryssning', + 'duration': 2566, + 'thumbnail': 're:^https?://.*[\.-]jpg$', + 'age_limit': 0, + }, + 'skip': 'Only works from Sweden', + }] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') + info = self._download_json( - 'http://www.svtplay.se/video/%s?output=json' % video_id, video_id) + 'http://www.%s.se/video/%s?output=json' % (host, video_id), video_id) title = info['context']['title'] thumbnail = info['context'].get('thumbnailImage') @@ -33,11 +52,16 @@ class SVTPlayIE(InfoExtractor): formats = [] for vr in video_info['videoReferences']: vurl = vr['url'] - if determine_ext(vurl) == 'm3u8': + ext = determine_ext(vurl) + if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( vurl, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id=vr.get('playerType'))) + elif ext == 'f4m': + formats.extend(self._extract_f4m_formats( + vurl + '?hdcore=3.3.0', video_id, + f4m_id=vr.get('playerType'))) else: formats.append({ 'format_id': vr.get('playerType'), @@ -46,6 +70,7 @@ class SVTPlayIE(InfoExtractor): self._sort_formats(formats) duration = video_info.get('materialLength') + age_limit = 18 if video_info.get('inappropriateForChildren') else 0 return { 'id': video_id, @@ -53,4 +78,5 @@ class SVTPlayIE(InfoExtractor): 'formats': formats, 'thumbnail': thumbnail, 'duration': duration, + 'age_limit': age_limit, } diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 886ce9613..58f811162 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -751,6 +751,10 @@ def parseOpts(overrideArguments=None): '--exec', metavar='CMD', dest='exec_cmd', help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'') + postproc.add_option( + '--convert-subtitles', '--convert-subs', + metavar='FORMAT', dest='convertsubtitles', default=None, + help='Convert the subtitles to other format (currently supported: srt|ass|vtt)') parser.add_option_group(general) parser.add_option_group(network) diff --git a/youtube_dl/postprocessor/__init__.py b/youtube_dl/postprocessor/__init__.py index 0ffbca258..708df3dd4 100644 --- a/youtube_dl/postprocessor/__init__.py +++ b/youtube_dl/postprocessor/__init__.py @@ -11,6 +11,7 @@ from .ffmpeg import ( FFmpegMergerPP, FFmpegMetadataPP, FFmpegVideoConvertorPP, + FFmpegSubtitlesConvertorPP, ) from .xattrpp import XAttrMetadataPP from .execafterdownload import ExecAfterDownloadPP @@ -31,6 +32,7 @@ __all__ = [ 'FFmpegMergerPP', 'FFmpegMetadataPP', 'FFmpegPostProcessor', + 'FFmpegSubtitlesConvertorPP', 'FFmpegVideoConvertorPP', 'XAttrMetadataPP', ] diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 398fe050e..30094c2f3 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -1,5 +1,6 @@ from __future__ import unicode_literals +import io import os import subprocess import sys @@ -635,3 +636,40 @@ class FFmpegFixupM4aPP(FFmpegPostProcessor): os.rename(encodeFilename(temp_filename), encodeFilename(filename)) return True, info + + +class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): + def __init__(self, downloader=None, format=None): + super(FFmpegSubtitlesConvertorPP, self).__init__(downloader) + self.format = format + + def run(self, info): + subs = info.get('requested_subtitles') + filename = info['filepath'] + new_ext = self.format + new_format = new_ext + if new_format == 'vtt': + new_format = 'webvtt' + if subs is None: + self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to convert') + return True, info + self._downloader.to_screen('[ffmpeg] Converting subtitles') + for lang, sub in subs.items(): + ext = sub['ext'] + if ext == new_ext: + self._downloader.to_screen( + '[ffmpeg] Subtitle file for %s is already in the requested' + 'format' % new_ext) + continue + new_file = subtitles_filename(filename, lang, new_ext) + self.run_ffmpeg( + subtitles_filename(filename, lang, ext), + new_file, ['-f', new_format]) + + with io.open(new_file, 'rt', encoding='utf-8') as f: + subs[lang] = { + 'ext': ext, + 'data': f.read(), + } + + return True, info |