From: Yen Chi Hsuan Date: Thu, 11 Aug 2016 11:03:08 +0000 (+0800) Subject: Merge branch 'pr/#10268' of https://github.com/lkho/youtube-dl into lkho-pr/#10268 X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=commitdiff_plain;h=3b9323d96e2be7341d2e309124075134ec8a50ca;hp=7f832413d6e4aa5aae4c904c42e0ecf4ae72aaf9 Merge branch 'pr/#10268' of https://github.com/lkho/youtube-dl into lkho-pr/#10268 --- diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 2319e45df..1c06ba36e 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.08.07*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.08.07** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.08.10*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.08.10** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ $ youtube-dl -v [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2016.08.07 +[debug] youtube-dl version 2016.08.10 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index fbf0ab7e8..95392030e 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -46,7 +46,7 @@ Make sure that someone has not already opened the issue you're trying to open. S ### Why are existing options not enough? -Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem. +Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem. ### Is there enough context in your bug report? diff --git a/ChangeLog b/ChangeLog index 657ff3e48..adbdc4f9b 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,8 +1,29 @@ version +Core ++ Recognize more formats in unified_timestamp + Extractors -* [kuwo:singer] Fix extraction +* [ctsnews] Fix extraction + + +version 2016.08.10 + +Core +* Make --metadata-from-title non fatal when title does not match the pattern +* Introduce options for randomized sleep before each download + --min-sleep-interval and --max-sleep-interval (#9930) +* Respect default in _search_json_ld + +Extractors ++ [uol] Add extractor for uol.com.br (#4263) +* [rbmaradio] Fix extraction and extract all formats (#10242) ++ [sonyliv] Add extractor for sonyliv.com (#10258) * [aparat] Fix extraction +* [cwtv] Extract HTTP formats ++ [rozhlas] Add extractor for prehravac.rozhlas.cz (#10253) +* [kuwo:singer] Fix extraction + version 2016.08.07 diff --git a/README.md b/README.md index b42d5c730..cabbbef76 100644 --- a/README.md +++ b/README.md @@ -330,7 +330,15 @@ which means you can modify it, redistribute it or use it however you like. bidirectional text support. Requires bidiv or fribidi executable in PATH --sleep-interval SECONDS Number of seconds to sleep before each - download. + download when used alone or a lower bound + of a range for randomized sleep before each + download (minimum possible number of + seconds to sleep) when used along with + --max-sleep-interval. + --max-sleep-interval SECONDS Upper bound of a range for randomized sleep + before each download (maximum possible + number of seconds to sleep). Must only be + used along with --min-sleep-interval. ## Video Format Options: -f, --format FORMAT Video format code, see the "FORMAT diff --git a/devscripts/prepare_manpage.py b/devscripts/prepare_manpage.py index e3f6339b5..ce548739f 100644 --- a/devscripts/prepare_manpage.py +++ b/devscripts/prepare_manpage.py @@ -54,17 +54,21 @@ def filter_options(readme): if in_options: if line.lstrip().startswith('-'): - option, description = re.split(r'\s{2,}', line.lstrip()) - split_option = option.split(' ') - - if not split_option[-1].startswith('-'): # metavar - option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]]) - - # Pandoc's definition_lists. See http://pandoc.org/README.html - # for more information. - ret += '\n%s\n: %s\n' % (option, description) - else: - ret += line.lstrip() + '\n' + split = re.split(r'\s{2,}', line.lstrip()) + # Description string may start with `-` as well. If there is + # only one piece then it's a description bit not an option. + if len(split) > 1: + option, description = split + split_option = option.split(' ') + + if not split_option[-1].startswith('-'): # metavar + option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]]) + + # Pandoc's definition_lists. See http://pandoc.org/README.html + # for more information. + ret += '\n%s\n: %s\n' % (option, description) + continue + ret += line.lstrip() + '\n' else: ret += line + '\n' diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 3608e1807..a44167a94 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -564,6 +564,7 @@ - **RoosterTeeth** - **RottenTomatoes** - **Roxwel** + - **Rozhlas** - **RTBF** - **rte**: Raidió Teilifís Éireann TV - **rte:radio**: Raidió Teilifís Éireann radio @@ -621,6 +622,7 @@ - **smotri:user**: Smotri.com user videos - **Snotr** - **Sohu** + - **SonyLIV** - **soundcloud** - **soundcloud:playlist** - **soundcloud:search**: Soundcloud search @@ -747,6 +749,7 @@ - **udemy:course** - **UDNEmbed**: 聯合影音 - **Unistra** + - **uol.com.br** - **Urort**: NRK P3 Urørt - **URPlay** - **USAToday** diff --git a/youtube_dl/extractor/ctsnews.py b/youtube_dl/extractor/ctsnews.py index 1622fc844..83ca90c3b 100644 --- a/youtube_dl/extractor/ctsnews.py +++ b/youtube_dl/extractor/ctsnews.py @@ -1,13 +1,12 @@ -# -*- coding: utf-8 -*- +# coding: utf-8 from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import parse_iso8601, ExtractorError +from ..utils import unified_timestamp class CtsNewsIE(InfoExtractor): IE_DESC = '華視新聞' - # https connection failed (Connection reset) _VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P\d+)\.html' _TESTS = [{ 'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html', @@ -16,7 +15,7 @@ class CtsNewsIE(InfoExtractor): 'id': '201501291578109', 'ext': 'mp4', 'title': '以色列.真主黨交火 3人死亡', - 'description': 'md5:95e9b295c898b7ff294f09d450178d7d', + 'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人...', 'timestamp': 1422528540, 'upload_date': '20150129', } @@ -28,7 +27,7 @@ class CtsNewsIE(InfoExtractor): 'id': '201309031304098', 'ext': 'mp4', 'title': '韓國31歲童顏男 貌如十多歲小孩', - 'description': 'md5:f183feeba3752b683827aab71adad584', + 'description': '越有年紀的人，越希望看起來年輕一點，而南韓卻有一位31歲的男子，看起來像是11、12歲的小孩，身...', 'thumbnail': 're:^https?://.*\.jpg$', 'timestamp': 1378205880, 'upload_date': '20130903', @@ -36,8 +35,7 @@ class CtsNewsIE(InfoExtractor): }, { # With Youtube embedded video 'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html', - 'md5': '1d842c771dc94c8c3bca5af2cc1db9c5', - 'add_ie': ['Youtube'], + 'md5': 'e4726b2ccd70ba2c319865e28f0a91d1', 'info_dict': { 'id': 'OVbfO7d0_hQ', 'ext': 'mp4', @@ -47,42 +45,37 @@ class CtsNewsIE(InfoExtractor): 'upload_date': '20150128', 'uploader_id': 'TBSCTS', 'uploader': '中華電視公司', - } + }, + 'add_ie': ['Youtube'], }] def _real_extract(self, url): news_id = self._match_id(url) page = self._download_webpage(url, news_id) - if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None): - feed_url = self._html_search_regex( - r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)', - page, 'feed url') - video_url = self._download_webpage( - feed_url, news_id, note='Fetching feed') + news_id = self._hidden_inputs(page).get('get_id') + + if news_id: + mp4_feed = self._download_json( + 'http://news.cts.com.tw/action/test_mp4feed.php', + news_id, note='Fetching feed', query={'news_id': news_id}) + video_url = mp4_feed['source_url'] else: self.to_screen('Not CTSPlayer video, trying Youtube...') youtube_url = self._search_regex( - r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url', - default=None) - if not youtube_url: - raise ExtractorError('The news includes no videos!', expected=True) + r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url') - return { - '_type': 'url', - 'url': youtube_url, - 'ie_key': 'Youtube', - } + return self.url_result(youtube_url, ie='Youtube') description = self._html_search_meta('description', page) - title = self._html_search_meta('title', page) + title = self._html_search_meta('title', page, fatal=True) thumbnail = self._html_search_meta('image', page) datetime_str = self._html_search_regex( - r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time') - # Transform into ISO 8601 format with timezone info - datetime_str = datetime_str.replace('/', '-') + ':00+0800' - timestamp = parse_iso8601(datetime_str, delimiter=' ') + r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time', fatal=False) + timestamp = None + if datetime_str: + timestamp = unified_timestamp(datetime_str) - 8 * 3600 return { 'id': news_id, diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index f1043dae6..387230be0 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -929,6 +929,7 @@ from .udemy import ( from .udn import UDNEmbedIE from .digiteka import DigitekaIE from .unistra import UnistraIE +from .uol import UOLIE from .urort import UrortIE from .urplay import URPlayIE from .usatoday import USATodayIE diff --git a/youtube_dl/extractor/uol.py b/youtube_dl/extractor/uol.py new file mode 100644 index 000000000..c27c64387 --- /dev/null +++ b/youtube_dl/extractor/uol.py @@ -0,0 +1,128 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + clean_html, + int_or_none, + parse_duration, + update_url_query, + str_or_none, +) + + +class UOLIE(InfoExtractor): + IE_NAME = 'uol.com.br' + _VALID_URL = r'https?://(?:.+?\.)?uol\.com\.br/.*?(?:(?:mediaId|v)=|view/(?:[a-z0-9]+/)?|video(?:=|/(?:\d{4}/\d{2}/\d{2}/)?))(?P\d+|[\w-]+-[A-Z0-9]+)' + _TESTS = [{ + 'url': 'http://player.mais.uol.com.br/player_video_v3.swf?mediaId=15951931', + 'md5': '25291da27dc45e0afb5718a8603d3816', + 'info_dict': { + 'id': '15951931', + 'ext': 'mp4', + 'title': 'Miss simpatia é encontrada morta', + 'description': 'md5:3f8c11a0c0556d66daf7e5b45ef823b2', + } + }, { + 'url': 'http://tvuol.uol.com.br/video/incendio-destroi-uma-das-maiores-casas-noturnas-de-londres-04024E9A3268D4C95326', + 'md5': 'e41a2fb7b7398a3a46b6af37b15c00c9', + 'info_dict': { + 'id': '15954259', + 'ext': 'mp4', + 'title': 'Incêndio destrói uma das maiores casas noturnas de Londres', + 'description': 'Em Londres, um incêndio destruiu uma das maiores boates da cidade. Não há informações sobre vítimas.', + } + }, { + 'url': 'http://mais.uol.com.br/static/uolplayer/index.html?mediaId=15951931', + 'only_matching': True, + }, { + 'url': 'http://mais.uol.com.br/view/15954259', + 'only_matching': True, + }, { + 'url': 'http://noticias.band.uol.com.br/brasilurgente/video/2016/08/05/15951931/miss-simpatia-e-encontrada-morta.html', + 'only_matching': True, + }, { + 'url': 'http://videos.band.uol.com.br/programa.asp?e=noticias&pr=brasil-urgente&v=15951931&t=Policia-desmonte-base-do-PCC-na-Cracolandia', + 'only_matching': True, + }, { + 'url': 'http://mais.uol.com.br/view/cphaa0gl2x8r/incendio-destroi-uma-das-maiores-casas-noturnas-de-londres-04024E9A3268D4C95326', + 'only_matching': True, + }, { + 'url': 'http://noticias.uol.com.br//videos/assistir.htm?video=rafaela-silva-inspira-criancas-no-judo-04024D983968D4C95326', + 'only_matching': True, + }, { + 'url': 'http://mais.uol.com.br/view/e0qbgxid79uv/15275470', + 'only_matching': True, + }] + + _FORMATS = { + '2': { + 'width': 640, + 'height': 360, + }, + '5': { + 'width': 1080, + 'height': 720, + }, + '6': { + 'width': 426, + 'height': 240, + }, + '7': { + 'width': 1920, + 'height': 1080, + }, + '8': { + 'width': 192, + 'height': 144, + }, + '9': { + 'width': 568, + 'height': 320, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + if not video_id.isdigit(): + embed_page = self._download_webpage('https://jsuol.com.br/c/tv/uol/embed/?params=[embed,%s]' % video_id, video_id) + video_id = self._search_regex(r'mediaId=(\d+)', embed_page, 'media id') + video_data = self._download_json( + 'http://mais.uol.com.br/apiuol/v3/player/getMedia/%s.json' % video_id, + video_id)['item'] + title = video_data['title'] + + query = { + 'ver': video_data.get('numRevision', 2), + 'r': 'http://mais.uol.com.br', + } + formats = [] + for f in video_data.get('formats', []): + f_url = f.get('url') or f.get('secureUrl') + if not f_url: + continue + format_id = str_or_none(f.get('id')) + fmt = { + 'format_id': format_id, + 'url': update_url_query(f_url, query), + } + fmt.update(self._FORMATS.get(format_id, {})) + formats.append(fmt) + self._sort_formats(formats) + + tags = [] + for tag in video_data.get('tags', []): + tag_description = tag.get('description') + if not tag_description: + continue + tags.append(tag_description) + + return { + 'id': video_id, + 'title': title, + 'description': clean_html(video_data.get('desMedia')), + 'thumbnail': video_data.get('thumbnail'), + 'duration': int_or_none(video_data.get('durationSeconds')) or parse_duration(video_data.get('duration')), + 'tags': tags, + 'formats': formats, + } diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index c50238ba1..a03f7184d 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -122,6 +122,7 @@ DATE_FORMATS = ( '%Y %m %d', '%Y-%m-%d', '%Y/%m/%d', + '%Y/%m/%d %H:%M', '%Y/%m/%d %H:%M:%S', '%Y-%m-%d %H:%M:%S', '%Y-%m-%d %H:%M:%S.%f', diff --git a/youtube_dl/version.py b/youtube_dl/version.py index b48552031..f7ad846d9 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2016.08.07' +__version__ = '2016.08.10'