diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index f40cb2c4e..98ab5b6ca 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 *2017.09.11*. 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 Issues with outdated version will be rejected.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 **2017.09.11** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.09.15*. 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 Issues with outdated version will be rejected.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 **2017.09.15** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [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 2017.09.11 +[debug] youtube-dl version 2017.09.15 [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/.gitignore b/.gitignore index a5b585f43..fbf7cecb2 100644 --- a/.gitignore +++ b/.gitignore @@ -22,6 +22,7 @@ cover/ updates_key.pem *.egg-info *.srt +*.ttml *.sbv *.vtt *.flv diff --git a/ChangeLog b/ChangeLog index c286da6c6..ba9260e3e 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,24 @@ +version + +Core +* [utils] Fix handling raw TTML subtitles (#14191) + + +version 2017.09.15 + +Core +* [downloader/fragment] Restart inconsistent incomplete fragment downloads + (#13731) +* [YoutubeDL] Download raw subtitles files (#12909, #14191) + +Extractors +* [condenast] Fix extraction (#14196, #14207) ++ [orf] Add support for f4m stories +* [tv4] Relax URL regular expression (#14206) +* [animeondemand] Bypass geo restriction ++ [animeondemand] Add support for flash videos (#9944) + + version 2017.09.11 Extractors diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 798a81d3c..6b01dc910 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -593,6 +593,7 @@ - **Openload** - **OraTV** - **orf:fm4**: radio FM4 + - **orf:fm4:story**: fm4.orf.at stories - **orf:iptv**: iptv.ORF.at - **orf:oe1**: Radio Österreich 1 - **orf:tvthek**: ORF TVthek diff --git a/test/test_utils.py b/test/test_utils.py index e50f3764e..efa73d0f4 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -1064,7 +1064,7 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')

Ignored, three

- ''' + '''.encode('utf-8') srt_data = '''1 00:00:00,000 --> 00:00:01,000 The following line contains Chinese characters and special symbols @@ -1089,7 +1089,7 @@ Line

The first line

- ''' + '''.encode('utf-8') srt_data = '''1 00:00:00,000 --> 00:00:01,000 The first line @@ -1115,7 +1115,7 @@ The first line

inner
style

-''' +'''.encode('utf-8') srt_data = '''1 00:00:02,080 --> 00:00:05,839 default stylecustom style @@ -1138,6 +1138,26 @@ part 3 ''' self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data) + dfxp_data_non_utf8 = ''' + + +
+

Line 1

+

第二行

+
+ + '''.encode('utf-16') + srt_data = '''1 +00:00:00,000 --> 00:00:01,000 +Line 1 + +2 +00:00:01,000 --> 00:00:02,000 +第二行 + +''' + self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data) + def test_cli_option(self): self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128']) self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), []) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 5405a87c5..bfb4ff225 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -89,6 +89,7 @@ from .utils import ( write_string, YoutubeDLCookieProcessor, YoutubeDLHandler, + PhantomJSwrapper, ) from .cache import Cache from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER @@ -2217,6 +2218,7 @@ class YoutubeDL(object): exe_versions = FFmpegPostProcessor.get_versions(self) exe_versions['rtmpdump'] = rtmpdump_version() + exe_versions['phantomjs'] = PhantomJSwrapper._version() exe_str = ', '.join( '%s %s' % (exe, v) for exe, v in sorted(exe_versions.items()) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 74d30ec50..2bbbf8f4d 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -2449,10 +2449,12 @@ class InfoExtractor(object): self._downloader.report_warning(msg) return res - def _set_cookie(self, domain, name, value, expire_time=None): + def _set_cookie(self, domain, name, value, expire_time=None, port=None, + path='/', secure=False, discard=False, rest={}, **kwargs): cookie = compat_cookiejar.Cookie( - 0, name, value, None, None, domain, None, - None, '/', True, False, expire_time, '', None, None, None) + 0, name, value, port, port is not None, domain, True, + domain.startswith('.'), path, True, secure, expire_time, + discard, None, None, rest) self._downloader.cookiejar.set_cookie(cookie) def _get_cookies(self, url): diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 74e991331..e9d0dd19c 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -325,7 +325,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor): class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): IE_NAME = 'dailymotion:playlist' - _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P.+?)/' + _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P[^/?#&]+)' _MORE_PAGES_INDICATOR = r'(?s)
.*?]+class="videoplayerjw"[^>]+data-title="([^"]+)"', + webpage, 'title') + + yt_urls = YoutubeIE._extract_urls(webpage) + if yt_urls: + return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key()) + container_id = self._search_regex( r'
]+data-container="([0-9]+)"', webpage, 'container ID') @@ -47,12 +74,6 @@ class HeiseIE(InfoExtractor): r'
]+data-sequenz="([0-9]+)"', webpage, 'sequenz ID') - title = self._html_search_meta('fulltitle', webpage, default=None) - if not title or title == "c't": - title = self._search_regex( - r']+class="videoplayerjw"[^>]+data-title="([^"]+)"', - webpage, 'title') - doc = self._download_xml( 'http://www.heise.de/videout/feed', video_id, query={ 'container': container_id, diff --git a/youtube_dl/extractor/morningstar.py b/youtube_dl/extractor/morningstar.py index 320d27bdd..0093bcd6c 100644 --- a/youtube_dl/extractor/morningstar.py +++ b/youtube_dl/extractor/morningstar.py @@ -8,8 +8,8 @@ from .common import InfoExtractor class MorningstarIE(InfoExtractor): IE_DESC = 'morningstar.com' - _VALID_URL = r'https?://(?:www\.)?morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www|news)\.)morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P[0-9]+)' + _TESTS = [{ 'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869', 'md5': '6c0acface7a787aadc8391e4bbf7b0f5', 'info_dict': { @@ -19,7 +19,10 @@ class MorningstarIE(InfoExtractor): 'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.", 'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$' } - } + }, { + 'url': 'http://news.morningstar.com/cover/videocenter.aspx?id=825556', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/noovo.py b/youtube_dl/extractor/noovo.py index f7fa098a5..974de3c3e 100644 --- a/youtube_dl/extractor/noovo.py +++ b/youtube_dl/extractor/noovo.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( int_or_none, + js_to_json, smuggle_url, try_get, ) @@ -24,8 +25,6 @@ class NoovoIE(InfoExtractor): 'timestamp': 1491399228, 'upload_date': '20170405', 'uploader_id': '618566855001', - 'creator': 'vtele', - 'view_count': int, 'series': 'RPM+', }, 'params': { @@ -37,13 +36,11 @@ class NoovoIE(InfoExtractor): 'info_dict': { 'id': '5395865725001', 'title': 'Épisode 13 : Les retrouvailles', - 'description': 'md5:336d5ebc5436534e61d16e63ddfca327', + 'description': 'md5:888c3330f0c1b4476c5bc99a1c040473', 'ext': 'mp4', 'timestamp': 1492019320, 'upload_date': '20170412', 'uploader_id': '618566855001', - 'creator': 'vtele', - 'view_count': int, 'series': "L'amour est dans le pré", 'season_number': 5, 'episode': 'Épisode 13', @@ -58,40 +55,46 @@ class NoovoIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - data = self._download_json( - 'http://api.noovo.ca/api/v1/pages/single-episode/%s' % video_id, - video_id)['data'] + webpage = self._download_webpage(url, video_id) - content = try_get(data, lambda x: x['contents'][0]) + bc_url = BrightcoveNewIE._extract_url(self, webpage) - brightcove_id = data.get('brightcoveId') or content['brightcoveId'] + data = self._parse_json( + self._search_regex( + r'(?s)dataLayer\.push\(\s*({.+?})\s*\);', webpage, 'data', + default='{}'), + video_id, transform_source=js_to_json, fatal=False) + + title = try_get( + data, lambda x: x['video']['nom'], + compat_str) or self._html_search_meta( + 'dcterms.Title', webpage, 'title', fatal=True) + + description = self._html_search_meta( + ('dcterms.Description', 'description'), webpage, 'description') series = try_get( - data, ( - lambda x: x['show']['title'], - lambda x: x['season']['show']['title']), - compat_str) + data, lambda x: x['emission']['nom']) or self._search_regex( + r']+class="banner-card__subtitle h4"[^>]*>([^<]+)', + webpage, 'series', default=None) - episode = None - og = data.get('og') - if isinstance(og, dict) and og.get('type') == 'video.episode': - episode = og.get('title') + season_el = try_get(data, lambda x: x['emission']['saison'], dict) or {} + season = try_get(season_el, lambda x: x['nom'], compat_str) + season_number = int_or_none(try_get(season_el, lambda x: x['numero'])) - video = content or data + episode_el = try_get(season_el, lambda x: x['episode'], dict) or {} + episode = try_get(episode_el, lambda x: x['nom'], compat_str) + episode_number = int_or_none(try_get(episode_el, lambda x: x['numero'])) return { '_type': 'url_transparent', 'ie_key': BrightcoveNewIE.ie_key(), - 'url': smuggle_url( - self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, - {'geo_countries': ['CA']}), - 'id': brightcove_id, - 'title': video.get('title'), - 'creator': video.get('source'), - 'view_count': int_or_none(video.get('viewsCount')), + 'url': smuggle_url(bc_url, {'geo_countries': ['CA']}), + 'title': title, + 'description': description, 'series': series, - 'season_number': int_or_none(try_get( - data, lambda x: x['season']['seasonNumber'])), + 'season': season, + 'season_number': season_number, 'episode': episode, - 'episode_number': int_or_none(data.get('episodeNumber')), + 'episode_number': episode_number, } diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index d8036b54a..292476ef8 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -4,10 +4,11 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_chr from ..utils import ( determine_ext, ExtractorError, + get_element_by_id, + PhantomJSwrapper, ) @@ -58,6 +59,8 @@ class OpenloadIE(InfoExtractor): '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' + @staticmethod def _extract_urls(webpage): return re.findall( @@ -66,47 +69,22 @@ class OpenloadIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id) + url = 'https://openload.co/embed/%s/' % video_id + headers = { + 'User-Agent': self._USER_AGENT, + } + + webpage = self._download_webpage(url, video_id, headers=headers) if 'File not found' in webpage or 'deleted by the owner' in webpage: - raise ExtractorError('File not found', expected=True) + raise ExtractorError('File not found', expected=True, video_id=video_id) - ol_id = self._search_regex( - ']+id="[^"]+"[^>]*>([0-9A-Za-z]+)', - webpage, 'openload ID') + phantom = PhantomJSwrapper(self, required_version='2.0') + webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers) - decoded = '' - a = ol_id[0:24] - b = [] - for i in range(0, len(a), 8): - b.append(int(a[i:i + 8] or '0', 16)) - ol_id = ol_id[24:] - j = 0 - k = 0 - while j < len(ol_id): - c = 128 - d = 0 - e = 0 - f = 0 - _more = True - while _more: - if j + 1 >= len(ol_id): - c = 143 - f = int(ol_id[j:j + 2] or '0', 16) - j += 2 - d += (f & 127) << e - e += 7 - _more = f >= c - g = d ^ b[k % 3] - for i in range(4): - char_dec = (g >> 8 * i) & (c + 127) - char = compat_chr(char_dec) - if char != '#': - decoded += char - k += 1 + decoded_id = get_element_by_id('streamurl', webpage) - video_url = 'https://openload.co/stream/%s?mime=true' - video_url = video_url % decoded + video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id title = self._og_search_title(webpage, default=None) or self._search_regex( r']+class=["\']title["\'][^>]*>([^<]+)', webpage, @@ -114,15 +92,17 @@ class OpenloadIE(InfoExtractor): 'description', webpage, 'title', fatal=True) entries = self._parse_html5_media_entries(url, webpage, video_id) - subtitles = entries[0]['subtitles'] if entries else None + entry = entries[0] if entries else {} + subtitles = entry.get('subtitles') info_dict = { 'id': video_id, 'title': title, - 'thumbnail': self._og_search_thumbnail(webpage, default=None), + 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None), 'url': video_url, # Seems all videos have extensions in their titles 'ext': determine_ext(title, 'mp4'), 'subtitles': subtitles, + 'http_headers': headers, } return info_dict diff --git a/youtube_dl/extractor/popcorntv.py b/youtube_dl/extractor/popcorntv.py new file mode 100644 index 000000000..ac901f426 --- /dev/null +++ b/youtube_dl/extractor/popcorntv.py @@ -0,0 +1,78 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + extract_attributes, + int_or_none, + unified_timestamp, +) + + +class PopcornTVIE(InfoExtractor): + _VALID_URL = r'https?://[^/]+\.popcorntv\.it/guarda/(?P[^/]+)/(?P\d+)' + _TESTS = [{ + 'url': 'https://animemanga.popcorntv.it/guarda/food-wars-battaglie-culinarie-episodio-01/9183', + 'md5': '47d65a48d147caf692ab8562fe630b45', + 'info_dict': { + 'id': '9183', + 'display_id': 'food-wars-battaglie-culinarie-episodio-01', + 'ext': 'mp4', + 'title': 'Food Wars, Battaglie Culinarie | Episodio 01', + 'description': 'md5:b8bea378faae4651d3b34c6e112463d0', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1497610857, + 'upload_date': '20170616', + 'duration': 1440, + 'view_count': int, + }, + }, { + 'url': 'https://cinema.popcorntv.it/guarda/smash-cut/10433', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id, video_id = mobj.group('display_id', 'id') + + webpage = self._download_webpage(url, display_id) + + m3u8_url = extract_attributes( + self._search_regex( + r'(]+itemprop=["\'](?:content|embed)Url[^>]*>)', + webpage, 'content' + ))['href'] + + formats = self._extract_m3u8_formats( + m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + + title = self._search_regex( + r']+itemprop=["\']name[^>]*>([^<]+)', webpage, + 'title', default=None) or self._og_search_title(webpage) + + description = self._html_search_regex( + r'(?s)]+itemprop=["\']description[^>]*>(.+?)', + webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + timestamp = unified_timestamp(self._html_search_meta( + 'uploadDate', webpage, 'timestamp')) + print(self._html_search_meta( + 'duration', webpage)) + duration = int_or_none(self._html_search_meta( + 'duration', webpage), invscale=60) + view_count = int_or_none(self._html_search_meta( + 'interactionCount', webpage, 'view count')) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + } diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index 2daf9dfac..c926c99a9 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -28,7 +28,7 @@ from ..utils import ( class TwitchBaseIE(InfoExtractor): - _VALID_URL_BASE = r'https?://(?:www\.)?twitch\.tv' + _VALID_URL_BASE = r'https?://(?:(?:www|go)\.)?twitch\.tv' _API_BASE = 'https://api.twitch.tv' _USHER_BASE = 'https://usher.ttvnw.net' @@ -217,7 +217,7 @@ class TwitchVodIE(TwitchItemBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:www\.)?twitch\.tv/(?:[^/]+/v|videos)/| + (?:(?:www|go)\.)?twitch\.tv/(?:[^/]+/v|videos)/| player\.twitch\.tv/\?.*?\bvideo=v ) (?P\d+) @@ -458,7 +458,7 @@ class TwitchStreamIE(TwitchBaseIE): _VALID_URL = r'''(?x) https?:// (?: - (?:www\.)?twitch\.tv/| + (?:(?:www|go)\.)?twitch\.tv/| player\.twitch\.tv/\?.*?\bchannel= ) (?P[^/#?]+) @@ -489,6 +489,9 @@ class TwitchStreamIE(TwitchBaseIE): }, { 'url': 'https://player.twitch.tv/?channel=lotsofs', 'only_matching': True, + }, { + 'url': 'https://go.twitch.tv/food', + 'only_matching': True, }] @classmethod diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index 0f8c156a7..c21a09c01 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -42,7 +42,7 @@ class VGTVIE(XstreamIE): ) /? (?: - \#!/(?:video|live)/| + (?:\#!/)?(?:video|live)/| embed?.*id=| articles/ )| @@ -146,7 +146,11 @@ class VGTVIE(XstreamIE): { 'url': 'abtv:140026', 'only_matching': True, - } + }, + { + 'url': 'http://www.vgtv.no/video/84196/hevnen-er-soet-episode-10-abu', + 'only_matching': True, + }, ] def _real_extract(self, url): diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index e9c8bf824..853e5c75f 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -23,9 +23,9 @@ class VikiBaseIE(InfoExtractor): _API_QUERY_TEMPLATE = '/v4/%sapp=%s&t=%s&site=www.viki.com' _API_URL_TEMPLATE = 'http://api.viki.io%s&sig=%s' - _APP = '65535a' + _APP = '100005a' _APP_VERSION = '2.2.5.1428709186' - _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)' + _APP_SECRET = 'MM_d*yP@`&1@]@!AVrXf_o-HVEnoTnm$O-ti4[G~$JDI/Dc-&piU&z&5.;:}95=Iad' _GEO_BYPASS = False _NETRC_MACHINE = 'viki' diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 51256a3fb..f71d413b5 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -585,7 +585,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor): dfxp_file = old_file srt_file = subtitles_filename(filename, lang, 'srt') - with io.open(dfxp_file, 'rt', encoding='utf-8') as f: + with open(dfxp_file, 'rb') as f: srt_data = dfxp2srt(f.read()) with io.open(srt_file, 'wt', encoding='utf-8') as f: diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index c42dd4c3a..acc4f987b 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -2572,14 +2572,18 @@ def srt_subtitles_timecode(seconds): def dfxp2srt(dfxp_data): + ''' + @param dfxp_data A bytes-like object containing DFXP data + @returns A unicode object containing converted SRT data + ''' LEGACY_NAMESPACES = ( - ('http://www.w3.org/ns/ttml', [ - 'http://www.w3.org/2004/11/ttaf1', - 'http://www.w3.org/2006/04/ttaf1', - 'http://www.w3.org/2006/10/ttaf1', + (b'http://www.w3.org/ns/ttml', [ + b'http://www.w3.org/2004/11/ttaf1', + b'http://www.w3.org/2006/04/ttaf1', + b'http://www.w3.org/2006/10/ttaf1', ]), - ('http://www.w3.org/ns/ttml#styling', [ - 'http://www.w3.org/ns/ttml#style', + (b'http://www.w3.org/ns/ttml#styling', [ + b'http://www.w3.org/ns/ttml#style', ]), ) @@ -2674,7 +2678,7 @@ def dfxp2srt(dfxp_data): for ns in v: dfxp_data = dfxp_data.replace(ns, k) - dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8')) + dfxp = compat_etree_fromstring(dfxp_data) out = [] paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p') @@ -3822,6 +3826,220 @@ def write_xattr(path, key, value): "or the 'xattr' binary.") +def cookie_to_dict(cookie): + cookie_dict = { + 'name': cookie.name, + 'value': cookie.value, + } + if cookie.port_specified: + cookie_dict['port'] = cookie.port + if cookie.domain_specified: + cookie_dict['domain'] = cookie.domain + if cookie.path_specified: + cookie_dict['path'] = cookie.path + if cookie.expires is not None: + cookie_dict['expires'] = cookie.expires + if cookie.secure is not None: + cookie_dict['secure'] = cookie.secure + if cookie.discard is not None: + cookie_dict['discard'] = cookie.discard + try: + if (cookie.has_nonstandard_attr('httpOnly') or + cookie.has_nonstandard_attr('httponly') or + cookie.has_nonstandard_attr('HttpOnly')): + cookie_dict['httponly'] = True + except TypeError: + pass + return cookie_dict + + +def cookie_jar_to_list(cookie_jar): + return [cookie_to_dict(cookie) for cookie in cookie_jar] + + +class PhantomJSwrapper(object): + """PhantomJS wrapper class""" + + _TEMPLATE = r''' + phantom.onError = function(msg, trace) {{ + var msgStack = ['PHANTOM ERROR: ' + msg]; + if(trace && trace.length) {{ + msgStack.push('TRACE:'); + trace.forEach(function(t) {{ + msgStack.push(' -> ' + (t.file || t.sourceURL) + ': ' + t.line + + (t.function ? ' (in function ' + t.function +')' : '')); + }}); + }} + console.error(msgStack.join('\n')); + phantom.exit(1); + }}; + var page = require('webpage').create(); + var fs = require('fs'); + var read = {{ mode: 'r', charset: 'utf-8' }}; + var write = {{ mode: 'w', charset: 'utf-8' }}; + JSON.parse(fs.read("{cookies}", read)).forEach(function(x) {{ + phantom.addCookie(x); + }}); + page.settings.resourceTimeout = {timeout}; + page.settings.userAgent = "{ua}"; + page.onLoadStarted = function() {{ + page.evaluate(function() {{ + delete window._phantom; + delete window.callPhantom; + }}); + }}; + var saveAndExit = function() {{ + fs.write("{html}", page.content, write); + fs.write("{cookies}", JSON.stringify(phantom.cookies), write); + phantom.exit(); + }}; + page.onLoadFinished = function(status) {{ + if(page.url === "") {{ + page.setContent(fs.read("{html}", read), "{url}"); + }} + else {{ + {jscode} + }} + }}; + page.open(""); + ''' + + _TMP_FILE_NAMES = ['script', 'html', 'cookies'] + + @staticmethod + def _version(): + return get_exe_version('phantomjs', version_re=r'([0-9.]+)') + + def __init__(self, extractor, required_version=None, timeout=10000): + self.exe = check_executable('phantomjs', ['-v']) + if not self.exe: + raise ExtractorError('PhantomJS executable not found in PATH, ' + 'download it from http://phantomjs.org', + expected=True) + + self.extractor = extractor + + if required_version: + version = self._version() + if is_outdated_version(version, required_version): + self.extractor._downloader.report_warning( + 'Your copy of PhantomJS is outdated, update it to version ' + '%s or newer if you encounter any errors.' % required_version) + + self.options = { + 'timeout': timeout, + } + self._TMP_FILES = {} + for name in self._TMP_FILE_NAMES: + tmp = tempfile.NamedTemporaryFile(delete=False) + tmp.close() + self._TMP_FILES[name] = tmp + + def __del__(self): + for name in self._TMP_FILE_NAMES: + try: + os.remove(self._TMP_FILES[name].name) + except: + pass + + def _save_cookies(self, url): + cookies = cookie_jar_to_list(self.extractor._downloader.cookiejar) + for cookie in cookies: + if 'path' not in cookie: + cookie['path'] = '/' + if 'domain' not in cookie: + cookie['domain'] = compat_urlparse.urlparse(url).netloc + with open(self._TMP_FILES['cookies'].name, 'wb') as f: + f.write(json.dumps(cookies).encode('utf-8')) + + def _load_cookies(self): + with open(self._TMP_FILES['cookies'].name, 'rb') as f: + cookies = json.loads(f.read().decode('utf-8')) + for cookie in cookies: + if cookie['httponly'] is True: + cookie['rest'] = {'httpOnly': None} + if 'expiry' in cookie: + cookie['expire_time'] = cookie['expiry'] + self.extractor._set_cookie(**cookie) + + def get(self, url, html=None, video_id=None, note=None, note2='Executing JS on webpage', headers={}, jscode='saveAndExit();'): + """ + Downloads webpage (if needed) and executes JS + + Params: + url: website url + html: optional, html code of website + video_id: video id + note: optional, displayed when downloading webpage + note2: optional, displayed when executing JS + headers: custom http headers + jscode: code to be executed when page is loaded + + Returns tuple with: + * downloaded website (after JS execution) + * anything you print with `console.log` (but not inside `page.execute`!) + + In most cases you don't need to add any `jscode`. + It is executed in `page.onLoadFinished`. + `saveAndExit();` is mandatory, use it instead of `phantom.exit()` + It is possible to wait for some element on the webpage, for example: + var check = function() { + var elementFound = page.evaluate(function() { + return document.querySelector('#b.done') !== null; + }); + if(elementFound) + saveAndExit(); + else + window.setTimeout(check, 500); + } + + page.evaluate(function(){ + document.querySelector('#a').click(); + }); + check(); + """ + if 'saveAndExit();' not in jscode: + raise ExtractorError('`saveAndExit();` not found in `jscode`') + if not html: + html = self.extractor._download_webpage(url, video_id, note=note, headers=headers) + with open(self._TMP_FILES['html'].name, 'wb') as f: + f.write(html.encode('utf-8')) + + self._save_cookies(url) + + replaces = self.options + replaces['url'] = url + user_agent = headers.get('User-Agent') or std_headers['User-Agent'] + replaces['ua'] = user_agent.replace('"', '\\"') + replaces['jscode'] = jscode + + for x in self._TMP_FILE_NAMES: + replaces[x] = self._TMP_FILES[x].name.replace('\\', '\\\\').replace('"', '\\"') + + with open(self._TMP_FILES['script'].name, 'wb') as f: + f.write(self._TEMPLATE.format(**replaces).encode('utf-8')) + + if video_id is None: + self.extractor.to_screen('%s' % (note2,)) + else: + self.extractor.to_screen('%s: %s' % (video_id, note2)) + + p = subprocess.Popen([ + self.exe, '--ssl-protocol=any', + self._TMP_FILES['script'].name + ], stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out, err = p.communicate() + if p.returncode != 0: + raise ExtractorError( + 'Executing JS failed\n:' + encodeArgument(err)) + with open(self._TMP_FILES['html'].name, 'rb') as f: + html = f.read().decode('utf-8') + + self._load_cookies() + + return (html, encodeArgument(out)) + + def random_birthday(year_field, month_field, day_field): return { year_field: str(random.randint(1950, 1995)), diff --git a/youtube_dl/version.py b/youtube_dl/version.py index cdcb32e06..8399c04fe 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2017.09.11' +__version__ = '2017.09.15'