diff options
| -rw-r--r-- | AUTHORS | 1 | ||||
| -rw-r--r-- | README.md | 2 | ||||
| -rw-r--r-- | test/test_utils.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 6 | ||||
| -rw-r--r-- | youtube_dl/extractor/airmozilla.py | 74 | ||||
| -rw-r--r-- | youtube_dl/extractor/escapist.py | 45 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/letv.py | 190 | ||||
| -rw-r--r-- | youtube_dl/extractor/mitele.py | 4 | ||||
| -rw-r--r-- | youtube_dl/extractor/rtlnow.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/telecinco.py | 9 | ||||
| -rw-r--r-- | youtube_dl/utils.py | 7 | ||||
| -rw-r--r-- | youtube_dl/version.py | 2 |
13 files changed, 326 insertions, 21 deletions
@@ -112,3 +112,4 @@ Frans de Jonge Robin de Rooij Ryan Schmidt Leslie P. Polzer +Duncan Keall @@ -139,6 +139,8 @@ which means you can modify it, redistribute it or use it however you like. dislike_count <? 50 & description" . --no-playlist If the URL refers to a video and a playlist, download only the video. + --yes-playlist If the URL refers to a video and a + playlist, download the playlist. --age-limit YEARS download only videos suitable for the given age --download-archive FILE Download only videos not listed in the diff --git a/test/test_utils.py b/test/test_utils.py index 2f8996d7b..3fba8ae11 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -246,6 +246,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_duration('2.5 hours'), 9000) self.assertEqual(parse_duration('02:03:04'), 7384) self.assertEqual(parse_duration('01:02:03:04'), 93784) + self.assertEqual(parse_duration('1 hour 3 minutes'), 3780) def test_fix_xml_ampersands(self): self.assertEqual( diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 40fc92cf7..ddb9d6670 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -8,6 +8,7 @@ from .adobetv import AdobeTVIE from .adultswim import AdultSwimIE from .aftenposten import AftenpostenIE from .aftonbladet import AftonbladetIE +from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE from .alphaporno import AlphaPornoIE from .anitube import AnitubeIE @@ -237,6 +238,11 @@ from .krasview import KrasViewIE from .ku6 import Ku6IE from .la7 import LA7IE from .laola1tv import Laola1TvIE +from .letv import ( + LetvIE, + LetvTvIE, + LetvPlaylistIE +) from .lifenews import LifeNewsIE from .liveleak import LiveLeakIE from .livestream import ( diff --git a/youtube_dl/extractor/airmozilla.py b/youtube_dl/extractor/airmozilla.py new file mode 100644 index 000000000..611ad1e9d --- /dev/null +++ b/youtube_dl/extractor/airmozilla.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + parse_iso8601, +) + + +class AirMozillaIE(InfoExtractor): + _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?' + _TEST = { + 'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/', + 'md5': '2e3e7486ba5d180e829d453875b9b8bf', + 'info_dict': { + 'id': '6x4q2w', + 'ext': 'mp4', + 'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco', + 'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+', + 'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...', + 'timestamp': 1422487800, + 'upload_date': '20150128', + 'location': 'SFO Commons', + 'duration': 3780, + 'view_count': int, + 'categories': ['Main'], + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id') + + embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id) + jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata') + metadata = self._parse_json(jwconfig, video_id) + + formats = [{ + 'url': source['file'], + 'ext': source['type'], + 'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'), + 'format': source['label'], + 'height': int(source['label'].rstrip('p')), + } for source in metadata['playlist'][0]['sources']] + self._sort_formats(formats) + + view_count = int_or_none(self._html_search_regex( + r'Views since archived: ([0-9]+)', + webpage, 'view count', fatal=False)) + timestamp = parse_iso8601(self._html_search_regex( + r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False)) + duration = parse_duration(self._search_regex( + r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)', + webpage, 'duration', fatal=False)) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'formats': formats, + 'url': self._og_search_url(webpage), + 'display_id': display_id, + 'thumbnail': metadata['playlist'][0].get('image'), + 'description': self._og_search_description(webpage), + 'timestamp': timestamp, + 'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None), + 'duration': duration, + 'view_count': view_count, + 'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage), + } diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py index 51ffec7ee..b45c1dbd0 100644 --- a/youtube_dl/extractor/escapist.py +++ b/youtube_dl/extractor/escapist.py @@ -44,14 +44,15 @@ class EscapistIE(InfoExtractor): config_url = compat_urllib_parse.unquote(self._html_search_regex( r'''(?x) (?: - <param\s+name="flashvars"\s+value="config=| + <param\s+name="flashvars".*?\s+value="config=| flashvars="config= ) - ([^"&]+) + (https?://[^"&]+) ''', webpage, 'config URL')) formats = [] + ad_formats = [] def _add_format(name, cfgurl, quality): config = self._download_json( @@ -61,14 +62,19 @@ class EscapistIE(InfoExtractor): transform_source=js_to_json) playlist = config['playlist'] - video_url = next( - p['url'] for p in playlist - if p.get('eventCategory') == 'Video') - formats.append({ - 'url': video_url, - 'format_id': name, - 'quality': quality, - }) + for p in playlist: + if p.get('eventCategory') == 'Video': + ar = formats + elif p.get('eventCategory') == 'Video Postroll': + ar = ad_formats + else: + continue + + ar.append({ + 'url': p['url'], + 'format_id': name, + 'quality': quality, + }) _add_format('normal', config_url, quality=0) hq_url = (config_url + @@ -77,10 +83,9 @@ class EscapistIE(InfoExtractor): _add_format('hq', hq_url, quality=1) except ExtractorError: pass # That's fine, we'll just use normal quality - self._sort_formats(formats) - return { + res = { 'id': video_id, 'formats': formats, 'uploader': uploader, @@ -89,3 +94,19 @@ class EscapistIE(InfoExtractor): 'thumbnail': self._og_search_thumbnail(webpage), 'description': description, } + + if self._downloader.params.get('include_ads') and ad_formats: + self._sort_formats(ad_formats) + ad_res = { + 'id': '%s-ad' % video_id, + 'title': '%s (Postroll)' % title, + 'formats': ad_formats, + } + return { + '_type': 'playlist', + 'entries': [res, ad_res], + 'title': title, + 'id': video_id, + } + + return res diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 875e1bf05..3aff57e30 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1208,7 +1208,9 @@ class GenericIE(InfoExtractor): return entries[0] else: for num, e in enumerate(entries, start=1): - e['title'] = '%s (%d)' % (e['title'], num) + # 'url' results don't have a title + if e.get('title') is not None: + e['title'] = '%s (%d)' % (e['title'], num) return { '_type': 'playlist', 'entries': entries, diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py new file mode 100644 index 000000000..583ce35b9 --- /dev/null +++ b/youtube_dl/extractor/letv.py @@ -0,0 +1,190 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import datetime +import re +import time + +from .common import InfoExtractor +from ..compat import ( + compat_urlparse, + compat_urllib_parse, +) +from ..utils import ( + determine_ext, + ExtractorError, + parse_iso8601, +) + + +class LetvIE(InfoExtractor): + _VALID_URL = r'http://www\.letv\.com/ptv/vplay/(?P<id>\d+).html' + + _TESTS = [{ + 'url': 'http://www.letv.com/ptv/vplay/22005890.html', + 'md5': 'cab23bd68d5a8db9be31c9a222c1e8df', + 'info_dict': { + 'id': '22005890', + 'ext': 'mp4', + 'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家', + 'timestamp': 1424747397, + 'upload_date': '20150224', + 'description': 'md5:a9cb175fd753e2962176b7beca21a47c', + } + }, { + 'url': 'http://www.letv.com/ptv/vplay/1415246.html', + 'info_dict': { + 'id': '1415246', + 'ext': 'mp4', + 'title': '美人天下01', + 'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda', + }, + 'expected_warnings': [ + 'publish time' + ] + }] + # http://www.letv.com/ptv/vplay/1118082.html + # This video is available only in Mainland China + + @staticmethod + def urshift(val, n): + return val >> n if val >= 0 else (val + 0x100000000) >> n + + # ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf + def ror(self, param1, param2): + _loc3_ = 0 + while _loc3_ < param2: + param1 = self.urshift(param1, 1) + ((param1 & 1) << 31) + _loc3_ += 1 + return param1 + + def calc_time_key(self, param1): + _loc2_ = 773625421 + _loc3_ = self.ror(param1, _loc2_ % 13) + _loc3_ = _loc3_ ^ _loc2_ + _loc3_ = self.ror(_loc3_, _loc2_ % 17) + return _loc3_ + + def _real_extract(self, url): + media_id = self._match_id(url) + page = self._download_webpage(url, media_id) + params = { + 'id': media_id, + 'platid': 1, + 'splatid': 101, + 'format': 1, + 'tkey': self.calc_time_key(int(time.time())), + 'domain': 'www.letv.com' + } + play_json = self._download_json( + 'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params), + media_id, 'playJson data') + + # Check for errors + playstatus = play_json['playstatus'] + if playstatus['status'] == 0: + flag = playstatus['flag'] + if flag == 1: + msg = 'Country %s auth error' % playstatus['country'] + else: + msg = 'Generic error. flag = %d' % flag + raise ExtractorError(msg, expected=True) + + playurl = play_json['playurl'] + + formats = ['350', '1000', '1300', '720p', '1080p'] + dispatch = playurl['dispatch'] + + urls = [] + for format_id in formats: + if format_id in dispatch: + media_url = playurl['domain'][0] + dispatch[format_id][0] + + # Mimic what flvxz.com do + url_parts = list(compat_urlparse.urlparse(media_url)) + qs = dict(compat_urlparse.parse_qs(url_parts[4])) + qs.update({ + 'platid': '14', + 'splatid': '1401', + 'tss': 'no', + 'retry': 1 + }) + url_parts[4] = compat_urllib_parse.urlencode(qs) + media_url = compat_urlparse.urlunparse(url_parts) + + url_info_dict = { + 'url': media_url, + 'ext': determine_ext(dispatch[format_id][1]) + } + + if format_id[-1:] == 'p': + url_info_dict['height'] = format_id[:-1] + + urls.append(url_info_dict) + + publish_time = parse_iso8601(self._html_search_regex( + r'发布时间 ([^<>]+) ', page, 'publish time', fatal=False), + delimiter=' ', timezone=datetime.timedelta(hours=8)) + description = self._html_search_meta('description', page, fatal=False) + + return { + 'id': media_id, + 'formats': urls, + 'title': playurl['title'], + 'thumbnail': playurl['pic'], + 'description': description, + 'timestamp': publish_time, + } + + +class LetvTvIE(InfoExtractor): + _VALID_URL = r'http://www.letv.com/tv/(?P<id>\d+).html' + _TESTS = [{ + 'url': 'http://www.letv.com/tv/46177.html', + 'info_dict': { + 'id': '46177', + 'title': '美人天下', + 'description': 'md5:395666ff41b44080396e59570dbac01c' + }, + 'playlist_count': 35 + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + page = self._download_webpage(url, playlist_id) + + media_urls = list(set(re.findall( + r'http://www.letv.com/ptv/vplay/\d+.html', page))) + entries = [self.url_result(media_url, ie='Letv') + for media_url in media_urls] + + title = self._html_search_meta('keywords', page, + fatal=False).split('，')[0] + description = self._html_search_meta('description', page, fatal=False) + + return self.playlist_result(entries, playlist_id, playlist_title=title, + playlist_description=description) + + +class LetvPlaylistIE(LetvTvIE): + _VALID_URL = r'http://tv.letv.com/[a-z]+/(?P<id>[a-z]+)/index.s?html' + _TESTS = [{ + 'url': 'http://tv.letv.com/izt/wuzetian/index.html', + 'info_dict': { + 'id': 'wuzetian', + 'title': '武媚娘传奇', + 'description': 'md5:e12499475ab3d50219e5bba00b3cb248' + }, + # This playlist contains some extra videos other than the drama itself + 'playlist_mincount': 96 + }, { + 'url': 'http://tv.letv.com/pzt/lswjzzjc/index.shtml', + 'info_dict': { + 'id': 'lswjzzjc', + # The title should be "劲舞青春", but I can't find a simple way to + # determine the playlist title + 'title': '乐视午间自制剧场', + 'description': 'md5:b1eef244f45589a7b5b1af9ff25a4489' + }, + 'playlist_mincount': 7 + }] diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 256758323..d8897eb90 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -18,7 +18,7 @@ class MiTeleIE(InfoExtractor): IE_NAME = 'mitele.es' _VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/' - _TEST = { + _TESTS = [{ 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', 'md5': '6a75fe9d0d3275bead0cb683c616fddb', 'info_dict': { @@ -29,7 +29,7 @@ class MiTeleIE(InfoExtractor): 'display_id': 'programa-144', 'duration': 2913, }, - } + }] def _real_extract(self, url): episode = self._match_id(url) diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py index fd93cc66f..785a8045e 100644 --- a/youtube_dl/extractor/rtlnow.py +++ b/youtube_dl/extractor/rtlnow.py @@ -146,7 +146,7 @@ class RTLnowIE(InfoExtractor): mobj = re.search(r'.*/(?P<hoster>[^/]+)/videos/(?P<play_path>.+)\.f4m', filename.text) if mobj: fmt = { - 'url': 'rtmpe://fmspay-fra2.rtl.de/' + mobj.group('hoster'), + 'url': 'rtmpe://fms.rtl.de/' + mobj.group('hoster'), 'play_path': 'mp4:' + mobj.group('play_path'), 'page_url': url, 'player_url': video_page_url + 'includes/vodplayer.swf', diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index be3f72df7..251a68680 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -6,9 +6,9 @@ from .mitele import MiTeleIE class TelecincoIE(MiTeleIE): IE_NAME = 'telecinco.es' - _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<id>.*?)\.html' + _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/(?:[^/]+/)?(?P<id>.*?)\.html' - _TEST = { + _TESTS = [{ 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html', 'info_dict': { 'id': 'MDSVID20141015_0058', @@ -16,4 +16,7 @@ class TelecincoIE(MiTeleIE): 'title': 'Con Martín Berasategui, hacer un bacalao al ...', 'duration': 662, }, - } + }, { + 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', + 'only_matching': True, + }] diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index e2631dccd..1f3bfef7d 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -54,7 +54,7 @@ from .compat import ( compiled_regex_type = type(re.compile('')) std_headers = { - 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0 (Chrome)', + 'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/20.0 (Chrome)', 'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 'Accept-Encoding': 'gzip, deflate', @@ -1290,6 +1290,7 @@ def parse_duration(s): (?P<only_mins>[0-9.]+)\s*(?:mins?|minutes?)\s*| (?P<only_hours>[0-9.]+)\s*(?:hours?)| + \s*(?P<hours_reversed>[0-9]+)\s*(?:[:h]|hours?)\s*(?P<mins_reversed>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*| (?: (?: (?:(?P<days>[0-9]+)\s*(?:[:d]|days?)\s*)? @@ -1308,10 +1309,14 @@ def parse_duration(s): return float_or_none(m.group('only_hours'), invscale=60 * 60) if m.group('secs'): res += int(m.group('secs')) + if m.group('mins_reversed'): + res += int(m.group('mins_reversed')) * 60 if m.group('mins'): res += int(m.group('mins')) * 60 if m.group('hours'): res += int(m.group('hours')) * 60 * 60 + if m.group('hours_reversed'): + res += int(m.group('hours_reversed')) * 60 * 60 if m.group('days'): res += int(m.group('days')) * 24 * 60 * 60 if m.group('ms'): diff --git a/youtube_dl/version.py b/youtube_dl/version.py index d23c6ae3d..0cbf66ed1 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2015.02.24.2' +__version__ = '2015.02.26' |