diff options
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
| -rw-r--r-- | youtube_dl/extractor/aftonbladet.py | 15 | ||||
| -rw-r--r-- | youtube_dl/extractor/bandcamp.py | 38 | ||||
| -rw-r--r-- | youtube_dl/extractor/blinkx.py | 30 | ||||
| -rw-r--r-- | youtube_dl/extractor/empflix.py | 22 | ||||
| -rw-r--r-- | youtube_dl/extractor/gamekings.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/generic.py | 9 | ||||
| -rw-r--r-- | youtube_dl/extractor/mailru.py | 5 | ||||
| -rw-r--r-- | youtube_dl/extractor/nowness.py | 9 | ||||
| -rw-r--r-- | youtube_dl/extractor/pornhub.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/streamcz.py | 22 | ||||
| -rw-r--r-- | youtube_dl/extractor/swrmediathek.py | 104 |
13 files changed, 187 insertions, 73 deletions
diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 4e657e297..cbb053e13 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -56,6 +56,7 @@ __authors__ = ( 'Nicolas Évrard', 'Jason Normore', 'Hoje Lee', + 'Adam Thalhammer', ) __license__ = 'Public Domain' diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 3503c76b7..4a4eb4b74 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -260,6 +260,7 @@ from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE from .streamcz import StreamCZIE +from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE from .teamcoco import TeamcocoIE diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py index 6a8cd14c9..cfc7370ae 100644 --- a/youtube_dl/extractor/aftonbladet.py +++ b/youtube_dl/extractor/aftonbladet.py @@ -1,7 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import datetime import re from .common import InfoExtractor @@ -16,6 +15,7 @@ class AftonbladetIE(InfoExtractor): 'ext': 'mp4', 'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna', 'description': 'Jupiters måne mest aktiv av alla himlakroppar', + 'timestamp': 1394142732, 'upload_date': '20140306', }, } @@ -27,17 +27,17 @@ class AftonbladetIE(InfoExtractor): webpage = self._download_webpage(url, video_id) # find internal video meta data - META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' + meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' internal_meta_id = self._html_search_regex( r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id') - internal_meta_url = META_URL % internal_meta_id + internal_meta_url = meta_url % internal_meta_id internal_meta_json = self._download_json( internal_meta_url, video_id, 'Downloading video meta data') # find internal video formats - FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s' + format_url = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s' internal_video_id = internal_meta_json['videoId'] - internal_formats_url = FORMATS_URL % internal_video_id + internal_formats_url = format_url % internal_video_id internal_formats_json = self._download_json( internal_formats_url, video_id, 'Downloading video formats') @@ -54,16 +54,13 @@ class AftonbladetIE(InfoExtractor): }) self._sort_formats(formats) - timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished']) - upload_date = timestamp.strftime('%Y%m%d') - return { 'id': video_id, 'title': internal_meta_json['title'], 'formats': formats, 'thumbnail': internal_meta_json['imageUrl'], 'description': internal_meta_json['shortPreamble'], - 'upload_date': upload_date, + 'timestamp': internal_meta_json['timePublished'], 'duration': internal_meta_json['duration'], 'view_count': internal_meta_json['views'], } diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index 929aafdff..dcbbdef43 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -19,7 +19,7 @@ class BandcampIE(InfoExtractor): 'md5': 'c557841d5e50261777a6585648adf439', 'info_dict': { "title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", - "duration": 10, + "duration": 9.8485, }, '_skip': 'There is a limit of 200 free downloads / month for the test song' }] @@ -28,36 +28,32 @@ class BandcampIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) title = mobj.group('title') webpage = self._download_webpage(url, title) - # We get the link to the free download page m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) - if m_download is None: + if not m_download: m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage) if m_trackinfo: json_code = m_trackinfo.group(1) - data = json.loads(json_code) - d = data[0] + data = json.loads(json_code)[0] - duration = int(round(d['duration'])) formats = [] - for format_id, format_url in d['file'].items(): - ext, _, abr_str = format_id.partition('-') - + for format_id, format_url in data['file'].items(): + ext, abr_str = format_id.split('-', 1) formats.append({ 'format_id': format_id, 'url': format_url, - 'ext': format_id.partition('-')[0], + 'ext': ext, 'vcodec': 'none', - 'acodec': format_id.partition('-')[0], - 'abr': int(format_id.partition('-')[2]), + 'acodec': ext, + 'abr': int(abr_str), }) self._sort_formats(formats) return { - 'id': compat_str(d['id']), - 'title': d['title'], + 'id': compat_str(data['id']), + 'title': data['title'], 'formats': formats, - 'duration': duration, + 'duration': float(data['duration']), } else: raise ExtractorError('No free songs found') @@ -67,11 +63,9 @@ class BandcampIE(InfoExtractor): r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', webpage, re.MULTILINE | re.DOTALL).group('id') - download_webpage = self._download_webpage(download_link, video_id, - 'Downloading free downloads page') - # We get the dictionary of the track from some javascrip code - info = re.search(r'items: (.*?),$', - download_webpage, re.MULTILINE).group(1) + download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page') + # We get the dictionary of the track from some javascript code + info = re.search(r'items: (.*?),$', download_webpage, re.MULTILINE).group(1) info = json.loads(info)[0] # We pick mp3-320 for now, until format selection can be easily implemented. mp3_info = info['downloads']['mp3-320'] @@ -100,7 +94,7 @@ class BandcampIE(InfoExtractor): class BandcampAlbumIE(InfoExtractor): IE_NAME = 'Bandcamp:album' - _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))?' + _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<title>[^?#]+))' _TEST = { 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', @@ -123,7 +117,7 @@ class BandcampAlbumIE(InfoExtractor): 'params': { 'playlistend': 2 }, - 'skip': 'Bancamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' + 'skip': 'Bandcamp imposes download limits. See test_playlists:test_bandcamp_album for the playlist test' } def _real_extract(self, url): diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py index 96408e4e0..38ccd957f 100644 --- a/youtube_dl/extractor/blinkx.py +++ b/youtube_dl/extractor/blinkx.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -import datetime import json import re @@ -19,15 +18,16 @@ class BlinkxIE(InfoExtractor): 'file': '8aQUy7GV.mp4', 'md5': '2e9a07364af40163a908edbf10bb2492', 'info_dict': { - "title": "Police Car Rolls Away", - "uploader": "stupidvideos.com", - "upload_date": "20131215", - "description": "A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!", - "duration": 14.886, - "thumbnails": [{ - "width": 100, - "height": 76, - "url": "http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg", + 'title': 'Police Car Rolls Away', + 'uploader': 'stupidvideos.com', + 'upload_date': '20131215', + 'timestamp': 1387068000, + 'description': 'A police car gently rolls away from a fight. Maybe it felt weird being around a confrontation and just had to get out of there!', + 'duration': 14.886, + 'thumbnails': [{ + 'width': 100, + 'height': 76, + 'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg', }], }, } @@ -41,9 +41,6 @@ class BlinkxIE(InfoExtractor): 'video=%s' % video_id) data_json = self._download_webpage(api_url, display_id) data = json.loads(data_json)['api']['results'][0] - dt = datetime.datetime.fromtimestamp(data['pubdate_epoch']) - pload_date = dt.strftime('%Y%m%d') - duration = None thumbnails = [] formats = [] @@ -64,10 +61,7 @@ class BlinkxIE(InfoExtractor): vcodec = remove_start(m['vcodec'], 'ff') acodec = remove_start(m['acodec'], 'ff') tbr = (int(m['vbr']) + int(m['abr'])) // 1000 - format_id = (u'%s-%sk-%s' % - (vcodec, - tbr, - m['w'])) + format_id = u'%s-%sk-%s' % (vcodec, tbr, m['w']) formats.append({ 'format_id': format_id, 'url': m['link'], @@ -88,7 +82,7 @@ class BlinkxIE(InfoExtractor): 'title': data['title'], 'formats': formats, 'uploader': data['channel_name'], - 'upload_date': pload_date, + 'timestamp': data['pubdate_epoch'], 'description': data.get('description'), 'thumbnails': thumbnails, 'duration': duration, diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index eaeee5a51..e6952588f 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -3,20 +3,18 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class EmpflixIE(InfoExtractor): _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html' _TEST = { 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', - 'md5': '5e5cc160f38ca9857f318eb97146e13e', + 'md5': 'b1bc15b6412d33902d6e5952035fcabc', 'info_dict': { 'id': '33051', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Amateur Finger Fuck', + 'description': 'Amateur solo finger fucking.', 'age_limit': 18, } } @@ -30,6 +28,8 @@ class EmpflixIE(InfoExtractor): video_title = self._html_search_regex( r'name="title" value="(?P<title>[^"]*)"', webpage, 'title') + video_description = self._html_search_regex( + r'name="description" value="([^"]*)"', webpage, 'description', fatal=False) cfg_url = self._html_search_regex( r'flashvars\.config = escape\("([^"]+)"', @@ -37,12 +37,18 @@ class EmpflixIE(InfoExtractor): cfg_xml = self._download_xml( cfg_url, video_id, note='Downloading metadata') - video_url = cfg_xml.find('videoLink').text + + formats = [ + { + 'url': item.find('videoLink').text, + 'format_id': item.find('res').text, + } for item in cfg_xml.findall('./quality/item') + ] return { 'id': video_id, - 'url': video_url, - 'ext': 'flv', 'title': video_title, + 'description': video_description, + 'formats': formats, 'age_limit': age_limit, } diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py index 233398966..11fee3d31 100644 --- a/youtube_dl/extractor/gamekings.py +++ b/youtube_dl/extractor/gamekings.py @@ -15,7 +15,7 @@ class GamekingsIE(InfoExtractor): 'id': '20130811', 'ext': 'mp4', 'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review', - 'description': 'md5:632e61a9f97d700e83f43d77ddafb6a4', + 'description': 'md5:36fd701e57e8c15ac8682a2374c99731', } } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 0e5cf0efb..38a357d3b 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -363,8 +363,13 @@ class GenericIE(InfoExtractor): return self.url_result('http://' + url) else: if default_search == 'auto_warning': - self._downloader.report_warning( - 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url) + if re.match(r'^(?:url|URL)$', url): + raise ExtractorError( + 'Invalid URL: %r . Call youtube-dl like this: youtube-dl -v "https://www.youtube.com/watch?v=BaW_jenozKc" ' % url, + expected=True) + else: + self._downloader.report_warning( + 'Falling back to youtube search for %s . Set --default-search to "auto" to suppress this warning.' % url) return self.url_result('ytsearch:' + url) else: assert ':' in default_search diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index f819c09b3..5016989cc 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import datetime from .common import InfoExtractor @@ -19,6 +18,7 @@ class MailRuIE(InfoExtractor): 'id': '46301138', 'ext': 'mp4', 'title': 'Новый Человек-Паук. Высокое напряжение. Восстание Электро', + 'timestamp': 1393232740, 'upload_date': '20140224', 'uploader': 'sonypicturesrus', 'uploader_id': 'sonypicturesrus@mail.ru', @@ -43,7 +43,6 @@ class MailRuIE(InfoExtractor): thumbnail = movie['poster'] duration = movie['duration'] - upload_date = datetime.datetime.fromtimestamp(video_data['timestamp']).strftime('%Y%m%d') view_count = video_data['views_count'] formats = [ @@ -57,7 +56,7 @@ class MailRuIE(InfoExtractor): 'id': content_id, 'title': title, 'thumbnail': thumbnail, - 'upload_date': upload_date, + 'timestamp': video_data['timestamp'], 'uploader': uploader, 'uploader_id': uploader_id, 'duration': duration, diff --git a/youtube_dl/extractor/nowness.py b/youtube_dl/extractor/nowness.py index b1bcb7e54..1c5e9401f 100644 --- a/youtube_dl/extractor/nowness.py +++ b/youtube_dl/extractor/nowness.py @@ -4,9 +4,7 @@ import re from .brightcove import BrightcoveIE from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) +from ..utils import ExtractorError class NownessIE(InfoExtractor): @@ -14,9 +12,10 @@ class NownessIE(InfoExtractor): _TEST = { 'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation', - 'file': '2520295746001.mp4', - 'md5': '0ece2f70a7bd252c7b00f3070182d418', + 'md5': '068bc0202558c2e391924cb8cc470676', 'info_dict': { + 'id': '2520295746001', + 'ext': 'mp4', 'description': 'Candor: The Art of Gesticulation', 'uploader': 'Nowness', 'title': 'Candor: The Art of Gesticulation', diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 7dd3dca0d..4118ee956 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -45,7 +45,7 @@ class PornHubIE(InfoExtractor): video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'(?s)<div class="video-info-row">\s*From: .+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<', + r'(?s)From: .+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<', webpage, 'uploader', fatal=False) thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False) if thumbnail: diff --git a/youtube_dl/extractor/streamcz.py b/youtube_dl/extractor/streamcz.py index 7362904db..73efe9542 100644 --- a/youtube_dl/extractor/streamcz.py +++ b/youtube_dl/extractor/streamcz.py @@ -5,13 +5,16 @@ import re import json from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + compat_str, +) class StreamCZIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?stream\.cz/.+/(?P<videoid>.+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.stream.cz/peklonataliri/765767-ecka-pro-deti', 'md5': '6d3ca61a8d0633c9c542b92fcb936b0c', 'info_dict': { @@ -22,7 +25,18 @@ class StreamCZIE(InfoExtractor): 'thumbnail': 'http://im.stream.cz/episode/52961d7e19d423f8f06f0100', 'duration': 256, }, - } + }, { + 'url': 'http://www.stream.cz/blanik/10002447-tri-roky-pro-mazanka', + 'md5': '246272e753e26bbace7fcd9deca0650c', + 'info_dict': { + 'id': '10002447', + 'ext': 'mp4', + 'title': 'Kancelář Blaník: Tři roky pro Mazánka', + 'description': 'md5:9177695a8b756a0a8ab160de4043b392', + 'thumbnail': 'http://im.stream.cz/episode/537f838c50c11f8d21320000', + 'duration': 368, + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -57,7 +71,7 @@ class StreamCZIE(InfoExtractor): self._sort_formats(formats) return { - 'id': str(jsonData['id']), + 'id': compat_str(jsonData['episode_id']), 'title': self._og_search_title(webpage), 'thumbnail': jsonData['episode_image_original_url'].replace('//', 'http://'), 'formats': formats, diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py new file mode 100644 index 000000000..6c688c520 --- /dev/null +++ b/youtube_dl/extractor/swrmediathek.py @@ -0,0 +1,104 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import parse_duration + + +class SWRMediathekIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?swrmediathek\.de/player\.htm\?show=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' + + _TESTS = [{ + 'url': 'http://swrmediathek.de/player.htm?show=849790d0-dab8-11e3-a953-0026b975f2e6', + 'md5': '8c5f6f0172753368547ca8413a7768ac', + 'info_dict': { + 'id': '849790d0-dab8-11e3-a953-0026b975f2e6', + 'ext': 'mp4', + 'title': 'SWR odysso', + 'description': 'md5:2012e31baad36162e97ce9eb3f157b8a', + 'thumbnail': 're:^http:.*\.jpg$', + 'duration': 2602, + 'upload_date': '20140515', + 'uploader': 'SWR Fernsehen', + 'uploader_id': '990030', + }, + }, { + 'url': 'http://swrmediathek.de/player.htm?show=0e1a8510-ddf2-11e3-9be3-0026b975f2e6', + 'md5': 'b10ab854f912eecc5a6b55cd6fc1f545', + 'info_dict': { + 'id': '0e1a8510-ddf2-11e3-9be3-0026b975f2e6', + 'ext': 'mp4', + 'title': 'Nachtcafé - Alltagsdroge Alkohol - zwischen Sektempfang und Komasaufen', + 'description': 'md5:e0a3adc17e47db2c23aab9ebc36dbee2', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 5305, + 'upload_date': '20140516', + 'uploader': 'SWR Fernsehen', + 'uploader_id': '990030', + }, + }, { + 'url': 'http://swrmediathek.de/player.htm?show=bba23e10-cb93-11e3-bf7f-0026b975f2e6', + 'md5': '4382e4ef2c9d7ce6852535fa867a0dd3', + 'info_dict': { + 'id': 'bba23e10-cb93-11e3-bf7f-0026b975f2e6', + 'ext': 'mp3', + 'title': 'Saša Stanišic: Vor dem Fest', + 'description': 'md5:5b792387dc3fbb171eb709060654e8c9', + 'thumbnail': 're:http://.*\.jpg', + 'duration': 3366, + 'upload_date': '20140520', + 'uploader': 'SWR 2', + 'uploader_id': '284670', + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + video = self._download_json( + 'http://swrmediathek.de/AjaxEntry?ekey=%s' % video_id, video_id, 'Downloading video JSON') + + attr = video['attr'] + media_type = attr['entry_etype'] + + formats = [] + for entry in video['sub']: + if entry['name'] != 'entry_media': + continue + + entry_attr = entry['attr'] + codec = entry_attr['val0'] + quality = int(entry_attr['val1']) + + fmt = { + 'url': entry_attr['val2'], + 'quality': quality, + } + + if media_type == 'Video': + fmt.update({ + 'format_note': ['144p', '288p', '544p'][quality-1], + 'vcodec': codec, + }) + elif media_type == 'Audio': + fmt.update({ + 'acodec': codec, + }) + formats.append(fmt) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': attr['entry_title'], + 'description': attr['entry_descl'], + 'thumbnail': attr['entry_image_16_9'], + 'duration': parse_duration(attr['entry_durat']), + 'upload_date': attr['entry_pdatet'][:-4], + 'uploader': attr['channel_title'], + 'uploader_id': attr['channel_idkey'], + 'formats': formats, + }
\ No newline at end of file |