Merge branch 'master' into BlenderCloud-issue-13282

This commit is contained in:
Parmjit Virk 2017-07-09 18:20:58 -05:00
commit 6e15af0db5
18 changed files with 470 additions and 83 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.07.02*. 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 Issues with outdated version will be rejected.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 **2017.07.02**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.07.09*. 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 Issues with outdated version will be rejected.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 **2017.07.09**
### 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 <your command line>
[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 2017.07.02
[debug] youtube-dl version 2017.07.09
[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: {}

View File

@ -1,7 +1,27 @@
version <unreleased>
version 2017.07.09
Core
+ [extractor/common] Add support for AMP tags in _parse_html5_media_entries
+ [utils] Support attributes with no values in get_elements_by_attribute
Extractors
+ [dailymail] Add support for embeds
+ [joj] Add support for joj.sk (#13268)
* [abc.net.au:iview] Extract more formats (#13492, #13489)
* [egghead:course] Fix extraction (#6635, #13370)
+ [cjsw] Add support for cjsw.com (#13525)
+ [eagleplatform] Add support for referrer protected videos (#13557)
+ [eagleplatform] Add support for another embed pattern (#13557)
* [veoh] Extend URL regular expression (#13601)
* [npo:live] Fix live stream id extraction (#13568, #13605)
* [googledrive] Fix height extraction (#13603)
+ [dailymotion] Add support for new layout (#13580)
- [yam] Remove extractor
* [xhamster] Extract all formats and fix duration extraction (#13593)
+ [xhamster] Add support for new URL schema (#13593)
* [espn] Extend URL regular expression (#13244, #13549)
* [kaltura] Fix typo in subtitles extraction (#13569)
* [vier] Adapt extraction to redesign (#13575)
version 2017.07.02

View File

@ -154,6 +154,7 @@
- **chirbit**
- **chirbit:profile**
- **Cinchcast**
- **CJSW**
- **Clipfish**
- **cliphunter**
- **ClipRs**
@ -369,6 +370,7 @@
- **Jamendo**
- **JamendoAlbum**
- **JeuxVideo**
- **Joj**
- **Jove**
- **jpopsuki.tv**
- **JWPlatform**
@ -996,7 +998,6 @@
- **XVideos**
- **XXXYMovies**
- **Yahoo**: Yahoo screen and movies
- **Yam**: 蕃薯藤yam天空部落
- **yandexmusic:album**: Яндекс.Музыка - Альбом
- **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
- **yandexmusic:track**: Яндекс.Музыка - Трек

View File

@ -1890,7 +1890,7 @@ class YoutubeDL(object):
info_dict.get('protocol') == 'm3u8' and
self.params.get('hls_prefer_native')):
if fixup_policy == 'warn':
self.report_warning('%s: malformated aac bitstream.' % (
self.report_warning('%s: malformed AAC bitstream detected.' % (
info_dict['id']))
elif fixup_policy == 'detect_or_warn':
fixup_pp = FFmpegFixupM3u8PP(self)
@ -1899,7 +1899,7 @@ class YoutubeDL(object):
info_dict['__postprocessors'].append(fixup_pp)
else:
self.report_warning(
'%s: malformated aac bitstream. %s'
'%s: malformed AAC bitstream detected. %s'
% (info_dict['id'], INSTALL_FFMPEG_MESSAGE))
else:
assert fixup_policy in ('ignore', 'never')

View File

@ -3,11 +3,13 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
js_to_json,
int_or_none,
parse_iso8601,
try_get,
)
@ -124,7 +126,20 @@ class ABCIViewIE(InfoExtractor):
title = video_params.get('title') or video_params['seriesTitle']
stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
formats = self._extract_akamai_formats(stream['hds-unmetered'], video_id)
format_urls = [
try_get(stream, lambda x: x['hds-unmetered'], compat_str)]
# May have higher quality video
sd_url = try_get(
stream, lambda x: x['streams']['hds']['sd'], compat_str)
if sd_url:
format_urls.append(sd_url.replace('metered', 'um'))
formats = []
for format_url in format_urls:
if format_url:
formats.extend(
self._extract_akamai_formats(format_url, video_id))
self._sort_formats(formats)
subtitles = {}

View File

@ -0,0 +1,72 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
unescapeHTML,
)
class CJSWIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program>[^/]+)/episode/(?P<id>\d+)'
_TESTS = [{
'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
'md5': 'cee14d40f1e9433632c56e3d14977120',
'info_dict': {
'id': '91d9f016-a2e7-46c5-8dcb-7cbcd7437c41',
'ext': 'mp3',
'title': 'Freshly Squeezed Episode June 20, 2017',
'description': 'md5:c967d63366c3898a80d0c7b0ff337202',
'series': 'Freshly Squeezed',
'episode_id': '20170620',
},
}, {
# no description
'url': 'http://cjsw.com/program/road-pops/episode/20170707/',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
program, episode_id = mobj.group('program', 'id')
audio_id = '%s/%s' % (program, episode_id)
webpage = self._download_webpage(url, episode_id)
title = unescapeHTML(self._search_regex(
(r'<h1[^>]+class=["\']episode-header__title["\'][^>]*>(?P<title>[^<]+)',
r'data-audio-title=(["\'])(?P<title>(?:(?!\1).)+)\1'),
webpage, 'title', group='title'))
audio_url = self._search_regex(
r'<button[^>]+data-audio-src=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'audio url', group='url')
audio_id = self._search_regex(
r'/([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.mp3',
audio_url, 'audio id', default=audio_id)
formats = [{
'url': audio_url,
'ext': determine_ext(audio_url, 'mp3'),
'vcodec': 'none',
}]
description = self._html_search_regex(
r'<p>(?P<description>.+?)</p>', webpage, 'description',
default=None)
series = self._search_regex(
r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
'series', default=program, group='name')
return {
'id': audio_id,
'title': title,
'description': description,
'formats': formats,
'series': series,
'episode_id': episode_id,
}

View File

@ -2132,15 +2132,18 @@ class InfoExtractor(object):
return is_plain_url, formats
entries = []
# amp-video and amp-audio are very similar to their HTML5 counterparts
# so we wll include them right here (see
# https://www.ampproject.org/docs/reference/components/amp-video)
media_tags = [(media_tag, media_type, '')
for media_tag, media_type
in re.findall(r'(?s)(<(video|audio)[^>]*/>)', webpage)]
in re.findall(r'(?s)(<(?:amp-)?(video|audio)[^>]*/>)', webpage)]
media_tags.extend(re.findall(
# We only allow video|audio followed by a whitespace or '>'.
# Allowing more characters may end up in significant slow down (see
# https://github.com/rg3/youtube-dl/issues/11979, example URL:
# http://www.porntrex.com/maps/videositemap.xml).
r'(?s)(<(?P<tag>video|audio)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
r'(?s)(<(?P<tag>(?:amp-)?(?:video|audio))(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
for media_tag, media_type, media_content in media_tags:
media_info = {
'formats': [],

View File

@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
@ -12,8 +14,8 @@ from ..utils import (
class DailyMailIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html',
'md5': 'f6129624562251f628296c3a9ffde124',
'info_dict': {
@ -22,7 +24,16 @@ class DailyMailIE(InfoExtractor):
'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
}
}
}, {
'url': 'http://www.dailymail.co.uk/embed/video/1295863.html',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)',
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@ -11,6 +11,7 @@ from ..compat import (
from ..utils import (
ExtractorError,
int_or_none,
unsmuggle_url,
)
@ -50,6 +51,10 @@ class EaglePlatformIE(InfoExtractor):
'view_count': int,
},
'skip': 'Georestricted',
}, {
# referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
'url': 'eagleplatform:tvrainru.media.eagleplatform.com:582306',
'only_matching': True,
}]
@staticmethod
@ -60,16 +65,40 @@ class EaglePlatformIE(InfoExtractor):
webpage)
if mobj is not None:
return mobj.group('url')
# Basic usage embedding (see http://dultonmedia.github.io/eplayer/)
PLAYER_JS_RE = r'''
<script[^>]+
src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
.+?
'''
# "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)
mobj = re.search(
r'''(?xs)
<script[^>]+
src=(?P<q1>["\'])(?:https?:)?//(?P<host>.+?\.media\.eagleplatform\.com)/player/player\.js(?P=q1)
.+?
%s
<div[^>]+
class=(?P<q2>["\'])eagleplayer(?P=q2)[^>]+
class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+
data-id=["\'](?P<id>\d+)
''', webpage)
''' % PLAYER_JS_RE, webpage)
if mobj is not None:
return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
# Generalization of "Javascript code usage", "Combined usage" and
# "Usage without attaching to DOM" embeddings (see
# http://dultonmedia.github.io/eplayer/)
mobj = re.search(
r'''(?xs)
%s
<script>
.+?
new\s+EaglePlayer\(
(?:[^,]+\s*,\s*)?
{
.+?
\bid\s*:\s*["\']?(?P<id>\d+)
.+?
}
\s*\)
.+?
</script>
''' % PLAYER_JS_RE, webpage)
if mobj is not None:
return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
@ -79,9 +108,10 @@ class EaglePlatformIE(InfoExtractor):
if status != 200:
raise ExtractorError(' '.join(response['errors']), expected=True)
def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata', *args, **kwargs):
def _download_json(self, url_or_request, video_id, *args, **kwargs):
try:
response = super(EaglePlatformIE, self)._download_json(url_or_request, video_id, note)
response = super(EaglePlatformIE, self)._download_json(
url_or_request, video_id, *args, **kwargs)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError):
response = self._parse_json(ee.cause.read().decode('utf-8'), video_id)
@ -93,11 +123,24 @@ class EaglePlatformIE(InfoExtractor):
return self._download_json(url_or_request, video_id, note)['data'][0]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
mobj = re.match(self._VALID_URL, url)
host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
headers = {}
query = {
'id': video_id,
}
referrer = smuggled_data.get('referrer')
if referrer:
headers['Referer'] = referrer
query['referrer'] = referrer
player_data = self._download_json(
'http://%s/api/player_data?id=%s' % (host, video_id), video_id)
'http://%s/api/player_data' % host, video_id,
headers=headers, query=query)
media = player_data['data']['playlist']['viewports'][0]['medialist'][0]

View File

@ -1,15 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class EggheadCourseIE(InfoExtractor):
IE_DESC = 'egghead.io course'
IE_NAME = 'egghead:course'
_VALID_URL = r'https://egghead\.io/courses/(?P<id>[a-zA-Z_0-9-]+)'
_VALID_URL = r'https://egghead\.io/courses/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
'playlist_count': 29,
@ -22,18 +20,16 @@ class EggheadCourseIE(InfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex(r'<h1 class="title">([^<]+)</h1>', webpage, 'title')
ul = self._search_regex(r'(?s)<ul class="series-lessons-list">(.*?)</ul>', webpage, 'session list')
course = self._download_json(
'https://egghead.io/api/v1/series/%s' % playlist_id, playlist_id)
found = re.findall(r'(?s)<a class="[^"]*"\s*href="([^"]+)">\s*<li class="item', ul)
entries = [self.url_result(m) for m in found]
entries = [
self.url_result(
'wistia:%s' % lesson['wistia_id'], ie='Wistia',
video_id=lesson['wistia_id'], video_title=lesson.get('title'))
for lesson in course['lessons'] if lesson.get('wistia_id')]
return {
'_type': 'playlist',
'id': playlist_id,
'title': title,
'description': self._og_search_description(webpage),
'entries': entries,
}
return self.playlist_result(
entries, playlist_id, course.get('title'),
course.get('description'))

View File

@ -189,6 +189,7 @@ from .chirbit import (
ChirbitProfileIE,
)
from .cinchcast import CinchcastIE
from .cjsw import CJSWIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .cliprs import ClipRsIE
@ -473,6 +474,7 @@ from .jamendo import (
)
from .jeuxvideo import JeuxVideoIE
from .jove import JoveIE
from .joj import JojIE
from .jwplatform import JWPlatformIE
from .jpopsukitv import JpopsukiIE
from .kaltura import KalturaIE
@ -1208,7 +1210,8 @@ from .vk import (
)
from .vlive import (
VLiveIE,
VLiveChannelIE
VLiveChannelIE,
VLivePlaylistIE
)
from .vodlocker import VodlockerIE
from .vodpl import VODPlIE

View File

@ -57,6 +57,7 @@ from .dailymotion import (
DailymotionIE,
DailymotionCloudIE,
)
from .dailymail import DailyMailIE
from .onionstudios import OnionStudiosIE
from .viewlift import ViewLiftEmbedIE
from .mtv import MTVServicesEmbeddedIE
@ -91,6 +92,7 @@ from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
from .wistia import WistiaIE
from .mediaset import MediasetIE
from .joj import JojIE
class GenericIE(InfoExtractor):
@ -759,6 +761,20 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Dailymotion'],
},
# DailyMail embed
{
'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
'info_dict': {
'id': '1495629',
'ext': 'mp4',
'title': 'Care worker punches elderly dementia patient in head 11 times',
'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
},
'add_ie': ['DailyMail'],
'params': {
'skip_download': True,
},
},
# YouTube embed
{
'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
@ -1185,7 +1201,7 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Kaltura'],
},
# Eagle.Platform embed (generic URL)
# EaglePlatform embed (generic URL)
{
'url': 'http://lenta.ru/news/2015/03/06/navalny/',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
@ -1199,8 +1215,26 @@ class GenericIE(InfoExtractor):
'view_count': int,
'age_limit': 0,
},
'params': {
'skip_download': True,
},
},
# ClipYou (Eagle.Platform) embed (custom URL)
# referrer protected EaglePlatform embed
{
'url': 'https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/',
'info_dict': {
'id': '582306',
'ext': 'mp4',
'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 3382,
'view_count': int,
},
'params': {
'skip_download': True,
},
},
# ClipYou (EaglePlatform) embed (custom URL)
{
'url': 'http://muz-tv.ru/play/7129/',
# Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
@ -1212,6 +1246,9 @@ class GenericIE(InfoExtractor):
'duration': 216,
'view_count': int,
},
'params': {
'skip_download': True,
},
},
# Pladform embed
{
@ -1749,6 +1786,26 @@ class GenericIE(InfoExtractor):
},
'add_ie': [MediasetIE.ie_key()],
},
{
# JOJ.sk embeds
'url': 'https://www.noviny.sk/slovensko/238543-slovenskom-sa-prehnala-vlna-silnych-burok',
'info_dict': {
'id': '238543-slovenskom-sa-prehnala-vlna-silnych-burok',
'title': 'Slovenskom sa prehnala vlna silných búrok',
},
'playlist_mincount': 5,
'add_ie': [JojIE.ie_key()],
},
{
# AMP embed (see https://www.ampproject.org/docs/reference/components/amp-video)
'url': 'https://tvrain.ru/amp/418921/',
'md5': 'cc00413936695987e8de148b67d14f1d',
'info_dict': {
'id': '418921',
'ext': 'mp4',
'title': 'Стас Намин: «Мы нарушили девственность Кремля»',
},
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@ -2148,6 +2205,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
# Look for DailyMail embeds
dailymail_urls = DailyMailIE._extract_urls(webpage)
if dailymail_urls:
return self.playlist_from_matches(
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
# Look for embedded Wistia player
wistia_url = WistiaIE._extract_url(webpage)
if wistia_url:
@ -2443,12 +2506,12 @@ class GenericIE(InfoExtractor):
if kaltura_url:
return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
# Look for Eagle.Platform embeds
# Look for EaglePlatform embeds
eagleplatform_url = EaglePlatformIE._extract_url(webpage)
if eagleplatform_url:
return self.url_result(eagleplatform_url, EaglePlatformIE.ie_key())
return self.url_result(smuggle_url(eagleplatform_url, {'referrer': url}), EaglePlatformIE.ie_key())
# Look for ClipYou (uses Eagle.Platform) embeds
# Look for ClipYou (uses EaglePlatform) embeds
mobj = re.search(
r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
if mobj is not None:
@ -2691,6 +2754,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
# Look for JOJ.sk embeds
joj_urls = JojIE._extract_urls(webpage)
if joj_urls:
return self.playlist_from_matches(
joj_urls, video_id, video_title, ie=JojIE.ie_key())
def merge_dicts(dict1, dict2):
merged = {}
for k, v in dict1.items():

100
youtube_dl/extractor/joj.py Executable file
View File

@ -0,0 +1,100 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
js_to_json,
try_get,
)
class JojIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
joj:|
https?://media\.joj\.sk/embed/
)
(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})
'''
_TESTS = [{
'url': 'https://media.joj.sk/embed/a388ec4c-6019-4a4a-9312-b1bee194e932',
'info_dict': {
'id': 'a388ec4c-6019-4a4a-9312-b1bee194e932',
'ext': 'mp4',
'title': 'NOVÉ BÝVANIE',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 3118,
}
}, {
'url': 'joj:a388ec4c-6019-4a4a-9312-b1bee194e932',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//media\.joj\.sk/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://media.joj.sk/embed/%s' % video_id, video_id)
title = self._search_regex(
(r'videoTitle\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
r'<title>(?P<title>[^<]+)'), webpage, 'title',
default=None, group='title') or self._og_search_title(webpage)
bitrates = self._parse_json(
self._search_regex(
r'(?s)bitrates\s*=\s*({.+?});', webpage, 'bitrates',
default='{}'),
video_id, transform_source=js_to_json, fatal=False)
formats = []
for format_url in try_get(bitrates, lambda x: x['mp4'], list) or []:
if isinstance(format_url, compat_str):
height = self._search_regex(
r'(\d+)[pP]\.', format_url, 'height', default=None)
formats.append({
'url': format_url,
'format_id': '%sp' % height if height else None,
'height': int(height),
})
if not formats:
playlist = self._download_xml(
'https://media.joj.sk/services/Video.php?clip=%s' % video_id,
video_id)
for file_el in playlist.findall('./files/file'):
path = file_el.get('path')
if not path:
continue
format_id = file_el.get('id') or file_el.get('label')
formats.append({
'url': 'http://n16.joj.sk/storage/%s' % path.replace(
'dat/', '', 1),
'format_id': format_id,
'height': int_or_none(self._search_regex(
r'(\d+)[pP]', format_id or path, 'height',
default=None)),
})
self._sort_formats(formats)
thumbnail = self._og_search_thumbnail(webpage)
duration = int_or_none(self._search_regex(
r'videoDuration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}

View File

@ -341,7 +341,7 @@ class NPOLiveIE(NPOBaseIE):
webpage = self._download_webpage(url, display_id)
live_id = self._search_regex(
r'data-prid="([^"]+)"', webpage, 'live id')
[r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
return {
'_type': 'url_transparent',

View File

@ -12,47 +12,46 @@ from ..utils import (
class VeohIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|yapi-)[\da-zA-Z]+)'
_VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'
_TESTS = [
{
'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
'md5': '620e68e6a3cff80086df3348426c9ca3',
'info_dict': {
'id': '56314296',
'ext': 'mp4',
'title': 'Straight Backs Are Stronger',
'uploader': 'LUMOback',
'description': 'At LUMOback, we believe straight backs are stronger. The LUMOback Posture & Movement Sensor: It gently vibrates when you slouch, inspiring improved posture and mobility. Use the app to track your data and improve your posture over time. ',
},
_TESTS = [{
'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
'md5': '620e68e6a3cff80086df3348426c9ca3',
'info_dict': {
'id': '56314296',
'ext': 'mp4',
'title': 'Straight Backs Are Stronger',
'uploader': 'LUMOback',
'description': 'At LUMOback, we believe straight backs are stronger. The LUMOback Posture & Movement Sensor: It gently vibrates when you slouch, inspiring improved posture and mobility. Use the app to track your data and improve your posture over time. ',
},
{
'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
'info_dict': {
'id': '27701988',
'ext': 'mp4',
'title': 'Chile workers cover up to avoid skin damage',
'description': 'md5:2bd151625a60a32822873efc246ba20d',
'uploader': 'afp-news',
'duration': 123,
},
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
'info_dict': {
'id': '27701988',
'ext': 'mp4',
'title': 'Chile workers cover up to avoid skin damage',
'description': 'md5:2bd151625a60a32822873efc246ba20d',
'uploader': 'afp-news',
'duration': 123,
},
{
'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
'md5': '4fde7b9e33577bab2f2f8f260e30e979',
'note': 'Embedded ooyala video',
'info_dict': {
'id': '69525809',
'ext': 'mp4',
'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
'uploader': 'newsy-videos',
},
'skip': 'This video has been deleted.',
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
'md5': '4fde7b9e33577bab2f2f8f260e30e979',
'note': 'Embedded ooyala video',
'info_dict': {
'id': '69525809',
'ext': 'mp4',
'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
'uploader': 'newsy-videos',
},
]
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
'only_matching': True,
}]
def _extract_formats(self, source):
formats = []

View File

@ -49,6 +49,10 @@ class VLiveIE(InfoExtractor):
},
}]
@classmethod
def suitable(cls, url):
return False if VLivePlaylistIE.suitable(url) else super(VLiveIE, cls).suitable(url)
def _real_extract(self, url):
video_id = self._match_id(url)
@ -261,3 +265,54 @@ class VLiveChannelIE(InfoExtractor):
return self.playlist_result(
entries, channel_code, channel_name)
class VLivePlaylistIE(InfoExtractor):
IE_NAME = 'vlive:playlist'
_VALID_URL = r'https?://(?:(?:www|m)\.)?vlive\.tv/video/(?P<video_id>[0-9]+)/playlist/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.vlive.tv/video/22867/playlist/22912',
'info_dict': {
'id': '22912',
'title': 'Valentine Day Message from TWICE'
},
'playlist_mincount': 9
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, playlist_id = mobj.group('video_id', 'id')
VIDEO_URL_TEMPLATE = 'http://www.vlive.tv/video/%s'
if self._downloader.params.get('noplaylist'):
self.to_screen(
'Downloading just video %s because of --no-playlist' % video_id)
return self.url_result(
VIDEO_URL_TEMPLATE % video_id,
ie=VLiveIE.ie_key(), video_id=video_id)
self.to_screen(
'Downloading playlist %s - add --no-playlist to just download video'
% playlist_id)
webpage = self._download_webpage(
'http://www.vlive.tv/video/%s/playlist/%s'
% (video_id, playlist_id), playlist_id)
item_ids = self._parse_json(
self._search_regex(
r'playlistVideoSeqs\s*=\s*(\[[^]]+\])', webpage,
'playlist video seqs'),
playlist_id)
entries = [
self.url_result(
VIDEO_URL_TEMPLATE % item_id, ie=VLiveIE.ie_key(),
video_id=compat_str(item_id))
for item_id in item_ids]
playlist_name = self._html_search_regex(
r'<div[^>]+class="[^"]*multicam_playlist[^>]*>\s*<h3[^>]+>([^<]+)',
webpage, 'playlist title', fatal=False)
return self.playlist_result(entries, playlist_id, playlist_name)

View File

@ -542,7 +542,7 @@ class FFmpegFixupM3u8PP(FFmpegPostProcessor):
temp_filename = prepend_extension(filename, 'temp')
options = ['-c', 'copy', '-f', 'mp4', '-bsf:a', 'aac_adtstoasc']
self._downloader.to_screen('[ffmpeg] Fixing malformated aac bitstream in "%s"' % filename)
self._downloader.to_screen('[ffmpeg] Fixing malformed AAC bitstream in "%s"' % filename)
self.run_ffmpeg(filename, temp_filename, options)
os.remove(encodeFilename(filename))

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2017.07.02'
__version__ = '2017.07.09'