mirror of
https://github.com/l1ving/youtube-dl
synced 2025-03-07 04:57:46 +08:00
Melvin Soldia
GitHub
commit
988d1eb469
6
.github/ISSUE_TEMPLATE.md
vendored
6
.github/ISSUE_TEMPLATE.md
vendored
@ -6,8 +6,8 @@
|
||||
|
||||
---
|
||||
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.08*. 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 Issues with outdated version will be rejected.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 **2018.09.08**
|
||||
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.10*. 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 Issues with outdated version will be rejected.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 **2018.09.10**
|
||||
|
||||
### 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
|
||||
@ -36,7 +36,7 @@ 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 2018.09.08
|
||||
[debug] youtube-dl version 2018.09.10
|
||||
[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: {}
|
||||
|
||||
11
ChangeLog
11
ChangeLog
@ -1,3 +1,14 @@
|
||||
version 2018.09.10
|
||||
|
||||
Core
|
||||
+ [utils] Properly recognize AV1 codec (#17506)
|
||||
|
||||
Extractors
|
||||
+ [iprima] Add support for prima.iprima.cz (#17514)
|
||||
+ [tele5] Add support for tele5.de (#7805, #7922, #17331, #17414)
|
||||
* [nbc] Fix extraction of percent encoded URLs (#17374)
|
||||
|
||||
|
||||
version 2018.09.08
|
||||
|
||||
Extractors
|
||||
|
||||
@ -847,6 +847,7 @@
|
||||
- **techtv.mit.edu**
|
||||
- **ted**
|
||||
- **Tele13**
|
||||
- **Tele5**
|
||||
- **TeleBruxelles**
|
||||
- **Telecinco**: telecinco.es, cuatro.com and mediaset.es
|
||||
- **Telegraaf**
|
||||
|
||||
@ -785,6 +785,10 @@ class TestUtil(unittest.TestCase):
|
||||
'vcodec': 'h264',
|
||||
'acodec': 'aac',
|
||||
})
|
||||
self.assertEqual(parse_codecs('av01.0.05M.08'), {
|
||||
'vcodec': 'av01.0.05M.08',
|
||||
'acodec': 'none',
|
||||
})
|
||||
|
||||
def test_escape_rfc3986(self):
|
||||
reserved = "!*'();:@&=+$,/?#[]"
|
||||
|
||||
@ -8,7 +8,6 @@ from .kaltura import KalturaIE
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
remove_end,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
@ -34,19 +33,40 @@ class AsianCrushIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
data = self._download_json(
|
||||
'https://www.asiancrush.com/wp-admin/admin-ajax.php', video_id,
|
||||
data=urlencode_postdata({
|
||||
'postid': video_id,
|
||||
'action': 'get_channel_kaltura_vars',
|
||||
}))
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
entry_id = data['entry_id']
|
||||
entry_id, partner_id, title = [None] * 3
|
||||
|
||||
vars = self._parse_json(
|
||||
self._search_regex(
|
||||
r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars',
|
||||
default='{}'), video_id, fatal=False)
|
||||
if vars:
|
||||
entry_id = vars.get('entry_id')
|
||||
partner_id = vars.get('partner_id')
|
||||
title = vars.get('vid_label')
|
||||
|
||||
if not entry_id:
|
||||
entry_id = self._search_regex(
|
||||
r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id')
|
||||
|
||||
player = self._download_webpage(
|
||||
'https://api.asiancrush.com/embeddedVideoPlayer', video_id,
|
||||
query={'id': entry_id})
|
||||
|
||||
kaltura_id = self._search_regex(
|
||||
r'entry_id["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', player,
|
||||
'kaltura id', group='id')
|
||||
|
||||
if not partner_id:
|
||||
partner_id = self._search_regex(
|
||||
r'/p(?:artner_id)?/(\d+)', player, 'partner id',
|
||||
default='513551')
|
||||
|
||||
return self.url_result(
|
||||
'kaltura:%s:%s' % (data['partner_id'], entry_id),
|
||||
ie=KalturaIE.ie_key(), video_id=entry_id,
|
||||
video_title=data.get('vid_label'))
|
||||
'kaltura:%s:%s' % (partner_id, kaltura_id),
|
||||
ie=KalturaIE.ie_key(), video_id=kaltura_id,
|
||||
video_title=title)
|
||||
|
||||
|
||||
class AsianCrushPlaylistIE(InfoExtractor):
|
||||
|
||||
@ -211,6 +211,11 @@ class InfoExtractor(object):
|
||||
If not explicitly set, calculated from timestamp.
|
||||
uploader_id: Nickname or id of the video uploader.
|
||||
uploader_url: Full URL to a personal webpage of the video uploader.
|
||||
channel: Full name of the channel the video is uploaded on.
|
||||
Note that channel fields may or may not repeat uploader
|
||||
fields. This depends on a particular extractor.
|
||||
channel_id: Id of the channel.
|
||||
channel_url: Full URL to a channel webpage.
|
||||
location: Physical location where the video was filmed.
|
||||
subtitles: The available subtitles as a dictionary in the format
|
||||
{tag: subformats}. "tag" is usually a language code, and
|
||||
@ -1701,9 +1706,9 @@ class InfoExtractor(object):
|
||||
# However, this is not always respected, for example, [2]
|
||||
# contains EXT-X-STREAM-INF tag which references AUDIO
|
||||
# rendition group but does not have CODECS and despite
|
||||
# referencing audio group an audio group, it represents
|
||||
# a complete (with audio and video) format. So, for such cases
|
||||
# we will ignore references to rendition groups and treat them
|
||||
# referencing an audio group it represents a complete
|
||||
# (with audio and video) format. So, for such cases we will
|
||||
# ignore references to rendition groups and treat them
|
||||
# as complete formats.
|
||||
if audio_group_id and codecs and f.get('vcodec') != 'none':
|
||||
audio_group = groups.get(audio_group_id)
|
||||
|
||||
@ -59,7 +59,7 @@ class DTubeIE(InfoExtractor):
|
||||
try:
|
||||
self.to_screen('%s: Checking %s video format URL' % (video_id, format_id))
|
||||
self._downloader._opener.open(video_url, timeout=5).close()
|
||||
except timeout as e:
|
||||
except timeout:
|
||||
self.to_screen(
|
||||
'%s: %s URL is invalid, skipping' % (video_id, format_id))
|
||||
continue
|
||||
|
||||
@ -9,6 +9,7 @@ from ..utils import (
|
||||
encode_base_n,
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
parse_duration,
|
||||
str_to_int,
|
||||
url_or_none,
|
||||
@ -25,10 +26,16 @@ class EpornerIE(InfoExtractor):
|
||||
'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
|
||||
'ext': 'mp4',
|
||||
'title': 'Infamous Tiffany Teen Strip Tease Video',
|
||||
'description': 'md5:764f39abf932daafa37485eb46efa152',
|
||||
'timestamp': 1232520922,
|
||||
'upload_date': '20090121',
|
||||
'duration': 1838,
|
||||
'view_count': int,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'params': {
|
||||
'proxy': '127.0.0.1:8118'
|
||||
}
|
||||
}, {
|
||||
# New (May 2016) URL layout
|
||||
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
|
||||
@ -104,12 +111,15 @@ class EpornerIE(InfoExtractor):
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
duration = parse_duration(self._html_search_meta('duration', webpage))
|
||||
json_ld = self._search_json_ld(webpage, display_id, default={})
|
||||
|
||||
duration = parse_duration(self._html_search_meta(
|
||||
'duration', webpage, default=None))
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'id="cinemaviews">\s*([0-9,]+)\s*<small>views',
|
||||
webpage, 'view count', fatal=False))
|
||||
|
||||
return {
|
||||
return merge_dicts(json_ld, {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
@ -117,4 +127,4 @@ class EpornerIE(InfoExtractor):
|
||||
'view_count': view_count,
|
||||
'formats': formats,
|
||||
'age_limit': 18,
|
||||
}
|
||||
})
|
||||
|
||||
@ -1086,6 +1086,7 @@ from .teachingchannel import TeachingChannelIE
|
||||
from .teamcoco import TeamcocoIE
|
||||
from .techtalks import TechTalksIE
|
||||
from .ted import TEDIE
|
||||
from .tele5 import Tele5IE
|
||||
from .tele13 import Tele13IE
|
||||
from .telebruxelles import TeleBruxellesIE
|
||||
from .telecinco import TelecincoIE
|
||||
|
||||
@ -3,15 +3,45 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..compat import (
|
||||
compat_b64decode,
|
||||
compat_str,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
str_to_int,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class FourTubeBaseIE(InfoExtractor):
|
||||
_TKN_HOST = 'tkn.kodicdn.com'
|
||||
|
||||
def _extract_formats(self, url, video_id, media_id, sources):
|
||||
token_url = 'https://%s/%s/desktop/%s' % (
|
||||
self._TKN_HOST, media_id, '+'.join(sources))
|
||||
|
||||
parsed_url = compat_urlparse.urlparse(url)
|
||||
tokens = self._download_json(token_url, video_id, data=b'', headers={
|
||||
'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname),
|
||||
'Referer': url,
|
||||
})
|
||||
formats = [{
|
||||
'url': tokens[format]['token'],
|
||||
'format_id': format + 'p',
|
||||
'resolution': format + 'p',
|
||||
'quality': int(format),
|
||||
} for format in sources]
|
||||
self._sort_formats(formats)
|
||||
return formats
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
kind, video_id, display_id = mobj.group('kind', 'id', 'display_id')
|
||||
@ -68,21 +98,7 @@ class FourTubeBaseIE(InfoExtractor):
|
||||
media_id = params[0]
|
||||
sources = ['%s' % p for p in params[2]]
|
||||
|
||||
token_url = 'https://tkn.kodicdn.com/{0}/desktop/{1}'.format(
|
||||
media_id, '+'.join(sources))
|
||||
|
||||
parsed_url = compat_urlparse.urlparse(url)
|
||||
tokens = self._download_json(token_url, video_id, data=b'', headers={
|
||||
'Origin': '%s://%s' % (parsed_url.scheme, parsed_url.hostname),
|
||||
'Referer': url,
|
||||
})
|
||||
formats = [{
|
||||
'url': tokens[format]['token'],
|
||||
'format_id': format + 'p',
|
||||
'resolution': format + 'p',
|
||||
'quality': int(format),
|
||||
} for format in sources]
|
||||
self._sort_formats(formats)
|
||||
formats = self._extract_formats(url, video_id, media_id, sources)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
@ -164,6 +180,7 @@ class FuxIE(FourTubeBaseIE):
|
||||
class PornTubeIE(FourTubeBaseIE):
|
||||
_VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?porntube\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
|
||||
_URL_TEMPLATE = 'https://www.porntube.com/videos/video_%s'
|
||||
_TKN_HOST = 'tkn.porntube.com'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.porntube.com/videos/teen-couple-doing-anal_7089759',
|
||||
'info_dict': {
|
||||
@ -171,13 +188,32 @@ class PornTubeIE(FourTubeBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'Teen couple doing anal',
|
||||
'uploader': 'Alexy',
|
||||
'uploader_id': 'Alexy',
|
||||
'uploader_id': '91488',
|
||||
'upload_date': '20150606',
|
||||
'timestamp': 1433595647,
|
||||
'duration': 5052,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'categories': list,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.porntube.com/videos/squirting-teen-ballerina-ecg_1331406',
|
||||
'info_dict': {
|
||||
'id': '1331406',
|
||||
'ext': 'mp4',
|
||||
'title': 'Squirting Teen Ballerina on ECG',
|
||||
'uploader': 'Exploited College Girls',
|
||||
'uploader_id': '665',
|
||||
'channel': 'Exploited College Girls',
|
||||
'channel_id': '665',
|
||||
'upload_date': '20130920',
|
||||
'timestamp': 1379685485,
|
||||
'duration': 851,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'age_limit': 18,
|
||||
},
|
||||
'params': {
|
||||
@ -191,6 +227,55 @@ class PornTubeIE(FourTubeBaseIE):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id, display_id = mobj.group('id', 'display_id')
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
video = self._parse_json(
|
||||
self._search_regex(
|
||||
r'INITIALSTATE\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
|
||||
webpage, 'data', group='value'), video_id,
|
||||
transform_source=lambda x: compat_urllib_parse_unquote(
|
||||
compat_b64decode(x).decode('utf-8')))['page']['video']
|
||||
|
||||
title = video['title']
|
||||
media_id = video['mediaId']
|
||||
sources = [compat_str(e['height'])
|
||||
for e in video['encodings'] if e.get('height')]
|
||||
formats = self._extract_formats(url, video_id, media_id, sources)
|
||||
|
||||
thumbnail = url_or_none(video.get('masterThumb'))
|
||||
uploader = try_get(video, lambda x: x['user']['username'], compat_str)
|
||||
uploader_id = str_or_none(try_get(
|
||||
video, lambda x: x['user']['id'], int))
|
||||
channel = try_get(video, lambda x: x['channel']['name'], compat_str)
|
||||
channel_id = str_or_none(try_get(
|
||||
video, lambda x: x['channel']['id'], int))
|
||||
like_count = int_or_none(video.get('likes'))
|
||||
dislike_count = int_or_none(video.get('dislikes'))
|
||||
view_count = int_or_none(video.get('playsQty'))
|
||||
duration = int_or_none(video.get('durationInSeconds'))
|
||||
timestamp = unified_timestamp(video.get('publishedAt'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader or channel,
|
||||
'uploader_id': uploader_id or channel_id,
|
||||
'channel': channel,
|
||||
'channel_id': channel_id,
|
||||
'timestamp': timestamp,
|
||||
'like_count': like_count,
|
||||
'dislike_count': dislike_count,
|
||||
'view_count': view_count,
|
||||
'duration': duration,
|
||||
'age_limit': 18,
|
||||
}
|
||||
|
||||
|
||||
class PornerBrosIE(FourTubeBaseIE):
|
||||
_VALID_URL = r'https?://(?:(?P<kind>www|m)\.)?pornerbros\.com/(?:videos/(?P<display_id>[^/]+)_|embed/)(?P<id>\d+)'
|
||||
|
||||
@ -3112,7 +3112,7 @@ class GenericIE(InfoExtractor):
|
||||
return self.playlist_from_matches(
|
||||
foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key())
|
||||
|
||||
sharevideos_urls = [mobj.group('url') for mobj in re.finditer(
|
||||
sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer(
|
||||
r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1',
|
||||
webpage)]
|
||||
if sharevideos_urls:
|
||||
|
||||
@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class IPrimaIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://play\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
|
||||
_VALID_URL = r'https?://(?:play|prima)\.iprima\.cz/(?:.+/)?(?P<id>[^?#]+)'
|
||||
_GEO_BYPASS = False
|
||||
|
||||
_TESTS = [{
|
||||
@ -33,6 +33,14 @@ class IPrimaIE(InfoExtractor):
|
||||
# geo restricted
|
||||
'url': 'http://play.iprima.cz/closer-nove-pripady/closer-nove-pripady-iv-1',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# iframe api.play-backend.iprima.cz
|
||||
'url': 'https://prima.iprima.cz/my-little-pony/mapa-znameni-2-2',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# iframe prima.iprima.cz
|
||||
'url': 'https://prima.iprima.cz/porady/jak-se-stavi-sen/rodina-rathousova-praha',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -42,7 +50,10 @@ class IPrimaIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_id = self._search_regex(r'data-product="([^"]+)">', webpage, 'real id')
|
||||
video_id = self._search_regex(
|
||||
(r'<iframe[^>]+\bsrc=["\'](?:https?:)?//(?:api\.play-backend\.iprima\.cz/prehravac/embedded|prima\.iprima\.cz/[^/]+/[^/]+)\?.*?\bid=(p\d+)',
|
||||
r'data-product="([^"]+)">'),
|
||||
webpage, 'real id')
|
||||
|
||||
playerpage = self._download_webpage(
|
||||
'http://play.iprima.cz/prehravac/init',
|
||||
|
||||
@ -167,9 +167,9 @@ class MotherlessGroupIE(InfoExtractor):
|
||||
if not entries:
|
||||
entries = [
|
||||
self.url_result(
|
||||
compat_urlparse.urljoin(base, '/' + video_id),
|
||||
ie=MotherlessIE.ie_key(), video_id=video_id)
|
||||
for video_id in orderedSet(re.findall(
|
||||
compat_urlparse.urljoin(base, '/' + entry_id),
|
||||
ie=MotherlessIE.ie_key(), video_id=entry_id)
|
||||
for entry_id in orderedSet(re.findall(
|
||||
r'data-codename=["\']([A-Z0-9]+)', webpage))]
|
||||
return entries
|
||||
|
||||
|
||||
@ -7,6 +7,7 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from .theplatform import ThePlatformIE
|
||||
from .adobepass import AdobePassIE
|
||||
from ..compat import compat_urllib_parse_unquote
|
||||
from ..utils import (
|
||||
find_xpath_attr,
|
||||
smuggle_url,
|
||||
@ -75,11 +76,16 @@ class NBCIE(AdobePassIE):
|
||||
'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# Percent escaped url
|
||||
'url': 'https://www.nbc.com/up-all-night/video/day-after-valentine%27s-day/n2189',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
permalink, video_id = re.match(self._VALID_URL, url).groups()
|
||||
permalink = 'http' + permalink
|
||||
permalink = 'http' + compat_urllib_parse_unquote(permalink)
|
||||
response = self._download_json(
|
||||
'https://api.nbc.com/v3/videos', video_id, query={
|
||||
'filter[permalink]': permalink,
|
||||
|
||||
@ -40,6 +40,7 @@ class PornHubIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
|
||||
'uploader': 'Babes',
|
||||
'upload_date': '20130628',
|
||||
'duration': 361,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -57,6 +58,7 @@ class PornHubIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': '重庆婷婷女王足交',
|
||||
'uploader': 'Unknown',
|
||||
'upload_date': '20150213',
|
||||
'duration': 1753,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
@ -237,8 +239,14 @@ class PornHubIE(InfoExtractor):
|
||||
video_urls.append((video_url, None))
|
||||
video_urls_set.add(video_url)
|
||||
|
||||
upload_date = None
|
||||
formats = []
|
||||
for video_url, height in video_urls:
|
||||
if not upload_date:
|
||||
upload_date = self._search_regex(
|
||||
r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
|
||||
if upload_date:
|
||||
upload_date = upload_date.replace('/', '')
|
||||
tbr = None
|
||||
mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
|
||||
if mobj:
|
||||
@ -278,6 +286,7 @@ class PornHubIE(InfoExtractor):
|
||||
return {
|
||||
'id': video_id,
|
||||
'uploader': video_uploader,
|
||||
'upload_date': upload_date,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
|
||||
@ -164,6 +164,6 @@ class SeznamZpravyArticleIE(InfoExtractor):
|
||||
description = info.get('description') or self._og_search_description(webpage)
|
||||
|
||||
return self.playlist_result([
|
||||
self.url_result(url, ie=SeznamZpravyIE.ie_key())
|
||||
for url in SeznamZpravyIE._extract_urls(webpage)],
|
||||
self.url_result(entry_url, ie=SeznamZpravyIE.ie_key())
|
||||
for entry_url in SeznamZpravyIE._extract_urls(webpage)],
|
||||
article_id, title, description)
|
||||
|
||||
44
youtube_dl/extractor/tele5.py
Normal file
44
youtube_dl/extractor/tele5.py
Normal file
@ -0,0 +1,44 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .nexx import NexxIE
|
||||
from ..compat import compat_urlparse
|
||||
|
||||
|
||||
class Tele5IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416',
|
||||
'info_dict': {
|
||||
'id': '1549416',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20180814',
|
||||
'timestamp': 1534290623,
|
||||
'title': 'Pandorum',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.tele5.de/tv/dark-matter/videos',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
|
||||
video_id = (qs.get('vid') or qs.get('ve_id') or [None])[0]
|
||||
|
||||
if not video_id:
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._html_search_regex(
|
||||
r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)',
|
||||
webpage, 'video id')
|
||||
|
||||
return self.url_result(
|
||||
'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id,
|
||||
ie=NexxIE.ie_key(), video_id=video_id)
|
||||
@ -45,7 +45,7 @@ class Tube8IE(KeezMoviesIE):
|
||||
r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
|
||||
|
||||
description = self._html_search_regex(
|
||||
r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
|
||||
r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
|
||||
uploader = self._html_search_regex(
|
||||
r'<span class="username">\s*(.+?)\s*<',
|
||||
webpage, 'uploader', fatal=False)
|
||||
@ -55,19 +55,19 @@ class Tube8IE(KeezMoviesIE):
|
||||
dislike_count = int_or_none(self._search_regex(
|
||||
r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
|
||||
view_count = str_to_int(self._search_regex(
|
||||
r'<strong>Views: </strong>([\d,\.]+)\s*</li>',
|
||||
r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
|
||||
webpage, 'view count', fatal=False))
|
||||
comment_count = str_to_int(self._search_regex(
|
||||
r'<span id="allCommentsCount">(\d+)</span>',
|
||||
webpage, 'comment count', fatal=False))
|
||||
|
||||
category = self._search_regex(
|
||||
r'Category:\s*</strong>\s*<a[^>]+href=[^>]+>([^<]+)',
|
||||
r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
|
||||
webpage, 'category', fatal=False)
|
||||
categories = [category] if category else None
|
||||
|
||||
tags_str = self._search_regex(
|
||||
r'(?s)Tags:\s*</strong>(.+?)</(?!a)',
|
||||
r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
|
||||
webpage, 'tags', fatal=False)
|
||||
tags = [t for t in re.findall(
|
||||
r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
|
||||
|
||||
@ -559,7 +559,8 @@ class TwitchStreamIE(TwitchBaseIE):
|
||||
TwitchAllVideosIE,
|
||||
TwitchUploadsIE,
|
||||
TwitchPastBroadcastsIE,
|
||||
TwitchHighlightsIE))
|
||||
TwitchHighlightsIE,
|
||||
TwitchClipsIE))
|
||||
else super(TwitchStreamIE, cls).suitable(url))
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -633,7 +634,7 @@ class TwitchStreamIE(TwitchBaseIE):
|
||||
|
||||
class TwitchClipsIE(TwitchBaseIE):
|
||||
IE_NAME = 'twitch:clips'
|
||||
_VALID_URL = r'https?://clips\.twitch\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:[^/]+/)*|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat',
|
||||
@ -653,6 +654,9 @@ class TwitchClipsIE(TwitchBaseIE):
|
||||
# multiple formats
|
||||
'url': 'https://clips.twitch.tv/rflegendary/UninterestedBeeDAESuppy',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.twitch.tv/sergeynixon/clip/StormyThankfulSproutFutureMan',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -299,10 +299,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
|
||||
'uploader_id': 'atencio',
|
||||
'uploader': 'Peter Atencio',
|
||||
'channel_id': 'keypeele',
|
||||
'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
|
||||
'timestamp': 1380339469,
|
||||
'upload_date': '20130928',
|
||||
'duration': 187,
|
||||
},
|
||||
'expected_warnings': ['Unable to download JSON metadata'],
|
||||
},
|
||||
{
|
||||
'url': 'http://vimeo.com/76979871',
|
||||
@ -355,11 +358,13 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
'url': 'https://vimeo.com/channels/tributes/6213729',
|
||||
'info_dict': {
|
||||
'id': '6213729',
|
||||
'ext': 'mov',
|
||||
'ext': 'mp4',
|
||||
'title': 'Vimeo Tribute: The Shining',
|
||||
'uploader': 'Casey Donahue',
|
||||
'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
|
||||
'uploader_id': 'caseydonahue',
|
||||
'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
|
||||
'channel_id': 'tributes',
|
||||
'timestamp': 1250886430,
|
||||
'upload_date': '20090821',
|
||||
'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
|
||||
@ -465,6 +470,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
if 'Referer' not in headers:
|
||||
headers['Referer'] = url
|
||||
|
||||
channel_id = self._search_regex(
|
||||
r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
|
||||
|
||||
# Extract ID from URL
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
@ -563,19 +571,23 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
if config.get('view') == 4:
|
||||
config = self._verify_player_video_password(redirect_url, video_id)
|
||||
|
||||
vod = config.get('video', {}).get('vod', {})
|
||||
|
||||
def is_rented():
|
||||
if '>You rented this title.<' in webpage:
|
||||
return True
|
||||
if config.get('user', {}).get('purchased'):
|
||||
return True
|
||||
label = try_get(
|
||||
config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
|
||||
if label and label.startswith('You rented this'):
|
||||
return True
|
||||
for purchase_option in vod.get('purchase_options', []):
|
||||
if purchase_option.get('purchased'):
|
||||
return True
|
||||
label = purchase_option.get('label_string')
|
||||
if label and (label.startswith('You rented this') or label.endswith(' remaining')):
|
||||
return True
|
||||
return False
|
||||
|
||||
if is_rented():
|
||||
feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
|
||||
if is_rented() and vod.get('is_trailer'):
|
||||
feature_id = vod.get('feature_id')
|
||||
if feature_id and not data.get('force_feature_id', False):
|
||||
return self.url_result(smuggle_url(
|
||||
'https://player.vimeo.com/player/%s' % feature_id,
|
||||
@ -652,6 +664,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
|
||||
webpage, 'license', default=None, group='license')
|
||||
|
||||
channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
|
||||
|
||||
info_dict = {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
@ -662,6 +676,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
'like_count': like_count,
|
||||
'comment_count': comment_count,
|
||||
'license': cc_license,
|
||||
'channel_id': channel_id,
|
||||
'channel_url': channel_url,
|
||||
}
|
||||
|
||||
info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
|
||||
|
||||
@ -4,15 +4,19 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
float_or_none,
|
||||
unified_timestamp,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class VzaarIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:www|view)\.)?vzaar\.com/(?:videos/)?(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
# HTTP and HLS
|
||||
'url': 'https://vzaar.com/videos/1152805',
|
||||
'md5': 'bde5ddfeb104a6c56a93a06b04901dbf',
|
||||
'info_dict': {
|
||||
@ -40,24 +44,48 @@ class VzaarIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
video_data = self._download_json(
|
||||
'http://view.vzaar.com/v2/%s/video' % video_id, video_id)
|
||||
source_url = video_data['sourceUrl']
|
||||
|
||||
info = {
|
||||
title = video_data['videoTitle']
|
||||
|
||||
formats = []
|
||||
|
||||
source_url = url_or_none(video_data.get('sourceUrl'))
|
||||
if source_url:
|
||||
f = {
|
||||
'url': source_url,
|
||||
'format_id': 'http',
|
||||
}
|
||||
if 'audio' in source_url:
|
||||
f.update({
|
||||
'vcodec': 'none',
|
||||
'ext': 'mp3',
|
||||
})
|
||||
else:
|
||||
f.update({
|
||||
'width': int_or_none(video_data.get('width')),
|
||||
'height': int_or_none(video_data.get('height')),
|
||||
'ext': 'mp4',
|
||||
'fps': float_or_none(video_data.get('fps')),
|
||||
})
|
||||
formats.append(f)
|
||||
|
||||
video_guid = video_data.get('guid')
|
||||
usp = video_data.get('usp')
|
||||
if isinstance(video_guid, compat_str) and isinstance(usp, dict):
|
||||
m3u8_url = ('http://fable.vzaar.com/v4/usp/%s/%s.ism/.m3u8?'
|
||||
% (video_guid, video_id)) + '&'.join(
|
||||
'%s=%s' % (k, v) for k, v in usp.items())
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': video_data['videoTitle'],
|
||||
'url': source_url,
|
||||
'title': title,
|
||||
'thumbnail': self._proto_relative_url(video_data.get('poster')),
|
||||
'duration': float_or_none(video_data.get('videoDuration')),
|
||||
'timestamp': unified_timestamp(video_data.get('ts')),
|
||||
'formats': formats,
|
||||
}
|
||||
if 'audio' in source_url:
|
||||
info.update({
|
||||
'vcodec': 'none',
|
||||
'ext': 'mp3',
|
||||
})
|
||||
else:
|
||||
info.update({
|
||||
'width': int_or_none(video_data.get('width')),
|
||||
'height': int_or_none(video_data.get('height')),
|
||||
'ext': 'mp4',
|
||||
})
|
||||
return info
|
||||
|
||||
@ -490,6 +490,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'uploader': 'Philipp Hagemeister',
|
||||
'uploader_id': 'phihag',
|
||||
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
|
||||
'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
|
||||
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
|
||||
'upload_date': '20121002',
|
||||
'license': 'Standard YouTube License',
|
||||
'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
|
||||
@ -1907,6 +1909,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
else:
|
||||
self._downloader.report_warning('unable to extract uploader nickname')
|
||||
|
||||
channel_id = self._html_search_meta(
|
||||
'channelId', video_webpage, 'channel id')
|
||||
channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
|
||||
|
||||
# thumbnail image
|
||||
# We try first to get a high quality image:
|
||||
m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
|
||||
@ -2078,6 +2084,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'uploader': video_uploader,
|
||||
'uploader_id': video_uploader_id,
|
||||
'uploader_url': video_uploader_url,
|
||||
'channel_id': channel_id,
|
||||
'channel_url': channel_url,
|
||||
'upload_date': upload_date,
|
||||
'license': video_license,
|
||||
'creator': video_creator or artist,
|
||||
|
||||
@ -2477,7 +2477,7 @@ def parse_codecs(codecs_str):
|
||||
vcodec, acodec = None, None
|
||||
for full_codec in splited_codecs:
|
||||
codec = full_codec.split('.')[0]
|
||||
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1'):
|
||||
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01'):
|
||||
if not vcodec:
|
||||
vcodec = full_codec
|
||||
elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
|
||||
|
||||
@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2018.09.08'
|
||||
__version__ = '2018.09.10'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user