mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-06-26 05:39:34 +00:00
Compare commits
12 commits
c3612a0e71
...
81c0fcd431
Author | SHA1 | Date | |
---|---|---|---|
|
81c0fcd431 | ||
|
0153b387e5 | ||
|
a48fe7491d | ||
|
e20ca543f0 | ||
|
e39466051f | ||
|
d95c0d203f | ||
|
3bde6a5752 | ||
|
50f6c5668a | ||
|
b4ff08bd2d | ||
|
88bd8b9f87 | ||
|
c7684156c2 | ||
|
ff2e049d3e |
|
@ -5,9 +5,9 @@ import hashlib
|
|||
import json
|
||||
import os.path
|
||||
import re
|
||||
import types
|
||||
import ssl
|
||||
import sys
|
||||
import types
|
||||
import unittest
|
||||
|
||||
import youtube_dl.extractor
|
||||
|
@ -181,18 +181,18 @@ def expect_value(self, got, expected, field):
|
|||
op, _, expected_num = expected.partition(':')
|
||||
expected_num = int(expected_num)
|
||||
if op == 'mincount':
|
||||
assert_func = assertGreaterEqual
|
||||
assert_func = self.assertGreaterEqual
|
||||
msg_tmpl = 'Expected %d items in field %s, but only got %d'
|
||||
elif op == 'maxcount':
|
||||
assert_func = assertLessEqual
|
||||
assert_func = self.assertLessEqual
|
||||
msg_tmpl = 'Expected maximum %d items in field %s, but got %d'
|
||||
elif op == 'count':
|
||||
assert_func = assertEqual
|
||||
assert_func = self.assertEqual
|
||||
msg_tmpl = 'Expected exactly %d items in field %s, but got %d'
|
||||
else:
|
||||
assert False
|
||||
assert_func(
|
||||
self, len(got), expected_num,
|
||||
len(got), expected_num,
|
||||
msg_tmpl % (expected_num, field, len(got)))
|
||||
return
|
||||
self.assertEqual(
|
||||
|
@ -262,27 +262,6 @@ def assertRegexpMatches(self, text, regexp, msg=None):
|
|||
self.assertTrue(m, msg)
|
||||
|
||||
|
||||
def assertGreaterEqual(self, got, expected, msg=None):
|
||||
if not (got >= expected):
|
||||
if msg is None:
|
||||
msg = '%r not greater than or equal to %r' % (got, expected)
|
||||
self.assertTrue(got >= expected, msg)
|
||||
|
||||
|
||||
def assertLessEqual(self, got, expected, msg=None):
|
||||
if not (got <= expected):
|
||||
if msg is None:
|
||||
msg = '%r not less than or equal to %r' % (got, expected)
|
||||
self.assertTrue(got <= expected, msg)
|
||||
|
||||
|
||||
def assertEqual(self, got, expected, msg=None):
|
||||
if not (got == expected):
|
||||
if msg is None:
|
||||
msg = '%r not equal to %r' % (got, expected)
|
||||
self.assertTrue(got == expected, msg)
|
||||
|
||||
|
||||
def expect_warnings(ydl, warnings_re):
|
||||
real_warning = ydl.report_warning
|
||||
|
||||
|
|
|
@ -9,8 +9,6 @@ import unittest
|
|||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from test.helper import (
|
||||
assertGreaterEqual,
|
||||
assertLessEqual,
|
||||
expect_warnings,
|
||||
get_params,
|
||||
gettestcases,
|
||||
|
@ -36,12 +34,20 @@ from youtube_dl.utils import (
|
|||
ExtractorError,
|
||||
error_to_compat_str,
|
||||
format_bytes,
|
||||
IDENTITY,
|
||||
preferredencoding,
|
||||
UnavailableVideoError,
|
||||
)
|
||||
from youtube_dl.extractor import get_info_extractor
|
||||
|
||||
RETRIES = 3
|
||||
|
||||
# Some unittest APIs require actual str
|
||||
if not isinstance('TEST', str):
|
||||
_encode_str = lambda s: s.encode(preferredencoding())
|
||||
else:
|
||||
_encode_str = IDENTITY
|
||||
|
||||
|
||||
class YoutubeDL(youtube_dl.YoutubeDL):
|
||||
def __init__(self, *args, **kwargs):
|
||||
|
@ -102,7 +108,7 @@ def generator(test_case, tname):
|
|||
|
||||
def print_skipping(reason):
|
||||
print('Skipping %s: %s' % (test_case['name'], reason))
|
||||
self.skipTest(reason)
|
||||
self.skipTest(_encode_str(reason))
|
||||
|
||||
if not ie.working():
|
||||
print_skipping('IE marked as not _WORKING')
|
||||
|
@ -187,16 +193,14 @@ def generator(test_case, tname):
|
|||
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
|
||||
|
||||
if 'playlist_mincount' in test_case:
|
||||
assertGreaterEqual(
|
||||
self,
|
||||
self.assertGreaterEqual(
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_mincount'],
|
||||
'Expected at least %d in playlist %s, but got only %d' % (
|
||||
test_case['playlist_mincount'], test_case['url'],
|
||||
len(res_dict['entries'])))
|
||||
if 'playlist_maxcount' in test_case:
|
||||
assertLessEqual(
|
||||
self,
|
||||
self.assertLessEqual(
|
||||
len(res_dict['entries']),
|
||||
test_case['playlist_maxcount'],
|
||||
'Expected at most %d in playlist %s, but got %d' % (
|
||||
|
@ -243,8 +247,8 @@ def generator(test_case, tname):
|
|||
if params.get('test'):
|
||||
expected_minsize = max(expected_minsize, 10000)
|
||||
got_fsize = os.path.getsize(tc_filename)
|
||||
assertGreaterEqual(
|
||||
self, got_fsize, expected_minsize,
|
||||
self.assertGreaterEqual(
|
||||
got_fsize, expected_minsize,
|
||||
'Expected %s to be at least %s, but it\'s only %s ' %
|
||||
(tc_filename, format_bytes(expected_minsize),
|
||||
format_bytes(got_fsize)))
|
||||
|
|
|
@ -1039,8 +1039,8 @@ class YoutubeDL(object):
|
|||
elif result_type in ('playlist', 'multi_video'):
|
||||
# Protect from infinite recursion due to recursively nested playlists
|
||||
# (see https://github.com/ytdl-org/youtube-dl/issues/27833)
|
||||
webpage_url = ie_result['webpage_url']
|
||||
if webpage_url in self._playlist_urls:
|
||||
webpage_url = ie_result.get('webpage_url') # not all pl/mv have this
|
||||
if webpage_url and webpage_url in self._playlist_urls:
|
||||
self.to_screen(
|
||||
'[download] Skipping already downloaded playlist: %s'
|
||||
% ie_result.get('title') or ie_result.get('id'))
|
||||
|
@ -1048,6 +1048,10 @@ class YoutubeDL(object):
|
|||
|
||||
self._playlist_level += 1
|
||||
self._playlist_urls.add(webpage_url)
|
||||
new_result = dict((k, v) for k, v in extra_info.items() if k not in ie_result)
|
||||
if new_result:
|
||||
new_result.update(ie_result)
|
||||
ie_result = new_result
|
||||
try:
|
||||
return self.__process_playlist(ie_result, download)
|
||||
finally:
|
||||
|
@ -1593,6 +1597,28 @@ class YoutubeDL(object):
|
|||
self.cookiejar.add_cookie_header(pr)
|
||||
return pr.get_header('Cookie')
|
||||
|
||||
def _fill_common_fields(self, info_dict, final=True):
|
||||
|
||||
for ts_key, date_key in (
|
||||
('timestamp', 'upload_date'),
|
||||
('release_timestamp', 'release_date'),
|
||||
):
|
||||
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
|
||||
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
|
||||
# see http://bugs.python.org/issue1646728)
|
||||
try:
|
||||
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
|
||||
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
|
||||
except (ValueError, OverflowError, OSError):
|
||||
pass
|
||||
|
||||
# Auto generate title fields corresponding to the *_number fields when missing
|
||||
# in order to always have clean titles. This is very common for TV series.
|
||||
if final:
|
||||
for field in ('chapter', 'season', 'episode'):
|
||||
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
|
||||
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
|
||||
|
||||
def process_video_result(self, info_dict, download=True):
|
||||
assert info_dict.get('_type', 'video') == 'video'
|
||||
|
||||
|
@ -1660,24 +1686,7 @@ class YoutubeDL(object):
|
|||
if 'display_id' not in info_dict and 'id' in info_dict:
|
||||
info_dict['display_id'] = info_dict['id']
|
||||
|
||||
for ts_key, date_key in (
|
||||
('timestamp', 'upload_date'),
|
||||
('release_timestamp', 'release_date'),
|
||||
):
|
||||
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
|
||||
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
|
||||
# see http://bugs.python.org/issue1646728)
|
||||
try:
|
||||
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
|
||||
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
|
||||
except (ValueError, OverflowError, OSError):
|
||||
pass
|
||||
|
||||
# Auto generate title fields corresponding to the *_number fields when missing
|
||||
# in order to always have clean titles. This is very common for TV series.
|
||||
for field in ('chapter', 'season', 'episode'):
|
||||
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
|
||||
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
|
||||
self._fill_common_fields(info_dict)
|
||||
|
||||
for cc_kind in ('subtitles', 'automatic_captions'):
|
||||
cc = info_dict.get(cc_kind)
|
||||
|
|
|
@ -898,21 +898,13 @@ from .ooyala import (
|
|||
)
|
||||
from .ora import OraTVIE
|
||||
from .orf import (
|
||||
ORFTVthekIE,
|
||||
ORFFM4IE,
|
||||
ORFONIE,
|
||||
ORFONLiveIE,
|
||||
ORFFM4StoryIE,
|
||||
ORFOE1IE,
|
||||
ORFOE3IE,
|
||||
ORFNOEIE,
|
||||
ORFWIEIE,
|
||||
ORFBGLIE,
|
||||
ORFOOEIE,
|
||||
ORFSTMIE,
|
||||
ORFKTNIE,
|
||||
ORFSBGIE,
|
||||
ORFTIRIE,
|
||||
ORFVBGIE,
|
||||
ORFIPTVIE,
|
||||
ORFPodcastIE,
|
||||
ORFRadioIE,
|
||||
ORFRadioCollectionIE,
|
||||
)
|
||||
from .outsidetv import OutsideTVIE
|
||||
from .packtpub import (
|
||||
|
@ -1483,7 +1475,11 @@ from .videomore import (
|
|||
VideomoreSeasonIE,
|
||||
)
|
||||
from .videopress import VideoPressIE
|
||||
from .vidio import VidioIE
|
||||
from .vidio import (
|
||||
VidioIE,
|
||||
VidioPremierIE,
|
||||
VidioLiveIE,
|
||||
)
|
||||
from .vidlii import VidLiiIE
|
||||
from .vidme import (
|
||||
VidmeIE,
|
||||
|
|
|
@ -1,3 +1,4 @@
|
|||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import itertools
|
||||
|
@ -10,7 +11,7 @@ from ..compat import (
|
|||
compat_ord,
|
||||
compat_str,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_zip
|
||||
compat_zip as zip,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
|
@ -24,7 +25,7 @@ class MixcloudBaseIE(InfoExtractor):
|
|||
def _call_api(self, object_type, object_fields, display_id, username, slug=None):
|
||||
lookup_key = object_type + 'Lookup'
|
||||
return self._download_json(
|
||||
'https://www.mixcloud.com/graphql', display_id, query={
|
||||
'https://app.mixcloud.com/graphql', display_id, query={
|
||||
'query': '''{
|
||||
%s(lookup: {username: "%s"%s}) {
|
||||
%s
|
||||
|
@ -44,7 +45,7 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'ext': 'm4a',
|
||||
'title': 'Cryptkeeper',
|
||||
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
|
||||
'uploader': 'Daniel Holbach',
|
||||
'uploader': 'dholbach', # was: 'Daniel Holbach',
|
||||
'uploader_id': 'dholbach',
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'view_count': int,
|
||||
|
@ -57,7 +58,7 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
|
||||
'ext': 'mp3',
|
||||
'title': 'Caribou 7 inch Vinyl Mix & Chat',
|
||||
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
|
||||
'description': r're:Last week Dan Snaith aka Caribou swung by the Brownswood.{136}',
|
||||
'uploader': 'Gilles Peterson Worldwide',
|
||||
'uploader_id': 'gillespeterson',
|
||||
'thumbnail': 're:https?://.*',
|
||||
|
@ -65,6 +66,23 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
'timestamp': 1422987057,
|
||||
'upload_date': '20150203',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': '404 not found',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.mixcloud.com/gillespeterson/carnival-m%C3%BAsica-popular-brasileira-mix/',
|
||||
'info_dict': {
|
||||
'id': 'gillespeterson_carnival-música-popular-brasileira-mix',
|
||||
'ext': 'm4a',
|
||||
'title': 'Carnival Música Popular Brasileira Mix',
|
||||
'description': r're:Gilles was recently in Brazil to play at Boiler Room.{208}',
|
||||
'timestamp': 1454347174,
|
||||
'upload_date': '20160201',
|
||||
'uploader': 'Gilles Peterson Worldwide',
|
||||
'uploader_id': 'gillespeterson',
|
||||
'thumbnail': 're:https?://.*',
|
||||
'view_count': int,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
|
||||
'only_matching': True,
|
||||
|
@ -76,10 +94,10 @@ class MixcloudIE(MixcloudBaseIE):
|
|||
"""Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
|
||||
return ''.join([
|
||||
compat_chr(compat_ord(ch) ^ compat_ord(k))
|
||||
for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
|
||||
for ch, k in zip(ciphertext, itertools.cycle(key))])
|
||||
|
||||
def _real_extract(self, url):
|
||||
username, slug = re.match(self._VALID_URL, url).groups()
|
||||
username, slug = self._match_valid_url(url).groups()
|
||||
username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
|
||||
track_id = '%s_%s' % (username, slug)
|
||||
|
||||
|
|
File diff suppressed because it is too large
Load diff
|
@ -5,15 +5,65 @@ import re
|
|||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
get_element_by_class,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
strip_or_none,
|
||||
try_get,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class VidioIE(InfoExtractor):
|
||||
class VidioBaseIE(InfoExtractor):
|
||||
_LOGIN_URL = 'https://www.vidio.com/users/login'
|
||||
_NETRC_MACHINE = 'vidio'
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
return
|
||||
|
||||
def is_logged_in():
|
||||
res = self._download_json(
|
||||
'https://www.vidio.com/interactions.json', None, 'Checking if logged in', fatal=False) or {}
|
||||
return bool(res.get('current_user'))
|
||||
|
||||
if is_logged_in():
|
||||
return
|
||||
|
||||
login_page = self._download_webpage(
|
||||
self._LOGIN_URL, None, 'Downloading log in page')
|
||||
|
||||
login_form = self._form_hidden_inputs("login-form", login_page)
|
||||
login_form.update({
|
||||
'user[login]': username,
|
||||
'user[password]': password,
|
||||
})
|
||||
login_post, login_post_urlh = self._download_webpage_handle(
|
||||
self._LOGIN_URL, None, 'Logging in', data=urlencode_postdata(login_form), expected_status=[302, 401])
|
||||
|
||||
if login_post_urlh.status == 401:
|
||||
reason = get_element_by_class('onboarding-form__general-error', login_post)
|
||||
if reason:
|
||||
raise ExtractorError(
|
||||
'Unable to log in: %s' % reason, expected=True)
|
||||
raise ExtractorError('Unable to log in')
|
||||
|
||||
def _real_initialize(self):
|
||||
self._api_key = self._download_json(
|
||||
'https://www.vidio.com/auth', None, data=b'')['api_key']
|
||||
self._login()
|
||||
|
||||
def _call_api(self, url, video_id, note=None):
|
||||
return self._download_json(url, video_id, note=note, headers={
|
||||
'Content-Type': 'application/vnd.api+json',
|
||||
'X-API-KEY': self._api_key,
|
||||
})
|
||||
|
||||
|
||||
class VidioIE(VidioBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?vidio\.com/watch/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015',
|
||||
|
@ -41,24 +91,38 @@ class VidioIE(InfoExtractor):
|
|||
}, {
|
||||
'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Premier-exclusive video
|
||||
'url': 'https://www.vidio.com/watch/1550718-stand-by-me-doraemon',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
self._api_key = self._download_json(
|
||||
'https://www.vidio.com/auth', None, data=b'')['api_key']
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
data = self._download_json(
|
||||
'https://api.vidio.com/videos/' + video_id, display_id, headers={
|
||||
'Content-Type': 'application/vnd.api+json',
|
||||
'X-API-KEY': self._api_key,
|
||||
})
|
||||
data = self._call_api('https://api.vidio.com/videos/' + video_id, display_id)
|
||||
video = data['videos'][0]
|
||||
title = video['title'].strip()
|
||||
is_premium = video.get('is_premium')
|
||||
|
||||
if is_premium:
|
||||
sources = self._download_json(
|
||||
'https://www.vidio.com/interactions_stream.json?video_id=%s&type=videos' % video_id,
|
||||
display_id, note='Downloading premier API JSON')
|
||||
if not (sources.get('source') or sources.get('source_dash')):
|
||||
self.raise_login_required('This video is only available for registered users with the appropriate subscription')
|
||||
|
||||
formats = []
|
||||
if sources.get('source'):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
sources['source'], display_id, 'mp4', 'm3u8_native'))
|
||||
if sources.get('source_dash'): # TODO: Find video example with source_dash
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
sources['source_dash'], display_id, 'dash'))
|
||||
else:
|
||||
hls_url = data['clips'][0]['hls_url']
|
||||
formats = self._extract_m3u8_formats(
|
||||
hls_url, display_id, 'mp4', 'm3u8_native')
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
data['clips'][0]['hls_url'], display_id, 'mp4', 'm3u8_native')
|
||||
self._sort_formats(formats)
|
||||
|
||||
get_first = lambda x: try_get(data, lambda y: y[x + 's'][0], dict) or {}
|
||||
|
@ -87,3 +151,131 @@ class VidioIE(InfoExtractor):
|
|||
'comment_count': get_count('comments'),
|
||||
'tags': video.get('tag_list'),
|
||||
}
|
||||
|
||||
|
||||
class VidioPremierIE(VidioBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?vidio\.com/premier/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.vidio.com/premier/2885/badai-pasti-berlalu',
|
||||
'playlist_mincount': 14,
|
||||
}, {
|
||||
# Series with both free and premier-exclusive videos
|
||||
'url': 'https://www.vidio.com/premier/2567/sosmed',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _playlist_entries(self, playlist, series_id, series_name, season_name, display_id):
|
||||
playlist_url = 'https://api.vidio.com/content_profiles/%s/playlists/%s/playlist_items' % (series_id, playlist['id'])
|
||||
|
||||
entries = []
|
||||
index = 1
|
||||
episode_index = 1
|
||||
while playlist_url:
|
||||
playlist_json = self._call_api(playlist_url, display_id, 'Downloading API JSON page %s' % index)
|
||||
for video_json in playlist_json.get('data', []):
|
||||
link = video_json['links']['watchpage']
|
||||
result = self.url_result(link, 'Vidio', video_json['id'])
|
||||
result.update({
|
||||
'series': series_name,
|
||||
'season': season_name,
|
||||
'episode': try_get(video_json, lambda x: x['attributes']['title']),
|
||||
'episode_number': episode_index,
|
||||
})
|
||||
entries.append(result)
|
||||
episode_index += 1
|
||||
playlist_url = try_get(playlist_json, lambda x: x['links']['next'])
|
||||
index += 1
|
||||
return entries
|
||||
|
||||
def _real_extract(self, url):
|
||||
premier_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
entries = []
|
||||
playlist_data = self._call_api('https://www.vidio.com/api/series/%s' % premier_id, display_id)
|
||||
# While the video entries are embedded within the series JSON metadata, they're (accidentally?) truncated on really long playlists so content profile API is still used
|
||||
for playlist in playlist_data.get('seasons', []):
|
||||
entries.extend(self._playlist_entries(
|
||||
playlist, premier_id, playlist_data.get('title'), playlist.get('name'), display_id))
|
||||
return self.playlist_result(
|
||||
entries, premier_id, playlist_data.get('title'), playlist_data.get('description'))
|
||||
|
||||
|
||||
class VidioLiveIE(VidioBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?vidio\.com/live/(?P<id>\d+)-(?P<display_id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.vidio.com/live/204-sctv',
|
||||
'info_dict': {
|
||||
'id': '204',
|
||||
'title': 'SCTV',
|
||||
'uploader': 'SCTV',
|
||||
'uploader_id': 'sctv',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
},
|
||||
}, {
|
||||
# Premier-exclusive livestream
|
||||
'url': 'https://www.vidio.com/live/6362-tvn',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# DRM premier-exclusive livestream
|
||||
'url': 'https://www.vidio.com/live/6299-bein-1',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
stream_data = self._call_api(
|
||||
'https://www.vidio.com/api/livestreamings/%s/detail' % video_id, display_id)
|
||||
stream_meta = stream_data['livestreamings'][0]
|
||||
user = stream_data.get('users', [{}])[0]
|
||||
|
||||
title = stream_meta.get('title')
|
||||
username = user.get('username')
|
||||
|
||||
formats = []
|
||||
if stream_meta.get('is_drm'):
|
||||
self.raise_no_formats(
|
||||
'This video is DRM protected.', expected=True)
|
||||
|
||||
if stream_meta.get('is_premium'):
|
||||
sources = self._download_json(
|
||||
'https://www.vidio.com/interactions_stream.json?video_id=%s&type=livestreamings' % video_id,
|
||||
display_id, note='Downloading premier API JSON')
|
||||
if not (sources.get('source') or sources.get('source_dash')):
|
||||
self.raise_login_required('This video is only available for registered users with the appropriate subscription')
|
||||
|
||||
if sources.get('source'):
|
||||
token_json = self._download_json(
|
||||
'https://www.vidio.com/live/%s/tokens' % video_id,
|
||||
display_id, note='Downloading HLS token JSON', data=b'')
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
sources['source'] + '?' + token_json.get('token', ''), display_id, 'mp4', 'm3u8_native'))
|
||||
if sources.get('source_dash'):
|
||||
pass
|
||||
else:
|
||||
if stream_meta.get('stream_token_url'):
|
||||
token_json = self._download_json(
|
||||
'https://www.vidio.com/live/%s/tokens' % video_id,
|
||||
display_id, note='Downloading HLS token JSON', data=b'')
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
stream_meta['stream_token_url'] + '?' + token_json.get('token', ''), display_id, 'mp4', 'm3u8_native'))
|
||||
if stream_meta.get('stream_dash_url'):
|
||||
pass
|
||||
if stream_meta.get('stream_url'):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
stream_meta['stream_url'], display_id, 'mp4', 'm3u8_native'))
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'is_live': True,
|
||||
'description': strip_or_none(stream_meta.get('description')),
|
||||
'thumbnail': stream_meta.get('image'),
|
||||
'like_count': int_or_none(stream_meta.get('like')),
|
||||
'dislike_count': int_or_none(stream_meta.get('dislike')),
|
||||
'formats': formats,
|
||||
'uploader': user.get('name'),
|
||||
'timestamp': parse_iso8601(stream_meta.get('start_time')),
|
||||
'uploader_id': username,
|
||||
'uploader_url': 'https://www.vidio.com/@' + username if username else None,
|
||||
}
|
||||
|
|
|
@ -4,6 +4,7 @@ from __future__ import unicode_literals
|
|||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
get_element_by_id,
|
||||
|
@ -11,6 +12,7 @@ from ..utils import (
|
|||
strip_or_none,
|
||||
unified_strdate,
|
||||
urljoin,
|
||||
str_to_int,
|
||||
)
|
||||
|
||||
|
||||
|
@ -35,6 +37,26 @@ class VidLiiIE(InfoExtractor):
|
|||
'categories': ['News & Politics'],
|
||||
'tags': ['Vidlii', 'Jan', 'Videogames'],
|
||||
}
|
||||
}, {
|
||||
# HD
|
||||
'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
|
||||
'md5': '450e7da379c884788c3a4fa02a3ce1a4',
|
||||
'info_dict': {
|
||||
'id': '2Ng8Abj2Fkl',
|
||||
'ext': 'mp4',
|
||||
'title': 'test',
|
||||
'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
|
||||
'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
|
||||
'uploader': 'VidLii',
|
||||
'uploader_url': 'https://www.vidlii.com/user/VidLii',
|
||||
'upload_date': '20200927',
|
||||
'duration': 5,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'average_rating': float,
|
||||
'categories': ['Film & Animation'],
|
||||
'tags': list,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
|
||||
'only_matching': True,
|
||||
|
@ -46,11 +68,32 @@ class VidLiiIE(InfoExtractor):
|
|||
webpage = self._download_webpage(
|
||||
'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
|
||||
|
||||
video_url = self._search_regex(
|
||||
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
|
||||
'video url', group='url')
|
||||
formats = []
|
||||
|
||||
title = self._search_regex(
|
||||
def add_format(format_url, height=None):
|
||||
height = int(self._search_regex(r'(\d+)\.mp4',
|
||||
format_url, 'height', default=360))
|
||||
|
||||
formats.append({
|
||||
'url': format_url,
|
||||
'format_id': '%dp' % height if height else None,
|
||||
'height': height,
|
||||
})
|
||||
|
||||
sources = re.findall(
|
||||
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
|
||||
webpage)
|
||||
|
||||
formats = []
|
||||
if len(sources) > 1:
|
||||
add_format(sources[1][1])
|
||||
self._check_formats(formats, video_id)
|
||||
if len(sources) > 0:
|
||||
add_format(sources[0][1])
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._html_search_regex(
|
||||
(r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
|
||||
'title')
|
||||
|
||||
|
@ -82,9 +125,9 @@ class VidLiiIE(InfoExtractor):
|
|||
default=None) or self._search_regex(
|
||||
r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
|
||||
|
||||
view_count = int_or_none(self._search_regex(
|
||||
(r'<strong>(\d+)</strong> views',
|
||||
r'Views\s*:\s*<strong>(\d+)</strong>'),
|
||||
view_count = str_to_int(self._html_search_regex(
|
||||
(r'<strong>([\d,.]+)</strong> views',
|
||||
r'Views\s*:\s*<strong>([\d,.]+)</strong>'),
|
||||
webpage, 'view count', fatal=False))
|
||||
|
||||
comment_count = int_or_none(self._search_regex(
|
||||
|
@ -109,7 +152,7 @@ class VidLiiIE(InfoExtractor):
|
|||
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
|
|
Loading…
Reference in a new issue