Merge branch 'master' into fixes_for_vier_extractor
Cedric Nugteren
2 years ago
commit
d893535d7b
@ -0,0 +1,26 @@
|
||||
#!/usr/bin/env python
|
||||
from __future__ import unicode_literals
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
|
||||
from youtube_dl.extractor import YoutubeIE
|
||||
|
||||
|
||||
class TestYoutubeMisc(unittest.TestCase):
|
||||
def test_youtube_extract(self):
|
||||
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
|
||||
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
|
||||
assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
|
||||
assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
|
||||
assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
|
||||
assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
|
||||
assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
@ -0,0 +1,66 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
try:
|
||||
import threading
|
||||
except ImportError:
|
||||
threading = None
|
||||
|
||||
from .common import FileDownloader
|
||||
from ..downloader import get_suitable_downloader
|
||||
from ..extractor.niconico import NiconicoIE
|
||||
from ..utils import sanitized_Request
|
||||
|
||||
|
||||
class NiconicoDmcFD(FileDownloader):
|
||||
""" Downloading niconico douga from DMC with heartbeat """
|
||||
|
||||
FD_NAME = 'niconico_dmc'
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
self.to_screen('[%s] Downloading from DMC' % self.FD_NAME)
|
||||
|
||||
ie = NiconicoIE(self.ydl)
|
||||
info_dict, heartbeat_info_dict = ie._get_heartbeat_info(info_dict)
|
||||
|
||||
fd = get_suitable_downloader(info_dict, params=self.params)(self.ydl, self.params)
|
||||
for ph in self._progress_hooks:
|
||||
fd.add_progress_hook(ph)
|
||||
|
||||
if not threading:
|
||||
self.to_screen('[%s] Threading for Heartbeat not available' % self.FD_NAME)
|
||||
return fd.real_download(filename, info_dict)
|
||||
|
||||
success = download_complete = False
|
||||
timer = [None]
|
||||
heartbeat_lock = threading.Lock()
|
||||
heartbeat_url = heartbeat_info_dict['url']
|
||||
heartbeat_data = heartbeat_info_dict['data'].encode()
|
||||
heartbeat_interval = heartbeat_info_dict.get('interval', 30)
|
||||
|
||||
request = sanitized_Request(heartbeat_url, heartbeat_data)
|
||||
|
||||
def heartbeat():
|
||||
try:
|
||||
self.ydl.urlopen(request).read()
|
||||
except Exception:
|
||||
self.to_screen('[%s] Heartbeat failed' % self.FD_NAME)
|
||||
|
||||
with heartbeat_lock:
|
||||
if not download_complete:
|
||||
timer[0] = threading.Timer(heartbeat_interval, heartbeat)
|
||||
timer[0].start()
|
||||
|
||||
heartbeat_info_dict['ping']()
|
||||
self.to_screen('[%s] Heartbeat with %d second interval ...' % (self.FD_NAME, heartbeat_interval))
|
||||
try:
|
||||
heartbeat()
|
||||
if type(fd).__name__ == 'HlsFD':
|
||||
info_dict.update(ie._extract_m3u8_formats(info_dict['url'], info_dict['id'])[0])
|
||||
success = fd.real_download(filename, info_dict)
|
||||
finally:
|
||||
if heartbeat_lock:
|
||||
with heartbeat_lock:
|
||||
timer[0].cancel()
|
||||
download_complete = True
|
||||
return success
|
||||
@ -0,0 +1,89 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
dict_get,
|
||||
get_element_by_class,
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class Alsace20TVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
|
||||
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
|
||||
'info_dict': {
|
||||
'id': 'lyNHCXpYJh',
|
||||
'ext': 'mp4',
|
||||
'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
|
||||
'title': 'Votre JT du jeudi 3 février',
|
||||
'upload_date': '20220203',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'duration': 1073,
|
||||
'view_count': int,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
}]
|
||||
|
||||
def _extract_video(self, video_id, url=None):
|
||||
info = self._download_json(
|
||||
'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
|
||||
video_id) or {}
|
||||
title = info['titre']
|
||||
|
||||
formats = []
|
||||
for res, fmt_url in (info.get('files') or {}).items():
|
||||
formats.extend(
|
||||
self._extract_smil_formats(fmt_url, video_id, fatal=False)
|
||||
if '/smil:_' in fmt_url
|
||||
else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
|
||||
self._sort_formats(formats)
|
||||
|
||||
webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
|
||||
thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
|
||||
upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
|
||||
upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'description': clean_html(get_element_by_class('wysiwyg', webpage)),
|
||||
'upload_date': upload_date,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
|
||||
'view_count': int_or_none(info.get('nb_vues')),
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
return self._extract_video(video_id, url)
|
||||
|
||||
|
||||
class Alsace20TVEmbedIE(Alsace20TVIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
|
||||
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
|
||||
'info_dict': {
|
||||
'id': 'lyNHCXpYJh',
|
||||
'ext': 'mp4',
|
||||
'title': 'Votre JT du jeudi 3 février',
|
||||
'upload_date': '20220203',
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'view_count': int,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
return self._extract_video(video_id)
|
||||
@ -0,0 +1,101 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_parse_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
remove_start,
|
||||
)
|
||||
|
||||
|
||||
class ArnesIE(InfoExtractor):
|
||||
IE_NAME = 'video.arnes.si'
|
||||
IE_DESC = 'Arnes Video'
|
||||
_VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P<id>[0-9a-zA-Z]{12})'
|
||||
_TESTS = [{
|
||||
'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10',
|
||||
'md5': '4d0f4d0a03571b33e1efac25fd4a065d',
|
||||
'info_dict': {
|
||||
'id': 'a1qrWTOQfVoU',
|
||||
'ext': 'mp4',
|
||||
'title': 'Linearna neodvisnost, definicija',
|
||||
'description': 'Linearna neodvisnost, definicija',
|
||||
'license': 'PRIVATE',
|
||||
'creator': 'Polona Oblak',
|
||||
'timestamp': 1585063725,
|
||||
'upload_date': '20200324',
|
||||
'channel': 'Polona Oblak',
|
||||
'channel_id': 'q6pc04hw24cj',
|
||||
'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj',
|
||||
'duration': 596.75,
|
||||
'view_count': int,
|
||||
'tags': ['linearna_algebra'],
|
||||
'start_time': 10,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.arnes.si/embed/s1YjnV7hadlC',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_BASE_URL = 'https://video.arnes.si'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
video = self._download_json(
|
||||
self._BASE_URL + '/api/public/video/' + video_id, video_id)['data']
|
||||
title = video['title']
|
||||
|
||||
formats = []
|
||||
for media in (video.get('media') or []):
|
||||
media_url = media.get('url')
|
||||
if not media_url:
|
||||
continue
|
||||
formats.append({
|
||||
'url': self._BASE_URL + media_url,
|
||||
'format_id': remove_start(media.get('format'), 'FORMAT_'),
|
||||
'format_note': media.get('formatTranslation'),
|
||||
'width': int_or_none(media.get('width')),
|
||||
'height': int_or_none(media.get('height')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
channel = video.get('channel') or {}
|
||||
channel_id = channel.get('url')
|
||||
thumbnail = video.get('thumbnailUrl')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': self._BASE_URL + thumbnail,
|
||||
'description': video.get('description'),
|
||||
'license': video.get('license'),
|
||||
'creator': video.get('author'),
|
||||
'timestamp': parse_iso8601(video.get('creationTime')),
|
||||
'channel': channel.get('name'),
|
||||
'channel_id': channel_id,
|
||||
'channel_url': self._BASE_URL + '/?channel=' + channel_id if channel_id else None,
|
||||
'duration': float_or_none(video.get('duration'), 1000),
|
||||
'view_count': int_or_none(video.get('views')),
|
||||
'tags': video.get('hashtags'),
|
||||
'start_time': int_or_none(compat_parse_qs(
|
||||
compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
|
||||
}
|
||||
@ -0,0 +1,37 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .brightcove import BrightcoveNewIE
|
||||
from ..utils import extract_attributes
|
||||
|
||||
|
||||
class BandaiChannelIE(BrightcoveNewIE):
|
||||
IE_NAME = 'bandaichannel'
|
||||
_VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.b-ch.com/titles/514/001',
|
||||
'md5': 'a0f2d787baa5729bed71108257f613a4',
|
||||
'info_dict': {
|
||||
'id': '6128044564001',
|
||||
'ext': 'mp4',
|
||||
'title': 'メタルファイターMIKU 第1話',
|
||||
'timestamp': 1580354056,
|
||||
'uploader_id': '5797077852001',
|
||||
'upload_date': '20200130',
|
||||
'duration': 1387.733,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
attrs = extract_attributes(self._search_regex(
|
||||
r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
|
||||
bc = self._download_json(
|
||||
'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
|
||||
video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
|
||||
return self._parse_brightcove_metadata(bc, bc['id'])
|
||||
@ -0,0 +1,59 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError, urlencode_postdata
|
||||
|
||||
|
||||
class BigoIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bigo.tv/ja/221338632',
|
||||
'info_dict': {
|
||||
'id': '6576287577575737440',
|
||||
'title': '土よ〜💁♂️ 休憩室/REST room',
|
||||
'thumbnail': r're:https?://.+',
|
||||
'uploader': '✨Shin💫',
|
||||
'uploader_id': '221338632',
|
||||
'is_live': True,
|
||||
},
|
||||
'skip': 'livestream',
|
||||
}, {
|
||||
'url': 'https://www.bigo.tv/th/Tarlerm1304',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://bigo.tv/115976881',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
user_id = self._match_id(url)
|
||||
|
||||
info_raw = self._download_json(
|
||||
'https://bigo.tv/studio/getInternalStudioInfo',
|
||||
user_id, data=urlencode_postdata({'siteId': user_id}))
|
||||
|
||||
if not isinstance(info_raw, dict):
|
||||
raise ExtractorError('Received invalid JSON data')
|
||||
if info_raw.get('code'):
|
||||
raise ExtractorError(
|
||||
'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
|
||||
info = info_raw.get('data') or {}
|
||||
|
||||
if not info.get('alive'):
|
||||
raise ExtractorError('This user is offline.', expected=True)
|
||||
|
||||
return {
|
||||
'id': info.get('roomId') or user_id,
|
||||
'title': info.get('roomTopic') or info.get('nick_name') or user_id,
|
||||
'formats': [{
|
||||
'url': info.get('hls_src'),
|
||||
'ext': 'mp4',
|
||||
'protocol': 'm3u8',
|
||||
}],
|
||||
'thumbnail': info.get('snapshot'),
|
||||
'uploader': info.get('nick_name'),
|
||||
'uploader_id': user_id,
|
||||
'is_live': True,
|
||||
}
|
||||
@ -1,86 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
remove_start,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class BlinkxIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?://(?:www\.)blinkx\.com/#?ce/|blinkx:)(?P<id>[^?]+)'
|
||||
IE_NAME = 'blinkx'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.blinkx.com/ce/Da0Gw3xc5ucpNduzLuDDlv4WC9PuI4fDi1-t6Y3LyfdY2SZS5Urbvn-UPJvrvbo8LTKTc67Wu2rPKSQDJyZeeORCR8bYkhs8lI7eqddznH2ofh5WEEdjYXnoRtj7ByQwt7atMErmXIeYKPsSDuMAAqJDlQZ-3Ff4HJVeH_s3Gh8oQ',
|
||||
'md5': '337cf7a344663ec79bf93a526a2e06c7',
|
||||
'info_dict': {
|
||||
'id': 'Da0Gw3xc',
|
||||
'ext': 'mp4',
|
||||
'title': 'No Daily Show for John Oliver; HBO Show Renewed - IGN News',
|
||||
'uploader': 'IGN News',
|
||||
'upload_date': '20150217',
|
||||
'timestamp': 1424215740,
|
||||
'description': 'HBO has renewed Last Week Tonight With John Oliver for two more seasons.',
|
||||
'duration': 47.743333,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
display_id = video_id[:8]
|
||||
|
||||
api_url = ('https://apib4.blinkx.com/api.php?action=play_video&'
|
||||
+ 'video=%s' % video_id)
|
||||
data_json = self._download_webpage(api_url, display_id)
|
||||
data = json.loads(data_json)['api']['results'][0]
|
||||
duration = None
|
||||
thumbnails = []
|
||||
formats = []
|
||||
for m in data['media']:
|
||||
if m['type'] == 'jpg':
|
||||
thumbnails.append({
|
||||
'url': m['link'],
|
||||
'width': int(m['w']),
|
||||
'height': int(m['h']),
|
||||
})
|
||||
elif m['type'] == 'original':
|
||||
duration = float(m['d'])
|
||||
elif m['type'] == 'youtube':
|
||||
yt_id = m['link']
|
||||
self.to_screen('Youtube video detected: %s' % yt_id)
|
||||
return self.url_result(yt_id, 'Youtube', video_id=yt_id)
|
||||
elif m['type'] in ('flv', 'mp4'):
|
||||
vcodec = remove_start(m['vcodec'], 'ff')
|
||||
acodec = remove_start(m['acodec'], 'ff')
|
||||
vbr = int_or_none(m.get('vbr') or m.get('vbitrate'), 1000)
|
||||
abr = int_or_none(m.get('abr') or m.get('abitrate'), 1000)
|
||||
tbr = vbr + abr if vbr and abr else None
|
||||
format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': m['link'],
|
||||
'vcodec': vcodec,
|
||||
'acodec': acodec,
|
||||
'abr': abr,
|
||||
'vbr': vbr,
|
||||
'tbr': tbr,
|
||||
'width': int_or_none(m.get('w')),
|
||||
'height': int_or_none(m.get('h')),
|
||||
})
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': display_id,
|
||||
'fullid': video_id,
|
||||
'title': data['title'],
|
||||
'formats': formats,
|
||||
'uploader': data['channel_name'],
|
||||
'timestamp': data['pubdate_epoch'],
|
||||
'description': data.get('description'),
|
||||
'thumbnails': thumbnails,
|
||||
'duration': duration,
|
||||
}
|
||||
@ -1,38 +1,113 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .cbs import CBSBaseIE
|
||||
import re
|
||||
|
||||
# from .cbs import CBSBaseIE
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
class CBSSportsIE(CBSBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/(?:video|news)/(?P<id>[^/?#&]+)'
|
||||
|
||||
# class CBSSportsEmbedIE(CBSBaseIE):
|
||||
class CBSSportsEmbedIE(InfoExtractor):
|
||||
IE_NAME = 'cbssports:embed'
|
||||
_VALID_URL = r'''(?ix)https?://(?:(?:www\.)?cbs|embed\.247)sports\.com/player/embed.+?
|
||||
(?:
|
||||
ids%3D(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})|
|
||||
pcid%3D(?P<pcid>\d+)
|
||||
)'''
|
||||
_TESTS = [{
|
||||
'url': 'https://www.cbssports.com/nba/video/donovan-mitchell-flashes-star-potential-in-game-2-victory-over-thunder/',
|
||||
'info_dict': {
|
||||
'id': '1214315075735',
|
||||
'ext': 'mp4',
|
||||
'title': 'Donovan Mitchell flashes star potential in Game 2 victory over Thunder',
|
||||
'description': 'md5:df6f48622612c2d6bd2e295ddef58def',
|
||||
'timestamp': 1524111457,
|
||||
'upload_date': '20180419',
|
||||
'uploader': 'CBSI-NEW',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
}
|
||||
'url': 'https://www.cbssports.com/player/embed/?args=player_id%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26ids%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26resizable%3D1%26autoplay%3Dtrue%26domain%3Dcbssports.com%26comp_ads_enabled%3Dfalse%26watchAndRead%3D0%26startTime%3D0%26env%3Dprod',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.cbssports.com/nba/news/nba-playoffs-2018-watch-76ers-vs-heat-game-3-series-schedule-tv-channel-online-stream/',
|
||||
'url': 'https://embed.247sports.com/player/embed/?args=%3fplayer_id%3d1827823171591%26channel%3dcollege-football-recruiting%26pcid%3d1827823171591%26width%3d640%26height%3d360%26autoplay%3dTrue%26comp_ads_enabled%3dFalse%26uvpc%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_v4%2526partner%253d247%26uvpc_m%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_m_v4%2526partner_m%253d247_mobile%26utag%3d247sportssite%26resizable%3dTrue',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_video_info(self, filter_query, video_id):
|
||||
return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
|
||||
# def _extract_video_info(self, filter_query, video_id):
|
||||
# return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
|
||||
|
||||
def _real_extract(self, url):
|
||||
uuid, pcid = re.match(self._VALID_URL, url).groups()
|
||||
query = {'id': uuid} if uuid else {'pcid': pcid}
|
||||
video = self._download_json(
|
||||
'https://www.cbssports.com/api/content/video/',
|
||||
uuid or pcid, query=query)[0]
|
||||
video_id = video['id']
|
||||
title = video['title']
|
||||
metadata = video.get('metaData') or {}
|
||||
# return self._extract_video_info('byId=%d' % metadata['mpxOutletId'], video_id)
|
||||
# return self._extract_video_info('byGuid=' + metadata['mpxRefId'], video_id)
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
metadata['files'][0]['url'], video_id, 'mp4',
|
||||
'm3u8_native', m3u8_id='hls', fatal=False)
|
||||
self._sort_formats(formats)
|
||||
|
||||
image = video.get('image')
|
||||
thumbnails = None
|
||||
if image:
|
||||
image_path = image.get('path')
|
||||
if image_path:
|
||||
thumbnails = [{
|
||||
'url': image_path,
|
||||
'width': int_or_none(image.get('width')),
|
||||
'height': int_or_none(image.get('height')),
|
||||
'filesize': int_or_none(image.get('size')),
|
||||
}]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnails': thumbnails,
|
||||
'description': video.get('description'),
|
||||
'timestamp': int_or_none(try_get(video, lambda x: x['dateCreated']['epoch'])),
|
||||
'duration': int_or_none(metadata.get('duration')),
|
||||
}
|
||||
|
||||
|
||||
class CBSSportsBaseIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._search_regex(
|
||||
[r'(?:=|%26)pcid%3D(\d+)', r'embedVideo(?:Container)?_(\d+)'],
|
||||
webpage, 'video id')
|
||||
return self._extract_video_info('byId=%s' % video_id, video_id)
|
||||
iframe_url = self._search_regex(
|
||||
r'<iframe[^>]+(?:data-)?src="(https?://[^/]+/player/embed[^"]+)"',
|
||||
webpage, 'embed url')
|
||||
return self.url_result(iframe_url, CBSSportsEmbedIE.ie_key())
|
||||
|
||||
|
||||
class CBSSportsIE(CBSSportsBaseIE):
|
||||
IE_NAME = 'cbssports'
|
||||
_VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/video/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.cbssports.com/college-football/video/cover-3-stanford-spring-gleaning/',
|
||||
'info_dict': {
|
||||
'id': 'b56c03a6-231a-4bbe-9c55-af3c8a8e9636',
|
||||
'ext': 'mp4',
|
||||
'title': 'Cover 3: Stanford Spring Gleaning',
|
||||
'description': 'The Cover 3 crew break down everything you need to know about the Stanford Cardinal this spring.',
|
||||
'timestamp': 1617218398,
|
||||
'upload_date': '20210331',
|
||||
'duration': 502,
|
||||
},
|
||||
}]
|
||||
|
||||
|
||||
class TwentyFourSevenSportsIE(CBSSportsBaseIE):
|
||||
IE_NAME = '247sports'
|
||||
_VALID_URL = r'https?://(?:www\.)?247sports\.com/Video/(?:[^/?#&]+-)?(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://247sports.com/Video/2021-QB-Jake-Garcia-senior-highlights-through-five-games-10084854/',
|
||||
'info_dict': {
|
||||
'id': '4f1265cb-c3b5-44a8-bb1d-1914119a0ccc',
|
||||
'ext': 'mp4',
|
||||
'title': '2021 QB Jake Garcia senior highlights through five games',
|
||||
'description': 'md5:8cb67ebed48e2e6adac1701e0ff6e45b',
|
||||
'timestamp': 1607114223,
|
||||
'upload_date': '20201204',
|
||||
'duration': 208,
|
||||
},
|
||||
}]
|
||||
|
||||
@ -1,193 +1,43 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
from .zdf import ZDFIE
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
xpath_text,
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class DreiSatIE(InfoExtractor):
|
||||
class DreiSatIE(ZDFIE):
|
||||
IE_NAME = '3sat'
|
||||
_GEO_COUNTRIES = ['DE']
|
||||
_VALID_URL = r'https?://(?:www\.)?3sat\.de/mediathek/(?:(?:index|mediathek)\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
|
||||
'md5': 'be37228896d30a88f315b638900a026e',
|
||||
'info_dict': {
|
||||
'id': '45918',
|
||||
'ext': 'mp4',
|
||||
'title': 'Waidmannsheil',
|
||||
'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
|
||||
'uploader': 'SCHWEIZWEIT',
|
||||
'uploader_id': '100000210',
|
||||
'upload_date': '20140913'
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # m3u8 downloads
|
||||
}
|
||||
_VALID_URL = r'https?://(?:www\.)?3sat\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
|
||||
_TESTS = [{
|
||||
# Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html
|
||||
'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html',
|
||||
'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
|
||||
'info_dict': {
|
||||
'id': '141007_ab18_10wochensommer_film',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ab 18! - 10 Wochen Sommer',
|
||||
'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
|
||||
'duration': 2660,
|
||||
'timestamp': 1608604200,
|
||||
'upload_date': '20201222',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html',
|
||||
'info_dict': {
|
||||
'id': '140913_sendung_schweizweit',
|
||||
'ext': 'mp4',
|
||||
'title': 'Waidmannsheil',
|
||||
'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
|
||||
'timestamp': 1410623100,
|
||||
'upload_date': '20140913'
|
||||
},
|
||||
]
|
||||
|
||||
def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
|
||||
param_groups = {}
|
||||
for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
|
||||
group_id = param_group.get(self._xpath_ns(
|
||||
'id', 'http://www.w3.org/XML/1998/namespace'))
|
||||
params = {}
|
||||
for param in param_group:
|
||||
params[param.get('name')] = param.get('value')
|
||||
param_groups[group_id] = params
|
||||
|
||||
formats = []
|
||||
for video in smil.findall(self._xpath_ns('.//video', namespace)):
|
||||
src = video.get('src')
|
||||
if not src:
|
||||
continue
|
||||
bitrate = int_or_none(self._search_regex(r'_(\d+)k', src, 'bitrate', None)) or float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
|
||||
group_id = video.get('paramGroup')
|
||||
param_group = param_groups[group_id]
|
||||
for proto in param_group['protocols'].split(','):
|
||||
formats.append({
|
||||
'url': '%s://%s' % (proto, param_group['host']),
|
||||
'app': param_group['app'],
|
||||
'play_path': src,
|
||||
'ext': 'flv',
|
||||
'format_id': '%s-%d' % (proto, bitrate),
|
||||
'tbr': bitrate,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
return formats
|
||||
|
||||
def extract_from_xml_url(self, video_id, xml_url):
|
||||
doc = self._download_xml(
|
||||
xml_url, video_id,
|
||||
note='Downloading video info',
|
||||
errnote='Failed to download video info')
|
||||
|
||||
status_code = xpath_text(doc, './status/statuscode')
|
||||
if status_code and status_code != 'ok':
|
||||
if status_code == 'notVisibleAnymore':
|
||||
message = 'Video %s is not available' % video_id
|
||||
else:
|
||||
message = '%s returned error: %s' % (self.IE_NAME, status_code)
|
||||
raise ExtractorError(message, expected=True)
|
||||
|
||||
title = xpath_text(doc, './/information/title', 'title', True)
|
||||
|
||||
urls = []
|
||||
formats = []
|
||||
for fnode in doc.findall('.//formitaeten/formitaet'):
|
||||
video_url = xpath_text(fnode, 'url')
|
||||
if not video_url or video_url in urls:
|
||||
continue
|
||||
urls.append(video_url)
|
||||
|
||||
is_available = 'http://www.metafilegenerator' not in video_url
|
||||
geoloced = 'static_geoloced_online' in video_url
|
||||
if not is_available or geoloced:
|
||||
continue
|
||||
|
||||
format_id = fnode.attrib['basetype']
|
||||
format_m = re.match(r'''(?x)
|
||||
(?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
|
||||
(?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
|
||||
''', format_id)
|
||||
|
||||
ext = determine_ext(video_url, None) or format_m.group('container')
|
||||
|
||||
if ext == 'meta':
|
||||
continue
|
||||
elif ext == 'smil':
|
||||
formats.extend(self._extract_smil_formats(
|
||||
video_url, video_id, fatal=False))
|
||||
elif ext == 'm3u8':
|
||||
# the certificates are misconfigured (see
|
||||
# https://github.com/ytdl-org/youtube-dl/issues/8665)
|
||||
if video_url.startswith('https://'):
|
||||
continue
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
video_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id=format_id, fatal=False))
|
||||
elif ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
video_url, video_id, f4m_id=format_id, fatal=False))
|
||||
else:
|
||||
quality = xpath_text(fnode, './quality')
|
||||
if quality:
|
||||
format_id += '-' + quality
|
||||
|
||||
abr = int_or_none(xpath_text(fnode, './audioBitrate'), 1000)
|
||||
vbr = int_or_none(xpath_text(fnode, './videoBitrate'), 1000)
|
||||
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'_(\d+)k', video_url, 'bitrate', None))
|
||||
if tbr and vbr and not abr:
|
||||
abr = tbr - vbr
|
||||
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': video_url,
|
||||
'ext': ext,
|
||||
'acodec': format_m.group('acodec'),
|
||||
'vcodec': format_m.group('vcodec'),
|
||||
'abr': abr,
|
||||
'vbr': vbr,
|
||||
'tbr': tbr,
|
||||
'width': int_or_none(xpath_text(fnode, './width')),
|
||||
'height': int_or_none(xpath_text(fnode, './height')),
|
||||
'filesize': int_or_none(xpath_text(fnode, './filesize')),
|
||||
'protocol': format_m.group('proto').lower(),
|
||||
})
|
||||
|
||||
geolocation = xpath_text(doc, './/details/geolocation')
|
||||
if not formats and geolocation and geolocation != 'none':
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnails = []
|
||||
for node in doc.findall('.//teaserimages/teaserimage'):
|
||||
thumbnail_url = node.text
|
||||
if not thumbnail_url:
|
||||
continue
|
||||
thumbnail = {
|
||||
'url': thumbnail_url,
|
||||
}
|
||||
thumbnail_key = node.get('key')
|
||||
if thumbnail_key:
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
thumbnails.append(thumbnail)
|
||||
|
||||
upload_date = unified_strdate(xpath_text(doc, './/details/airtime'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': xpath_text(doc, './/information/detail'),
|
||||
'duration': int_or_none(xpath_text(doc, './/details/lengthSec')),
|
||||
'thumbnails': thumbnails,
|
||||
'uploader': xpath_text(doc, './/details/originChannelTitle'),
|
||||
'uploader_id': xpath_text(doc, './/details/originChannelId'),
|
||||
'upload_date': upload_date,
|
||||
'formats': formats,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?id=%s' % video_id
|
||||
return self.extract_from_xml_url(video_id, details_url)
|
||||
}, {
|
||||
# Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
|
||||
'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Same as https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
|
||||
'url': 'https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@ -0,0 +1,161 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class GediDigitalIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://video\.
|
||||
(?:
|
||||
(?:
|
||||
(?:espresso\.)?repubblica
|
||||
|lastampa
|
||||
|ilsecoloxix
|
||||
)|
|
||||
(?:
|
||||
iltirreno
|
||||
|messaggeroveneto
|
||||
|ilpiccolo
|
||||
|gazzettadimantova
|
||||
|mattinopadova
|
||||
|laprovinciapavese
|
||||
|tribunatreviso
|
||||
|nuovavenezia
|
||||
|gazzettadimodena
|
||||
|lanuovaferrara
|
||||
|corrierealpi
|
||||
|lasentinella
|
||||
)\.gelocal
|
||||
)\.it(?:/[^/]+){2,3}?/(?P<id>\d+)(?:[/?&#]|$)'''
|
||||
_TESTS = [{
|
||||
'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
|
||||
'md5': '84658d7fb9e55a6e57ecc77b73137494',
|
||||
'info_dict': {
|
||||
'id': '121559',
|
||||
'ext': 'mp4',
|
||||
'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
|
||||
'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
|
||||
'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$',
|
||||
'duration': 125,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.messaggeroveneto.gelocal.it/locale/maria-giovanna-elmi-covid-vaccino/138155/139268',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.ilpiccolo.gelocal.it/dossier/big-john/dinosauro-big-john-al-via-le-visite-guidate-a-trieste/135226/135751',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.gazzettadimantova.gelocal.it/locale/dal-ponte-visconteo-di-valeggio-l-and-8217sos-dei-ristoratori-aprire-anche-a-cena/137310/137818',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.mattinopadova.gelocal.it/dossier/coronavirus-in-veneto/covid-a-vo-un-anno-dopo-un-cuore-tricolore-per-non-dimenticare/138402/138964',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.laprovinciapavese.gelocal.it/locale/mede-zona-rossa-via-alle-vaccinazioni-per-gli-over-80/137545/138120',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.tribunatreviso.gelocal.it/dossier/coronavirus-in-veneto/ecco-le-prima-vaccinazioni-di-massa-nella-marca/134485/135024',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.nuovavenezia.gelocal.it/locale/camion-troppo-alto-per-il-ponte-ferroviario-perde-il-carico/135734/136266',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.gazzettadimodena.gelocal.it/locale/modena-scoperta-la-proteina-che-predice-il-livello-di-gravita-del-covid/139109/139796',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.lanuovaferrara.gelocal.it/locale/due-bombole-di-gpl-aperte-e-abbandonate-i-vigili-bruciano-il-gas/134391/134957',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.corrierealpi.gelocal.it/dossier/cortina-2021-i-mondiali-di-sci-alpino/mondiali-di-sci-il-timelapse-sulla-splendida-olympia/133760/134331',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.lasentinella.gelocal.it/locale/vestigne-centra-un-auto-e-si-ribalta/138931/139466',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.espresso.repubblica.it/tutti-i-video/01-ted-villa/14772',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._html_search_meta(
|
||||
['twitter:title', 'og:title'], webpage, fatal=True)
|
||||
player_data = re.findall(
|
||||
r"PlayerFactory\.setParam\('(?P<type>format|param)',\s*'(?P<name>[^']+)',\s*'(?P<val>[^']+)'\);",
|
||||
webpage)
|
||||
|
||||
formats = []
|
||||
duration = thumb = None
|
||||
for t, n, v in player_data:
|
||||
if t == 'format':
|
||||
if n in ('video-hds-vod-ec', 'video-hls-vod-ec', 'video-viralize', 'video-youtube-pfp'):
|
||||
continue
|
||||
elif n.endswith('-vod-ak'):
|
||||
formats.extend(self._extract_akamai_formats(
|
||||
v, video_id, {'http': 'media.gedidigital.it'}))
|
||||
else:
|
||||
ext = determine_ext(v)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
v, video_id, 'mp4', 'm3u8_native', m3u8_id=n, fatal=False))
|
||||
continue
|
||||
f = {
|
||||
'format_id': n,
|
||||
'url': v,
|
||||
}
|
||||
if ext == 'mp3':
|
||||
abr = int_or_none(self._search_regex(
|
||||
r'-mp3-audio-(\d+)', v, 'abr', default=None))
|
||||
f.update({
|
||||
'abr': abr,
|
||||
'tbr': abr,
|
||||
'vcodec': 'none'
|
||||
})
|
||||
else:
|
||||
mobj = re.match(r'^video-rrtv-(\d+)(?:-(\d+))?$', n)
|
||||
if mobj:
|
||||
f.update({
|
||||
'height': int(mobj.group(1)),
|
||||
'vbr': int_or_none(mobj.group(2)),
|
||||
})
|
||||
if not f.get('vbr'):
|
||||
f['vbr'] = int_or_none(self._search_regex(
|
||||
r'-video-rrtv-(\d+)', v, 'abr', default=None))
|
||||
formats.append(f)
|
||||
elif t == 'param':
|
||||
if n in ['image_full', 'image']:
|
||||
thumb = v
|
||||
elif n == 'videoDuration':
|
||||
duration = int_or_none(v)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': self._html_search_meta(
|
||||
['twitter:description', 'og:description', 'description'], webpage),
|
||||
'thumbnail': thumb or self._og_search_thumbnail(webpage),
|
||||
'formats': formats,
|
||||
'duration': duration,
|
||||
}
|
||||
@ -1,191 +0,0 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class LiveLeakIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?.*?\b[it]=(?P<id>[\w_]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.liveleak.com/view?i=757_1364311680',
|
||||
'md5': '0813c2430bea7a46bf13acf3406992f4',
|
||||
'info_dict': {
|
||||
'id': '757_1364311680',
|
||||
'ext': 'mp4',
|
||||
'description': 'extremely bad day for this guy..!',
|
||||
'uploader': 'ljfriel2',
|
||||
'title': 'Most unlucky car accident',
|
||||
'thumbnail': r're:^https?://.*\.jpg$'
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.liveleak.com/view?i=f93_1390833151',
|
||||
'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
|
||||
'info_dict': {
|
||||
'id': 'f93_1390833151',
|
||||
'ext': 'mp4',
|
||||
'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
|
||||
'uploader': 'ARD_Stinkt',
|
||||
'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
|
||||
'thumbnail': r're:^https?://.*\.jpg$'
|
||||
}
|
||||
}, {
|
||||
# Prochan embed
|
||||
'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
|
||||
'md5': '42c6d97d54f1db107958760788c5f48f',
|
||||
'info_dict': {
|
||||
'id': '4f7_1392687779',
|
||||
'ext': 'mp4',
|
||||
'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing... I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
|
||||
'uploader': 'CapObveus',
|
||||
'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
|
||||
'age_limit': 18,
|
||||
},
|
||||
'skip': 'Video is dead',
|
||||
}, {
|
||||
# Covers https://github.com/ytdl-org/youtube-dl/pull/5983
|
||||
# Multiple resolutions
|
||||
'url': 'http://www.liveleak.com/view?i=801_1409392012',
|
||||
'md5': 'c3a449dbaca5c0d1825caecd52a57d7b',
|
||||
'info_dict': {
|
||||
'id': '801_1409392012',
|
||||
'ext': 'mp4',
|
||||
'description': 'Happened on 27.7.2014. \r\nAt 0:53 you can see people still swimming at near beach.',
|
||||
'uploader': 'bony333',
|
||||
'title': 'Crazy Hungarian tourist films close call waterspout in Croatia',
|
||||
'thumbnail': r're:^https?://.*\.jpg$'
|
||||
}
|
||||
}, {
|
||||
# Covers https://github.com/ytdl-org/youtube-dl/pull/10664#issuecomment-247439521
|
||||
'url': 'http://m.liveleak.com/view?i=763_1473349649',
|
||||
'add_ie': ['Youtube'],
|
||||
'info_dict': {
|
||||
'id': '763_1473349649',
|
||||
'ext': 'mp4',
|
||||
'title': 'Reporters and public officials ignore epidemic of black on asian violence in Sacramento | Colin Flaherty',
|
||||
'description': 'Colin being the warrior he is and showing the injustice Asians in Sacramento are being subjected to.',
|
||||
'uploader': 'Ziz',
|
||||
'upload_date': '20160908',
|
||||
'uploader_id': 'UCEbta5E_jqlZmEJsriTEtnw'
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.liveleak.com/view?i=677_1439397581',
|
||||
'info_dict': {
|
||||
'id': '677_1439397581',
|
||||
'title': 'Fuel Depot in China Explosion caught on video',
|
||||
},
|
||||
'playlist_count': 3,
|
||||
}, {
|
||||
'url': 'https://www.liveleak.com/view?t=HvHi_1523016227',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# No original video
|
||||
'url': 'https://www.liveleak.com/view?t=C26ZZ_1558612804',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+src="(https?://(?:\w+\.)?liveleak\.com/ll_embed\?[^"]*[ift]=[\w_]+[^"]+)"',
|
||||
webpage)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
|
||||
video_description = self._og_search_description(webpage)
|
||||
video_uploader = self._html_search_regex(
|
||||
r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
|
||||
age_limit = int_or_none(self._search_regex(
|
||||
r'you confirm that you are ([0-9]+) years and over.',
|
||||
webpage, 'age limit', default=None))
|
||||
video_thumbnail = self._og_search_thumbnail(webpage)
|
||||
|
||||
entries = self._parse_html5_media_entries(url, webpage, video_id)
|
||||
if not entries:
|
||||
# Maybe an embed?
|
||||
embed_url = self._search_regex(
|
||||
r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
|
||||
webpage, 'embed URL')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': embed_url,
|
||||
'id': video_id,
|
||||
'title': video_title,
|
||||
'description': video_description,
|
||||
'uploader': video_uploader,
|
||||
'age_limit': age_limit,
|
||||
}
|
||||
|
||||
for idx, info_dict in enumerate(entries):
|
||||
formats = []
|
||||
for a_format in info_dict['formats']:
|
||||
if not a_format.get('height'):
|
||||
a_format['height'] = int_or_none(self._search_regex(
|
||||
r'([0-9]+)p\.mp4', a_format['url'], 'height label',
|
||||
default=None))
|
||||
formats.append(a_format)
|
||||
|
||||
# Removing '.*.mp4' gives the raw video, which is essentially
|
||||
# the same video without the LiveLeak logo at the top (see
|
||||
# https://github.com/ytdl-org/youtube-dl/pull/4768)
|
||||
orig_url = re.sub(r'\.mp4\.[^.]+', '', a_format['url'])
|
||||
if a_format['url'] != orig_url:
|
||||
format_id = a_format.get('format_id')
|
||||
format_id = 'original' + ('-' + format_id if format_id else '')
|
||||
if self._is_valid_url(orig_url, video_id, format_id):
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': orig_url,
|
||||
'preference': 1,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
info_dict['formats'] = formats
|
||||
|
||||
# Don't append entry ID for one-video pages to keep backward compatibility
|
||||
if len(entries) > 1:
|
||||
info_dict['id'] = '%s_%s' % (video_id, idx + 1)
|
||||
else:
|
||||
info_dict['id'] = video_id
|
||||
|
||||
info_dict.update({
|
||||
'title': video_title,
|
||||
'description': video_description,
|
||||
'uploader': video_uploader,
|
||||
'age_limit': age_limit,
|
||||
'thumbnail': video_thumbnail,
|
||||
})
|
||||
|
||||
return self.playlist_result(entries, video_id, video_title)
|
||||
|
||||
|
||||
class LiveLeakEmbedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?liveleak\.com/ll_embed\?.*?\b(?P<kind>[ift])=(?P<id>[\w_]+)'
|
||||
|
||||
# See generic.py for actual test cases
|
||||
_TESTS = [{
|
||||
'url': 'https://www.liveleak.com/ll_embed?i=874_1459135191',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.liveleak.com/ll_embed?f=ab065df993c1',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
kind, video_id = re.match(self._VALID_URL, url).groups()
|
||||
|
||||
if kind == 'f':
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
liveleak_url = self._search_regex(
|
||||
r'(?:logourl\s*:\s*|window\.open\()(?P<q1>[\'"])(?P<url>%s)(?P=q1)' % LiveLeakIE._VALID_URL,
|
||||
webpage, 'LiveLeak URL', group='url')
|
||||
else:
|
||||
liveleak_url = 'http://www.liveleak.com/view?%s=%s' % (kind, video_id)
|
||||
|
||||
return self.url_result(liveleak_url, ie=LiveLeakIE.ie_key())
|
||||
@ -0,0 +1,31 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class MaoriTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?maoritelevision\.com/shows/(?:[^/]+/)+(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.maoritelevision.com/shows/korero-mai/S01E054/korero-mai-series-1-episode-54',
|
||||
'md5': '5ade8ef53851b6a132c051b1cd858899',
|
||||
'info_dict': {
|
||||
'id': '4774724855001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Kōrero Mai, Series 1 Episode 54',
|
||||
'upload_date': '20160226',
|
||||
'timestamp': 1456455018,
|
||||
'description': 'md5:59bde32fd066d637a1a55794c56d8dcb',
|
||||
'uploader_id': '1614493167001',
|
||||
},
|
||||
}
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1614493167001/HJlhIQhQf_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
brightcove_id = self._search_regex(
|
||||
r'data-main-video-id=["\'](\d+)', webpage, 'brightcove id')
|
||||
return self.url_result(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
|
||||
'BrightcoveNew', brightcove_id)
|
||||
@ -1,71 +1,113 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
parse_duration,
|
||||
int_or_none,
|
||||
try_get,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
import re
|
||||
|
||||
|
||||
class NuvidIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www|m)\.nuvid\.com/video/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'http://m.nuvid.com/video/1310741/',
|
||||
'md5': 'eab207b7ac4fccfb4e23c86201f11277',
|
||||
_TESTS = [{
|
||||
'url': 'https://www.nuvid.com/video/6513023/italian-babe',
|
||||
'md5': '772d2f8288f3d3c5c45f7a41761c7844',
|
||||
'info_dict': {
|
||||
'id': '6513023',
|
||||
'ext': 'mp4',
|
||||
'title': 'italian babe',
|
||||
'format_id': '360p',
|
||||
'duration': 321.0,
|
||||
'age_limit': 18,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'thumbnails': list,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://m.nuvid.com/video/6523263',
|
||||
'md5': 'ebd22ce8e47e1d9a4d0756a15c67da52',
|
||||
'info_dict': {
|
||||
'id': '1310741',
|
||||
'id': '6523263',
|
||||
'ext': 'mp4',
|
||||
'title': 'Horny babes show their awesome bodeis and',
|
||||
'duration': 129,
|
||||
'title': 'Slut brunette college student anal dorm',
|
||||
'format_id': '720p',
|
||||
'duration': 421.0,
|
||||
'age_limit': 18,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'thumbnails': list,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'http://m.nuvid.com/video/6415801/',
|
||||
'md5': '638d5ececb138d5753593f751ae3f697',
|
||||
'info_dict': {
|
||||
'id': '6415801',
|
||||
'ext': 'mp4',
|
||||
'title': 'My best friend wanted to fuck my wife for a long time',
|
||||
'format_id': '720p',
|
||||
'duration': 1882,
|
||||
'age_limit': 18,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'thumbnails': list,
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
page_url = 'http://m.nuvid.com/video/%s' % video_id
|
||||
qualities = {
|
||||
'lq': '360p',
|
||||
'hq': '720p',
|
||||
}
|
||||
|
||||
json_url = 'https://www.nuvid.com/player_config_json/?vid={video_id}&aid=0&domain_id=0&embed=0&check_speed=0'.format(**locals())
|
||||
video_data = self._download_json(
|
||||
json_url, video_id, headers={
|
||||
'Accept': 'application/json, text/javascript, */*; q = 0.01',
|
||||
'Content-Type': 'application/x-www-form-urlencoded; charset=utf-8',
|
||||
}) or {}
|
||||
|
||||
# nice to have, not required
|
||||
webpage = self._download_webpage(
|
||||
page_url, video_id, 'Downloading video page')
|
||||
# When dwnld_speed exists and has a value larger than the MP4 file's
|
||||
# bitrate, Nuvid returns the MP4 URL
|
||||
# It's unit is 100bytes/millisecond, see mobile-nuvid-min.js for the algorithm
|
||||
self._set_cookie('nuvid.com', 'dwnld_speed', '10.0')
|
||||
mp4_webpage = self._download_webpage(
|
||||
page_url, video_id, 'Downloading video page for MP4 format')
|
||||
'http://m.nuvid.com/video/%s' % (video_id, ),
|
||||
video_id, 'Downloading video page', fatal=False) or ''
|
||||
|
||||
title = (
|
||||
try_get(video_data, lambda x: x['title'], compat_str)
|
||||
or self._html_search_regex(
|
||||
(r'''<span\s[^>]*?\btitle\s*=\s*(?P<q>"|'|\b)(?P<title>[^"]+)(?P=q)\s*>''',
|
||||
r'''<div\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)thumb-holder video(?P=q)>\s*<h5\b[^>]*>(?P<title>[^<]+)</h5''',
|
||||
r'''<span\s[^>]*?\bclass\s*=\s*(?P<q>"|'|\b)title_thumb(?P=q)>(?P<title>[^<]+)</span'''),
|
||||
webpage, 'title', group='title')).strip()
|
||||
|
||||
html5_video_re = r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']',
|
||||
video_url = self._html_search_regex(html5_video_re, webpage, video_id)
|
||||
mp4_video_url = self._html_search_regex(html5_video_re, mp4_webpage, video_id)
|
||||
formats = [{
|
||||
'url': video_url,
|
||||
}]
|
||||
if mp4_video_url != video_url:
|
||||
formats.append({
|
||||
'url': mp4_video_url,
|
||||
})
|
||||
'url': source,
|
||||
'format_id': qualities.get(quality),
|
||||
'height': int_or_none(qualities.get(quality)[:-1]),
|
||||
} for quality, source in video_data.get('files').items() if source]
|
||||
|
||||
self._check_formats(formats, video_id)
|
||||
self._sort_formats(formats)
|
||||
|
||||
title = self._html_search_regex(
|
||||
[r'<span title="([^"]+)">',
|
||||
r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>',
|
||||
r'<span[^>]+class="title_thumb">([^<]+)</span>'], webpage, 'title').strip()
|
||||
duration = parse_duration(video_data.get('duration') or video_data.get('duration_format'))
|
||||
thumbnails = [
|
||||
{
|
||||
'url': thumb_url,
|
||||
} for thumb_url in re.findall(r'<img src="([^"]+)" alt="" />', webpage)
|
||||
{'url': thumb_url, }
|
||||
for thumb_url in (
|
||||
url_or_none(src) for src in re.findall(
|
||||
r'<div\s+class\s*=\s*"video-tmb-wrap"\s*>\s*<img\s+src\s*=\s*"([^"]+)"\s*/>',
|
||||
webpage))
|
||||
]
|
||||
thumbnail = thumbnails[0]['url'] if thumbnails else None
|
||||
duration = parse_duration(self._html_search_regex(
|
||||
[r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})',
|
||||
r'<span[^>]+class="view_time">([^<]+)</span>'], webpage, 'duration', fatal=False))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'thumbnail': url_or_none(video_data.get('poster')),
|
||||
'thumbnails': thumbnails,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'age_limit': 18,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -0,0 +1,148 @@
|
||||
# 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,
|
||||
str_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class PalcoMP3BaseIE(InfoExtractor):
|
||||
_GQL_QUERY_TMPL = '''{
|
||||
artist(slug: "%s") {
|
||||
%s
|
||||
}
|
||||
}'''
|
||||
_ARTIST_FIELDS_TMPL = '''music(slug: "%%s") {
|
||||
%s
|
||||
}'''
|
||||
_MUSIC_FIELDS = '''duration
|
||||
hls
|
||||
mp3File
|
||||
musicID
|
||||
plays
|
||||
title'''
|
||||
|
||||
def _call_api(self, artist_slug, artist_fields):
|
||||
return self._download_json(
|
||||
'https://www.palcomp3.com.br/graphql/', artist_slug, query={
|
||||
'query': self._GQL_QUERY_TMPL % (artist_slug, artist_fields),
|
||||
})['data']
|
||||
|
||||
def _parse_music(self, music):
|
||||
music_id = compat_str(music['musicID'])
|
||||
title = music['title']
|
||||
|
||||
formats = []
|
||||
hls_url = music.get('hls')
|
||||
if hls_url:
|
||||
formats.append({
|
||||
'url': hls_url,
|
||||
'protocol': 'm3u8_native',
|
||||
'ext': 'mp4',
|
||||
})
|
||||
mp3_file = music.get('mp3File')
|
||||
if mp3_file:
|
||||
formats.append({
|
||||
'url': mp3_file,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': music_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'duration': int_or_none(music.get('duration')),
|
||||
'view_count': int_or_none(music.get('plays')),
|
||||
}
|
||||
|
||||
def _real_initialize(self):
|
||||
self._ARTIST_FIELDS_TMPL = self._ARTIST_FIELDS_TMPL % self._MUSIC_FIELDS
|
||||
|
||||
def _real_extract(self, url):
|
||||
artist_slug, music_slug = re.match(self._VALID_URL, url).groups()
|
||||
artist_fields = self._ARTIST_FIELDS_TMPL % music_slug
|
||||
music = self._call_api(artist_slug, artist_fields)['artist']['music']
|
||||
return self._parse_music(music)
|
||||
|
||||
|
||||
class PalcoMP3IE(PalcoMP3BaseIE):
|
||||
IE_NAME = 'PalcoMP3:song'
|
||||
_VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/nossas-composicoes-cuida-bem-dela/',
|
||||
'md5': '99fd6405b2d8fd589670f6db1ba3b358',
|
||||
'info_dict': {
|
||||
'id': '3162927',
|
||||
'ext': 'mp3',
|
||||
'title': 'Nossas Composições - CUIDA BEM DELA',
|
||||
'duration': 210,
|
||||
'view_count': int,
|
||||
}
|
||||
}]
|
||||
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
return False if PalcoMP3VideoIE.suitable(url) else super(PalcoMP3IE, cls).suitable(url)
|
||||
|
||||
|
||||
class PalcoMP3ArtistIE(PalcoMP3BaseIE):
|
||||
IE_NAME = 'PalcoMP3:artist'
|
||||
_VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<id>[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.palcomp3.com.br/condedoforro/',
|
||||
'info_dict': {
|
||||
'id': '358396',
|
||||
'title': 'Conde do Forró',
|
||||
},
|
||||
'playlist_mincount': 188,
|
||||
}]
|
||||
_ARTIST_FIELDS_TMPL = '''artistID
|
||||
musics {
|
||||
nodes {
|
||||
%s
|
||||
}
|
||||
}
|
||||
name'''
|
||||
|
||||
@ classmethod
|
||||
def suitable(cls, url):
|
||||
return False if re.match(PalcoMP3IE._VALID_URL, url) else super(PalcoMP3ArtistIE, cls).suitable(url)
|
||||
|
||||
def _real_extract(self, url):
|
||||
artist_slug = self._match_id(url)
|
||||
artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist']
|
||||
|
||||
def entries():
|
||||
for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []):
|
||||
yield self._parse_music(music)
|
||||
|
||||
return self.playlist_result(
|
||||
entries(), str_or_none(artist.get('artistID')), artist.get('name'))
|
||||
|
||||
|
||||
class PalcoMP3VideoIE(PalcoMP3BaseIE):
|
||||
IE_NAME = 'PalcoMP3:video'
|
||||
_VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)/?#clipe'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/maiara-e-maraisa-voce-faz-falta-aqui-ao-vivo-em-vicosa-mg/#clipe',
|
||||
'add_ie': ['Youtube'],
|
||||
'info_dict': {
|
||||
'id': '_pD1nR2qqPg',
|
||||
'ext': 'mp4',
|
||||
'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande',
|
||||
'description': 'md5:7043342c09a224598e93546e98e49282',
|
||||
'upload_date': '20161107',
|
||||
'uploader_id': 'maiaramaraisaoficial',
|
||||
'uploader': 'Maiara e Maraisa',
|
||||
}
|
||||
}]
|
||||
_MUSIC_FIELDS = 'youtubeID'
|
||||
|
||||
def _parse_music(self, music):
|
||||
youtube_id = music['youtubeID']
|
||||
return self.url_result(youtube_id, 'Youtube', youtube_id)
|
||||
@ -1,45 +1,133 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .dreisat import DreiSatIE
|
||||
import re
|
||||
|
||||
from .youtube import YoutubeIE
|
||||
from .zdf import ZDFBaseIE
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
class PhoenixIE(DreiSatIE):
|
||||
|
||||
class PhoenixIE(ZDFBaseIE):
|
||||
IE_NAME = 'phoenix.de'
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?phoenix\.de/content/
|
||||
(?:
|
||||
phoenix/die_sendungen/(?:[^/]+/)?
|
||||
)?
|
||||
(?P<id>[0-9]+)'''
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.phoenix.de/content/884301',
|
||||
'md5': 'ed249f045256150c92e72dbb70eadec6',
|
||||
'info_dict': {
|
||||
'id': '884301',
|
||||
'ext': 'mp4',
|
||||
'title': 'Michael Krons mit Hans-Werner Sinn',
|
||||
'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
|
||||
'upload_date': '20141025',
|
||||
'uploader': 'Im Dialog',
|
||||
}
|
||||
_VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
|
||||
_TESTS = [{
|
||||
# Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
|
||||
'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
|
||||
'md5': '34ec321e7eb34231fd88616c65c92db0',
|
||||
'info_dict': {
|
||||
'id': '210222_phx_nachgehakt_corona_protest',
|
||||
'ext': 'mp4',
|
||||
'title': 'Wohin führt der Protest in der Pandemie?',
|
||||
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
|
||||
'duration': 1691,
|
||||
'timestamp': 1613902500,
|
||||
'upload_date': '20210221',
|
||||
'uploader': 'Phoenix',
|
||||
'series': 'corona nachgehakt',
|
||||
'episode': 'Wohin führt der Protest in der Pandemie?',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/869815',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Youtube embed
|
||||
'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
|
||||
'info_dict': {
|
||||
'id': 'hMQtqFYjomk',
|
||||
'ext': 'mp4',
|
||||
'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
|
||||
'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
|
||||
'duration': 3509,
|
||||
'upload_date': '20201219',
|
||||
'uploader': 'phoenix',
|
||||
'uploader_id': 'phoenix',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/diskussionen/928234',
|
||||
'only_matching': True,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
]
|
||||
}, {
|
||||
'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# no media
|
||||
'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
|
||||
'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
article_id = self._match_id(url)
|
||||
|
||||
article = self._download_json(
|
||||
'https://www.phoenix.de/response/id/%s' % article_id, article_id,
|
||||
'Downloading article JSON')
|
||||
|
||||
video = article['absaetze'][0]
|
||||
title = video.get('titel') or article.get('subtitel')
|
||||
|
||||
if video.get('typ') == 'video-youtube':
|
||||
video_id = video['id']
|
||||
return self.url_result(
|
||||
video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
|
||||
video_title=title)
|
||||
|
||||
video_id = compat_str(video.get('basename') or video.get('content'))
|
||||
|
||||
internal_id = self._search_regex(
|
||||
r'<div class="phx_vod" id="phx_vod_([0-9]+)"',
|
||||
webpage, 'internal video ID')
|
||||
details = self._download_json(
|
||||
'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
|
||||
video_id, 'Downloading details JSON', query={
|
||||
'ak': 'web',
|
||||
'ptmd': 'true',
|
||||
'id': video_id,
|
||||
'profile': 'player2',
|
||||
})
|
||||
|
||||
title = title or details['title']
|
||||
content_id = details['tracking']['nielsen']['content']['assetid']
|
||||
|
||||
info = self._extract_ptmd(
|
||||
'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
|
||||
content_id, None, url)
|
||||
|
||||
duration = int_or_none(try_get(
|
||||
details, lambda x: x['tracking']['nielsen']['content']['length']))
|
||||
timestamp = unified_timestamp(details.get('editorialDate'))
|
||||
series = try_get(
|
||||
details, lambda x: x['tracking']['nielsen']['content']['program'],
|
||||
compat_str)
|
||||
episode = title if details.get('contentType') == 'episode' else None
|
||||
|
||||
thumbnails = []
|
||||
teaser_images = try_get(details, lambda x: x['teaserImageRef']['layouts'], dict) or {}
|
||||
for thumbnail_key, thumbnail_url in teaser_images.items():
|
||||
thumbnail_url = urljoin(url, thumbnail_url)
|
||||
if not thumbnail_url:
|
||||
continue
|
||||
thumbnail = {
|
||||
'url': thumbnail_url,
|
||||
}
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
thumbnails.append(thumbnail)
|
||||
|
||||
api_url = 'http://www.phoenix.de/php/mediaplayer/data/beitrags_details.php?ak=web&id=%s' % internal_id
|
||||
return self.extract_from_xml_url(video_id, api_url)
|
||||
return merge_dicts(info, {
|
||||
'id': content_id,
|
||||
'title': title,
|
||||
'description': details.get('leadParagraph'),
|
||||
'duration': duration,
|
||||
'thumbnails': thumbnails,
|
||||
'timestamp': timestamp,
|
||||
'uploader': details.get('tvService'),
|
||||
'series': series,
|
||||
'episode': episode,
|
||||
})
|
||||
|
||||
@ -0,0 +1,65 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
smuggle_url,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class PlayStuffIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?play\.stuff\.co\.nz/details/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://play.stuff.co.nz/details/608778ac1de1c4001a3fa09a',
|
||||
'md5': 'c82d3669e5247c64bc382577843e5bd0',
|
||||
'info_dict': {
|
||||
'id': '6250584958001',
|
||||
'ext': 'mp4',
|
||||
'title': 'Episode 1: Rotorua/Mt Maunganui/Tauranga',
|
||||
'description': 'md5:c154bafb9f0dd02d01fd4100fb1c1913',
|
||||
'uploader_id': '6005208634001',
|
||||
'timestamp': 1619491027,
|
||||
'upload_date': '20210427',
|
||||
},
|
||||
'add_ie': ['BrightcoveNew'],
|
||||
}, {
|
||||
# geo restricted, bypassable
|
||||
'url': 'https://play.stuff.co.nz/details/_6155660351001',
|
||||
'only_matching': True,
|
||||
}]
|
||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
state = self._parse_json(
|
||||
self._search_regex(
|
||||
r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'state'),
|
||||
video_id)
|
||||
|
||||
account_id = try_get(
|
||||
state, lambda x: x['configurations']['accountId'],
|
||||
compat_str) or '6005208634001'
|
||||
player_id = try_get(
|
||||
state, lambda x: x['configurations']['playerId'],
|
||||
compat_str) or 'default'
|
||||
|
||||
entries = []
|
||||
for item_id, video in state['items'].items():
|
||||
if not isinstance(video, dict):
|
||||
continue
|
||||
asset_id = try_get(
|
||||
video, lambda x: x['content']['attributes']['assetId'],
|
||||
compat_str)
|
||||
if not asset_id:
|
||||
continue
|
||||
entries.append(self.url_result(
|
||||
smuggle_url(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, asset_id),
|
||||
{'geo_countries': ['NZ']}),
|
||||
'BrightcoveNew', video_id))
|
||||
|
||||
return self.playlist_result(entries, video_id)
|
||||
@ -0,0 +1,100 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
get_element_by_attribute,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class SampleFocusIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P<id>[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar',
|
||||
'md5': '48c8d62d60be467293912e0e619a5120',
|
||||
'info_dict': {
|
||||
'id': '40316',
|
||||
'display_id': 'lil-peep-sad-emo-guitar',
|
||||
'ext': 'mp3',
|
||||
'title': 'Lil Peep Sad Emo Guitar',
|
||||
'thumbnail': r're:^https?://.+\.png',
|
||||
'license': 'Standard License',
|
||||
'uploader': 'CapsCtrl',
|
||||
'uploader_id': 'capsctrl',
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
'categories': ['Samples', 'Guitar', 'Electric guitar'],
|
||||
},
|
||||
}, {
|
||||
'url': 'https://samplefocus.com/samples/dababy-style-bass-808',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'https://samplefocus.com/samples/young-chop-kick',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
sample_id = self._search_regex(
|
||||
r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
|
||||
webpage, 'sample id', group='id')
|
||||
|
||||
title = self._og_search_title(webpage, fatal=False) or self._html_search_regex(
|
||||
r'<h1>(.+?)</h1>', webpage, 'title')
|
||||
|
||||
mp3_url = self._search_regex(
|
||||
r'<input[^>]+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P<url>(?:(?!\2).)+)',
|
||||
webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex(
|
||||
r'<meta[^>]+itemprop=(["\'])contentUrl\1[^>]*>',
|
||||
webpage, 'mp3 url', group=0))['content']
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex(
|
||||
r'<img[^>]+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P<url>(?:(?!\1).)+)',
|
||||
webpage, 'mp3', fatal=False, group='url')
|
||||
|
||||
comments = []
|
||||
for author_id, author, body in re.findall(r'(?s)<p[^>]+class="comment-author"><a[^>]+href="/users/([^"]+)">([^"]+)</a>.+?<p[^>]+class="comment-body">([^>]+)</p>', webpage):
|
||||
comments.append({
|
||||
'author': author,
|
||||
'author_id': author_id,
|
||||
'text': body,
|
||||
})
|
||||
|
||||
uploader_id = uploader = None
|
||||
mobj = re.search(r'>By <a[^>]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage)
|
||||
if mobj:
|
||||
uploader_id, uploader = mobj.groups()
|
||||
|
||||
breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage)
|
||||
categories = []
|
||||
if breadcrumb:
|
||||
for _, name in re.findall(r'<span[^>]+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb):
|
||||
categories.append(name)
|
||||
|
||||
def extract_count(klass):
|
||||
return int_or_none(self._html_search_regex(
|
||||
r'<span[^>]+class=(?:["\'])?%s-count[^>]*>(\d+)' % klass,
|
||||
webpage, klass, fatal=False))
|
||||
|
||||
return {
|
||||
'id': sample_id,
|
||||
'title': title,
|
||||
'url': mp3_url,
|
||||
'display_id': display_id,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
'license': self._html_search_regex(
|
||||
r'<a[^>]+href=(["\'])/license\1[^>]*>(?P<license>[^<]+)<',
|
||||
webpage, 'license', fatal=False, group='license'),
|
||||
'uploader_id': uploader_id,
|
||||
'like_count': extract_count('sample-%s-favorites' % sample_id),
|
||||
'comment_count': extract_count('comments'),
|
||||
'comments': comments,
|
||||
'categories': categories,
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue