etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-04 23:35:04 +00:00
Code Issues Projects Releases Wiki Activity
yt-dlp/youtube_dl/extractor/nbc.py
Remita Amine 90b633f86b [nbc] improve info extraction(fixes #16440)
2018-05-13 11:31:41 +01:00

456 lines
18 KiB
Python
Raw Blame History

from __future__ import unicode_literals
import re
import base64
from .common import InfoExtractor
from .theplatform import ThePlatformIE
from .adobepass import AdobePassIE
from ..utils import (
find_xpath_attr,
smuggle_url,
try_get,
unescapeHTML,
update_url_query,
int_or_none,
)
class NBCIE(AdobePassIE):
_VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
_TESTS = [
{
'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
'info_dict': {
'id': '2848237',
'ext': 'mp4',
'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
'timestamp': 1424246400,
'upload_date': '20150218',
'uploader': 'NBCU-COM',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
'info_dict': {
'id': '2832821',
'ext': 'mp4',
'title': 'Star Wars Teaser',
'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
'timestamp': 1417852800,
'upload_date': '20141206',
'uploader': 'NBCU-COM',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Only works from US',
},
{
# HLS streams requires the 'hdnea3' cookie
'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
'info_dict': {
'id': '101528f5a9e8127b107e98c5e6ce4638',
'ext': 'mp4',
'title': 'Goliath',
'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
'timestamp': 1237100400,
'upload_date': '20090315',
'uploader': 'NBCU-COM',
},
'params': {
'skip_download': True,
},
'skip': 'Only works from US',
},
{
'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
'only_matching': True,
},
]
def _real_extract(self, url):
permalink, video_id = re.match(self._VALID_URL, url).groups()
permalink = 'http' + permalink
response = self._download_json(
'https://api.nbc.com/v3/videos', video_id, query={
'filter[permalink]': permalink,
'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating',
'fields[shows]': 'shortTitle',
'include': 'show.shortTitle',
})
video_data = response['data'][0]['attributes']
query = {
'mbr': 'true',
'manifest': 'm3u',
}
video_id = video_data['guid']
title = video_data['title']
if video_data.get('entitlement') == 'auth':
resource = self._get_mvpd_resource(
'nbcentertainment', title, video_id,
video_data.get('vChipRating'))
query['auth'] = self._extract_mvpd_auth(
url, video_id, 'nbcentertainment', resource)
theplatform_url = smuggle_url(update_url_query(
'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
query), {'force_smil_url': True})
return {
'_type': 'url_transparent',
'id': video_id,
'title': title,
'url': theplatform_url,
'description': video_data.get('description'),
'tags': video_data.get('keywords'),
'season_number': int_or_none(video_data.get('seasonNumber')),
'episode_number': int_or_none(video_data.get('episodeNumber')),
'episode': title,
'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']),
'ie_key': 'ThePlatform',
}
class NBCSportsVPlayerIE(InfoExtractor):
_VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
_TESTS = [{
'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/9CsDKds0kvHI',
'info_dict': {
'id': '9CsDKds0kvHI',
'ext': 'mp4',
'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
'timestamp': 1426270238,
'upload_date': '20150313',
'uploader': 'NBCU-SPORTS',
}
}, {
'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/_hqLjQ95yx8Z',
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
iframe_m = re.search(
r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
if iframe_m:
return iframe_m.group('url')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
theplatform_url = self._og_search_video_url(webpage).replace(
'vplayer.nbcsports.com', 'player.theplatform.com')
return self.url_result(theplatform_url, 'ThePlatform')
class NBCSportsIE(InfoExtractor):
# Does not include https because its certificate is invalid
_VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
_TEST = {
'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
'info_dict': {
'id': 'PHJSaFWbrTY9',
'ext': 'flv',
'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
'uploader': 'NBCU-SPORTS',
'upload_date': '20150330',
'timestamp': 1427726529,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
return self.url_result(
NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
class CSNNEIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?csnne\.com/video/(?P<id>[0-9a-z-]+)'
_TEST = {
'url': 'http://www.csnne.com/video/snc-evening-update-wright-named-red-sox-no-5-starter',
'info_dict': {
'id': 'yvBLLUgQ8WU0',
'ext': 'mp4',
'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
'timestamp': 1459369979,
'upload_date': '20160330',
'uploader': 'NBCU-SPORTS',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': self._html_search_meta('twitter:player:stream', webpage),
'display_id': display_id,
}
class NBCNewsIE(ThePlatformIE):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:nbcnews|today|msnbc)\.com/
(?:video/.+?/(?P<id>\d+)|
([^/]+/)*(?:.*-)?(?P<mpx_id>[^/?]+))
'''
_TESTS = [
{
'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
'info_dict': {
'id': '52753292',
'ext': 'flv',
'title': 'Crew emerges after four-month Mars food study',
'description': 'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
},
},
{
'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
'md5': 'af1adfa51312291a017720403826bb64',
'info_dict': {
'id': 'p_tweet_snow_140529',
'ext': 'mp4',
'title': 'How Twitter Reacted To The Snowden Interview',
'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
'uploader': 'NBCU-NEWS',
'timestamp': 1401363060,
'upload_date': '20140529',
},
},
{
'url': 'http://www.nbcnews.com/feature/dateline-full-episodes/full-episode-family-business-n285156',
'md5': 'fdbf39ab73a72df5896b6234ff98518a',
'info_dict': {
'id': '529953347624',
'ext': 'mp4',
'title': 'FULL EPISODE: Family Business',
'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
},
'skip': 'This page is unavailable.',
},
{
'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
'md5': '73135a2e0ef819107bbb55a5a9b2a802',
'info_dict': {
'id': 'nn_netcast_150204',
'ext': 'mp4',
'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
'timestamp': 1423104900,
'uploader': 'NBCU-NEWS',
'upload_date': '20150205',
},
},
{
'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
'md5': 'a49e173825e5fcd15c13fc297fced39d',
'info_dict': {
'id': 'x_lon_vwhorn_150922',
'ext': 'mp4',
'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
'description': 'md5:c8be487b2d80ff0594c005add88d8351',
'upload_date': '20150922',
'timestamp': 1442917800,
'uploader': 'NBCU-NEWS',
},
},
{
'url': 'http://www.today.com/video/see-the-aurora-borealis-from-space-in-stunning-new-nasa-video-669831235788',
'md5': '118d7ca3f0bea6534f119c68ef539f71',
'info_dict': {
'id': 'tdy_al_space_160420',
'ext': 'mp4',
'title': 'See the aurora borealis from space in stunning new NASA video',
'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
'upload_date': '20160420',
'timestamp': 1461152093,
'uploader': 'NBCU-NEWS',
},
},
{
'url': 'http://www.msnbc.com/all-in-with-chris-hayes/watch/the-chaotic-gop-immigration-vote-314487875924',
'md5': '6d236bf4f3dddc226633ce6e2c3f814d',
'info_dict': {
'id': 'n_hayes_Aimm_140801_272214',
'ext': 'mp4',
'title': 'The chaotic GOP immigration vote',
'description': 'The Republican House votes on a border bill that has no chance of getting through the Senate or signed by the President and is drawing criticism from all sides.',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1406937606,
'upload_date': '20140802',
'uploader': 'NBCU-NEWS',
},
},
{
'url': 'http://www.nbcnews.com/watch/dateline/full-episode--deadly-betrayal-386250819952',
'only_matching': True,
},
{
# From http://www.vulture.com/2016/06/letterman-couldnt-care-less-about-late-night.html
'url': 'http://www.nbcnews.com/widget/video-embed/701714499682',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if video_id is not None:
all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
info = all_info.find('video')
return {
'id': video_id,
'title': info.find('headline').text,
'ext': 'flv',
'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
'description': info.find('caption').text,
'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
}
else:
# "feature" and "nightly-news" pages use theplatform.com
video_id = mobj.group('mpx_id')
webpage = self._download_webpage(url, video_id)
filter_param = 'byId'
bootstrap_json = self._search_regex(
[r'(?m)(?:var\s+(?:bootstrapJson|playlistData)|NEWS\.videoObj)\s*=\s*({.+});?\s*$',
r'videoObj\s*:\s*({.+})', r'data-video="([^"]+)"',
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);'],
webpage, 'bootstrap json', default=None)
if bootstrap_json:
bootstrap = self._parse_json(
bootstrap_json, video_id, transform_source=unescapeHTML)
info = None
if 'results' in bootstrap:
info = bootstrap['results'][0]['video']
elif 'video' in bootstrap:
info = bootstrap['video']
elif 'msnbcVideoInfo' in bootstrap:
info = bootstrap['msnbcVideoInfo']['meta']
elif 'msnbcThePlatform' in bootstrap:
info = bootstrap['msnbcThePlatform']['videoPlayer']['video']
else:
info = bootstrap
if 'guid' in info:
video_id = info['guid']
filter_param = 'byGuid'
elif 'mpxId' in info:
video_id = info['mpxId']
return {
'_type': 'url_transparent',
'id': video_id,
# http://feed.theplatform.com/f/2E2eJC/nbcnews also works
'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {filter_param: video_id}),
'ie_key': 'ThePlatformFeed',
}
class NBCOlympicsIE(InfoExtractor):
IE_NAME = 'nbcolympics'
_VALID_URL = r'https?://www\.nbcolympics\.com/video/(?P<id>[a-z-]+)'
_TEST = {
# Geo-restricted to US
'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
'md5': '54fecf846d05429fbaa18af557ee523a',
'info_dict': {
'id': 'WjTBzDXx5AUq',
'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
'ext': 'mp4',
'title': 'Rose\'s son Leo was in tears after his dad won gold',
'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
'timestamp': 1471274964,
'upload_date': '20160815',
'uploader': 'NBCU-SPORTS',
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
drupal_settings = self._parse_json(self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'drupal settings'), display_id)
iframe_url = drupal_settings['vod']['iframe_url']
theplatform_url = iframe_url.replace(
'vplayer.nbcolympics.com', 'player.theplatform.com')
return {
'_type': 'url_transparent',
'url': theplatform_url,
'ie_key': ThePlatformIE.ie_key(),
'display_id': display_id,
}
class NBCOlympicsStreamIE(AdobePassIE):
IE_NAME = 'nbcolympics:stream'
_VALID_URL = r'https?://stream\.nbcolympics\.com/(?P<id>[0-9a-z-]+)'
_TEST = {
'url': 'http://stream.nbcolympics.com/2018-winter-olympics-nbcsn-evening-feb-8',
'info_dict': {
'id': '203493',
'ext': 'mp4',
'title': 're:Curling, Alpine, Luge [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
_DATA_URL_TEMPLATE = 'http://stream.nbcolympics.com/data/%s_%s.json'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
pid = self._search_regex(r'pid\s*=\s*(\d+);', webpage, 'pid')
resource = self._search_regex(
r"resource\s*=\s*'(.+)';", webpage,
'resource').replace("' + pid + '", pid)
event_config = self._download_json(
self._DATA_URL_TEMPLATE % ('event_config', pid),
pid)['eventConfig']
title = self._live_title(event_config['eventTitle'])
source_url = self._download_json(
self._DATA_URL_TEMPLATE % ('live_sources', pid),
pid)['videoSources'][0]['sourceUrl']
media_token = self._extract_mvpd_auth(
url, pid, event_config.get('requestorId', 'NBCOlympics'), resource)
formats = self._extract_m3u8_formats(self._download_webpage(
'http://sp.auth.adobe.com/tvs/v1/sign', pid, query={
'cdn': 'akamai',
'mediaToken': base64.b64encode(media_token.encode()),
'resource': base64.b64encode(resource.encode()),
'url': source_url,
}), pid, 'mp4')
self._sort_formats(formats)
return {
'id': pid,
'display_id': display_id,
'title': title,
'formats': formats,
'is_live': True,
}
Reference in a new issue View git blame Copy permalink