[nhl] remove old extractors

This commit is contained in:
Remita Amine 2018-05-31 02:49:35 +01:00
parent 4fd1437d9d
commit 128b58ad13
2 changed files with 62 additions and 290 deletions

View file

@ -705,12 +705,7 @@ from .nexx import (
from .nfb import NFBIE from .nfb import NFBIE
from .nfl import NFLIE from .nfl import NFLIE
from .nhk import NhkVodIE from .nhk import NhkVodIE
from .nhl import ( from .nhl import NHLIE
NHLVideocenterIE,
NHLNewsIE,
NHLVideocenterCategoryIE,
NHLIE,
)
from .nick import ( from .nick import (
NickIE, NickIE,
NickBrIE, NickBrIE,

View file

@ -1,18 +1,10 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
import os
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import compat_str
compat_urlparse,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_str,
)
from ..utils import ( from ..utils import (
unified_strdate,
determine_ext, determine_ext,
int_or_none, int_or_none,
parse_iso8601, parse_iso8601,
@ -20,236 +12,77 @@ from ..utils import (
) )
class NHLBaseInfoExtractor(InfoExtractor): class NHLBaseIE(InfoExtractor):
@staticmethod def _real_extract(self, url):
def _fix_json(json_string): site, tmp_id = re.match(self._VALID_URL, url).groups()
return json_string.replace('\\\'', '\'') video_data = self._download_json(
'https://%s/%s/%sid/v1/%s/details/web-v1.json'
def _real_extract_video(self, video_id): % (self._CONTENT_DOMAIN, site[:3], 'item/' if site == 'mlb' else '', tmp_id), tmp_id)
vid_parts = video_id.split(',') if video_data.get('type') != 'video':
if len(vid_parts) == 3: video_data = video_data['media']
video_id = '%s0%s%s-X-h' % (vid_parts[0][:4], vid_parts[1], vid_parts[2].rjust(4, '0')) video = video_data.get('video')
json_url = 'http://video.nhl.com/videocenter/servlets/playlist?ids=%s&format=json' % video_id if video:
data = self._download_json( video_data = video
json_url, video_id, transform_source=self._fix_json)
return self._extract_video(data[0])
def _extract_video(self, info):
video_id = info['id']
self.report_extraction(video_id)
initial_video_url = info['publishPoint']
if info['formats'] == '1':
parsed_url = compat_urllib_parse_urlparse(initial_video_url)
filename, ext = os.path.splitext(parsed_url.path)
path = '%s_sd%s' % (filename, ext)
data = compat_urllib_parse_urlencode({
'type': 'fvod',
'path': compat_urlparse.urlunparse(parsed_url[:2] + (path,) + parsed_url[3:])
})
path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data
path_doc = self._download_xml(
path_url, video_id, 'Downloading final video url')
video_url = path_doc.find('path').text
else: else:
video_url = initial_video_url videos = video_data.get('videos')
if videos:
video_data = videos[0]
join = compat_urlparse.urljoin video_id = compat_str(video_data['id'])
ret = { title = video_data['title']
'id': video_id,
'title': info['name'], formats = []
'url': video_url, for playback in video_data.get('playbacks', []):
'description': info['description'], playback_url = playback.get('url')
'duration': int(info['duration']), if not playback_url:
'thumbnail': join(join(video_url, '/u/'), info['bigImage']), continue
'upload_date': unified_strdate(info['releaseDate'].split('.')[0]), ext = determine_ext(playback_url)
} if ext == 'm3u8':
if video_url.startswith('rtmp:'): m3u8_formats = self._extract_m3u8_formats(
mobj = re.match(r'(?P<tc_url>rtmp://[^/]+/(?P<app>[a-z0-9/]+))/(?P<play_path>mp4:.*)', video_url) playback_url, video_id, 'mp4', 'm3u8_native',
ret.update({ m3u8_id=playback.get('name', 'hls'), fatal=False)
'tc_url': mobj.group('tc_url'), self._check_formats(m3u8_formats, video_id)
'play_path': mobj.group('play_path'), formats.extend(m3u8_formats)
'app': mobj.group('app'), else:
'no_resume': True, height = int_or_none(playback.get('height'))
formats.append({
'format_id': playback.get('name', 'http' + ('-%dp' % height if height else '')),
'url': playback_url,
'width': int_or_none(playback.get('width')),
'height': height,
'tbr': int_or_none(self._search_regex(r'_(\d+)[kK]', playback_url, 'bitrate', default=None)),
}) })
return ret self._sort_formats(formats)
thumbnails = []
class NHLVideocenterIE(NHLBaseInfoExtractor): cuts = video_data.get('image', {}).get('cuts') or []
IE_NAME = 'nhl.com:videocenter' if isinstance(cuts, dict):
_VALID_URL = r'https?://video(?P<team>\.[^.]*)?\.nhl\.com/videocenter/(?:console|embed)?(?:\?(?:.*?[?&])?)(?:id|hlg|playlist)=(?P<id>[-0-9a-zA-Z,]+)' cuts = cuts.values()
for thumbnail_data in cuts:
_TESTS = [{ thumbnail_url = thumbnail_data.get('src')
'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', if not thumbnail_url:
'md5': 'db704a4ea09e8d3988c85e36cc892d09', continue
'info_dict': { thumbnails.append({
'id': '453614', 'url': thumbnail_url,
'ext': 'mp4', 'width': int_or_none(thumbnail_data.get('width')),
'title': 'Quick clip: Weise 4-3 goal vs Flames', 'height': int_or_none(thumbnail_data.get('height')),
'description': 'Dale Weise scores his first of the season to put the Canucks up 4-3.',
'duration': 18,
'upload_date': '20131006',
},
}, {
'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h',
'md5': 'd22e82bc592f52d37d24b03531ee9696',
'info_dict': {
'id': '2014020024-628-h',
'ext': 'mp4',
'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)',
'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014',
'duration': 0,
'upload_date': '20141011',
},
}, {
'url': 'http://video.mapleleafs.nhl.com/videocenter/console?id=58665&catid=802',
'md5': 'c78fc64ea01777e426cfc202b746c825',
'info_dict': {
'id': '58665',
'ext': 'flv',
'title': 'Classic Game In Six - April 22, 1979',
'description': 'It was the last playoff game for the Leafs in the decade, and the last time the Leafs and Habs played in the playoffs. Great game, not a great ending.',
'duration': 400,
'upload_date': '20100129'
},
}, {
'url': 'http://video.flames.nhl.com/videocenter/console?id=630616',
'only_matching': True,
}, {
'url': 'http://video.nhl.com/videocenter/?id=736722',
'only_matching': True,
}, {
'url': 'http://video.nhl.com/videocenter/console?hlg=20142015,2,299&lang=en',
'md5': '076fcb88c255154aacbf0a7accc3f340',
'info_dict': {
'id': '2014020299-X-h',
'ext': 'mp4',
'title': 'Penguins at Islanders / Game Highlights',
'description': 'Home broadcast - Pittsburgh Penguins at New York Islanders - November 22, 2014',
'duration': 268,
'upload_date': '20141122',
}
}, {
'url': 'http://video.oilers.nhl.com/videocenter/console?id=691469&catid=4',
'info_dict': {
'id': '691469',
'ext': 'mp4',
'title': 'RAW | Craig MacTavish Full Press Conference',
'description': 'Oilers GM Craig MacTavish addresses the media at Rexall Place on Friday.',
'upload_date': '20141205',
},
'params': {
'skip_download': True, # Requires rtmpdump
}
}, {
'url': 'http://video.nhl.com/videocenter/embed?playlist=836127',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._real_extract_video(video_id)
class NHLNewsIE(NHLBaseInfoExtractor):
IE_NAME = 'nhl.com:news'
IE_DESC = 'NHL news'
_VALID_URL = r'https?://(?:.+?\.)?nhl\.com/(?:ice|club)/news\.html?(?:\?(?:.*?[?&])?)id=(?P<id>[-0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://www.nhl.com/ice/news.htm?id=750727',
'md5': '4b3d1262e177687a3009937bd9ec0be8',
'info_dict': {
'id': '736722',
'ext': 'mp4',
'title': 'Cal Clutterbuck has been fined $2,000',
'description': 'md5:45fe547d30edab88b23e0dd0ab1ed9e6',
'duration': 37,
'upload_date': '20150128',
},
}, {
# iframe embed
'url': 'http://sabres.nhl.com/club/news.htm?id=780189',
'md5': '9f663d1c006c90ac9fb82777d4294e12',
'info_dict': {
'id': '836127',
'ext': 'mp4',
'title': 'Morning Skate: OTT vs. BUF (9/23/15)',
'description': "Brian Duff chats with Tyler Ennis prior to Buffalo's first preseason home game.",
'duration': 93,
'upload_date': '20150923',
},
}]
def _real_extract(self, url):
news_id = self._match_id(url)
webpage = self._download_webpage(url, news_id)
video_id = self._search_regex(
[r'pVid(\d+)', r"nlid\s*:\s*'(\d+)'",
r'<iframe[^>]+src=["\']https?://video.*?\.nhl\.com/videocenter/embed\?.*\bplaylist=(\d+)'],
webpage, 'video id')
return self._real_extract_video(video_id)
class NHLVideocenterCategoryIE(NHLBaseInfoExtractor):
IE_NAME = 'nhl.com:videocenter:category'
IE_DESC = 'NHL videocenter category'
_VALID_URL = r'https?://video\.(?P<team>[^.]*)\.nhl\.com/videocenter/(console\?[^(id=)]*catid=(?P<catid>[0-9]+)(?![&?]id=).*?)?$'
_TEST = {
'url': 'http://video.canucks.nhl.com/videocenter/console?catid=999',
'info_dict': {
'id': '999',
'title': 'Highlights',
},
'playlist_count': 12,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
team = mobj.group('team')
webpage = self._download_webpage(url, team)
cat_id = self._search_regex(
[r'var defaultCatId = "(.+?)";',
r'{statusIndex:0,index:0,.*?id:(.*?),'],
webpage, 'category id')
playlist_title = self._html_search_regex(
r'tab0"[^>]*?>(.*?)</td>',
webpage, 'playlist title', flags=re.DOTALL).lower().capitalize()
data = compat_urllib_parse_urlencode({
'cid': cat_id,
# This is the default value
'count': 12,
'ptrs': 3,
'format': 'json',
}) })
path = '/videocenter/servlets/browse?' + data
request_url = compat_urlparse.urljoin(url, path)
response = self._download_webpage(request_url, playlist_title)
response = self._fix_json(response)
if not response.strip():
self._downloader.report_warning('Got an empty response, trying '
'adding the "newvideos" parameter')
response = self._download_webpage(request_url + '&newvideos=true',
playlist_title)
response = self._fix_json(response)
videos = json.loads(response)
return { return {
'_type': 'playlist', 'id': video_id,
'title': playlist_title, 'title': title,
'id': cat_id, 'description': video_data.get('description'),
'entries': [self._extract_video(v) for v in videos], 'timestamp': parse_iso8601(video_data.get('date')),
'duration': parse_duration(video_data.get('duration')),
'thumbnails': thumbnails,
'formats': formats,
} }
class NHLIE(InfoExtractor): class NHLIE(NHLBaseIE):
IE_NAME = 'nhl.com' IE_NAME = 'nhl.com'
_VALID_URL = r'https?://(?:www\.)?(?P<site>nhl|wch2016)\.com/(?:[^/]+/)*c-(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?(?P<site>nhl|wch2016)\.com/(?:[^/]+/)*c-(?P<id>\d+)'
_SITES_MAP = { _CONTENT_DOMAIN = 'nhl.bamcontent.com'
'nhl': 'nhl',
'wch2016': 'wch',
}
_TESTS = [{ _TESTS = [{
# type=video # type=video
'url': 'https://www.nhl.com/video/anisimov-cleans-up-mess/t-277752844/c-43663503', 'url': 'https://www.nhl.com/video/anisimov-cleans-up-mess/t-277752844/c-43663503',
@ -293,59 +126,3 @@ class NHLIE(InfoExtractor):
'url': 'https://www.wch2016.com/news/3-stars-team-europe-vs-team-canada/c-282195068', 'url': 'https://www.wch2016.com/news/3-stars-team-europe-vs-team-canada/c-282195068',
'only_matching': True, 'only_matching': True,
}] }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
tmp_id, site = mobj.group('id'), mobj.group('site')
video_data = self._download_json(
'https://nhl.bamcontent.com/%s/id/v1/%s/details/web-v1.json'
% (self._SITES_MAP[site], tmp_id), tmp_id)
if video_data.get('type') == 'article':
video_data = video_data['media']
video_id = compat_str(video_data['id'])
title = video_data['title']
formats = []
for playback in video_data.get('playbacks', []):
playback_url = playback.get('url')
if not playback_url:
continue
ext = determine_ext(playback_url)
if ext == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
playback_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=playback.get('name', 'hls'), fatal=False)
self._check_formats(m3u8_formats, video_id)
formats.extend(m3u8_formats)
else:
height = int_or_none(playback.get('height'))
formats.append({
'format_id': playback.get('name', 'http' + ('-%dp' % height if height else '')),
'url': playback_url,
'width': int_or_none(playback.get('width')),
'height': height,
})
self._sort_formats(formats, ('preference', 'width', 'height', 'tbr', 'format_id'))
thumbnails = []
for thumbnail_id, thumbnail_data in video_data.get('image', {}).get('cuts', {}).items():
thumbnail_url = thumbnail_data.get('src')
if not thumbnail_url:
continue
thumbnails.append({
'id': thumbnail_id,
'url': thumbnail_url,
'width': int_or_none(thumbnail_data.get('width')),
'height': int_or_none(thumbnail_data.get('height')),
})
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'timestamp': parse_iso8601(video_data.get('date')),
'duration': parse_duration(video_data.get('duration')),
'thumbnails': thumbnails,
'formats': formats,
}