-# coding: utf-8
-from __future__ import unicode_literals
-
import re
from .adobepass import AdobePassIE
+from ..compat import compat_str
from ..utils import (
int_or_none,
determine_ext,
parse_age_limit,
+ remove_start,
+ remove_end,
+ try_get,
urlencode_postdata,
ExtractorError,
+ unified_timestamp,
+ traverse_obj,
)
}
_VALID_URL = r'''(?x)
https?://
- (?:
- (?:(?P<sub_domain>%s)\.)?go|
- (?P<sub_domain_2>abc|freeform|disneynow|fxnow\.fxnetworks)
+ (?P<sub_domain>
+ (?:%s\.)?go|fxnow\.fxnetworks|
+ (?:www\.)?(?:abc|freeform|disneynow)
)\.com/
(?:
(?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
(?:[^/]+/)*(?P<display_id>[^/?\#]+)
)
- ''' % '|'.join(list(_SITE_INFO.keys()))
+ ''' % r'\.|'.join(list(_SITE_INFO.keys()))
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'info_dict': {
},
'skip': 'This content is no longer available.',
}, {
- 'url': 'http://watchdisneyxd.go.com/doraemon',
+ 'url': 'https://disneynow.com/shows/big-hero-6-the-series',
'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
'info_dict': {
'id': 'VDKA3609139',
- 'ext': 'mp4',
'title': 'This Guilty Blood',
'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
'age_limit': 14,
+ 'episode': 'Episode 1',
+ 'upload_date': '20170102',
+ 'season': 'Season 2',
+ 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abcf/Shadowhunters/video/201/ae5f75608d86bf88aa4f9f4aa76ab1b7/579x325-Q100_ae5f75608d86bf88aa4f9f4aa76ab1b7.jpg',
+ 'duration': 2544,
+ 'season_number': 2,
+ 'series': 'Shadowhunters',
+ 'episode_number': 1,
+ 'timestamp': 1483387200,
+ 'ext': 'mp4'
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
'skip_download': True,
},
}, {
- 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet',
+ 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-04/12-the-knock',
'info_dict': {
- 'id': 'VDKA13435179',
- 'ext': 'mp4',
- 'title': 'The Bet',
- 'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404',
+ 'id': 'VDKA26050359',
+ 'title': 'The Knock',
+ 'description': 'md5:0c2947e3ada4c31f28296db7db14aa64',
'age_limit': 14,
+ 'ext': 'mp4',
+ 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abc/TheRookie/video/412/daf830d06e83b11eaf5c0a299d993ae3/1556x876-Q75_daf830d06e83b11eaf5c0a299d993ae3.jpg',
+ 'episode': 'Episode 12',
+ 'season_number': 4,
+ 'season': 'Season 4',
+ 'timestamp': 1642975200,
+ 'episode_number': 12,
+ 'upload_date': '20220123',
+ 'series': 'The Rookie',
+ 'duration': 2572,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
'info_dict': {
'id': 'VDKA12782841',
- 'ext': 'mp4',
'title': 'First Look: Better Things - Season 2',
'description': 'md5:fa73584a95761c605d9d54904e35b407',
+ 'ext': 'mp4',
+ 'age_limit': 14,
+ 'upload_date': '20170825',
+ 'duration': 161,
+ 'series': 'Better Things',
+ 'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/fx/BetterThings/video/12782841/b6b05e58264121cc2c98811318e6d507/1556x876-Q75_b6b05e58264121cc2c98811318e6d507.jpg',
+ 'timestamp': 1503661074,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
}, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
+ }, {
+ 'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
+ 'only_matching': True,
}]
def _extract_videos(self, brand, video_id='-1', show_id='-1'):
display_id)['video']
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- sub_domain = mobj.group('sub_domain') or mobj.group('sub_domain_2')
+ mobj = self._match_valid_url(url)
+ sub_domain = remove_start(remove_end(mobj.group('sub_domain') or '', '.go'), 'www.')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
if not video_id or not site_info:
webpage = self._download_webpage(url, display_id or video_id)
- video_id = self._search_regex(
- (
- # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
- # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
- r'data-video-id=["\']*(VDKA\w+)',
- # https://github.com/ytdl-org/youtube-dl/pull/25216/files
- # The following is based on the pull request on the line above. Changed the ABC.com URL to a show available now.
- # https://abc.com/shows/the-rookie/episode-guide/season-02/19-the-q-word
- r'\bvideoIdCode["\']\s*:\s*["\'](vdka\w+)',
- # Deprecated fallback pattern
- r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
- ), webpage, 'video id', default=video_id)
+ data = self._parse_json(
+ self._search_regex(
+ r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
+ 'data', default='{}'),
+ display_id or video_id, fatal=False)
+ # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
+ layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
+ video_id = None
+ if layout:
+ video_id = try_get(
+ layout,
+ (lambda x: x['videoid'], lambda x: x['video']['id']),
+ compat_str)
+ if not video_id:
+ video_id = self._search_regex(
+ (
+ # There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
+ # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
+ r'data-video-id=["\']*(VDKA\w+)',
+ # page.analytics.videoIdCode
+ r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
+ # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
+ r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
+ ), webpage, 'video id', default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',
title = video_data['title']
formats = []
+ subtitles = {}
for asset in video_data.get('assets', {}).get('asset', []):
asset_url = asset.get('value')
if not asset_url:
error_message = ', '.join([error['message'] for error in errors])
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True)
asset_url += '?' + entitlement['uplynkData']['sessionKey']
- formats.extend(self._extract_m3u8_formats(
- asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
+ fmts, subs = self._extract_m3u8_formats_and_subtitles(
+ asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)
+ formats.extend(fmts)
+ self._merge_subtitles(subs, target=subtitles)
else:
f = {
'format_id': format_id,
'height': height,
})
formats.append(f)
- self._sort_formats(formats)
- subtitles = {}
for cc in video_data.get('closedcaption', {}).get('src', []):
cc_url = cc.get('value')
if not cc_url:
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subtitles,
+ 'timestamp': unified_timestamp(traverse_obj(video_data, ('airdates', 'airdate', 0))),
}