go.py (12909B)
1 # coding: utf-8 2 from __future__ import unicode_literals 3 4 import re 5 6 from .adobepass import AdobePassIE 7 from ..compat import compat_str 8 from ..utils import ( 9 int_or_none, 10 determine_ext, 11 parse_age_limit, 12 try_get, 13 urlencode_postdata, 14 ExtractorError, 15 ) 16 17 18 class GoIE(AdobePassIE): 19 _SITE_INFO = { 20 'abc': { 21 'brand': '001', 22 'requestor_id': 'ABC', 23 }, 24 'freeform': { 25 'brand': '002', 26 'requestor_id': 'ABCFamily', 27 }, 28 'watchdisneychannel': { 29 'brand': '004', 30 'resource_id': 'Disney', 31 }, 32 'watchdisneyjunior': { 33 'brand': '008', 34 'resource_id': 'DisneyJunior', 35 }, 36 'watchdisneyxd': { 37 'brand': '009', 38 'resource_id': 'DisneyXD', 39 }, 40 'disneynow': { 41 'brand': '011', 42 'resource_id': 'Disney', 43 }, 44 'fxnow.fxnetworks': { 45 'brand': '025', 46 'requestor_id': 'dtci', 47 }, 48 } 49 _VALID_URL = r'''(?x) 50 https?:// 51 (?: 52 (?:(?P<sub_domain>%s)\.)?go| 53 (?P<sub_domain_2>abc|freeform|disneynow|fxnow\.fxnetworks) 54 )\.com/ 55 (?: 56 (?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)| 57 (?:[^/]+/)*(?P<display_id>[^/?\#]+) 58 ) 59 ''' % '|'.join(list(_SITE_INFO.keys())) 60 _TESTS = [{ 61 'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643', 62 'info_dict': { 63 'id': 'VDKA3807643', 64 'ext': 'mp4', 65 'title': 'The Traitor in the White House', 66 'description': 'md5:05b009d2d145a1e85d25111bd37222e8', 67 }, 68 'params': { 69 # m3u8 download 70 'skip_download': True, 71 }, 72 'skip': 'This content is no longer available.', 73 }, { 74 'url': 'http://watchdisneyxd.go.com/doraemon', 75 'info_dict': { 76 'title': 'Doraemon', 77 'id': 'SH55574025', 78 }, 79 'playlist_mincount': 51, 80 }, { 81 'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood', 82 'info_dict': { 83 'id': 'VDKA3609139', 84 'ext': 'mp4', 85 'title': 'This Guilty Blood', 86 'description': 'md5:f18e79ad1c613798d95fdabfe96cd292', 87 'age_limit': 14, 88 }, 89 'params': { 90 'geo_bypass_ip_block': '3.244.239.0/24', 91 # m3u8 download 92 'skip_download': True, 93 }, 94 }, { 95 'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet', 96 'info_dict': { 97 'id': 'VDKA13435179', 98 'ext': 'mp4', 99 'title': 'The Bet', 100 'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404', 101 'age_limit': 14, 102 }, 103 'params': { 104 'geo_bypass_ip_block': '3.244.239.0/24', 105 # m3u8 download 106 'skip_download': True, 107 }, 108 }, { 109 'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841', 110 'info_dict': { 111 'id': 'VDKA12782841', 112 'ext': 'mp4', 113 'title': 'First Look: Better Things - Season 2', 114 'description': 'md5:fa73584a95761c605d9d54904e35b407', 115 }, 116 'params': { 117 'geo_bypass_ip_block': '3.244.239.0/24', 118 # m3u8 download 119 'skip_download': True, 120 }, 121 }, { 122 'url': 'https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot', 123 'info_dict': { 124 'id': 'VDKA22600213', 125 'ext': 'mp4', 126 'title': 'Pilot', 127 'description': 'md5:74306df917cfc199d76d061d66bebdb4', 128 }, 129 'params': { 130 # m3u8 download 131 'skip_download': True, 132 }, 133 }, { 134 'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding', 135 'only_matching': True, 136 }, { 137 'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland', 138 'only_matching': True, 139 }, { 140 # brand 004 141 'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915', 142 'only_matching': True, 143 }, { 144 # brand 008 145 'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013', 146 'only_matching': True, 147 }, { 148 'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013', 149 'only_matching': True, 150 }] 151 152 def _extract_videos(self, brand, video_id='-1', show_id='-1'): 153 display_id = video_id if video_id != '-1' else show_id 154 return self._download_json( 155 'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id), 156 display_id)['video'] 157 158 def _real_extract(self, url): 159 mobj = re.match(self._VALID_URL, url) 160 sub_domain = mobj.group('sub_domain') or mobj.group('sub_domain_2') 161 video_id, display_id = mobj.group('id', 'display_id') 162 site_info = self._SITE_INFO.get(sub_domain, {}) 163 brand = site_info.get('brand') 164 if not video_id or not site_info: 165 webpage = self._download_webpage(url, display_id or video_id) 166 data = self._parse_json( 167 self._search_regex( 168 r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage, 169 'data', default='{}'), 170 display_id or video_id, fatal=False) 171 # https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot 172 layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict) 173 video_id = None 174 if layout: 175 video_id = try_get( 176 layout, 177 (lambda x: x['videoid'], lambda x: x['video']['id']), 178 compat_str) 179 if not video_id: 180 video_id = self._search_regex( 181 ( 182 # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" 183 # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood 184 r'data-video-id=["\']*(VDKA\w+)', 185 # page.analytics.videoIdCode 186 r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)', 187 # https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet 188 r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)' 189 ), webpage, 'video id', default=video_id) 190 if not site_info: 191 brand = self._search_regex( 192 (r'data-brand=\s*["\']\s*(\d+)', 193 r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand', 194 default='004') 195 site_info = next( 196 si for _, si in self._SITE_INFO.items() 197 if si.get('brand') == brand) 198 if not video_id: 199 # show extraction works for Disney, DisneyJunior and DisneyXD 200 # ABC and Freeform has different layout 201 show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id') 202 videos = self._extract_videos(brand, show_id=show_id) 203 show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False) 204 entries = [] 205 for video in videos: 206 entries.append(self.url_result( 207 video['url'], 'Go', video.get('id'), video.get('title'))) 208 entries.reverse() 209 return self.playlist_result(entries, show_id, show_title) 210 video_data = self._extract_videos(brand, video_id)[0] 211 video_id = video_data['id'] 212 title = video_data['title'] 213 214 formats = [] 215 for asset in video_data.get('assets', {}).get('asset', []): 216 asset_url = asset.get('value') 217 if not asset_url: 218 continue 219 format_id = asset.get('format') 220 ext = determine_ext(asset_url) 221 if ext == 'm3u8': 222 video_type = video_data.get('type') 223 data = { 224 'video_id': video_data['id'], 225 'video_type': video_type, 226 'brand': brand, 227 'device': '001', 228 } 229 if video_data.get('accesslevel') == '1': 230 requestor_id = site_info.get('requestor_id', 'DisneyChannels') 231 resource = site_info.get('resource_id') or self._get_mvpd_resource( 232 requestor_id, title, video_id, None) 233 auth = self._extract_mvpd_auth( 234 url, video_id, requestor_id, resource) 235 data.update({ 236 'token': auth, 237 'token_type': 'ap', 238 'adobe_requestor_id': requestor_id, 239 }) 240 else: 241 self._initialize_geo_bypass({'countries': ['US']}) 242 entitlement = self._download_json( 243 'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json', 244 video_id, data=urlencode_postdata(data)) 245 errors = entitlement.get('errors', {}).get('errors', []) 246 if errors: 247 for error in errors: 248 if error.get('code') == 1002: 249 self.raise_geo_restricted( 250 error['message'], countries=['US']) 251 error_message = ', '.join([error['message'] for error in errors]) 252 raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message), expected=True) 253 asset_url += '?' + entitlement['uplynkData']['sessionKey'] 254 formats.extend(self._extract_m3u8_formats( 255 asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)) 256 else: 257 f = { 258 'format_id': format_id, 259 'url': asset_url, 260 'ext': ext, 261 } 262 if re.search(r'(?:/mp4/source/|_source\.mp4)', asset_url): 263 f.update({ 264 'format_id': ('%s-' % format_id if format_id else '') + 'SOURCE', 265 'preference': 1, 266 }) 267 else: 268 mobj = re.search(r'/(\d+)x(\d+)/', asset_url) 269 if mobj: 270 height = int(mobj.group(2)) 271 f.update({ 272 'format_id': ('%s-' % format_id if format_id else '') + '%dP' % height, 273 'width': int(mobj.group(1)), 274 'height': height, 275 }) 276 formats.append(f) 277 self._sort_formats(formats) 278 279 subtitles = {} 280 for cc in video_data.get('closedcaption', {}).get('src', []): 281 cc_url = cc.get('value') 282 if not cc_url: 283 continue 284 ext = determine_ext(cc_url) 285 if ext == 'xml': 286 ext = 'ttml' 287 subtitles.setdefault(cc.get('lang'), []).append({ 288 'url': cc_url, 289 'ext': ext, 290 }) 291 292 thumbnails = [] 293 for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []): 294 thumbnail_url = thumbnail.get('value') 295 if not thumbnail_url: 296 continue 297 thumbnails.append({ 298 'url': thumbnail_url, 299 'width': int_or_none(thumbnail.get('width')), 300 'height': int_or_none(thumbnail.get('height')), 301 }) 302 303 return { 304 'id': video_id, 305 'title': title, 306 'description': video_data.get('longdescription') or video_data.get('description'), 307 'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000), 308 'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')), 309 'episode_number': int_or_none(video_data.get('episodenumber')), 310 'series': video_data.get('show', {}).get('title'), 311 'season_number': int_or_none(video_data.get('season', {}).get('num')), 312 'thumbnails': thumbnails, 313 'formats': formats, 314 'subtitles': subtitles, 315 }