[noco] Remove Extractor(closes #10864)

youtube_dl/extractor/anvato.py

@@ -9,6 +9,7 @@ import re
 import time
 
 from .common import InfoExtractor
+from .anvato_token_generator import NFLTokenGenerator
 from ..aes import aes_encrypt
 from ..compat import compat_str
 from ..utils import (
@@ -116,7 +117,76 @@ class AnvatoIE(InfoExtractor):
         'anvato_scripps_app_ios_prod_409c41960c60b308db43c3cc1da79cab9f1c3d93': 'WPxj5GraLTkYCyj3M7RozLqIycjrXOEcDGFMIJPn',
         'EZqvRyKBJLrgpClDPDF8I7Xpdp40Vx73': '4OxGd2dEakylntVKjKF0UK9PDPYB6A9W',
         'M2v78QkpleXm9hPp9jUXI63x5vA6BogR': 'ka6K32k7ZALmpINkjJUGUo0OE42Md1BQ',
-        'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ'
+        'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
+        'X8POa4zPPaKVZHqmWjuEzfP31b1QM9VN': 'Dn5vOY9ooDw7VSl9qztjZI5o0g08mA0z',
+        'M2v78QkBMpNJlSPp9diX5F2PBmBy6Bog': 'ka6K32kyo7nDZfNkjQCGWf1lpApXMd1B',
+        'bvJ0dQpav07l0hG5JgfVLF2dv1vARwpP': 'BzoQW24GrJZoJfmNodiJKSPeB9B8NOxj',
+        'lxQMLg2XZKuEZaWgsqubBxV9INZ6bryY': 'Vm2Mx6noKds9jB71h6urazwlTG3m9x8l',
+        '04EnjvXeoSmkbJ9ckPs7oY0mcxv7PlyN': 'aXERQP9LMfQVlEDsgGs6eEA1SWznAQ8P',
+        'mQbO2ge6BFRWVPYCYpU06YvNt80XLvAX': 'E2BV1NGmasN5v7eujECVPJgwflnLPm2A',
+        'g43oeBzJrCml7o6fa5fRL1ErCdeD8z4K': 'RX34mZ6zVH4Nr6whbxIGLv9WSbxEKo8V',
+        'VQrDJoP7mtdBzkxhXbSPwGB1coeElk4x': 'j2VejQx0VFKQepAF7dI0mJLKtOVJE18z',
+        'WxA5NzLRjCrmq0NUgaU5pdMDuZO7RJ4w': 'lyY5ADLKaIOLEgAsGQCveEMAcqnx3rY9',
+        'M4lpMXB71ie0PjMCjdFzVXq0SeRVqz49': 'n2zVkOqaLIv3GbLfBjcwW51LcveWOZ2e',
+        'dyDZGEqN8u8nkJZcJns0oxYmtP7KbGAn': 'VXOEqQW9BtEVLajfZQSLEqxgS5B7qn2D',
+        'E7QNjrVY5u5mGvgu67IoDgV1CjEND8QR': 'rz8AaDmdKIkLmPNhB5ILPJnjS5PnlL8d',
+        'a4zrqjoKlfzg0dwHEWtP31VqcLBpjm4g': 'LY9J16gwETdGWa3hjBu5o0RzuoQDjqXQ',
+        'dQP5BZroMsMVLO1hbmT5r2Enu86GjxA6': '7XR3oOdbPF6x3PRFLDCq9RkgsRjAo48V',
+        'M4lKNBO1NFe0PjMCj1tzVXq0SeRVqzA9': 'n2zoRqGLRUv3GbLfBmTwW51LcveWOZYe',
+        'nAZ7MZdpGCGg1pqFEbsoJOz2C60mv143': 'dYJgdqA9aT4yojETqGi7yNgoFADxqmXP',
+        '3y1MERYgOuE9NzbFgwhV6Wv2F0YKvbyz': '081xpZDQgC4VadLTavhWQxrku56DAgXV',
+        'bmQvmEXr5HWklBMCZOcpE2Z3HBYwqGyl': 'zxXPbVNyMiMAZldhr9FkOmA0fl4aKr2v',
+        'wA7oDNYldfr6050Hwxi52lPZiVlB86Ap': 'ZYK16aA7ni0d3l3c34uwpxD7CbReMm8Q',
+        'g43MbKMWmFml7o7sJoSRkXxZiXRvJ3QK': 'RX3oBJonvs4Nr6rUWBCGn3matRGqJPXV',
+        'mA9VdlqpLS0raGaSDvtoqNrBTzb8XY4q': '0XN4OjBD3fnW7r7IbmtJB4AyfOmlrE2r',
+        'mAajOwgkGt17oGoFmEuklMP9H0GnW54d': 'lXbBLPGyzikNGeGujAuAJGjZiwLRxyXR',
+        'vy8vjJ9kbUwrRqRu59Cj5dWZfzYErlAb': 'K8l7gpwaGcBpnAnCLNCmPZRdin3eaQX0',
+        'xQMWBpR8oHEZaWaSMGUb0avOHjLVYn4Y': 'm2MrN4vEaf9jB7BFy5Srb40jTrN67AYl',
+        'xyKEmVO3miRr6D6UVkt7oB8jtD6aJEAv': 'g2ddDebqDfqdgKgswyUKwGjbTWwzq923',
+        '7Qk0wa2D9FjKapacoJF27aLvUDKkLGA0': 'b2kgBEkephJaMkMTL7s1PLe4Ua6WyP2P',
+        '3QLg6nqmNTJ5VvVTo7f508LPidz1xwyY': 'g2L1GgpraipmAOAUqmIbBnPxHOmw4MYa',
+        '3y1B7zZjXTE9NZNSzZSVNPZaTNLjo6Qz': '081b5G6wzH4VagaURmcWbN5mT4JGEe2V',
+        'lAqnwvkw6SG6D8DSqmUg6DRLUp0w3G4x': 'O2pbP0xPDFNJjpjIEvcdryOJtpkVM4X5',
+        'awA7xd1N0Hr6050Hw2c52lPZiVlB864p': 'GZYKpn4aoT0d3l3c3PiwpxD7CbReMmXQ',
+        'jQVqPLl9YHL1WGWtR1HDgWBGT63qRNyV': '6X03ne6vrU4oWyWUN7tQVoajikxJR3Ye',
+        'GQRMR8mL7uZK797t7xH3eNzPIP5dOny1': 'm2vqPWGd4U31zWzSyasDRAoMT1PKRp8o',
+        'zydq9RdmRhXLkNkfNoTJlMzaF0lWekQB': '3X7LnvE7vH5nkEkSqLiey793Un7dLB8e',
+        'VQrDzwkB2IdBzjzu9MHPbEYkSB50gR4x': 'j2VebLzoKUKQeEesmVh0gM1eIp9jKz8z',
+        'mAa2wMamBs17oGoFmktklMP9H0GnW54d': 'lXbgP74xZTkNGeGujVUAJGjZiwLRxy8R',
+        '7yjB6ZLG6sW8R6RF2xcan1KGfJ5dNoyd': 'wXQkPorvPHZ45N5t4Jf6qwg5Tp4xvw29',
+        'a4zPpNeWGuzg0m0iX3tPeanGSkRKWXQg': 'LY9oa3QAyHdGW9Wu3Ri5JGeEik7l1N8Q',
+        'k2rneA2M38k25cXDwwSknTJlxPxQLZ6M': '61lyA2aEVDzklfdwmmh31saPxQx2VRjp',
+        'bK9Zk4OvPnvxduLgxvi8VUeojnjA02eV': 'o5jANYjbeMb4nfBaQvcLAt1jzLzYx6ze',
+        '5VD6EydM3R9orHmNMGInGCJwbxbQvGRw': 'w3zjmX7g4vnxzCxElvUEOiewkokXprkZ',
+        '70X35QbVYVYNPUmP9YfbzI06YqYQk2R1': 'vG4Aj2BMjMjoztB7zeFOnCVPJpJ8lMOa',
+        '26qYwQVG9p1Bks2GgBckjfDJOXOAMgG1': 'r4ev9X0mv5zqJc0yk5IBDcQOwZw8mnwQ',
+        'rvVKpA56MBXWlSxMw3cobT5pdkd4Dm7q': '1J7ZkY53pZ645c93owcLZuveE7E8B3rL',
+        'qN1zdy1zlYL23IWZGWtDvfV6WeWQWkJo': 'qN1zdy1zlYL23IWZGWtDvfV6WeWQWkJo',
+        'jdKqRGF16dKsBviMDae7IGDl7oTjEbVV': 'Q09l7vhlNxPFErIOK6BVCe7KnwUW5DVV',
+        '3QLkogW1OUJ5VvPsrDH56DY2u7lgZWyY': 'g2LRE1V9espmAOPhE4ubj4ZdUA57yDXa',
+        'wyJvWbXGBSdbkEzhv0CW8meou82aqRy8': 'M2wolPvyBIpQGkbT4juedD4ruzQGdK2y',
+        '7QkdZrzEkFjKap6IYDU2PB0oCNZORmA0': 'b2kN1l96qhJaMkPs9dt1lpjBfwqZoA8P',
+        'pvA05113MHG1w3JTYxc6DVlRCjErVz4O': 'gQXeAbblBUnDJ7vujbHvbRd1cxlz3AXO',
+        'mA9blJDZwT0raG1cvkuoeVjLC7ZWd54q': '0XN9jRPwMHnW7rvumgfJZOD9CJgVkWYr',
+        '5QwRN5qKJTvGKlDTmnf7xwNZcjRmvEy9': 'R2GP6LWBJU1QlnytwGt0B9pytWwAdDYy',
+        'eyn5rPPbkfw2KYxH32fG1q58CbLJzM40': 'p2gyqooZnS56JWeiDgfmOy1VugOQEBXn',
+        '3BABn3b5RfPJGDwilbHe7l82uBoR05Am': '7OYZG7KMVhbPdKJS3xcWEN3AuDlLNmXj',
+        'xA5zNGXD3HrmqMlF6OS5pdMDuZO7RJ4w': 'yY5DAm6r1IOLE3BCVMFveEMAcqnx3r29',
+        'g43PgW3JZfml7o6fDEURL1ErCdeD8zyK': 'RX3aQn1zrS4Nr6whDgCGLv9WSbxEKo2V',
+        'lAqp8WbGgiG6D8LTKJcg3O72CDdre1Qx': 'O2pnm6473HNJjpKuVosd3vVeh975yrX5',
+        'wyJbYEDxKSdbkJ6S6RhW8meou82aqRy8': 'M2wPm7EgRSpQGlAh70CedD4ruzQGdKYy',
+        'M4lgW28nLCe0PVdtaXszVXq0SeRVqzA9': 'n2zmJvg4jHv3G0ETNgiwW51LcveWOZ8e',
+        '5Qw3OVvp9FvGKlDTmOC7xwNZcjRmvEQ9': 'R2GzDdml9F1Qlnytw9s0B9pytWwAdD8y',
+        'vy8a98X7zCwrRqbHrLUjYzwDiK2b70Qb': 'K8lVwzyjZiBpnAaSGeUmnAgxuGOBxmY0',
+        'g4eGjJLLoiqRD3Pf9oT5O03LuNbLRDQp': '6XqD59zzpfN4EwQuaGt67qNpSyRBlnYy',
+        'g43OPp9boIml7o6fDOIRL1ErCdeD8z4K': 'RX33alNB4s4Nr6whDPUGLv9WSbxEKoXV',
+        'xA2ng9OkBcGKzDbTkKsJlx7dUK8R3dA5': 'z2aPnJvzBfObkwGC3vFaPxeBhxoMqZ8K',
+        'xyKEgBajZuRr6DEC0Kt7XpD1cnNW9gAv': 'g2ddlEBvRsqdgKaI4jUK9PrgfMexGZ23',
+        'BAogww51jIMa2JnH1BcYpXM5F658RNAL': 'rYWDmm0KptlkGv4FGJFMdZmjs9RDE6XR',
+        'BAokpg62VtMa2JnH1mHYpXM5F658RNAL': 'rYWryDnlNslkGv4FG4HMdZmjs9RDE62R',
+        'a4z1Px5e2hzg0m0iMMCPeanGSkRKWXAg': 'LY9eorNQGUdGW9WuKKf5JGeEik7l1NYQ',
+        'kAx69R58kF9nY5YcdecJdl2pFXP53WyX': 'gXyRxELpbfPvLeLSaRil0mp6UEzbZJ8L',
+        'BAoY13nwViMa2J2uo2cY6BlETgmdwryL': 'rYWwKzJmNFlkGvGtNoUM9bzwIJVzB1YR',
     }
 
     _MCP_TO_ACCESS_KEY_TABLE = {
@@ -134,6 +204,10 @@ class AnvatoIE(InfoExtractor):
         'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
     }
 
+    _TOKEN_GENERATORS = {
+        'GXvEgwyJeWem8KCYXfeoHWknwP48Mboj': NFLTokenGenerator,
+    }
+
     _API_KEY = '3hwbSuqqT690uxjNYBktSQpa5ZrpYYR0Iofx7NcJHyA'
 
     _ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
@@ -189,19 +263,20 @@ class AnvatoIE(InfoExtractor):
 
         video_data_url += '&X-Anvato-Adst-Auth=' + base64.b64encode(auth_secret).decode('ascii')
         anvrid = md5_text(time.time() * 1000 * random.random())[:30]
-        payload = {
-            'api': {
-                'anvrid': anvrid,
-                'anvstk': md5_text('%s|%s|%d|%s' % (
-                    access_key, anvrid, server_time,
-                    self._ANVACK_TABLE.get(access_key, self._API_KEY))),
-                'anvts': server_time,
-            },
+        api = {
+            'anvrid': anvrid,
+            'anvts': server_time,
         }
+        if access_key in self._TOKEN_GENERATORS:
+            api['anvstk2'] = self._TOKEN_GENERATORS[access_key].generate(self, access_key, video_id)
+        else:
+            api['anvstk'] = md5_text('%s|%s|%d|%s' % (
+                access_key, anvrid, server_time,
+                self._ANVACK_TABLE.get(access_key, self._API_KEY)))
 
         return self._download_json(
             video_data_url, video_id, transform_source=strip_jsonp,
-            data=json.dumps(payload).encode('utf-8'))
+            data=json.dumps({'api': api}).encode('utf-8'))
 
     def _get_anvato_videos(self, access_key, video_id):
         video_data = self._get_video_json(access_key, video_id)
@@ -259,7 +334,7 @@ class AnvatoIE(InfoExtractor):
             'description': video_data.get('def_description'),
             'tags': video_data.get('def_tags', '').split(','),
             'categories': video_data.get('categories'),
-            'thumbnail': video_data.get('thumbnail'),
+            'thumbnail': video_data.get('src_image_url') or video_data.get('thumbnail'),
             'timestamp': int_or_none(video_data.get(
                 'ts_published') or video_data.get('ts_added')),
             'uploader': video_data.get('mcp_id'),

youtube_dl/extractor/anvato_token_generator/__init__.py

@@ -0,0 +1,7 @@
+from __future__ import unicode_literals
+
+from .nfl import NFLTokenGenerator
+
+__all__ = [
+    'NFLTokenGenerator',
+]

youtube_dl/extractor/anvato_token_generator/common.py

@@ -0,0 +1,6 @@
+from __future__ import unicode_literals
+
+
+class TokenGenerator:
+    def generate(self, anvack, mcp_id):
+        raise NotImplementedError('This method must be implemented by subclasses')

youtube_dl/extractor/anvato_token_generator/nfl.py

@@ -0,0 +1,30 @@
+from __future__ import unicode_literals
+
+import json
+
+from .common import TokenGenerator
+
+
+class NFLTokenGenerator(TokenGenerator):
+    _AUTHORIZATION = None
+
+    def generate(ie, anvack, mcp_id):
+        if not NFLTokenGenerator._AUTHORIZATION:
+            reroute = ie._download_json(
+                'https://api.nfl.com/v1/reroute', mcp_id,
+                data=b'grant_type=client_credentials',
+                headers={'X-Domain-Id': 100})
+            NFLTokenGenerator._AUTHORIZATION = '%s %s' % (reroute.get('token_type') or 'Bearer', reroute['access_token'])
+        return ie._download_json(
+            'https://api.nfl.com/v3/shield/', mcp_id, data=json.dumps({
+                'query': '''{
+  viewer {
+    mediaToken(anvack: "%s", id: %s) {
+      token
+    }
+  }
+}''' % (anvack, mcp_id),
+            }).encode(), headers={
+                'Authorization': NFLTokenGenerator._AUTHORIZATION,
+                'Content-Type': 'application/json',
+            })['data']['viewer']['mediaToken']['token']

youtube_dl/extractor/extractors.py

@@ -724,7 +724,10 @@ from .nexx import (
     NexxIE,
     NexxEmbedIE,
 )
-from .nfl import NFLIE
+from .nfl import (
+    NFLIE,
+    NFLArticleIE,
+)
 from .nhk import (
     NhkVodIE,
     NhkVodProgramIE,
@@ -744,7 +747,6 @@ from .ninenow import NineNowIE
 from .nintendo import NintendoIE
 from .njpwworld import NJPWWorldIE
 from .nobelprize import NobelPrizeIE
-from .noco import NocoIE
 from .nonktube import NonkTubeIE
 from .noovo import NoovoIE
 from .normalboots import NormalbootsIE

youtube_dl/extractor/nfl.py

@@ -4,19 +4,15 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlparse,
-)
 from ..utils import (
-    ExtractorError,
-    int_or_none,
-    remove_end,
+    clean_html,
+    determine_ext,
+    get_element_by_class,
 )
 
 
-class NFLIE(InfoExtractor):
-    IE_NAME = 'nfl.com'
-    _VALID_URL = r'''(?x)
+class NFLBaseIE(InfoExtractor):
+    _VALID_URL_BASE = r'''(?x)
                     https?://
                         (?P<host>
                             (?:www\.)?
@@ -34,15 +30,15 @@ class NFLIE(InfoExtractor):
                                     houstontexans|
                                     colts|
                                     jaguars|
-                                    titansonline|
+                                    (?:titansonline|tennesseetitans)|
                                     denverbroncos|
-                                    kcchiefs|
+                                    (?:kc)?chiefs|
                                     raiders|
                                     chargers|
                                     dallascowboys|
                                     giants|
                                     philadelphiaeagles|
-                                    redskins|
+                                    (?:redskins|washingtonfootball)|
                                     chicagobears|
                                     detroitlions|
                                     packers|
@@ -52,180 +48,112 @@ class NFLIE(InfoExtractor):
                                     neworleanssaints|
                                     buccaneers|
                                     azcardinals|
-                                    stlouisrams|
+                                    (?:stlouis|the)rams|
                                     49ers|
                                     seahawks
                                 )\.com|
                                 .+?\.clubs\.nfl\.com
                             )
                         )/
-                        (?:.+?/)*
-                        (?P<id>[^/#?&]+)
                     '''
+    _VIDEO_CONFIG_REGEX = r'<script[^>]+id="[^"]*video-config-[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}[^"]*"[^>]*>\s*({.+})'
+
+    def _parse_video_config(self, video_config, display_id):
+        video_config = self._parse_json(video_config, display_id)
+        item = video_config['playlist'][0]
+        mcp_id = item.get('mcpID')
+        if mcp_id:
+            info = self.url_result(
+                'anvato:GXvEgwyJeWem8KCYXfeoHWknwP48Mboj:' + mcp_id,
+                'Anvato', mcp_id)
+        else:
+            media_id = item.get('id') or item['entityId']
+            title = item['title']
+            item_url = item['url']
+            info = {'id': media_id}
+            ext = determine_ext(item_url)
+            if ext == 'm3u8':
+                info['formats'] = self._extract_m3u8_formats(item_url, media_id, 'mp4')
+                self._sort_formats(info['formats'])
+            else:
+                info['url'] = item_url
+                if item.get('audio') is True:
+                    info['vcodec'] = 'none'
+            is_live = video_config.get('live') is True
+            thumbnails = None
+            image_url = item.get(item.get('imageSrc')) or item.get(item.get('posterImage'))
+            if image_url:
+                thumbnails = [{
+                    'url': image_url,
+                    'ext': determine_ext(image_url, 'jpg'),
+                }]
+            info.update({
+                'title': self._live_title(title) if is_live else title,
+                'is_live': is_live,
+                'description': clean_html(item.get('description')),
+                'thumbnails': thumbnails,
+            })
+        return info
+
+
+class NFLIE(NFLBaseIE):
+    IE_NAME = 'nfl.com'
+    _VALID_URL = NFLBaseIE._VALID_URL_BASE + r'(?:videos?|listen|audio)/(?P<id>[^/#?&]+)'
     _TESTS = [{
-        'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
-        'md5': '394ef771ddcd1354f665b471d78ec4c6',
+        'url': 'https://www.nfl.com/videos/baker-mayfield-s-game-changing-plays-from-3-td-game-week-14',
         'info_dict': {
-            'id': '0ap3000000398478',
+            'id': '899441',
             'ext': 'mp4',
-            'title': 'Week 3: Redskins vs. Eagles highlights',
-            'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478',
-            'upload_date': '20140921',
-            'timestamp': 1411337580,
+            'title': "Baker Mayfield's game-changing plays from 3-TD game Week 14",
+            'description': 'md5:85e05a3cc163f8c344340f220521136d',
+            'upload_date': '20201215',
+            'timestamp': 1608009755,
             'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'NFL',
         }
     }, {
-        'url': 'http://prod.www.steelers.clubs.nfl.com/video-and-audio/videos/LIVE_Post_Game_vs_Browns/9d72f26a-9e2b-4718-84d3-09fb4046c266',
-        'md5': 'cf85bdb4bc49f6e9d3816d130c78279c',
+        'url': 'https://www.chiefs.com/listen/patrick-mahomes-travis-kelce-react-to-win-over-dolphins-the-breakdown',
+        'md5': '6886b32c24b463038c760ceb55a34566',
         'info_dict': {
-            'id': '9d72f26a-9e2b-4718-84d3-09fb4046c266',
-            'ext': 'mp4',
-            'title': 'LIVE: Post Game vs. Browns',
-            'description': 'md5:6a97f7e5ebeb4c0e69a418a89e0636e8',
-            'upload_date': '20131229',
-            'timestamp': 1388354455,
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'id': 'd87e8790-3e14-11eb-8ceb-ff05c2867f99',
+            'ext': 'mp3',
+            'title': 'Patrick Mahomes, Travis Kelce React to Win Over Dolphins | The Breakdown',
+            'description': 'md5:12ada8ee70e6762658c30e223e095075',
         }
     }, {
-        'url': 'http://www.nfl.com/news/story/0ap3000000467586/article/patriots-seahawks-involved-in-lategame-skirmish',
-        'info_dict': {
-            'id': '0ap3000000467607',
-            'ext': 'mp4',
-            'title': 'Frustrations flare on the field',
-            'description': 'Emotions ran high at the end of the Super Bowl on both sides of the ball after a dramatic finish.',
-            'timestamp': 1422850320,
-            'upload_date': '20150202',
-        },
-    }, {
-        'url': 'http://www.patriots.com/video/2015/09/18/10-days-gillette',
-        'md5': '4c319e2f625ffd0b481b4382c6fc124c',
-        'info_dict': {
-            'id': 'n-238346',
-            'ext': 'mp4',
-            'title': '10 Days at Gillette',
-            'description': 'md5:8cd9cd48fac16de596eadc0b24add951',
-            'timestamp': 1442618809,
-            'upload_date': '20150918',
-        },
-    }, {
-        # lowercase data-contentid
-        'url': 'http://www.steelers.com/news/article-1/Tomlin-on-Ben-getting-Vick-ready/56399c96-4160-48cf-a7ad-1d17d4a3aef7',
-        'info_dict': {
-            'id': '12693586-6ea9-4743-9c1c-02c59e4a5ef2',
-            'ext': 'mp4',
-            'title': 'Tomlin looks ahead to Ravens on a short week',
-            'description': 'md5:32f3f7b139f43913181d5cbb24ecad75',
-            'timestamp': 1443459651,
-            'upload_date': '20150928',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.nfl.com/videos/nfl-network-top-ten/09000d5d810a6bd4/Top-10-Gutsiest-Performances-Jack-Youngblood',
+        'url': 'https://www.buffalobills.com/video/buffalo-bills-military-recognition-week-14',
         'only_matching': True,
     }, {
-        'url': 'http://www.buffalobills.com/video/videos/Rex_Ryan_Show_World_Wide_Rex/b1dcfab2-3190-4bb1-bfc0-d6e603d6601a',
+        'url': 'https://www.raiders.com/audio/instant-reactions-raiders-week-14-loss-to-indianapolis-colts-espn-jason-fitz',
         'only_matching': True,
     }]
 
-    @staticmethod
-    def prepend_host(host, url):
-        if not url.startswith('http'):
-            if not url.startswith('/'):
-                url = '/%s' % url
-            url = 'http://{0:}{1:}'.format(host, url)
-        return url
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        return self._parse_video_config(self._search_regex(
+            self._VIDEO_CONFIG_REGEX, webpage, 'video config'), display_id)
 
-    @staticmethod
-    def format_from_stream(stream, protocol, host, path_prefix='',
-                           preference=0, note=None):
-        url = '{protocol:}://{host:}/{prefix:}{path:}'.format(
-            protocol=protocol,
-            host=host,
-            prefix=path_prefix,
-            path=stream.get('path'),
-        )
-        return {
-            'url': url,
-            'vbr': int_or_none(stream.get('rate', 0), 1000),
-            'preference': preference,
-            'format_note': note,
-        }
+
+class NFLArticleIE(NFLBaseIE):
+    IE_NAME = 'nfl.com:article'
+    _VALID_URL = NFLBaseIE._VALID_URL_BASE + r'news/(?P<id>[^/#?&]+)'
+    _TEST = {
+        'url': 'https://www.buffalobills.com/news/the-only-thing-we-ve-earned-is-the-noise-bills-coaches-discuss-handling-rising-e',
+        'info_dict': {
+            'id': 'the-only-thing-we-ve-earned-is-the-noise-bills-coaches-discuss-handling-rising-e',
+            'title': "'The only thing we've earned is the noise' | Bills coaches discuss handling rising expectations",
+        },
+        'playlist_count': 4,
+    }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id, host = mobj.group('id'), mobj.group('host')
-
-        webpage = self._download_webpage(url, video_id)
-
-        config_url = NFLIE.prepend_host(host, self._search_regex(
-            r'(?:(?:config|configURL)\s*:\s*|<nflcs:avplayer[^>]+data-config\s*=\s*)(["\'])(?P<config>.+?)\1',
-            webpage, 'config URL', default='static/content/static/config/video/config.json',
-            group='config'))
-        # For articles, the id in the url is not the video id
-        video_id = self._search_regex(
-            r'(?:<nflcs:avplayer[^>]+data-content[Ii]d\s*=\s*|content[Ii]d\s*:\s*)(["\'])(?P<id>(?:(?!\1).)+)\1',
-            webpage, 'video id', default=video_id, group='id')
-        config = self._download_json(config_url, video_id, 'Downloading player config')
-        url_template = NFLIE.prepend_host(
-            host, '{contentURLTemplate:}'.format(**config))
-        video_data = self._download_json(
-            url_template.format(id=video_id), video_id)
-
-        formats = []
-        cdn_data = video_data.get('cdnData', {})
-        streams = cdn_data.get('bitrateInfo', [])
-        if cdn_data.get('format') == 'EXTERNAL_HTTP_STREAM':
-            parts = compat_urllib_parse_urlparse(cdn_data.get('uri'))
-            protocol, host = parts.scheme, parts.netloc
-            for stream in streams:
-                formats.append(
-                    NFLIE.format_from_stream(stream, protocol, host))
-        else:
-            cdns = config.get('cdns')
-            if not cdns:
-                raise ExtractorError('Failed to get CDN data', expected=True)
-
-            for name, cdn in cdns.items():
-                # LimeLight streams don't seem to work
-                if cdn.get('name') == 'LIMELIGHT':
-                    continue
-
-                protocol = cdn.get('protocol')
-                host = remove_end(cdn.get('host', ''), '/')
-                if not (protocol and host):
-                    continue
-
-                prefix = cdn.get('pathprefix', '')
-                if prefix and not prefix.endswith('/'):
-                    prefix = '%s/' % prefix
-
-                preference = 0
-                if protocol == 'rtmp':
-                    preference = -2
-                elif 'prog' in name.lower():
-                    preference = 1
-
-                for stream in streams:
-                    formats.append(
-                        NFLIE.format_from_stream(stream, protocol, host,
-                                                 prefix, preference, name))
-
-        self._sort_formats(formats)
-
-        thumbnail = None
-        for q in ('xl', 'l', 'm', 's', 'xs'):
-            thumbnail = video_data.get('imagePaths', {}).get(q)
-            if thumbnail:
-                break
-
-        return {
-            'id': video_id,
-            'title': video_data.get('headline'),
-            'formats': formats,
-            'description': video_data.get('caption'),
-            'duration': video_data.get('duration'),
-            'thumbnail': thumbnail,
-            'timestamp': int_or_none(video_data.get('posted'), 1000),
-        }
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        entries = []
+        for video_config in re.findall(self._VIDEO_CONFIG_REGEX, webpage):
+            entries.append(self._parse_video_config(video_config, display_id))
+        title = clean_html(get_element_by_class(
+            'nfl-c-article__title', webpage)) or self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage)
+        return self.playlist_result(entries, display_id, title)

youtube_dl/extractor/noco.py

@@ -1,235 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-import time
-import hashlib
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-    compat_urlparse,
-)
-from ..utils import (
-    clean_html,
-    ExtractorError,
-    int_or_none,
-    float_or_none,
-    parse_iso8601,
-    sanitized_Request,
-    urlencode_postdata,
-)
-
-
-class NocoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
-    _LOGIN_URL = 'https://noco.tv/do.php'
-    _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
-    _SUB_LANG_TEMPLATE = '&sub_lang=%s'
-    _NETRC_MACHINE = 'noco'
-
-    _TESTS = [
-        {
-            'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
-            'md5': '0a993f0058ddbcd902630b2047ef710e',
-            'info_dict': {
-                'id': '11538',
-                'ext': 'mp4',
-                'title': 'Ami Ami Idol - Hello! France',
-                'description': 'md5:4eaab46ab68fa4197a317a88a53d3b86',
-                'upload_date': '20140412',
-                'uploader': 'Nolife',
-                'uploader_id': 'NOL',
-                'duration': 2851.2,
-            },
-            'skip': 'Requires noco account',
-        },
-        {
-            'url': 'http://noco.tv/emission/12610/lbl42/the-guild/s01e01-wake-up-call',
-            'md5': 'c190f1f48e313c55838f1f412225934d',
-            'info_dict': {
-                'id': '12610',
-                'ext': 'mp4',
-                'title': 'The Guild #1 - Wake-Up Call',
-                'timestamp': 1403863200,
-                'upload_date': '20140627',
-                'uploader': 'LBL42',
-                'uploader_id': 'LBL',
-                'duration': 233.023,
-            },
-            'skip': 'Requires noco account',
-        }
-    ]
-
-    def _real_initialize(self):
-        self._login()
-
-    def _login(self):
-        username, password = self._get_login_info()
-        if username is None:
-            return
-
-        login = self._download_json(
-            self._LOGIN_URL, None, 'Logging in',
-            data=urlencode_postdata({
-                'a': 'login',
-                'cookie': '1',
-                'username': username,
-                'password': password,
-            }),
-            headers={
-                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
-            })
-
-        if 'erreur' in login:
-            raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
-
-    @staticmethod
-    def _ts():
-        return int(time.time() * 1000)
-
-    def _call_api(self, path, video_id, note, sub_lang=None):
-        ts = compat_str(self._ts() + self._ts_offset)
-        tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest()
-        url = self._API_URL_TEMPLATE % (path, ts, tk)
-        if sub_lang:
-            url += self._SUB_LANG_TEMPLATE % sub_lang
-
-        request = sanitized_Request(url)
-        request.add_header('Referer', self._referer)
-
-        resp = self._download_json(request, video_id, note)
-
-        if isinstance(resp, dict) and resp.get('error'):
-            self._raise_error(resp['error'], resp['description'])
-
-        return resp
-
-    def _raise_error(self, error, description):
-        raise ExtractorError(
-            '%s returned error: %s - %s' % (self.IE_NAME, error, description),
-            expected=True)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        # Timestamp adjustment offset between server time and local time
-        # must be calculated in order to use timestamps closest to server's
-        # in all API requests (see https://github.com/ytdl-org/youtube-dl/issues/7864)
-        webpage = self._download_webpage(url, video_id)
-
-        player_url = self._search_regex(
-            r'(["\'])(?P<player>https?://noco\.tv/(?:[^/]+/)+NocoPlayer.+?\.swf.*?)\1',
-            webpage, 'noco player', group='player',
-            default='http://noco.tv/cdata/js/player/NocoPlayer-v1.2.40.swf')
-
-        qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query)
-        ts = int_or_none(qs.get('ts', [None])[0])
-        self._ts_offset = ts - self._ts() if ts else 0
-        self._referer = player_url
-
-        medias = self._call_api(
-            'shows/%s/medias' % video_id,
-            video_id, 'Downloading video JSON')
-
-        show = self._call_api(
-            'shows/by_id/%s' % video_id,
-            video_id, 'Downloading show JSON')[0]
-
-        options = self._call_api(
-            'users/init', video_id,
-            'Downloading user options JSON')['options']
-        audio_lang_pref = options.get('audio_language') or options.get('language', 'fr')
-
-        if audio_lang_pref == 'original':
-            audio_lang_pref = show['original_lang']
-        if len(medias) == 1:
-            audio_lang_pref = list(medias.keys())[0]
-        elif audio_lang_pref not in medias:
-            audio_lang_pref = 'fr'
-
-        qualities = self._call_api(
-            'qualities',
-            video_id, 'Downloading qualities JSON')
-
-        formats = []
-
-        for audio_lang, audio_lang_dict in medias.items():
-            preference = 1 if audio_lang == audio_lang_pref else 0
-            for sub_lang, lang_dict in audio_lang_dict['video_list'].items():
-                for format_id, fmt in lang_dict['quality_list'].items():
-                    format_id_extended = 'audio-%s_sub-%s_%s' % (audio_lang, sub_lang, format_id)
-
-                    video = self._call_api(
-                        'shows/%s/video/%s/%s' % (video_id, format_id.lower(), audio_lang),
-                        video_id, 'Downloading %s video JSON' % format_id_extended,
-                        sub_lang if sub_lang != 'none' else None)
-
-                    file_url = video['file']
-                    if not file_url:
-                        continue
-
-                    if file_url in ['forbidden', 'not found']:
-                        popmessage = video['popmessage']
-                        self._raise_error(popmessage['title'], popmessage['message'])
-
-                    formats.append({
-                        'url': file_url,
-                        'format_id': format_id_extended,
-                        'width': int_or_none(fmt.get('res_width')),
-                        'height': int_or_none(fmt.get('res_lines')),
-                        'abr': int_or_none(fmt.get('audiobitrate'), 1000),
-                        'vbr': int_or_none(fmt.get('videobitrate'), 1000),
-                        'filesize': int_or_none(fmt.get('filesize')),
-                        'format_note': qualities[format_id].get('quality_name'),
-                        'quality': qualities[format_id].get('priority'),
-                        'preference': preference,
-                    })
-
-        self._sort_formats(formats)
-
-        timestamp = parse_iso8601(show.get('online_date_start_utc'), ' ')
-
-        if timestamp is not None and timestamp < 0:
-            timestamp = None
-
-        uploader = show.get('partner_name')
-        uploader_id = show.get('partner_key')
-        duration = float_or_none(show.get('duration_ms'), 1000)
-
-        thumbnails = []
-        for thumbnail_key, thumbnail_url in show.items():
-            m = re.search(r'^screenshot_(?P<width>\d+)x(?P<height>\d+)$', thumbnail_key)
-            if not m:
-                continue
-            thumbnails.append({
-                'url': thumbnail_url,
-                'width': int(m.group('width')),
-                'height': int(m.group('height')),
-            })
-
-        episode = show.get('show_TT') or show.get('show_OT')
-        family = show.get('family_TT') or show.get('family_OT')
-        episode_number = show.get('episode_number')
-
-        title = ''
-        if family:
-            title += family
-        if episode_number:
-            title += ' #' + compat_str(episode_number)
-        if episode:
-            title += ' - ' + compat_str(episode)
-
-        description = show.get('show_resume') or show.get('family_resume')
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnails': thumbnails,
-            'timestamp': timestamp,
-            'uploader': uploader,
-            'uploader_id': uploader_id,
-            'duration': duration,
-            'formats': formats,
-        }