[fox] add support National Geographic(closes #17985)(closes #15333)(closes #14698)

youtube_dl/extractor/extractors.py

@@ -687,11 +687,7 @@
     MyviEmbedIE,
 )
 from .myvidster import MyVidsterIE
-from .nationalgeographic import (
+from .nationalgeographic import NationalGeographicVideoIE
-    NationalGeographicVideoIE,
-    NationalGeographicIE,
-    NationalGeographicEpisodeGuideIE,
-)
 from .naver import NaverIE
 from .nba import NBAIE
 from .nbc import (

youtube_dl/extractor/fox.py

@@ -1,11 +1,11 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+# import json
+# import uuid
+
 from .adobepass import AdobePassIE
-from .uplynk import UplynkPreplayIE
-from ..compat import compat_str
 from ..utils import (
-    HEADRequest,
     int_or_none,
     parse_age_limit,
     parse_duration,
@@ -16,7 +16,7 @@
 
 
 class FOXIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?fox\.com/watch/(?P<id>[\da-fA-F]+)'
+    _VALID_URL = r'https?://(?:www\.)?(?:fox\.com|nationalgeographic\.com/tv)/watch/(?P<id>[\da-fA-F]+)'
     _TESTS = [{
         # clip
         'url': 'https://www.fox.com/watch/4b765a60490325103ea69888fb2bd4e8/',
@@ -43,41 +43,47 @@ class FOXIE(AdobePassIE):
         # episode, geo-restricted, tv provided required
         'url': 'https://www.fox.com/watch/30056b295fb57f7452aeeb4920bc3024/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.nationalgeographic.com/tv/watch/f690e05ebbe23ab79747becd0cc223d1/',
+        'only_matching': True,
     }]
+    # _access_token = None
+
+    # def _call_api(self, path, video_id, data=None):
+    #     headers = {
+    #         'X-Api-Key': '238bb0a0c2aba67922c48709ce0c06fd',
+    #     }
+    #     if self._access_token:
+    #         headers['Authorization'] = 'Bearer ' + self._access_token
+    #     return self._download_json(
+    #         'https://api2.fox.com/v2.0/' + path, video_id, data=data, headers=headers)
+
+    # def _real_initialize(self):
+    #     self._access_token = self._call_api(
+    #         'login', None, json.dumps({
+    #             'deviceId': compat_str(uuid.uuid4()),
+    #         }).encode())['accessToken']
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         video = self._download_json(
-            'https://api.fox.com/fbc-content/v1_4/video/%s' % video_id,
+            'https://api.fox.com/fbc-content/v1_5/video/%s' % video_id,
             video_id, headers={
                 'apikey': 'abdcbed02c124d393b39e818a4312055',
                 'Content-Type': 'application/json',
                 'Referer': url,
             })
+        # video = self._call_api('vodplayer/' + video_id, video_id)
 
         title = video['name']
         release_url = video['videoRelease']['url']
-
+        # release_url = video['url']
-        description = video.get('description')
-        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
-            video.get('duration')) or parse_duration(video.get('duration'))
-        timestamp = unified_timestamp(video.get('datePublished'))
-        rating = video.get('contentRating')
-        age_limit = parse_age_limit(rating)
 
         data = try_get(
             video, lambda x: x['trackingData']['properties'], dict) or {}
 
-        creator = data.get('brand') or data.get('network') or video.get('network')
+        rating = video.get('contentRating')
-
-        series = video.get('seriesName') or data.get(
-            'seriesName') or data.get('show')
-        season_number = int_or_none(video.get('seasonNumber'))
-        episode = video.get('name')
-        episode_number = int_or_none(video.get('episodeNumber'))
-        release_year = int_or_none(video.get('releaseYear'))
-
         if data.get('authRequired'):
             resource = self._get_mvpd_resource(
                 'fbc-fox', title, video.get('guid'), rating)
@@ -86,6 +92,18 @@ def _real_extract(self, url):
                     'auth': self._extract_mvpd_auth(
                         url, video_id, 'fbc-fox', resource)
                 })
+        m3u8_url = self._download_json(release_url, video_id)['playURL']
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, 'mp4',
+            entry_protocol='m3u8_native', m3u8_id='hls')
+        self._sort_formats(formats)
+
+        duration = int_or_none(video.get('durationInSeconds')) or int_or_none(
+            video.get('duration')) or parse_duration(video.get('duration'))
+        timestamp = unified_timestamp(video.get('datePublished'))
+        creator = data.get('brand') or data.get('network') or video.get('network')
+        series = video.get('seriesName') or data.get(
+            'seriesName') or data.get('show')
 
         subtitles = {}
         for doc_rel in video.get('documentReleases', []):
@@ -98,36 +116,19 @@ def _real_extract(self, url):
             }]
             break
 
-        info = {
+        return {
             'id': video_id,
             'title': title,
-            'description': description,
+            'formats': formats,
+            'description': video.get('description'),
             'duration': duration,
             'timestamp': timestamp,
-            'age_limit': age_limit,
+            'age_limit': parse_age_limit(rating),
             'creator': creator,
             'series': series,
-            'season_number': season_number,
+            'season_number': int_or_none(video.get('seasonNumber')),
-            'episode': episode,
+            'episode': video.get('name'),
-            'episode_number': episode_number,
+            'episode_number': int_or_none(video.get('episodeNumber')),
-            'release_year': release_year,
+            'release_year': int_or_none(video.get('releaseYear')),
             'subtitles': subtitles,
         }
-
-        urlh = self._request_webpage(HEADRequest(release_url), video_id)
-        video_url = compat_str(urlh.geturl())
-
-        if UplynkPreplayIE.suitable(video_url):
-            info.update({
-                '_type': 'url_transparent',
-                'url': video_url,
-                'ie_key': UplynkPreplayIE.ie_key(),
-            })
-        else:
-            m3u8_url = self._download_json(release_url, video_id)['playURL']
-            formats = self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4',
-                entry_protocol='m3u8_native', m3u8_id='hls')
-            self._sort_formats(formats)
-            info['formats'] = formats
-        return info

youtube_dl/extractor/nationalgeographic.py

@@ -1,15 +1,9 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
-from .adobepass import AdobePassIE
-from .theplatform import ThePlatformIE
 from ..utils import (
     smuggle_url,
     url_basename,
-    update_url_query,
-    get_element_by_class,
 )
 
 
@@ -64,132 +58,3 @@ def _real_extract(self, url):
                 {'force_smil_url': True}),
             'id': guid,
         }
-
-
-class NationalGeographicIE(ThePlatformIE, AdobePassIE):
-    IE_NAME = 'natgeo'
-    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:(?:(?:wild/)?[^/]+/)?(?:videos|episodes)|u)/(?P<id>[^/?]+)'
-
-    _TESTS = [
-        {
-            'url': 'http://channel.nationalgeographic.com/u/kdi9Ld0PN2molUUIMSBGxoeDhD729KRjQcnxtetilWPMevo8ZwUBIDuPR0Q3D2LVaTsk0MPRkRWDB8ZhqWVeyoxfsZZm36yRp1j-zPfsHEyI_EgAeFY/',
-            'md5': '518c9aa655686cf81493af5cc21e2a04',
-            'info_dict': {
-                'id': 'vKInpacll2pC',
-                'ext': 'mp4',
-                'title': 'Uncovering a Universal Knowledge',
-                'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
-                'timestamp': 1458680907,
-                'upload_date': '20160322',
-                'uploader': 'NEWA-FNG-NGTV',
-            },
-            'add_ie': ['ThePlatform'],
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/u/kdvOstqYaBY-vSBPyYgAZRUL4sWUJ5XUUPEhc7ISyBHqoIO4_dzfY3K6EjHIC0hmFXoQ7Cpzm6RkET7S3oMlm6CFnrQwSUwo/',
-            'md5': 'c4912f656b4cbe58f3e000c489360989',
-            'info_dict': {
-                'id': 'Pok5lWCkiEFA',
-                'ext': 'mp4',
-                'title': 'The Stunning Red Bird of Paradise',
-                'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
-                'timestamp': 1459362152,
-                'upload_date': '20160330',
-                'uploader': 'NEWA-FNG-NGTV',
-            },
-            'add_ie': ['ThePlatform'],
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/videos/treasures-rediscovered/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
-            'only_matching': True,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
-            'only_matching': True,
-        }
-    ]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        release_url = self._search_regex(
-            r'video_auth_playlist_url\s*=\s*"([^"]+)"',
-            webpage, 'release url')
-        theplatform_path = self._search_regex(r'https?://link\.theplatform\.com/s/([^?]+)', release_url, 'theplatform path')
-        video_id = theplatform_path.split('/')[-1]
-        query = {
-            'mbr': 'true',
-        }
-        is_auth = self._search_regex(r'video_is_auth\s*=\s*"([^"]+)"', webpage, 'is auth', fatal=False)
-        if is_auth == 'auth':
-            auth_resource_id = self._search_regex(
-                r"video_auth_resourceId\s*=\s*'([^']+)'",
-                webpage, 'auth resource id')
-            query['auth'] = self._extract_mvpd_auth(url, video_id, 'natgeo', auth_resource_id)
-
-        formats = []
-        subtitles = {}
-        for key, value in (('switch', 'http'), ('manifest', 'm3u')):
-            tp_query = query.copy()
-            tp_query.update({
-                key: value,
-            })
-            tp_formats, tp_subtitles = self._extract_theplatform_smil(
-                update_url_query(release_url, tp_query), video_id, 'Downloading %s SMIL data' % value)
-            formats.extend(tp_formats)
-            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        self._sort_formats(formats)
-
-        info = self._extract_theplatform_metadata(theplatform_path, display_id)
-        info.update({
-            'id': video_id,
-            'formats': formats,
-            'subtitles': subtitles,
-            'display_id': display_id,
-        })
-        return info
-
-
-class NationalGeographicEpisodeGuideIE(InfoExtractor):
-    IE_NAME = 'natgeo:episodeguide'
-    _VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
-    _TESTS = [
-        {
-            'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/',
-            'info_dict': {
-                'id': 'the-story-of-god-with-morgan-freeman-season-1',
-                'title': 'The Story of God with Morgan Freeman - Season 1',
-            },
-            'playlist_mincount': 6,
-        },
-        {
-            'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2',
-            'info_dict': {
-                'id': 'underworld-inc-season-2',
-                'title': 'Underworld, Inc. - Season 2',
-            },
-            'playlist_mincount': 7,
-        },
-    ]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-        show = get_element_by_class('show', webpage)
-        selected_season = self._search_regex(
-            r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>',
-            webpage, 'selected season')
-        entries = [
-            self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic')
-            for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)]
-        return self.playlist_result(
-            entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')),
-            '%s - %s' % (show, selected_season))