Merge remote-tracking branch 'upstream/master' into porntrex

youtube_dl/extractor/aenetworks.py

@@ -1,14 +1,15 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .theplatform import ThePlatformIE
 from ..utils import (
+    extract_attributes,
+    ExtractorError,
+    int_or_none,
     smuggle_url,
     update_url_query,
-    unescapeHTML,
-    extract_attributes,
-    get_element_by_attribute,
 )
 from ..compat import (
     compat_urlparse,
@@ -19,6 +20,43 @@ class AENetworksBaseIE(ThePlatformIE):
     _THEPLATFORM_KEY = 'crazyjava'
     _THEPLATFORM_SECRET = 's3cr3t'
 
+    def _extract_aen_smil(self, smil_url, video_id, auth=None):
+        query = {'mbr': 'true'}
+        if auth:
+            query['auth'] = auth
+        TP_SMIL_QUERY = [{
+            'assetTypes': 'high_video_ak',
+            'switch': 'hls_high_ak'
+        }, {
+            'assetTypes': 'high_video_s3'
+        }, {
+            'assetTypes': 'high_video_s3',
+            'switch': 'hls_ingest_fastly'
+        }]
+        formats = []
+        subtitles = {}
+        last_e = None
+        for q in TP_SMIL_QUERY:
+            q.update(query)
+            m_url = update_url_query(smil_url, q)
+            m_url = self._sign_url(m_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
+            try:
+                tp_formats, tp_subtitles = self._extract_theplatform_smil(
+                    m_url, video_id, 'Downloading %s SMIL data' % (q.get('switch') or q['assetTypes']))
+            except ExtractorError as e:
+                last_e = e
+                continue
+            formats.extend(tp_formats)
+            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
+        if last_e and not formats:
+            raise last_e
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
 
 class AENetworksIE(AENetworksBaseIE):
     IE_NAME = 'aenetworks'
@@ -33,22 +71,25 @@ class AENetworksIE(AENetworksBaseIE):
                         (?:
                             shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
                             movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
-                            specials/(?P<special_display_id>[^/]+)/full-special|
+                            specials/(?P<special_display_id>[^/]+)/(?:full-special|preview-)|
                             collections/[^/]+/(?P<collection_display_id>[^/]+)
                         )
                     '''
     _TESTS = [{
         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
-        'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
         'info_dict': {
             'id': '22253814',
             'ext': 'mp4',
-            'title': 'Winter Is Coming',
+            'title': 'Winter is Coming',
             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
             'timestamp': 1338306241,
             'upload_date': '20120529',
             'uploader': 'AENE-NEW',
         },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
         'add_ie': ['ThePlatform'],
     }, {
         'url': 'http://www.history.com/shows/ancient-aliens/season-1',
@@ -84,6 +125,9 @@ class AENetworksIE(AENetworksBaseIE):
     }, {
         'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
         'only_matching': True
+    }, {
+        'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
+        'only_matching': True
     }]
     _DOMAIN_TO_REQUESTOR_ID = {
         'history.com': 'HISTORY',
@@ -124,11 +168,6 @@ class AENetworksIE(AENetworksBaseIE):
                 return self.playlist_result(
                     entries, self._html_search_meta('aetn:SeasonId', webpage))
 
-        query = {
-            'mbr': 'true',
-            'assetTypes': 'high_video_ak',
-            'switch': 'hls_high_ak',
-        }
         video_id = self._html_search_meta('aetn:VideoID', webpage)
         media_url = self._search_regex(
             [r"media_url\s*=\s*'(?P<url>[^']+)'",
@@ -138,64 +177,39 @@ class AENetworksIE(AENetworksBaseIE):
         theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
             r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
         info = self._parse_theplatform_metadata(theplatform_metadata)
+        auth = None
         if theplatform_metadata.get('AETN$isBehindWall'):
             requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
             resource = self._get_mvpd_resource(
                 requestor_id, theplatform_metadata['title'],
                 theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
                 theplatform_metadata['ratings'][0]['rating'])
-            query['auth'] = self._extract_mvpd_auth(
+            auth = self._extract_mvpd_auth(
                 url, video_id, requestor_id, resource)
         info.update(self._search_json_ld(webpage, video_id, fatal=False))
-        media_url = update_url_query(media_url, query)
-        media_url = self._sign_url(media_url, self._THEPLATFORM_KEY, self._THEPLATFORM_SECRET)
-        formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
-        self._sort_formats(formats)
-        info.update({
-            'id': video_id,
-            'formats': formats,
-            'subtitles': subtitles,
-        })
+        info.update(self._extract_aen_smil(media_url, video_id, auth))
         return info
 
 
 class HistoryTopicIE(AENetworksBaseIE):
     IE_NAME = 'history:topic'
     IE_DESC = 'History.com Topic'
-    _VALID_URL = r'https?://(?:www\.)?history\.com/topics/(?:[^/]+/)?(?P<topic_id>[^/]+)(?:/[^/]+(?:/(?P<video_display_id>[^/?#]+))?)?'
+    _VALID_URL = r'https?://(?:www\.)?history\.com/topics/[^/]+/(?P<id>[\w+-]+?)-video'
     _TESTS = [{
-        'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
+        'url': 'https://www.history.com/topics/valentines-day/history-of-valentines-day-video',
         'info_dict': {
             'id': '40700995724',
             'ext': 'mp4',
-            'title': "Bet You Didn't Know: Valentine's Day",
+            'title': "History of Valentine’s Day",
             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
             'timestamp': 1375819729,
             'upload_date': '20130806',
-            'uploader': 'AENE-NEW',
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
         'add_ie': ['ThePlatform'],
-    }, {
-        'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/videos',
-        'info_dict':
-        {
-            'id': 'world-war-i-history',
-            'title': 'World War I History',
-        },
-        'playlist_mincount': 23,
-    }, {
-        'url': 'http://www.history.com/topics/world-war-i-history/videos',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.history.com/topics/world-war-i/world-war-i-history',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.history.com/topics/world-war-i/world-war-i-history/speeches',
-        'only_matching': True,
     }]
 
     def theplatform_url_result(self, theplatform_url, video_id, query):
@@ -215,27 +229,19 @@ class HistoryTopicIE(AENetworksBaseIE):
         }
 
     def _real_extract(self, url):
-        topic_id, video_display_id = re.match(self._VALID_URL, url).groups()
-        if video_display_id:
-            webpage = self._download_webpage(url, video_display_id)
-            release_url, video_id = re.search(r"_videoPlayer.play\('([^']+)'\s*,\s*'[^']+'\s*,\s*'(\d+)'\)", webpage).groups()
-            release_url = unescapeHTML(release_url)
-
-            return self.theplatform_url_result(
-                release_url, video_id, {
-                    'mbr': 'true',
-                    'switch': 'hls',
-                    'assetTypes': 'high_video_ak',
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        video_id = self._search_regex(
+            r'<phoenix-iframe[^>]+src="[^"]+\btpid=(\d+)', webpage, 'tpid')
+        result = self._download_json(
+            'https://feeds.video.aetnd.com/api/v2/history/videos',
+            video_id, query={'filter[id]': video_id})['results'][0]
+        title = result['title']
+        info = self._extract_aen_smil(result['publicUrl'], video_id)
+        info.update({
+            'title': title,
+            'description': result.get('description'),
+            'duration': int_or_none(result.get('duration')),
+            'timestamp': int_or_none(result.get('added'), 1000),
         })
-        else:
-            webpage = self._download_webpage(url, topic_id)
-            entries = []
-            for episode_item in re.findall(r'<a.+?data-release-url="[^"]+"[^>]*>', webpage):
-                video_attributes = extract_attributes(episode_item)
-                entries.append(self.theplatform_url_result(
-                    video_attributes['data-release-url'], video_attributes['data-id'], {
-                        'mbr': 'true',
-                        'switch': 'hls',
-                        'assetTypes': 'high_video_ak',
-                    }))
-            return self.playlist_result(entries, topic_id, get_element_by_attribute('class', 'show-title', webpage))
+        return info

youtube_dl/extractor/aol.py

@@ -17,7 +17,7 @@ from ..utils import (
 
 class AolIE(InfoExtractor):
     IE_NAME = 'aol.com'
-    _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.com/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)'
+    _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)'
 
     _TESTS = [{
         # video with 5min ID
@@ -64,6 +64,18 @@ class AolIE(InfoExtractor):
     }, {
         'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.aol.ca/video/view/u-s-woman-s-family-arrested-for-murder-first-pinned-on-panhandler-police/5c7ccf45bc03931fa04b2fe1/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.aol.co.uk/video/view/-one-dead-and-22-hurt-in-bus-crash-/5cb3a6f3d21f1a072b457347/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.aol.de/video/view/eva-braun-privataufnahmen-von-hitlers-geliebter-werden-digitalisiert/5cb2d49de98ab54c113d3d5d/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

youtube_dl/extractor/extractors.py

@@ -1456,6 +1456,8 @@ from .xxxymovies import XXXYMoviesIE
 from .yahoo import (
     YahooIE,
     YahooSearchIE,
+    YahooGyaOPlayerIE,
+    YahooGyaOIE,
 )
 from .yandexdisk import YandexDiskIE
 from .yandexmusic import (

youtube_dl/extractor/yahoo.py

@@ -477,3 +477,77 @@ class YahooSearchIE(SearchInfoExtractor):
             'id': query,
             'entries': entries,
         }
+
+
+class YahooGyaOPlayerIE(InfoExtractor):
+    IE_NAME = 'yahoo:gyao:player'
+    _VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/(?:player|episode/[^/]+)|streaming\.yahoo\.co\.jp/c/y)/(?P<id>\d+/v\d+/v\d+|[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _TESTS = [{
+        'url': 'https://gyao.yahoo.co.jp/player/00998/v00818/v0000000000000008564/',
+        'info_dict': {
+            'id': '5993125228001',
+            'ext': 'mp4',
+            'title': 'フューリー　【字幕版】',
+            'description': 'md5:21e691c798a15330eda4db17a8fe45a5',
+            'uploader_id': '4235717419001',
+            'upload_date': '20190124',
+            'timestamp': 1548294365,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://streaming.yahoo.co.jp/c/y/01034/v00133/v0000000000000000706/',
+        'only_matching': True,
+    }, {
+        'url': 'https://gyao.yahoo.co.jp/episode/%E3%81%8D%E3%81%AE%E3%81%86%E4%BD%95%E9%A3%9F%E3%81%B9%E3%81%9F%EF%BC%9F%20%E7%AC%AC2%E8%A9%B1%202019%2F4%2F12%E6%94%BE%E9%80%81%E5%88%86/5cb02352-b725-409e-9f8d-88f947a9f682',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url).replace('/', ':')
+        video = self._download_json(
+            'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id,
+            video_id, query={
+                'fields': 'longDescription,title,videoId',
+            })
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'title': video['title'],
+            'url': smuggle_url(
+                'http://players.brightcove.net/4235717419001/default_default/index.html?videoId=' + video['videoId'],
+                {'geo_countries': ['JP']}),
+            'description': video.get('longDescription'),
+            'ie_key': BrightcoveNewIE.ie_key(),
+        }
+
+
+class YahooGyaOIE(InfoExtractor):
+    IE_NAME = 'yahoo:gyao'
+    _VALID_URL = r'https?://(?:gyao\.yahoo\.co\.jp/p|streaming\.yahoo\.co\.jp/p/y)/(?P<id>\d+/v\d+)'
+    _TESTS = [{
+        'url': 'https://gyao.yahoo.co.jp/p/00449/v03102/',
+        'info_dict': {
+            'id': '00449:v03102',
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'https://streaming.yahoo.co.jp/p/y/01034/v00133/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        program_id = self._match_id(url).replace('/', ':')
+        videos = self._download_json(
+            'https://gyao.yahoo.co.jp/api/programs/%s/videos' % program_id, program_id)['videos']
+        entries = []
+        for video in videos:
+            video_id = video.get('id')
+            if not video_id:
+                continue
+            entries.append(self.url_result(
+                'https://gyao.yahoo.co.jp/player/%s/' % video_id.replace(':', '/'),
+                YahooGyaOPlayerIE.ie_key(), video_id))
+        return self.playlist_result(entries, program_id)