From 1a1c9e3f7122c93da81977c79de3f510c4c8bfc2 Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Fri, 24 May 2019 18:01:49 +0900
Subject: [PATCH 1/9] Add Yahoo Japan News extractor.

---
 youtube_dl/extractor/extractors.py |   1 +
 youtube_dl/extractor/yahoo.py      | 286 +++++++++++++++++++++++++++++
 2 files changed, 287 insertions(+)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 15f54a214..06de556b7 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1448,6 +1448,7 @@ from .yahoo import (
     YahooSearchIE,
     YahooGyaOPlayerIE,
     YahooGyaOIE,
+    YahooJapanNewsIE,
 )
 from .yandexdisk import YandexDiskIE
 from .yandexmusic import (
diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index a3b5f00c8..4d6d04c5c 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -1,12 +1,14 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import hashlib
 import itertools
 import json
 import re
 
 from .common import InfoExtractor, SearchInfoExtractor
 from ..compat import (
+    compat_str,
     compat_urllib_parse,
     compat_urlparse,
 )
@@ -18,7 +20,9 @@ from ..utils import (
     int_or_none,
     mimetype2ext,
     smuggle_url,
+    try_get,
     unescapeHTML,
+    url_or_none,
 )
 
 from .brightcove import (
@@ -556,3 +560,285 @@ class YahooGyaOIE(InfoExtractor):
                 'https://gyao.yahoo.co.jp/player/%s/' % video_id.replace(':', '/'),
                 YahooGyaOPlayerIE.ie_key(), video_id))
         return self.playlist_result(entries, program_id)
+
+
+class YahooJapanNewsIE(InfoExtractor):
+    IE_NAME = 'yahoo:japannews'
+    IE_DESC = 'Yahoo! Japan News'
+    _VALID_URL = r'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)(/[^\d]*(?P<id>\d[\d-]*\d))?'
+    _TESTS = [
+        {
+            'url': 'https://headlines.yahoo.co.jp/videonews/nnn?a=20190531-00000180-nnn-int',
+            'info_dict': {
+                'id': '20190531-00000180',
+                'ext': 'mp4',
+                'title': '北“対米担当特別代表を銃殺”韓国紙報じる（日本テレビ系（NNN）） - Yahoo!ニュース',
+                'description': '韓国の主要紙である朝鮮日報は、２回目の米朝首脳会談が決裂した責任を問われ、北朝鮮 - Yahoo!ニュース(日本テレビ系（NNN）)',
+                'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
+            },
+            'params': {'skip_download': True},
+        },
+        {
+            'url': 'https://headlines.yahoo.co.jp/hl?a=20190529-00010015-houdoukvq-soci',
+            'info_dict': {
+                'id': '20190529-00010015',
+                'ext': 'mp4',
+                'title': '高校屋上から男子高校生 転落\u3000目撃 女子生徒パニックで搬送（FNN.jpプライムオンライン） - Yahoo!ニュース',
+                'description': '29日午後、宮崎市の高校の屋上から男子高校生が転落し、重傷となっている。29日午後2 - Yahoo!ニュース(FNN.jpプライムオンライン)',
+                'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
+            },
+            'params': {'skip_download': True},
+        },
+        {
+            'url': 'https://headlines.yahoo.co.jp/videonews/',
+            'info_dict': {
+                'id': 'headlines.yahoo.co.jp',
+                'ext': 'mp4',
+                'title': '映像ニュース - Yahoo!ニュース',
+                'description': 'テレビ局などが配信する映像ニュースを掲載。',
+            },
+            'params': {'skip_download': True},
+        },
+        {
+            'url': 'https://news.yahoo.co.jp',
+            'info_dict': {
+                'id': 'news.yahoo.co.jp',
+                'ext': 'mp4',
+                'title': 'Yahoo!ニュース',
+                'description': 'Yahoo!ニュースは、新聞・通信社が配信するニュースのほか、映像、雑誌や個人の書き手が執筆する記事など多種多様なニュースを掲載しています。',
+            },
+            'params': {'skip_download': True},
+        },
+        {
+            'url': 'https://news.yahoo.co.jp/byline/fujitatakanori/20190528-00127666/',
+            'only_matching': True,
+        },
+        {'url': 'https://news.yahoo.co.jp/pickup/6325141', 'only_matching': True},
+    ]
+    _USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
+    _ORIGIN = 'https://s.yimg.jp'
+
+    def _extract_formats(self, json_data, content_id):
+        formats = []
+
+        video_data = try_get(
+            json_data,
+            lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
+            list,
+        )
+        if video_data:
+            # Article page
+            for vid in video_data:
+                delivery = vid.get('delivery')
+                url = url_or_none(vid.get('Url'))
+                if not delivery or not url:
+                    continue
+                elif delivery == 'hls':
+                    formats.extend(
+                        self._extract_m3u8_formats(
+                            url,
+                            content_id,
+                            'mp4',
+                            entry_protocol='m3u8_native',
+                            m3u8_id='hls',
+                            fatal=False,
+                        )
+                    )
+                elif delivery == 'progressive':
+                    formats.append(
+                        {
+                            'url': url,
+                            'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')),
+                            'ext': determine_ext(url),
+                            'height': int_or_none(vid.get('height')),
+                            'width': int_or_none(vid.get('width')),
+                            'btr': int_or_none(vid.get('bitrate')),
+                        }
+                    )
+        else:
+            # Headline page with multiple videos
+            for vid in json_data.get('videos', []):
+                for src in vid.get('sources', []):
+                    url = url_or_none(src.get('src'))
+                    ext = determine_ext(url)
+                    if not url:
+                        continue
+                    if ext == 'm3u8':
+                        formats.extend(
+                            self._extract_m3u8_formats(
+                                url,
+                                content_id,
+                                'mp4',
+                                entry_protocol='m3u8_native',
+                                m3u8_id='hls',
+                                fatal=False,
+                            )
+                        )
+                    else:
+                        formats.append({'url': url, 'ext': ext})
+
+        self._remove_duplicate_formats(formats)
+        self._sort_formats(formats)
+
+        return formats
+
+    @staticmethod
+    def _get_md5(s):
+        return hashlib.md5(s.encode()).hexdigest()
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        # Headline page without `displayid` defaults to `host`.
+        display_id = mobj.group('id') or host
+        webpage = self._download_webpage(url, display_id)
+
+        title = (
+            self._og_search_title(webpage, default=None)
+            or self._html_search_meta('twitter:title', webpage, default=None)
+            or self._html_search_regex('<title>([^<]+)</title>', webpage, 'title')
+        )
+        description = (
+            self._og_search_description(webpage, default=None)
+            or self._html_search_meta('description', webpage, default=None)
+            or self._html_search_meta('twitter:description', webpage, default=None)
+        )
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None
+        ) or self._html_search_meta('twitter:image', webpage, default=None)
+
+        if display_id == host:
+            # Headline page with playlist of videos
+            formats = []
+
+            # No single useful `contentid` on page
+            content_id = display_id
+
+            stream_urls_plists = re.findall(
+                r'YJNEWS\.LIVESTREAM\.SRC.+=(?:\s+)?["\'](?P<streamurl>[^"\']+plist=(?P<plist>\d+)[^"\']+)',
+                webpage,
+            )
+            if not stream_urls_plists:
+                # Manually build stream urls ('news.yahoo.co.jp', ...)
+                sbase_url = 'https://s.yimg.jp/images/media/video/player/html/embed_1.2.5.html?service=news&service_type=video&plist=%s&poster=%s&sp=%s&country=JP'
+
+                params = re.findall(
+                    r'["\']plist["\']:\s*["\'](?P<plist>[^"\']+)[^;]+?["\']poster["\']:\s*["\'](?P<poster>[^"\']+)[^;]+?["\']spaceId["\']:\s*["\'](?P<spaceid>[^"\']+)',
+                    webpage,
+                )
+                for p in params:
+                    stream_urls_plists.append((sbase_url % p, p[0]))
+
+            for url, plist_id in stream_urls_plists:
+                embed_page = self._download_webpage(
+                    'https://s.yimg.jp/images/media/video/player/js/embed_1.0.9.min.js',
+                    plist_id,
+                    headers={
+                        'Authority': 's.yimg.jp',
+                        'Path': '/images/media/video/player/js/embed_1.0.9.min.js',
+                        'Referer': url,
+                        'User-Agent': self._USER_AGENT,
+                    },
+                )
+                account = self._search_regex(
+                    r'\w+\.video_attr\[(["\'])data-account\1\]\s*=\s*\1(?P<accountid>[\d]+)',
+                    embed_page,
+                    'account id',
+                    group='accountid',
+                )
+                player = self._search_regex(
+                    r'\w+\.video_attr\[(["\'])data-player\1\]\s*=\s*\1(?P<playerid>[^"\']+)',
+                    embed_page,
+                    'player id',
+                    group='playerid',
+                )
+                embed = self._search_regex(
+                    r'(["\'])data-embed\1\s*:\s*\1(?P<embed>[^"\']+)',
+                    embed_page,
+                    'embed',
+                    group='embed',
+                )
+                indexjs_page = self._download_webpage(
+                    'https://players.brightcove.net/%s/%s_%s/index.min.js'
+                    % (account, player, embed),
+                    plist_id,
+                    headers={'Referer': url, 'User-Agent': self._USER_AGENT},
+                )
+                policy_key = self._search_regex(
+                    r'policyKey:\s*["\']([^"\']+)', indexjs_page, 'policy key'
+                )
+
+                json_data = self._download_json(
+                    'https://edge.api.brightcove.com/playback/v1/accounts/%s/playlists/%s'
+                    % (account, plist_id),
+                    plist_id,
+                    headers={
+                        'Accept': 'application/json;pk=%s' % policy_key,
+                        'Origin': self._ORIGIN,
+                        'Referer': url,
+                        'User-Agent': self._USER_AGENT,
+                    },
+                    fatal=False,
+                )
+
+                formats.extend(self._extract_formats(json_data, content_id))
+
+        else:
+            # Article page
+            app_id = 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-'
+            space_id = (
+                self._search_regex(
+                    r'<script[^>]+class=(["\'])yvpub-player\1[^>]+spaceid=(?P<spaceid>[^&"\']+)',
+                    webpage,
+                    'spaceid',
+                    group='spaceid',
+                    default=None,
+                )
+                or self._search_regex(
+                    r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
+                    webpage,
+                    'spaceid',
+                    default=None,
+                )
+                or self._search_regex(r'<!--\s+SpaceID=(\d+)', webpage, 'spaceid')
+            )
+            content_id = self._search_regex(
+                r'<script[^>]+class=(["\'])yvpub-player\1[^>]+contentid=(?P<contentid>[^&"\']+)',
+                webpage,
+                'contentid',
+                group='contentid',
+                default=space_id,
+            )
+            # md5 hash of space_id + '_headlines.yahoo.co.jp'
+            ak = YahooJapanNewsIE._get_md5('_'.join((space_id, host)))
+
+            json_data = self._download_json(
+                'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
+                content_id,
+                headers={
+                    'Accept': 'application/json, text/javascript, */*; q=0.01',
+                    'Origin': self._ORIGIN,
+                    'Host': 'feapi-yvpub.yahooapis.jp',
+                    'User-Agent': self._USER_AGENT,
+                    'Referer': 'https://s.yimg.jp/images/yvpub/player/vamos/pc/latest/player.html',
+                },
+                query={
+                    'appid': app_id,
+                    'output': 'json',
+                    'space_id': space_id,
+                    'domain': host,
+                    'ak': ak,
+                    'device_type': '1100',
+                },
+                fatal=False,
+            )
+
+            formats = self._extract_formats(json_data, content_id)
+
+        return {
+            'id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }

From 466f151a76408c2e58a60ce57257f256b9492c17 Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Sat, 8 Jun 2019 04:30:49 +0900
Subject: [PATCH 2/9] Make requested changes.

---
 youtube_dl/extractor/yahoo.py | 205 ++++++++++------------------------
 1 file changed, 59 insertions(+), 146 deletions(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 4d6d04c5c..881841f9e 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -568,55 +568,34 @@ class YahooJapanNewsIE(InfoExtractor):
     _VALID_URL = r'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)(/[^\d]*(?P<id>\d[\d-]*\d))?'
     _TESTS = [
         {
-            'url': 'https://headlines.yahoo.co.jp/videonews/nnn?a=20190531-00000180-nnn-int',
+            'url': 'https://headlines.yahoo.co.jp/videonews/fnn?a=20190719-00421051-fnn-soci',
             'info_dict': {
-                'id': '20190531-00000180',
+                'id': '20190719-00421051',
                 'ext': 'mp4',
-                'title': '北“対米担当特別代表を銃殺”韓国紙報じる（日本テレビ系（NNN）） - Yahoo!ニュース',
-                'description': '韓国の主要紙である朝鮮日報は、２回目の米朝首脳会談が決裂した責任を問われ、北朝鮮 - Yahoo!ニュース(日本テレビ系（NNN）)',
-                'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
-            },
-            'params': {'skip_download': True},
-        },
-        {
-            'url': 'https://headlines.yahoo.co.jp/hl?a=20190529-00010015-houdoukvq-soci',
-            'info_dict': {
-                'id': '20190529-00010015',
-                'ext': 'mp4',
-                'title': '高校屋上から男子高校生 転落\u3000目撃 女子生徒パニックで搬送（FNN.jpプライムオンライン） - Yahoo!ニュース',
-                'description': '29日午後、宮崎市の高校の屋上から男子高校生が転落し、重傷となっている。29日午後2 - Yahoo!ニュース(FNN.jpプライムオンライン)',
+                'title': '15階から2歳女児転落死\u3000母は台所「目を離した隙に」（フジテレビ系（FNN）） - Yahoo!ニュース',
+                'description': '大阪市で18日夜、マンションの15階から2歳の女の子が転落し病院に運ばれたが、まもな - Yahoo!ニュース(フジテレビ系（FNN）)',
                 'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
             },
             'params': {'skip_download': True},
         },
         {
             'url': 'https://headlines.yahoo.co.jp/videonews/',
-            'info_dict': {
-                'id': 'headlines.yahoo.co.jp',
-                'ext': 'mp4',
-                'title': '映像ニュース - Yahoo!ニュース',
-                'description': 'テレビ局などが配信する映像ニュースを掲載。',
-            },
-            'params': {'skip_download': True},
+            'only_matching': True,
         },
         {
             'url': 'https://news.yahoo.co.jp',
-            'info_dict': {
-                'id': 'news.yahoo.co.jp',
-                'ext': 'mp4',
-                'title': 'Yahoo!ニュース',
-                'description': 'Yahoo!ニュースは、新聞・通信社が配信するニュースのほか、映像、雑誌や個人の書き手が執筆する記事など多種多様なニュースを掲載しています。',
-            },
-            'params': {'skip_download': True},
-        },
-        {
-            'url': 'https://news.yahoo.co.jp/byline/fujitatakanori/20190528-00127666/',
             'only_matching': True,
         },
-        {'url': 'https://news.yahoo.co.jp/pickup/6325141', 'only_matching': True},
+        {
+            'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://news.yahoo.co.jp/feature/1356',
+            'only_matching': True
+        },
     ]
     _USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
-    _ORIGIN = 'https://s.yimg.jp'
 
     def _extract_formats(self, json_data, content_id):
         formats = []
@@ -626,57 +605,29 @@ class YahooJapanNewsIE(InfoExtractor):
             lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
             list,
         )
-        if video_data:
-            # Article page
-            for vid in video_data:
-                delivery = vid.get('delivery')
-                url = url_or_none(vid.get('Url'))
-                if not delivery or not url:
-                    continue
-                elif delivery == 'hls':
-                    formats.extend(
-                        self._extract_m3u8_formats(
-                            url,
-                            content_id,
-                            'mp4',
-                            entry_protocol='m3u8_native',
-                            m3u8_id='hls',
-                            fatal=False,
-                        )
+        for vid in video_data or []:
+            delivery = vid.get('delivery')
+            url = url_or_none(vid.get('Url'))
+            if not delivery or not url:
+                continue
+            elif delivery == 'hls':
+                formats.extend(
+                    self._extract_m3u8_formats(
+                        url, content_id, 'mp4', 'm3u8_native',
+                        m3u8_id='hls', fatal=False,
                     )
-                elif delivery == 'progressive':
-                    formats.append(
-                        {
-                            'url': url,
-                            'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')),
-                            'ext': determine_ext(url),
-                            'height': int_or_none(vid.get('height')),
-                            'width': int_or_none(vid.get('width')),
-                            'btr': int_or_none(vid.get('bitrate')),
-                        }
-                    )
-        else:
-            # Headline page with multiple videos
-            for vid in json_data.get('videos', []):
-                for src in vid.get('sources', []):
-                    url = url_or_none(src.get('src'))
-                    ext = determine_ext(url)
-                    if not url:
-                        continue
-                    if ext == 'm3u8':
-                        formats.extend(
-                            self._extract_m3u8_formats(
-                                url,
-                                content_id,
-                                'mp4',
-                                entry_protocol='m3u8_native',
-                                m3u8_id='hls',
-                                fatal=False,
-                            )
-                        )
-                    else:
-                        formats.append({'url': url, 'ext': ext})
-
+                )
+            else:
+                formats.append(
+                    {
+                        'url': url,
+                        'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')),
+                        'ext': determine_ext(url),
+                        'height': int_or_none(vid.get('height')),
+                        'width': int_or_none(vid.get('width')),
+                        'btr': int_or_none(vid.get('bitrate')),
+                    }
+                )
         self._remove_duplicate_formats(formats)
         self._sort_formats(formats)
 
@@ -689,7 +640,7 @@ class YahooJapanNewsIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         host = mobj.group('host')
-        # Headline page without `displayid` defaults to `host`.
+        # Headline pages without `displayid` default to `host`.
         display_id = mobj.group('id') or host
         webpage = self._download_webpage(url, display_id)
 
@@ -706,20 +657,27 @@ class YahooJapanNewsIE(InfoExtractor):
         thumbnail = self._og_search_thumbnail(
             webpage, default=None
         ) or self._html_search_meta('twitter:image', webpage, default=None)
+        space_id = (
+            self._search_regex(
+                r'<script[^>]+class=(["\'])yvpub-player\1[^>]+spaceid=(?P<spaceid>[^&"\']+)',
+                webpage, 'spaceid', group='spaceid', default=None,
+            )
+            or self._search_regex(
+                r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
+                webpage, 'spaceid', default=None,
+            )
+            or self._search_regex(r'<!--\s+SpaceID=(\d+)', webpage, 'spaceid')
+        )
+        formats = []
 
         if display_id == host:
-            # Headline page with playlist of videos
-            formats = []
-
-            # No single useful `contentid` on page
-            content_id = display_id
-
+            # Headline page (w/ multiple BC playlists)
             stream_urls_plists = re.findall(
                 r'YJNEWS\.LIVESTREAM\.SRC.+=(?:\s+)?["\'](?P<streamurl>[^"\']+plist=(?P<plist>\d+)[^"\']+)',
                 webpage,
             )
             if not stream_urls_plists:
-                # Manually build stream urls ('news.yahoo.co.jp', ...)
+                # Manually build ('news.yahoo.co.jp', ...)
                 sbase_url = 'https://s.yimg.jp/images/media/video/player/html/embed_1.2.5.html?service=news&service_type=video&plist=%s&poster=%s&sp=%s&country=JP'
 
                 params = re.findall(
@@ -729,6 +687,8 @@ class YahooJapanNewsIE(InfoExtractor):
                 for p in params:
                     stream_urls_plists.append((sbase_url % p, p[0]))
 
+            bc_url = 'http://players.brightcove.net/%s/%s_%s/index.html?playlistId=%s'
+            entries = []
             for url, plist_id in stream_urls_plists:
                 embed_page = self._download_webpage(
                     'https://s.yimg.jp/images/media/video/player/js/embed_1.0.9.min.js',
@@ -742,72 +702,26 @@ class YahooJapanNewsIE(InfoExtractor):
                 )
                 account = self._search_regex(
                     r'\w+\.video_attr\[(["\'])data-account\1\]\s*=\s*\1(?P<accountid>[\d]+)',
-                    embed_page,
-                    'account id',
-                    group='accountid',
+                    embed_page, 'account id', group='accountid',
                 )
                 player = self._search_regex(
                     r'\w+\.video_attr\[(["\'])data-player\1\]\s*=\s*\1(?P<playerid>[^"\']+)',
-                    embed_page,
-                    'player id',
-                    group='playerid',
+                    embed_page, 'player id', group='playerid',
                 )
                 embed = self._search_regex(
                     r'(["\'])data-embed\1\s*:\s*\1(?P<embed>[^"\']+)',
-                    embed_page,
-                    'embed',
-                    group='embed',
-                )
-                indexjs_page = self._download_webpage(
-                    'https://players.brightcove.net/%s/%s_%s/index.min.js'
-                    % (account, player, embed),
-                    plist_id,
-                    headers={'Referer': url, 'User-Agent': self._USER_AGENT},
-                )
-                policy_key = self._search_regex(
-                    r'policyKey:\s*["\']([^"\']+)', indexjs_page, 'policy key'
+                    embed_page, 'embed', group='embed',
                 )
+                entries.append(bc_url % (account, player, embed, plist_id))
 
-                json_data = self._download_json(
-                    'https://edge.api.brightcove.com/playback/v1/accounts/%s/playlists/%s'
-                    % (account, plist_id),
-                    plist_id,
-                    headers={
-                        'Accept': 'application/json;pk=%s' % policy_key,
-                        'Origin': self._ORIGIN,
-                        'Referer': url,
-                        'User-Agent': self._USER_AGENT,
-                    },
-                    fatal=False,
-                )
-
-                formats.extend(self._extract_formats(json_data, content_id))
+            return self.playlist_from_matches(entries, space_id, title, ie='BrightcoveNew')
 
         else:
             # Article page
             app_id = 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-'
-            space_id = (
-                self._search_regex(
-                    r'<script[^>]+class=(["\'])yvpub-player\1[^>]+spaceid=(?P<spaceid>[^&"\']+)',
-                    webpage,
-                    'spaceid',
-                    group='spaceid',
-                    default=None,
-                )
-                or self._search_regex(
-                    r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
-                    webpage,
-                    'spaceid',
-                    default=None,
-                )
-                or self._search_regex(r'<!--\s+SpaceID=(\d+)', webpage, 'spaceid')
-            )
             content_id = self._search_regex(
                 r'<script[^>]+class=(["\'])yvpub-player\1[^>]+contentid=(?P<contentid>[^&"\']+)',
-                webpage,
-                'contentid',
-                group='contentid',
-                default=space_id,
+                webpage, 'contentid', group='contentid', default=space_id,
             )
             # md5 hash of space_id + '_headlines.yahoo.co.jp'
             ak = YahooJapanNewsIE._get_md5('_'.join((space_id, host)))
@@ -817,7 +731,7 @@ class YahooJapanNewsIE(InfoExtractor):
                 content_id,
                 headers={
                     'Accept': 'application/json, text/javascript, */*; q=0.01',
-                    'Origin': self._ORIGIN,
+                    'Origin': 'https://s.yimg.jp',
                     'Host': 'feapi-yvpub.yahooapis.jp',
                     'User-Agent': self._USER_AGENT,
                     'Referer': 'https://s.yimg.jp/images/yvpub/player/vamos/pc/latest/player.html',
@@ -832,7 +746,6 @@ class YahooJapanNewsIE(InfoExtractor):
                 },
                 fatal=False,
             )
-
             formats = self._extract_formats(json_data, content_id)
 
         return {

From 5da61feddffc2d03e9a7c9b95bc0b63d44424ab9 Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Sun, 21 Jul 2019 09:47:57 +0900
Subject: [PATCH 3/9] Make further requested changes.

---
 youtube_dl/extractor/yahoo.py | 171 +++++++++++++---------------------
 1 file changed, 67 insertions(+), 104 deletions(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 881841f9e..b54605ba0 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -566,36 +566,28 @@ class YahooJapanNewsIE(InfoExtractor):
     IE_NAME = 'yahoo:japannews'
     IE_DESC = 'Yahoo! Japan News'
     _VALID_URL = r'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)(/[^\d]*(?P<id>\d[\d-]*\d))?'
-    _TESTS = [
-        {
-            'url': 'https://headlines.yahoo.co.jp/videonews/fnn?a=20190719-00421051-fnn-soci',
+    _TESTS = [{
+            'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int',
             'info_dict': {
-                'id': '20190719-00421051',
+                'id': '1736242',
                 'ext': 'mp4',
-                'title': '15階から2歳女児転落死\u3000母は台所「目を離した隙に」（フジテレビ系（FNN）） - Yahoo!ニュース',
-                'description': '大阪市で18日夜、マンションの15階から2歳の女の子が転落し病院に運ばれたが、まもな - Yahoo!ニュース(フジテレビ系（FNN）)',
+                'title': 'ムン大統領が対日批判を強化“現金化”効果は？（テレビ朝日系（ANN）） - Yahoo!ニュース',
+                'description': '韓国の元徴用工らを巡る裁判の原告が弁護士が差し押さえた三菱重工業の資産を売却して - Yahoo!ニュース(テレビ朝日系（ANN）)',
                 'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
-            },
-            'params': {'skip_download': True},
-        },
-        {
+            }, 'params': {'skip_download': True},
+        }, {
             'url': 'https://headlines.yahoo.co.jp/videonews/',
             'only_matching': True,
-        },
-        {
+        }, {
             'url': 'https://news.yahoo.co.jp',
             'only_matching': True,
-        },
-        {
+        }, {
             'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/',
             'only_matching': True,
-        },
-        {
+        }, {
             'url': 'https://news.yahoo.co.jp/feature/1356',
             'only_matching': True
-        },
-    ]
-    _USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
+        }]
 
     def _extract_formats(self, json_data, content_id):
         formats = []
@@ -603,8 +595,7 @@ class YahooJapanNewsIE(InfoExtractor):
         video_data = try_get(
             json_data,
             lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
-            list,
-        )
+            list)
         for vid in video_data or []:
             delivery = vid.get('delivery')
             url = url_or_none(vid.get('Url'))
@@ -614,29 +605,21 @@ class YahooJapanNewsIE(InfoExtractor):
                 formats.extend(
                     self._extract_m3u8_formats(
                         url, content_id, 'mp4', 'm3u8_native',
-                        m3u8_id='hls', fatal=False,
-                    )
-                )
+                        m3u8_id='hls', fatal=False))
             else:
-                formats.append(
-                    {
-                        'url': url,
-                        'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')),
-                        'ext': determine_ext(url),
-                        'height': int_or_none(vid.get('height')),
-                        'width': int_or_none(vid.get('width')),
-                        'btr': int_or_none(vid.get('bitrate')),
-                    }
-                )
+                formats.append({
+                    'url': url,
+                    'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')),
+                    'ext': determine_ext(url),
+                    'height': int_or_none(vid.get('height')),
+                    'width': int_or_none(vid.get('width')),
+                    'btr': int_or_none(vid.get('bitrate'))
+                })
         self._remove_duplicate_formats(formats)
         self._sort_formats(formats)
 
         return formats
 
-    @staticmethod
-    def _get_md5(s):
-        return hashlib.md5(s.encode()).hexdigest()
-
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         host = mobj.group('host')
@@ -644,46 +627,34 @@ class YahooJapanNewsIE(InfoExtractor):
         display_id = mobj.group('id') or host
         webpage = self._download_webpage(url, display_id)
 
-        title = (
-            self._og_search_title(webpage, default=None)
-            or self._html_search_meta('twitter:title', webpage, default=None)
-            or self._html_search_regex('<title>([^<]+)</title>', webpage, 'title')
-        )
-        description = (
-            self._og_search_description(webpage, default=None)
-            or self._html_search_meta('description', webpage, default=None)
-            or self._html_search_meta('twitter:description', webpage, default=None)
-        )
+        title = self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage, 'title', default=None
+        ) or self._html_search_regex('<title>([^<]+)</title>', webpage, 'title')
+        description = self._html_search_meta([
+            'og:description', 'description', 'twitter:description'
+        ], webpage, 'description', default=None)
         thumbnail = self._og_search_thumbnail(
             webpage, default=None
-        ) or self._html_search_meta('twitter:image', webpage, default=None)
-        space_id = (
-            self._search_regex(
-                r'<script[^>]+class=(["\'])yvpub-player\1[^>]+spaceid=(?P<spaceid>[^&"\']+)',
-                webpage, 'spaceid', group='spaceid', default=None,
-            )
-            or self._search_regex(
-                r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
-                webpage, 'spaceid', default=None,
-            )
-            or self._search_regex(r'<!--\s+SpaceID=(\d+)', webpage, 'spaceid')
-        )
+        ) or self._html_search_meta('twitter:image', webpage, 'thumbnail', default=None)
+        space_id = self._search_regex([
+            r'<script[^>]+class=["\']yvpub-player["\'][^>]+spaceid=([^&"\']+)',
+            r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
+            r'<!--\s+SpaceID=(\d+)'
+        ], webpage, 'spaceid')
         formats = []
 
         if display_id == host:
             # Headline page (w/ multiple BC playlists)
             stream_urls_plists = re.findall(
                 r'YJNEWS\.LIVESTREAM\.SRC.+=(?:\s+)?["\'](?P<streamurl>[^"\']+plist=(?P<plist>\d+)[^"\']+)',
-                webpage,
-            )
+                webpage)
             if not stream_urls_plists:
                 # Manually build ('news.yahoo.co.jp', ...)
                 sbase_url = 'https://s.yimg.jp/images/media/video/player/html/embed_1.2.5.html?service=news&service_type=video&plist=%s&poster=%s&sp=%s&country=JP'
 
                 params = re.findall(
                     r'["\']plist["\']:\s*["\'](?P<plist>[^"\']+)[^;]+?["\']poster["\']:\s*["\'](?P<poster>[^"\']+)[^;]+?["\']spaceId["\']:\s*["\'](?P<spaceid>[^"\']+)',
-                    webpage,
-                )
+                    webpage)
                 for p in params:
                     stream_urls_plists.append((sbase_url % p, p[0]))
 
@@ -697,59 +668,51 @@ class YahooJapanNewsIE(InfoExtractor):
                         'Authority': 's.yimg.jp',
                         'Path': '/images/media/video/player/js/embed_1.0.9.min.js',
                         'Referer': url,
-                        'User-Agent': self._USER_AGENT,
-                    },
-                )
+                    }, fatal=False)
                 account = self._search_regex(
                     r'\w+\.video_attr\[(["\'])data-account\1\]\s*=\s*\1(?P<accountid>[\d]+)',
-                    embed_page, 'account id', group='accountid',
-                )
+                    embed_page, 'account id', group='accountid', fatal=False)
                 player = self._search_regex(
                     r'\w+\.video_attr\[(["\'])data-player\1\]\s*=\s*\1(?P<playerid>[^"\']+)',
-                    embed_page, 'player id', group='playerid',
-                )
+                    embed_page, 'player id', group='playerid', fatal=False)
                 embed = self._search_regex(
                     r'(["\'])data-embed\1\s*:\s*\1(?P<embed>[^"\']+)',
-                    embed_page, 'embed', group='embed',
-                )
+                    embed_page, 'embed', group='embed', fatal=False)
+                if not all([embed_page, account, player,  embed]):
+                    continue
                 entries.append(bc_url % (account, player, embed, plist_id))
 
             return self.playlist_from_matches(entries, space_id, title, ie='BrightcoveNew')
 
-        else:
-            # Article page
-            app_id = 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-'
-            content_id = self._search_regex(
-                r'<script[^>]+class=(["\'])yvpub-player\1[^>]+contentid=(?P<contentid>[^&"\']+)',
-                webpage, 'contentid', group='contentid', default=space_id,
-            )
-            # md5 hash of space_id + '_headlines.yahoo.co.jp'
-            ak = YahooJapanNewsIE._get_md5('_'.join((space_id, host)))
+        # Article page
+        app_id = 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-'
+        content_id = self._search_regex(
+            r'<script[^>]+class=(["\'])yvpub-player\1[^>]+contentid=(?P<contentid>[^&"\']+)',
+            webpage, 'contentid', group='contentid', default=space_id)
+        # md5 hash of space_id + '_headlines.yahoo.co.jp'
+        ak = hashlib.md5('_'.join((space_id, host)).encode()).hexdigest()
 
-            json_data = self._download_json(
-                'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
-                content_id,
-                headers={
-                    'Accept': 'application/json, text/javascript, */*; q=0.01',
-                    'Origin': 'https://s.yimg.jp',
-                    'Host': 'feapi-yvpub.yahooapis.jp',
-                    'User-Agent': self._USER_AGENT,
-                    'Referer': 'https://s.yimg.jp/images/yvpub/player/vamos/pc/latest/player.html',
-                },
-                query={
-                    'appid': app_id,
-                    'output': 'json',
-                    'space_id': space_id,
-                    'domain': host,
-                    'ak': ak,
-                    'device_type': '1100',
-                },
-                fatal=False,
-            )
-            formats = self._extract_formats(json_data, content_id)
+        json_data = self._download_json(
+            'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
+            content_id,
+            headers={
+                'Accept': 'application/json, text/javascript, */*; q=0.01',
+                'Origin': 'https://s.yimg.jp',
+                'Host': 'feapi-yvpub.yahooapis.jp',
+                'Referer': 'https://s.yimg.jp/images/yvpub/player/vamos/pc/latest/player.html',
+            },
+            query={
+                'appid': app_id,
+                'output': 'json',
+                'space_id': space_id,
+                'domain': host,
+                'ak': ak,
+                'device_type': '1100',
+            })
+        formats = self._extract_formats(json_data, content_id)
 
         return {
-            'id': display_id,
+            'id': content_id,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,

From 446ebd6fc3a30fa3e3d94fe671f3d0e9d60fbc50 Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Sun, 21 Jul 2019 16:08:47 +0900
Subject: [PATCH 4/9] Make more request changes

---
 youtube_dl/extractor/yahoo.py | 44 ++++++++++++++---------------------
 1 file changed, 18 insertions(+), 26 deletions(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index b54605ba0..d6ea8bf79 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -565,7 +565,7 @@ class YahooGyaOIE(InfoExtractor):
 class YahooJapanNewsIE(InfoExtractor):
     IE_NAME = 'yahoo:japannews'
     IE_DESC = 'Yahoo! Japan News'
-    _VALID_URL = r'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)(/[^\d]*(?P<id>\d[\d-]*\d))?'
+    _VALID_URL = r'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)[^\d]*(?P<id>\d[\d-]*\d)?'
     _TESTS = [{
             'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int',
             'info_dict': {
@@ -610,10 +610,8 @@ class YahooJapanNewsIE(InfoExtractor):
                 formats.append({
                     'url': url,
                     'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')),
-                    'ext': determine_ext(url),
                     'height': int_or_none(vid.get('height')),
-                    'width': int_or_none(vid.get('width')),
-                    'btr': int_or_none(vid.get('bitrate'))
+                    'width': int_or_none(vid.get('width'))
                 })
         self._remove_duplicate_formats(formats)
         self._sort_formats(formats)
@@ -630,18 +628,6 @@ class YahooJapanNewsIE(InfoExtractor):
         title = self._html_search_meta(
             ['og:title', 'twitter:title'], webpage, 'title', default=None
         ) or self._html_search_regex('<title>([^<]+)</title>', webpage, 'title')
-        description = self._html_search_meta([
-            'og:description', 'description', 'twitter:description'
-        ], webpage, 'description', default=None)
-        thumbnail = self._og_search_thumbnail(
-            webpage, default=None
-        ) or self._html_search_meta('twitter:image', webpage, 'thumbnail', default=None)
-        space_id = self._search_regex([
-            r'<script[^>]+class=["\']yvpub-player["\'][^>]+spaceid=([^&"\']+)',
-            r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
-            r'<!--\s+SpaceID=(\d+)'
-        ], webpage, 'spaceid')
-        formats = []
 
         if display_id == host:
             # Headline page (w/ multiple BC playlists)
@@ -678,29 +664,35 @@ class YahooJapanNewsIE(InfoExtractor):
                 embed = self._search_regex(
                     r'(["\'])data-embed\1\s*:\s*\1(?P<embed>[^"\']+)',
                     embed_page, 'embed', group='embed', fatal=False)
-                if not all([embed_page, account, player,  embed]):
+                if not all([embed_page, account, player, embed]):
                     continue
                 entries.append(bc_url % (account, player, embed, plist_id))
 
-            return self.playlist_from_matches(entries, space_id, title, ie='BrightcoveNew')
+            return self.playlist_from_matches(entries, playlist_title=title, ie='BrightcoveNew')
 
         # Article page
+        description = self._html_search_meta([
+            'og:description', 'description', 'twitter:description'
+        ], webpage, 'description', default=None)
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None
+        ) or self._html_search_meta('twitter:image', webpage, 'thumbnail', default=None)
+        space_id = self._search_regex([
+            r'<script[^>]+class=["\']yvpub-player["\'][^>]+spaceid=([^&"\']+)',
+            r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
+            r'<!--\s+SpaceID=(\d+)'
+        ], webpage, 'spaceid')
+
         app_id = 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-'
         content_id = self._search_regex(
-            r'<script[^>]+class=(["\'])yvpub-player\1[^>]+contentid=(?P<contentid>[^&"\']+)',
-            webpage, 'contentid', group='contentid', default=space_id)
+            r'<script[^>]+class=["\']yvpub-player["\'][^>]+contentid=(?P<contentid>[^&"\']+)',
+            webpage, 'contentid', group='contentid')
         # md5 hash of space_id + '_headlines.yahoo.co.jp'
         ak = hashlib.md5('_'.join((space_id, host)).encode()).hexdigest()
 
         json_data = self._download_json(
             'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
             content_id,
-            headers={
-                'Accept': 'application/json, text/javascript, */*; q=0.01',
-                'Origin': 'https://s.yimg.jp',
-                'Host': 'feapi-yvpub.yahooapis.jp',
-                'Referer': 'https://s.yimg.jp/images/yvpub/player/vamos/pc/latest/player.html',
-            },
             query={
                 'appid': app_id,
                 'output': 'json',

From 17fa2ad22c83858ebb313ef71f6d775b6f87365e Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Sun, 21 Jul 2019 18:16:19 +0900
Subject: [PATCH 5/9] Make next requested changes.

---
 youtube_dl/extractor/yahoo.py | 41 ++++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 20 deletions(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index d6ea8bf79..8ebdf9f58 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -566,15 +566,25 @@ class YahooJapanNewsIE(InfoExtractor):
     IE_NAME = 'yahoo:japannews'
     IE_DESC = 'Yahoo! Japan News'
     _VALID_URL = r'https?://(?P<host>(?:news|headlines)\.yahoo\.co\.jp)[^\d]*(?P<id>\d[\d-]*\d)?'
+    _GEO_COUNTRIES = ['JP']
     _TESTS = [{
-            'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int',
-            'info_dict': {
-                'id': '1736242',
-                'ext': 'mp4',
-                'title': 'ムン大統領が対日批判を強化“現金化”効果は？（テレビ朝日系（ANN）） - Yahoo!ニュース',
-                'description': '韓国の元徴用工らを巡る裁判の原告が弁護士が差し押さえた三菱重工業の資産を売却して - Yahoo!ニュース(テレビ朝日系（ANN）)',
-                'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
-            }, 'params': {'skip_download': True},
+        'url': 'https://headlines.yahoo.co.jp/videonews/ann?a=20190716-00000071-ann-int',
+        'info_dict': {
+            'id': '1736242',
+            'ext': 'mp4',
+            'title': 'ムン大統領が対日批判を強化“現金化”効果は？（テレビ朝日系（ANN）） - Yahoo!ニュース',
+            'description': '韓国の元徴用工らを巡る裁判の原告が弁護士が差し押さえた三菱重工業の資産を売却して - Yahoo!ニュース(テレビ朝日系（ANN）)',
+            'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
+        }, 'params': {'skip_download': True}
+        }, {
+        'url': 'https://news.yahoo.co.jp/pickup/6330725',
+        'info_dict': {
+            'id': '1750855',
+            'ext': 'mp4',
+            'title': 'ひき逃げか 200m引きずった痕 | 2019/7/21(日) - Yahoo!ニュース',
+            'description': '21日午前4時40分ごろ、仙台市泉区で、倒れていた女性（39）が見つかり、病院で死亡が確認された。路上に女…',
+            'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
+        }, 'params': {'skip_download': True}
         }, {
             'url': 'https://headlines.yahoo.co.jp/videonews/',
             'only_matching': True,
@@ -644,7 +654,7 @@ class YahooJapanNewsIE(InfoExtractor):
                 for p in params:
                     stream_urls_plists.append((sbase_url % p, p[0]))
 
-            bc_url = 'http://players.brightcove.net/%s/%s_%s/index.html?playlistId=%s'
+            bc_url = 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=%s'
             entries = []
             for url, plist_id in stream_urls_plists:
                 embed_page = self._download_webpage(
@@ -655,18 +665,9 @@ class YahooJapanNewsIE(InfoExtractor):
                         'Path': '/images/media/video/player/js/embed_1.0.9.min.js',
                         'Referer': url,
                     }, fatal=False)
-                account = self._search_regex(
-                    r'\w+\.video_attr\[(["\'])data-account\1\]\s*=\s*\1(?P<accountid>[\d]+)',
-                    embed_page, 'account id', group='accountid', fatal=False)
-                player = self._search_regex(
-                    r'\w+\.video_attr\[(["\'])data-player\1\]\s*=\s*\1(?P<playerid>[^"\']+)',
-                    embed_page, 'player id', group='playerid', fatal=False)
-                embed = self._search_regex(
-                    r'(["\'])data-embed\1\s*:\s*\1(?P<embed>[^"\']+)',
-                    embed_page, 'embed', group='embed', fatal=False)
-                if not all([embed_page, account, player, embed]):
+                if not embed_page:
                     continue
-                entries.append(bc_url % (account, player, embed, plist_id))
+                entries.append(bc_url % plist_id)
 
             return self.playlist_from_matches(entries, playlist_title=title, ie='BrightcoveNew')
 

From 9a638de694b741eb1e46da5a48f9cef0e3b5ced8 Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Sun, 21 Jul 2019 18:32:53 +0900
Subject: [PATCH 6/9] Generalize md5 hash comment

---
 youtube_dl/extractor/yahoo.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 8ebdf9f58..d89c044d2 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -688,7 +688,7 @@ class YahooJapanNewsIE(InfoExtractor):
         content_id = self._search_regex(
             r'<script[^>]+class=["\']yvpub-player["\'][^>]+contentid=(?P<contentid>[^&"\']+)',
             webpage, 'contentid', group='contentid')
-        # md5 hash of space_id + '_headlines.yahoo.co.jp'
+        # md5 hash of space_id + '_' + host
         ak = hashlib.md5('_'.join((space_id, host)).encode()).hexdigest()
 
         json_data = self._download_json(

From 2dd59e16779dc93afb1b9bfaca6dc8880539a507 Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Sun, 21 Jul 2019 21:02:29 +0900
Subject: [PATCH 7/9] Update second test due to sudden URL change.

---
 youtube_dl/extractor/yahoo.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index d89c044d2..a75d07c00 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -577,12 +577,12 @@ class YahooJapanNewsIE(InfoExtractor):
             'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
         }, 'params': {'skip_download': True}
         }, {
-        'url': 'https://news.yahoo.co.jp/pickup/6330725',
+        'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04',
         'info_dict': {
             'id': '1750855',
             'ext': 'mp4',
-            'title': 'ひき逃げか 200m引きずった痕 | 2019/7/21(日) - Yahoo!ニュース',
-            'description': '21日午前4時40分ごろ、仙台市泉区で、倒れていた女性（39）が見つかり、病院で死亡が確認された。路上に女…',
+            'title': '200ｍ引きずられたか\u3000路上で女性死亡\u3000ひき逃げ事件として捜査\u3000仙台（仙台放送） - Yahoo!ニュース',
+            'description': '倒れている女性が見つかったのは、仙台市泉区松陵１丁目の路上です。21日午前4時40分 - Yahoo!ニュース(仙台放送)',
             'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
         }, 'params': {'skip_download': True}
         }, {

From b6922fbaf8774f7ef3c94921ca89146c2582e232 Mon Sep 17 00:00:00 2001
From: Kyle <kylepw@gmail.com>
Date: Sun, 21 Jul 2019 21:26:13 +0900
Subject: [PATCH 8/9] Additional fix

---
 youtube_dl/extractor/yahoo.py | 29 +++--------------------------
 1 file changed, 3 insertions(+), 26 deletions(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index a75d07c00..5b23e6cae 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -640,34 +640,11 @@ class YahooJapanNewsIE(InfoExtractor):
         ) or self._html_search_regex('<title>([^<]+)</title>', webpage, 'title')
 
         if display_id == host:
-            # Headline page (w/ multiple BC playlists)
-            stream_urls_plists = re.findall(
-                r'YJNEWS\.LIVESTREAM\.SRC.+=(?:\s+)?["\'](?P<streamurl>[^"\']+plist=(?P<plist>\d+)[^"\']+)',
-                webpage)
-            if not stream_urls_plists:
-                # Manually build ('news.yahoo.co.jp', ...)
-                sbase_url = 'https://s.yimg.jp/images/media/video/player/html/embed_1.2.5.html?service=news&service_type=video&plist=%s&poster=%s&sp=%s&country=JP'
-
-                params = re.findall(
-                    r'["\']plist["\']:\s*["\'](?P<plist>[^"\']+)[^;]+?["\']poster["\']:\s*["\'](?P<poster>[^"\']+)[^;]+?["\']spaceId["\']:\s*["\'](?P<spaceid>[^"\']+)',
-                    webpage)
-                for p in params:
-                    stream_urls_plists.append((sbase_url % p, p[0]))
+            # Headline page (w/ multiple BC playlists) ('news.yahoo.co.jp', 'headlines.yahoo.co.jp/videonews/', ...)
+            stream_plists = re.findall(r'plist=(\d+)', webpage) or re.findall(r'plist["\']:\s*["\']([^"\']+)', webpage)
 
             bc_url = 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=%s'
-            entries = []
-            for url, plist_id in stream_urls_plists:
-                embed_page = self._download_webpage(
-                    'https://s.yimg.jp/images/media/video/player/js/embed_1.0.9.min.js',
-                    plist_id,
-                    headers={
-                        'Authority': 's.yimg.jp',
-                        'Path': '/images/media/video/player/js/embed_1.0.9.min.js',
-                        'Referer': url,
-                    }, fatal=False)
-                if not embed_page:
-                    continue
-                entries.append(bc_url % plist_id)
+            entries = [bc_url % plist_id for plist_id in stream_plists]
 
             return self.playlist_from_matches(entries, playlist_title=title, ie='BrightcoveNew')
 

From 681305fb6259cf953d974aca5da5368ae576ff75 Mon Sep 17 00:00:00 2001
From: Sergey M <dstftw@gmail.com>
Date: Mon, 22 Jul 2019 00:56:45 +0700
Subject: [PATCH 9/9] Update yahoo.py

---
 youtube_dl/extractor/yahoo.py | 77 +++++++++++++++++------------------
 1 file changed, 38 insertions(+), 39 deletions(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 5b23e6cae..e5ebdd180 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -575,29 +575,27 @@ class YahooJapanNewsIE(InfoExtractor):
             'title': 'ムン大統領が対日批判を強化“現金化”効果は？（テレビ朝日系（ANN）） - Yahoo!ニュース',
             'description': '韓国の元徴用工らを巡る裁判の原告が弁護士が差し押さえた三菱重工業の資産を売却して - Yahoo!ニュース(テレビ朝日系（ANN）)',
             'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
-        }, 'params': {'skip_download': True}
-        }, {
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # geo restricted
         'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04',
-        'info_dict': {
-            'id': '1750855',
-            'ext': 'mp4',
-            'title': '200ｍ引きずられたか\u3000路上で女性死亡\u3000ひき逃げ事件として捜査\u3000仙台（仙台放送） - Yahoo!ニュース',
-            'description': '倒れている女性が見つかったのは、仙台市泉区松陵１丁目の路上です。21日午前4時40分 - Yahoo!ニュース(仙台放送)',
-            'thumbnail': r're:^https?://.*\.[a-zA-Z\d]{3,4}$',
-        }, 'params': {'skip_download': True}
-        }, {
-            'url': 'https://headlines.yahoo.co.jp/videonews/',
-            'only_matching': True,
-        }, {
-            'url': 'https://news.yahoo.co.jp',
-            'only_matching': True,
-        }, {
-            'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/',
-            'only_matching': True,
-        }, {
-            'url': 'https://news.yahoo.co.jp/feature/1356',
-            'only_matching': True
-        }]
+        'only_matching': True,
+    }, {
+        'url': 'https://headlines.yahoo.co.jp/videonews/',
+        'only_matching': True,
+    }, {
+        'url': 'https://news.yahoo.co.jp',
+        'only_matching': True,
+    }, {
+        'url': 'https://news.yahoo.co.jp/byline/hashimotojunji/20190628-00131977/',
+        'only_matching': True,
+    }, {
+        'url': 'https://news.yahoo.co.jp/feature/1356',
+        'only_matching': True
+    }]
 
     def _extract_formats(self, json_data, content_id):
         formats = []
@@ -621,7 +619,8 @@ class YahooJapanNewsIE(InfoExtractor):
                     'url': url,
                     'format_id': 'http-%s' % compat_str(vid.get('bitrate', '')),
                     'height': int_or_none(vid.get('height')),
-                    'width': int_or_none(vid.get('width'))
+                    'width': int_or_none(vid.get('width')),
+                    'tbr': int_or_none(vid.get('bitrate')),
                 })
         self._remove_duplicate_formats(formats)
         self._sort_formats(formats)
@@ -631,8 +630,8 @@ class YahooJapanNewsIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         host = mobj.group('host')
-        # Headline pages without `displayid` default to `host`.
         display_id = mobj.group('id') or host
+
         webpage = self._download_webpage(url, display_id)
 
         title = self._html_search_meta(
@@ -642,41 +641,41 @@ class YahooJapanNewsIE(InfoExtractor):
         if display_id == host:
             # Headline page (w/ multiple BC playlists) ('news.yahoo.co.jp', 'headlines.yahoo.co.jp/videonews/', ...)
             stream_plists = re.findall(r'plist=(\d+)', webpage) or re.findall(r'plist["\']:\s*["\']([^"\']+)', webpage)
-
-            bc_url = 'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=%s'
-            entries = [bc_url % plist_id for plist_id in stream_plists]
-
-            return self.playlist_from_matches(entries, playlist_title=title, ie='BrightcoveNew')
+            entries = [
+                self.url_result(
+                    smuggle_url(
+                        'http://players.brightcove.net/5690807595001/HyZNerRl7_default/index.html?playlistId=%s' % plist_id,
+                        {'geo_countries': ['JP']}),
+                    ie='BrightcoveNew', video_id=plist_id)
+                for plist_id in stream_plists]
+            return self.playlist_result(entries, playlist_title=title)
 
         # Article page
-        description = self._html_search_meta([
-            'og:description', 'description', 'twitter:description'
-        ], webpage, 'description', default=None)
+        description = self._html_search_meta(
+            ['og:description', 'description', 'twitter:description'],
+            webpage, 'description', default=None)
         thumbnail = self._og_search_thumbnail(
-            webpage, default=None
-        ) or self._html_search_meta('twitter:image', webpage, 'thumbnail', default=None)
+            webpage, default=None) or self._html_search_meta(
+            'twitter:image', webpage, 'thumbnail', default=None)
         space_id = self._search_regex([
             r'<script[^>]+class=["\']yvpub-player["\'][^>]+spaceid=([^&"\']+)',
             r'YAHOO\.JP\.srch\.\w+link\.onLoad[^;]+spaceID["\' ]*:["\' ]+([^"\']+)',
             r'<!--\s+SpaceID=(\d+)'
         ], webpage, 'spaceid')
 
-        app_id = 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-'
         content_id = self._search_regex(
             r'<script[^>]+class=["\']yvpub-player["\'][^>]+contentid=(?P<contentid>[^&"\']+)',
             webpage, 'contentid', group='contentid')
-        # md5 hash of space_id + '_' + host
-        ak = hashlib.md5('_'.join((space_id, host)).encode()).hexdigest()
 
         json_data = self._download_json(
             'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
             content_id,
             query={
-                'appid': app_id,
+                'appid': 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-',
                 'output': 'json',
                 'space_id': space_id,
                 'domain': host,
-                'ak': ak,
+                'ak': hashlib.md5('_'.join((space_id, host)).encode()).hexdigest(),
                 'device_type': '1100',
             })
         formats = self._extract_formats(json_data, content_id)