[yahoo:japannews] Add extractor (closes #21698) (#21265)

2 files changed, 132 insertions, 0 deletions

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..e5ebdd180 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 +560,130 @@ 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)?'
+    _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,
+        },
+    }, {
+        # geo restricted
+        'url': 'https://headlines.yahoo.co.jp/hl?a=20190721-00000001-oxv-l04',
+        '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 = []
+
+        video_data = try_get(
+            json_data,
+            lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
+            list)
+        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))
+            else:
+                formats.append({
+                    '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')),
+                    'tbr': int_or_none(vid.get('bitrate')),
+                })
+        self._remove_duplicate_formats(formats)
+        self._sort_formats(formats)
+
+        return formats
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        host = mobj.group('host')
+        display_id = mobj.group('id') or host
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage, 'title', default=None
+        ) or self._html_search_regex('<title>([^<]+)</title>', webpage, 'title')
+
+        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)
+            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)
+        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')
+
+        content_id = self._search_regex(
+            r'<script[^>]+class=["\']yvpub-player["\'][^>]+contentid=(?P<contentid>[^&"\']+)',
+            webpage, 'contentid', group='contentid')
+
+        json_data = self._download_json(
+            'https://feapi-yvpub.yahooapis.jp/v1/content/%s' % content_id,
+            content_id,
+            query={
+                'appid': 'dj0zaiZpPVZMTVFJR0FwZWpiMyZzPWNvbnN1bWVyc2VjcmV0Jng9YjU-',
+                'output': 'json',
+                'space_id': space_id,
+                'domain': host,
+                'ak': hashlib.md5('_'.join((space_id, host)).encode()).hexdigest(),
+                'device_type': '1100',
+            })
+        formats = self._extract_formats(json_data, content_id)
+
+        return {
+            'id': content_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'formats': formats,
+        }