feat: add support for uliza in pia-live

yt_dlp/extractor/_extractors.py

@@ -1510,8 +1510,9 @@ from .pgatour import PGATourIE
 from .philharmoniedeparis import PhilharmonieDeParisIE
 from .phoenix import PhoenixIE
 from .photobucket import PhotobucketIE
+from .pialive import PiaLiveIE
 from .piapro import PiaproIE
-from .piaulizaportal import PIAULIZAPortalIE
+from .piaulizaportal import PIAULIZAPortalAPIIE, PIAULIZAPortalIE
 from .picarto import (
     PicartoIE,
     PicartoVodIE,

yt_dlp/extractor/pialive.py

@@ -0,0 +1,55 @@
+from .common import InfoExtractor
+from .piaulizaportal import PIAULIZAPortalAPIIE
+from ..networking import Request
+from ..utils import multipart_encode, smuggle_url
+
+
+class PiaLiveIE(InfoExtractor):
+    PLAYER_ROOT_URL = 'https://player.pia-live.jp'
+    PIA_LIVE_API_URL = 'https://api.pia-live.jp'
+    _VALID_URL = r'https?://player\.pia-live\.jp/stream/(?P<id>[\w-]+)'
+
+    def _real_extract(self, url):
+        video_key = self._match_id(url)
+        webpage = self._download_webpage(url, video_key)
+        program_code = self._search_regex(r"const programCode = '(.*?)';", webpage, 'program code')
+
+        prod_configure = self._download_webpage(
+            self.PLAYER_ROOT_URL + self._search_regex(r'<script [^>]*\bsrc="(/statics/js/s_prod[^"]+)"', webpage, 'prod configure page'),
+            program_code,
+            headers={'Referer': self.PLAYER_ROOT_URL},
+            note='Fetching prod configure page', errnote='Unable to fetch prod configure page',
+        )
+
+        api_key = self._search_regex(r"const APIKEY = '(.*?)';", prod_configure, 'api key')
+        payload, content_type = multipart_encode({
+            'play_url': video_key,
+            'api_key': api_key,
+        })
+        player_tag_list = self._download_json(
+            Request(
+                url=f'{self.PIA_LIVE_API_URL}/perf/player-tag-list/{program_code}',
+                method='POST',
+                data=payload,
+                headers={
+                    'Content-Type': content_type,
+                },
+            ),
+            program_code,
+        )
+
+        player_data_url = self._search_regex(PIAULIZAPortalAPIIE.SCRIPT_TAG_REGEX_PATTERN,
+                                             player_tag_list['data']['movie_one_tag'], 'player data url')
+
+        return {
+            **self.url_result(
+                smuggle_url(
+                    player_data_url,
+                    {'video_id': program_code, 'referer': self.PLAYER_ROOT_URL, 'info_dict': {
+                        'id': program_code,
+                        'title': self._html_extract_title(webpage),
+                    }},
+                ),
+                ie=PIAULIZAPortalAPIIE.ie_key(),
+            ),
+        }

yt_dlp/extractor/piaulizaportal.py

@@ -1,11 +1,78 @@
 from .common import InfoExtractor
-from ..utils import (
+from ..utils import ExtractorError, int_or_none, parse_qs, smuggle_url, time_seconds, traverse_obj, unsmuggle_url
-    ExtractorError,
+
-    int_or_none,
+
-    parse_qs,
+class PIAULIZAPortalAPIIE(InfoExtractor):
-    time_seconds,
+    IE_DESC = 'https://player-api.p.uliza.jp - PIA ULIZA m3u8'
-    traverse_obj,
+    SCRIPT_TAG_REGEX_PATTERN = r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"'
-)
+
+    _VALID_URL = r'https://player-api\.p\.uliza\.jp/v1/players/(?P<id>.*)'
+    _TESTS = [
+        {
+            'url': 'https://player-api.p.uliza.jp/v1/players/timeshift-disabled/pia/admin?type=normal&playerobjectname=ulizaPlayer&name=livestream01_dvr&repeatable=true',
+            'info_dict': {
+                'id': 'timeshift-disabled/pia/admin?type=normal&playerobjectname=ulizaPlayer&name=livestream01_dvr&repeatable=true',
+                'title': 'livestream01_dvr',
+                'live_status': 'was_live',
+            },
+            'params': {
+                'skip_download': True,
+                'ignore_no_formats_error': True,
+            },
+        },
+        {
+            'url': 'https://player-api.p.uliza.jp/v1/players/uliza_jp_gallery_normal/promotion/admin?type=presentation&name=cookings&targetid=player1',
+            'info_dict': {
+                'id': 'uliza_jp_gallery_normal/promotion/admin?type=presentation&name=cookings&targetid=player1',
+                'title': 'cookings',
+                'live_status': 'not_live',
+            },
+            'params': {
+                'skip_download': True,
+                'ignore_no_formats_error': True,
+            },
+        },
+        {
+            'url': 'https://player-api.p.uliza.jp/v1/players/default-player/pia/admin?type=normal&name=pia_movie_uliza_fix&targetid=ulizahtml5&repeatable=true',
+            'info_dict': {
+                'id': 'default-player/pia/admin?type=normal&name=pia_movie_uliza_fix&targetid=ulizahtml5&repeatable=true',
+                'title': 'pia_movie_uliza_fix',
+                'live_status': 'not_live',
+            },
+            'params': {
+                'skip_download': True,
+                'ignore_no_formats_error': True,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        video_id = smuggled_data.get('video_id') or self._search_regex(r'&name=([^&]+)', self._match_id(url), 'video id')
+        player_data = self._download_webpage(
+            url,
+            video_id,
+            headers={'Referer': smuggled_data.get('referer') or 'https://player-api.p.uliza.jp/'},
+            note='Fetching player data', errnote='Unable to fetch player data',
+        )
+
+        formats = self._extract_m3u8_formats(
+            self._search_regex(
+                r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data,
+                'm3u8 url', default=None),
+            video_id, fatal=False)
+        m3u8_type = self._search_regex(
+            r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
+        return {
+            'id': video_id,
+            'title': smuggled_data.get('video_title') or video_id,
+            'formats': formats,
+            'live_status': {
+                'video': 'is_live',
+                'dvr': 'was_live',  # short-term archives
+            }.get(m3u8_type, 'not_live'),  # VOD or long-term archives
+            **smuggled_data.get('info_dict', {}),
+        }
 
 
 class PIAULIZAPortalIE(InfoExtractor):
@@ -44,27 +111,16 @@ class PIAULIZAPortalIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        player_data = self._download_webpage(
+        player_data_url = self._search_regex(
-            self._search_regex(
+            PIAULIZAPortalAPIIE.SCRIPT_TAG_REGEX_PATTERN,
-                r'<script [^>]*\bsrc="(https://player-api\.p\.uliza\.jp/v1/players/[^"]+)"',
+            webpage, 'player data url')
-                webpage, 'player data url'),
+        return self.url_result(
-            video_id, headers={'Referer': 'https://ulizaportal.jp/'},
+            smuggle_url(
-            note='Fetching player data', errnote='Unable to fetch player data')
+                player_data_url,
-
+                {'video_id': video_id, 'referer': 'https://ulizaportal.jp/', 'info_dict': {
-        formats = self._extract_m3u8_formats(
-            self._search_regex(
-                r'["\'](https://vms-api\.p\.uliza\.jp/v1/prog-index\.m3u8[^"\']+)', player_data,
-                'm3u8 url', default=None),
-            video_id, fatal=False)
-        m3u8_type = self._search_regex(
-            r'/hls/(dvr|video)/', traverse_obj(formats, (0, 'url')), 'm3u8 type', default=None)
-
-        return {
                     'id': video_id,
                     'title': self._html_extract_title(webpage),
-            'formats': formats,
+                }},
-            'live_status': {
+            ),
-                'video': 'is_live',
+            ie=PIAULIZAPortalAPIIE.ie_key(),
-                'dvr': 'was_live',  # short-term archives
+        )
-            }.get(m3u8_type, 'not_live'),  # VOD or long-term archives
-        }