[ABC:iview] Add show extractor (#1630)

Authored by: pabs3

yt_dlp/extractor/abc.py

@@ -8,6 +8,7 @@ import time
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    dict_get,
     ExtractorError,
     js_to_json,
     int_or_none,
@@ -253,3 +254,66 @@ class ABCIViewIE(InfoExtractor):
             'subtitles': subtitles,
             'is_live': is_live,
         }
+
+
+class ABCIViewShowSeriesIE(InfoExtractor):
+    IE_NAME = 'abc.net.au:iview:showseries'
+    _VALID_URL = r'https?://iview\.abc\.net\.au/show/(?P<id>[^/]+)(?:/series/\d+)?$'
+    _GEO_COUNTRIES = ['AU']
+
+    _TESTS = [{
+        'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
+        'info_dict': {
+            'id': '124870-1',
+            'title': 'Series 1',
+            'description': 'md5:93119346c24a7c322d446d8eece430ff',
+            'series': 'Upper Middle Bogan',
+            'season': 'Series 1',
+            'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
+        },
+        'playlist_count': 8,
+    }, {
+        'url': 'https://iview.abc.net.au/show/upper-middle-bogan',
+        'info_dict': {
+            'id': 'CO1108V001S00',
+            'ext': 'mp4',
+            'title': 'Series 1 Ep 1 I\'m A Swan',
+            'description': 'md5:7b676758c1de11a30b79b4d301e8da93',
+            'series': 'Upper Middle Bogan',
+            'uploader_id': 'abc1',
+            'upload_date': '20210630',
+            'timestamp': 1625036400,
+        },
+        'params': {
+            'noplaylist': True,
+            'skip_download': 'm3u8',
+        },
+    }]
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        webpage = self._download_webpage(url, show_id)
+        webpage_data = self._search_regex(
+            r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
+            webpage, 'initial state')
+        video_data = self._parse_json(
+            unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id)
+        video_data = video_data['route']['pageData']['_embedded']
+
+        if self.get_param('noplaylist') and 'highlightVideo' in video_data:
+            self.to_screen('Downloading just the highlight video because of --no-playlist')
+            return self.url_result(video_data['highlightVideo']['shareUrl'], ie=ABCIViewIE.ie_key())
+
+        self.to_screen(f'Downloading playlist {show_id} - add --no-playlist to just download the highlight video')
+        series = video_data['selectedSeries']
+        return {
+            '_type': 'playlist',
+            'entries': [self.url_result(episode['shareUrl'])
+                        for episode in series['_embedded']['videoEpisodes']],
+            'id': series.get('id'),
+            'title': dict_get(series, ('title', 'displaySubtitle')),
+            'description': series.get('description'),
+            'series': dict_get(series, ('showTitle', 'displayTitle')),
+            'season': dict_get(series, ('title', 'displaySubtitle')),
+            'thumbnail': series.get('thumbnail'),
+        }

yt_dlp/extractor/extractors.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 from .abc import (
     ABCIE,
     ABCIViewIE,
+    ABCIViewShowSeriesIE,
 )
 from .abcnews import (
     AbcNewsIE,