Update upstream source from tag 'upstream/2020.09.14'

[youtubedl] / youtube_dl / extractor / abc.py

diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py
index 87017ed397bfd75690b0e4cab3821f549d6132cd..6637f4f3537591b46870cb7ec3f35d1167cb3cb7 100644 (file)
--- a/youtube_dl/extractor/abc.py
+++ b/youtube_dl/extractor/abc.py
@@ -13,6 +13,7 @@ from ..utils import (
     int_or_none,
     parse_iso8601,
     try_get,
     int_or_none,
     parse_iso8601,
     try_get,

+    unescapeHTML,

     update_url_query,
 )
 
     update_url_query,
 )
 


@@ -104,21 +105,22 @@ class ABCIE(InfoExtractor):
 
 class ABCIViewIE(InfoExtractor):
     IE_NAME = 'abc.net.au:iview'
 
 class ABCIViewIE(InfoExtractor):
     IE_NAME = 'abc.net.au:iview'

-    _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'

     _GEO_COUNTRIES = ['AU']
 
     # ABC iview programs are normally available for 14 days only.
     _TESTS = [{
     _GEO_COUNTRIES = ['AU']
 
     # ABC iview programs are normally available for 14 days only.
     _TESTS = [{

-        'url': 'http://iview.abc.net.au/programs/call-the-midwife/ZW0898A003S00',
-        'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
+        'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
+        'md5': '67715ce3c78426b11ba167d875ac6abf',

         'info_dict': {
         'info_dict': {

-            'id': 'ZW0898A003S00',
+            'id': 'LE1927H001S00',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Series 5 Ep 3',
-            'description': 'md5:e0ef7d4f92055b86c4f33611f180ed79',
-            'upload_date': '20171228',
+            'title': "Series 11 Ep 1",
+            'series': "Gruen",
+            'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
+            'upload_date': '20190925',

             'uploader_id': 'abc1',
             'uploader_id': 'abc1',

-            'timestamp': 1514499187,
+            'timestamp': 1569445289,

         },
         'params': {
             'skip_download': True,
         },
         'params': {
             'skip_download': True,


@@ -127,17 +129,16 @@ class ABCIViewIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

-        webpage = self._download_webpage(url, video_id)
-        video_params = self._parse_json(self._search_regex(
-            r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
-        title = video_params.get('title') or video_params['seriesTitle']
-        stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
+        video_params = self._download_json(
+            'https://iview.abc.net.au/api/programs/' + video_id, video_id)
+        title = unescapeHTML(video_params.get('title') or video_params['seriesTitle'])
+        stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))

 
 

-        house_number = video_params.get('episodeHouseNumber')
-        path = '/auth/hls/sign?ts={0}&hn={1}&d=android-mobile'.format(
+        house_number = video_params.get('episodeHouseNumber') or video_id
+        path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(

             int(time.time()), house_number)
         sig = hmac.new(
             int(time.time()), house_number)
         sig = hmac.new(

-            'android.content.res.Resources'.encode('utf-8'),
+            b'android.content.res.Resources',

             path.encode('utf-8'), hashlib.sha256).hexdigest()
         token = self._download_webpage(
             'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
             path.encode('utf-8'), hashlib.sha256).hexdigest()
         token = self._download_webpage(
             'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)


@@ -147,7 +148,7 @@ class ABCIViewIE(InfoExtractor):
                 'hdnea': token,
             })
 
                 'hdnea': token,
             })
 

-        for sd in ('sd', 'sd-low'):
+        for sd in ('720', 'sd', 'sd-low'):

             sd_url = try_get(
                 stream, lambda x: x['streams']['hls'][sd], compat_str)
             if not sd_url:
             sd_url = try_get(
                 stream, lambda x: x['streams']['hls'][sd], compat_str)
             if not sd_url:


@@ -167,18 +168,26 @@ class ABCIViewIE(InfoExtractor):
                 'ext': 'vtt',
             }]
 
                 'ext': 'vtt',
             }]
 

+        is_live = video_params.get('livestream') == '1'
+        if is_live:
+            title = self._live_title(title)
+

         return {
             'id': video_id,
             'title': title,
         return {
             'id': video_id,
             'title': title,

-            'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
-            'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
+            'description': video_params.get('description'),
+            'thumbnail': video_params.get('thumbnail'),

             'duration': int_or_none(video_params.get('eventDuration')),
             'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
             'duration': int_or_none(video_params.get('eventDuration')),
             'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),

-            'series': video_params.get('seriesTitle'),
+            'series': unescapeHTML(video_params.get('seriesTitle')),

             'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
             'series_id': video_params.get('seriesHouseNumber') or video_id[:7],

-            'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage, default=None)),
-            'episode': self._html_search_meta('episode_title', webpage, default=None),
+            'season_number': int_or_none(self._search_regex(
+                r'\bSeries\s+(\d+)\b', title, 'season number', default=None)),
+            'episode_number': int_or_none(self._search_regex(
+                r'\bEp\s+(\d+)\b', title, 'episode number', default=None)),
+            'episode_id': house_number,

             'uploader_id': video_params.get('channel'),
             'formats': formats,
             'subtitles': subtitles,
             'uploader_id': video_params.get('channel'),
             'formats': formats,
             'subtitles': subtitles,

+            'is_live': is_live,

         }
         }