New upstream version 2019.01.16

[youtubedl] / youtube_dl / extractor / abc.py

diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py
index 6a29e587f007b28cfaf8bd2e714e276ab0b681a1..4ac323bf6de6d17016c2425c133aad460072cadd 100644 (file)
--- a/youtube_dl/extractor/abc.py
+++ b/youtube_dl/extractor/abc.py
@@ -1,18 +1,26 @@
 from __future__ import unicode_literals
 
+import hashlib
+import hmac
 import re
+import time
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     js_to_json,
     int_or_none,
+    parse_iso8601,
+    try_get,
+    unescapeHTML,
+    update_url_query,
 )
 
 
 class ABCIE(InfoExtractor):
     IE_NAME = 'abc.net.au'
-    _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@@ -93,3 +101,93 @@ class ABCIE(InfoExtractor):
             'description': self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }
+
+
+class ABCIViewIE(InfoExtractor):
+    IE_NAME = 'abc.net.au:iview'
+    _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 = [{
+        'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00',
+        'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
+        'info_dict': {
+            'id': 'ZX9371A050S00',
+            'ext': 'mp4',
+            'title': "Gaston's Birthday",
+            'series': "Ben And Holly's Little Kingdom",
+            'description': 'md5:f9de914d02f226968f598ac76f105bcf',
+            'upload_date': '20180604',
+            'uploader_id': 'abc4kids',
+            'timestamp': 1528140219,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        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') or video_id
+        path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
+            int(time.time()), house_number)
+        sig = hmac.new(
+            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)
+
+        def tokenize_url(url, token):
+            return update_url_query(url, {
+                'hdnea': token,
+            })
+
+        for sd in ('sd', 'sd-low'):
+            sd_url = try_get(
+                stream, lambda x: x['streams']['hls'][sd], compat_str)
+            if not sd_url:
+                continue
+            formats = self._extract_m3u8_formats(
+                tokenize_url(sd_url, token), video_id, 'mp4',
+                entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+            if formats:
+                break
+        self._sort_formats(formats)
+
+        subtitles = {}
+        src_vtt = stream.get('captions', {}).get('src-vtt')
+        if src_vtt:
+            subtitles['en'] = [{
+                'url': src_vtt,
+                'ext': 'vtt',
+            }]
+
+        is_live = video_params.get('livestream') == '1'
+        if is_live:
+            title = self._live_title(title)
+
+        return {
+            'id': video_id,
+            'title': title,
+            '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'), ' '),
+            'series': unescapeHTML(video_params.get('seriesTitle')),
+            'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
+            '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,
+            'is_live': is_live,
+        }