Merge pull request #12909 from remitamine/raw-sub

[youtube-dl] / youtube_dl / extractor / abc.py

diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py
index c0e5d1abffca7ded0186f64e2b38d7a74ea25d30..60f753b95c6e89158c3d292bd62e8bee2cd74746 100644 (file)
--- a/youtube_dl/extractor/abc.py
+++ b/youtube_dl/extractor/abc.py
@@ -3,16 +3,19 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     js_to_json,
     int_or_none,
+    parse_iso8601,
+    try_get,
 )
 
 
 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',
@@ -23,6 +26,7 @@ class ABCIE(InfoExtractor):
             'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
             'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
         },
+        'skip': 'this video has expired',
     }, {
         'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326',
         'md5': 'db2a5369238b51f9811ad815b69dc086',
@@ -36,6 +40,7 @@ class ABCIE(InfoExtractor):
             'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
         },
         'add_ie': ['Youtube'],
+        'skip': 'Not accessible from Travis CI server',
     }, {
         'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
         'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
@@ -58,6 +63,9 @@ class ABCIE(InfoExtractor):
             r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
             webpage)
         if mobj is None:
+            expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
+            if expired:
+                raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
             raise ExtractorError('Unable to extract video urls')
 
         urls_info = self._parse_json(
@@ -88,3 +96,72 @@ 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/programs/[^/]+/(?P<id>[^/?#]+)'
+
+    # ABC iview programs are normally available for 14 days only.
+    _TESTS = [{
+        'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00',
+        'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
+        'info_dict': {
+            'id': 'ZX9735A001S00',
+            'ext': 'mp4',
+            'title': 'Diaries Of A Broken Mind',
+            'description': 'md5:7de3903874b7a1be279fe6b68718fc9e',
+            'upload_date': '20161010',
+            'uploader_id': 'abc2',
+            'timestamp': 1476064920,
+        },
+        'skip': 'Video gone',
+    }]
+
+    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')
+
+        format_urls = [
+            try_get(stream, lambda x: x['hds-unmetered'], compat_str)]
+
+        # May have higher quality video
+        sd_url = try_get(
+            stream, lambda x: x['streams']['hds']['sd'], compat_str)
+        if sd_url:
+            format_urls.append(sd_url.replace('metered', 'um'))
+
+        formats = []
+        for format_url in format_urls:
+            if format_url:
+                formats.extend(
+                    self._extract_akamai_formats(format_url, video_id))
+        self._sort_formats(formats)
+
+        subtitles = {}
+        src_vtt = stream.get('captions', {}).get('src-vtt')
+        if src_vtt:
+            subtitles['en'] = [{
+                'url': src_vtt,
+                'ext': 'vtt',
+            }]
+
+        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),
+            'duration': int_or_none(video_params.get('eventDuration')),
+            'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
+            'series': video_params.get('seriesTitle'),
+            '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),
+            'uploader_id': video_params.get('channel'),
+            'formats': formats,
+            'subtitles': subtitles,
+        }