Annotate some highlights of the release.

[youtubedl] / youtube_dl / extractor / discoverygo.py

diff --git a/youtube_dl/extractor/discoverygo.py b/youtube_dl/extractor/discoverygo.py
index adb68b96c4033a3ef5cf8dcf3357fa64ed73acb8..9e7b14a7d594e5fbb145aab0521bc4f8250305a6 100644 (file)
--- a/youtube_dl/extractor/discoverygo.py
+++ b/youtube_dl/extractor/discoverygo.py
@@ -1,49 +1,43 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     extract_attributes,
+    ExtractorError,
     int_or_none,
     parse_age_limit,
+    remove_end,
     unescapeHTML,
+    url_or_none,
 )
 
 
-class DiscoveryGoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?discoverygo\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
-    _TEST = {
-        'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
-        'info_dict': {
-            'id': '57a33c536b66d1cd0345eeb1',
-            'ext': 'mp4',
-            'title': 'Kiss First, Ask Questions Later!',
-            'description': 'md5:fe923ba34050eae468bffae10831cb22',
-            'duration': 2579,
-            'series': 'Love at First Kiss',
-            'season_number': 1,
-            'episode_number': 1,
-            'age_limit': 14,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, display_id)
-
-        container = extract_attributes(
-            self._search_regex(
-                r'(<div[^>]+class=["\']video-player-container[^>]+>)',
-                webpage, 'video container'))
-
-        video = self._parse_json(
-            unescapeHTML(container.get('data-video') or container.get('data-json')),
-            display_id)
+class DiscoveryGoBaseIE(InfoExtractor):
+    _VALID_URL_TEMPLATE = r'''(?x)https?://(?:www\.)?(?:
+            discovery|
+            investigationdiscovery|
+            discoverylife|
+            animalplanet|
+            ahctv|
+            destinationamerica|
+            sciencechannel|
+            tlc|
+            velocitychannel
+        )go\.com/%s(?P<id>[^/?#&]+)'''
 
+    def _extract_video_info(self, video, stream, display_id):
         title = video['name']
 
-        stream = video['stream']
+        if not stream:
+            if video.get('authenticated') is True:
+                raise ExtractorError(
+                    'This video is only available via cable service provider subscription that'
+                    ' is not currently supported. You may want to use --cookies.', expected=True)
+            else:
+                raise ExtractorError('Unable to find stream')
         STREAM_URL_SUFFIX = 'streamUrl'
         formats = []
         for stream_kind in ('', 'hds'):
@@ -75,12 +69,15 @@ class DiscoveryGoIE(InfoExtractor):
         captions = stream.get('captions')
         if isinstance(captions, list):
             for caption in captions:
-                subtitle_url = caption.get('fileUrl')
-                if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
-                        not subtitle_url.startswith('http')):
+                subtitle_url = url_or_none(caption.get('fileUrl'))
+                if not subtitle_url or not subtitle_url.startswith('http'):
                     continue
                 lang = caption.get('fileLang', 'en')
-                subtitles.setdefault(lang, []).append({'url': subtitle_url})
+                ext = determine_ext(subtitle_url)
+                subtitles.setdefault(lang, []).append({
+                    'url': subtitle_url,
+                    'ext': 'ttml' if ext == 'xml' else ext,
+                })
 
         return {
             'id': video_id,
@@ -96,3 +93,83 @@ class DiscoveryGoIE(InfoExtractor):
             'formats': formats,
             'subtitles': subtitles,
         }
+
+
+class DiscoveryGoIE(DiscoveryGoBaseIE):
+    _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+'
+    _GEO_COUNTRIES = ['US']
+    _TEST = {
+        'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/',
+        'info_dict': {
+            'id': '58c167d86b66d12f2addeb01',
+            'ext': 'mp4',
+            'title': 'Reaper Madness',
+            'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78',
+            'duration': 2519,
+            'series': 'Bering Sea Gold',
+            'season_number': 8,
+            'episode_number': 6,
+            'age_limit': 14,
+        },
+    }
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        container = extract_attributes(
+            self._search_regex(
+                r'(<div[^>]+class=["\']video-player-container[^>]+>)',
+                webpage, 'video container'))
+
+        video = self._parse_json(
+            container.get('data-video') or container.get('data-json'),
+            display_id)
+
+        stream = video.get('stream')
+
+        return self._extract_video_info(video, stream, display_id)
+
+
+class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE):
+    _VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % ''
+    _TEST = {
+        'url': 'https://www.discoverygo.com/bering-sea-gold/',
+        'info_dict': {
+            'id': 'bering-sea-gold',
+            'title': 'Bering Sea Gold',
+            'description': 'md5:cc5c6489835949043c0cc3ad66c2fa0e',
+        },
+        'playlist_mincount': 6,
+    }
+
+    @classmethod
+    def suitable(cls, url):
+        return False if DiscoveryGoIE.suitable(url) else super(
+            DiscoveryGoPlaylistIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        entries = []
+        for mobj in re.finditer(r'data-json=(["\'])(?P<json>{.+?})\1', webpage):
+            data = self._parse_json(
+                mobj.group('json'), display_id,
+                transform_source=unescapeHTML, fatal=False)
+            if not isinstance(data, dict) or data.get('type') != 'episode':
+                continue
+            episode_url = data.get('socialUrl')
+            if not episode_url:
+                continue
+            entries.append(self.url_result(
+                episode_url, ie=DiscoveryGoIE.ie_key(),
+                video_id=data.get('id')))
+
+        return self.playlist_result(
+            entries, display_id,
+            remove_end(self._og_search_title(
+                webpage, fatal=False), ' | Discovery GO'),
+            self._og_search_description(webpage))