toss new stuff into old file

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

diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py
index dcc5fc2fadff772b58615c7beb9bc18084a6465f..ea682fb6f2785919e88dc6de03e25ca899d1c29f 100644 (file)
--- a/youtube_dl/extractor/bbccouk.py
+++ b/youtube_dl/extractor/bbccouk.py
@@ -5,9 +5,11 @@ import xml.etree.ElementTree
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
+    parse_duration,
     int_or_none,
 )
 from ..compat import compat_HTTPError
+import re
 
 
 class BBCCoUkIE(InfoExtractor):
@@ -394,3 +396,102 @@ class BBCCoUkIE(InfoExtractor):
             'formats': formats,
             'subtitles': subtitles,
         }
+
+
+class BBCNewsIE(BBCCoUkIE):
+    IE_NAME = 'bbc.com'
+    IE_DESC = 'BBC news'
+    _VALID_URL = r'https?://(?:www\.)?(?:bbc\.co\.uk|bbc\.com)/news/(?P<id>[^/]+)'
+
+    mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s'
+
+    _TESTS = [{
+        'url': 'http://www.bbc.com/news/world-europe-32668511',
+        'info_dict': {
+            'id': 'world-europe-32668511',
+            'title': 'Russia stages massive WW2 parade despite Western boycott',
+        },
+        'playlist_count': 2,
+    },{
+        'url': 'http://www.bbc.com/news/business-28299555',
+        'info_dict': {
+            'id': 'business-28299555',
+            'title': 'Farnborough Airshow: Video highlights',
+        },
+        'playlist_count': 9,
+    },{
+        'url': 'http://www.bbc.com/news/world-europe-32041533',
+        'note': 'Video',
+        'info_dict': {
+            'id': 'p02mprgb',
+            'ext': 'mp4',
+            'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
+            'description': 'Germanwings plane crash site in aerial video - Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
+            'duration': 47,
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }]
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        webpage = self._download_webpage(url, list_id)
+
+        list_title = self._html_search_regex(r'<title>(.*?)(?:\s*-\s*BBC News)?</title>', webpage, 'list title')
+
+        pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None)
+        if pubdate:
+           pubdate = pubdate.replace('-','')
+
+        ret = []
+        # works with bbc.com/news/something-something-123456 articles
+        matches = re.findall(r"data-media-meta='({[^']+})'", webpage)
+        if not matches:
+           # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc}
+           # in http://www.bbc.com/news/video_and_audio/international
+           matches = re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
+        if not matches:
+           raise ExtractorError('No video found', expected=True)
+
+        for ent in matches:
+            jent = self._parse_json(ent,list_id)
+
+            programme_id = jent.get('externalId',None)
+            xml_url = jent.get('href', None)
+
+            title = jent['caption']
+            duration = parse_duration(jent.get('duration',None))
+            description = list_title + ' - ' + jent.get('caption','')
+            thumbnail = None
+            if jent.has_key('image'):
+               thumbnail=jent['image'].get('href',None)
+
+            if programme_id:
+               formats, subtitles = self._download_media_selector(programme_id)
+            elif xml_url:
+               # Cheap fallback
+               # http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml
+               xml = self._download_webpage(xml_url, programme_id, 'Downloading playlist.sxml for externalId (fallback)')
+               programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)')
+               formats, subtitles = self._download_media_selector(programme_id)
+            else:
+               raise ExtractorError('data-media-meta entry has no externalId or href value.')
+               
+            self._sort_formats(formats)
+
+            ret.append( {
+                'id': programme_id,
+                'uploader': 'BBC News',
+                'upload_date': pubdate,
+                'title': title,
+                'description': description,
+                'thumbnail': thumbnail,
+                'duration': duration,
+                'formats': formats,
+                'subtitles': subtitles,
+            } )
+
+        if len(ret) > 0:
+           return self.playlist_result(ret, list_id, list_title)
+        raise ExtractorError('No video found', expected=True)