Prepare to release.

[youtubedl] / youtube_dl / extractor / bbc.py

diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index deb9cc1c0fe2855c77c330f36f06069e8448189f..8a2ed0ab6851e3ee128aea4fbb1254c0d37cdd7b 100644 (file)
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -225,6 +225,8 @@ class BBCCoUkIE(InfoExtractor):
         }
     ]
 
         }
     ]
 

+    _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
+

     class MediaSelectionError(Exception):
         def __init__(self, id):
             self.id = id
     class MediaSelectionError(Exception):
         def __init__(self, id):
             self.id = id


@@ -336,6 +338,15 @@ class BBCCoUkIE(InfoExtractor):
                         formats.extend(self._extract_m3u8_formats(
                             href, programme_id, ext='mp4', entry_protocol='m3u8_native',
                             m3u8_id=format_id, fatal=False))
                         formats.extend(self._extract_m3u8_formats(
                             href, programme_id, ext='mp4', entry_protocol='m3u8_native',
                             m3u8_id=format_id, fatal=False))

+                        if re.search(self._USP_RE, href):
+                            usp_formats = self._extract_m3u8_formats(
+                                re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href),
+                                programme_id, ext='mp4', entry_protocol='m3u8_native',
+                                m3u8_id=format_id, fatal=False)
+                            for f in usp_formats:
+                                if f.get('height') and f['height'] > 720:
+                                    continue
+                                formats.append(f)

                     elif transfer_format == 'hds':
                         formats.extend(self._extract_f4m_formats(
                             href, programme_id, f4m_id=format_id, fatal=False))
                     elif transfer_format == 'hds':
                         formats.extend(self._extract_f4m_formats(
                             href, programme_id, f4m_id=format_id, fatal=False))


@@ -1028,7 +1039,7 @@ class BBCIE(BBCCoUkIE):
 
 
 class BBCCoUkArticleIE(InfoExtractor):
 
 
 class BBCCoUkArticleIE(InfoExtractor):

-    _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'

     IE_NAME = 'bbc.co.uk:article'
     IE_DESC = 'BBC articles'
 
     IE_NAME = 'bbc.co.uk:article'
     IE_DESC = 'BBC articles'