X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fbbc.py;h=dd65b8d86a36f3bbb486072260f14ab652a1868e;hb=9e35298f973b25c513e30bbc1fe2a05a1c6b7fab;hp=83e6d024c7fd4c6ee2adde607e4f1cd203910805;hpb=522f6c066da93b6baec3399b7098556e5ec55f43;p=youtube-dl

diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py
index 83e6d024c..dd65b8d86 100644
--- a/youtube_dl/extractor/bbc.py
+++ b/youtube_dl/extractor/bbc.py
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 from ..utils import (
@@ -17,6 +18,7 @@ from ..utils import (
 from ..compat import (
     compat_etree_fromstring,
     compat_HTTPError,
+    compat_urlparse,
 )
 
 
@@ -223,6 +225,8 @@ class BBCCoUkIE(InfoExtractor):
         }
     ]
 
+    _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
+
     class MediaSelectionError(Exception):
         def __init__(self, id):
             self.id = id
@@ -334,6 +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))
+                        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))
@@ -348,7 +361,7 @@ class BBCCoUkIE(InfoExtractor):
                             fmt.update({
                                 'width': width,
                                 'height': height,
-                                'vbr': bitrate,
+                                'tbr': bitrate,
                                 'vcodec': encoding,
                             })
                         else:
@@ -357,7 +370,7 @@ class BBCCoUkIE(InfoExtractor):
                                 'acodec': encoding,
                                 'vcodec': 'none',
                             })
-                        if protocol == 'http':
+                        if protocol in ('http', 'https'):
                             # Direct link
                             fmt.update({
                                 'url': href,
@@ -376,6 +389,8 @@ class BBCCoUkIE(InfoExtractor):
                                 'rtmp_live': False,
                                 'ext': 'flv',
                             })
+                        else:
+                            continue
                         formats.append(fmt)
             elif kind == 'captions':
                 subtitles = self.extract_subtitles(media, programme_id)
@@ -394,7 +409,7 @@ class BBCCoUkIE(InfoExtractor):
                 description = smp_config['summary']
                 for item in smp_config['items']:
                     kind = item['kind']
-                    if kind != 'programme' and kind != 'radioProgramme':
+                    if kind not in ('programme', 'radioProgramme'):
                         continue
                     programme_id = item.get('vpid')
                     duration = int_or_none(item.get('duration'))
@@ -435,7 +450,7 @@ class BBCCoUkIE(InfoExtractor):
 
         for item in self._extract_items(playlist):
             kind = item.get('kind')
-            if kind != 'programme' and kind != 'radioProgramme':
+            if kind not in ('programme', 'radioProgramme'):
                 continue
             title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
             description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
@@ -1026,7 +1041,7 @@ class BBCIE(BBCCoUkIE):
 
 
 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'
 
@@ -1056,19 +1071,35 @@ class BBCCoUkArticleIE(InfoExtractor):
 
 
 class BBCCoUkPlaylistBaseIE(InfoExtractor):
+    def _entries(self, webpage, url, playlist_id):
+        single_page = 'page' in compat_urlparse.parse_qs(
+            compat_urlparse.urlparse(url).query)
+        for page_num in itertools.count(2):
+            for video_id in re.findall(
+                    self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
+                yield self.url_result(
+                    self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
+            if single_page:
+                return
+            next_page = self._search_regex(
+                r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2',
+                webpage, 'next page url', default=None, group='url')
+            if not next_page:
+                break
+            webpage = self._download_webpage(
+                compat_urlparse.urljoin(url, next_page), playlist_id,
+                'Downloading page %d' % page_num, page_num)
+
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        entries = [
-            self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
-            for video_id in re.findall(
-                self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
-
         title, description = self._extract_title_and_description(webpage)
 
-        return self.playlist_result(entries, playlist_id, title, description)
+        return self.playlist_result(
+            self._entries(webpage, url, playlist_id),
+            playlist_id, title, description)
 
 
 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
@@ -1117,6 +1148,24 @@ class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'French thriller serial about a missing teenager.',
         },
         'playlist_mincount': 7,
+    }, {
+        # multipage playlist, explicit page
+        'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
+        'info_dict': {
+            'id': 'b00mfl7n',
+            'title': 'Frozen Planet - Clips - BBC One',
+            'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+        },
+        'playlist_mincount': 24,
+    }, {
+        # multipage playlist, all pages
+        'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
+        'info_dict': {
+            'id': 'b00mfl7n',
+            'title': 'Frozen Planet - Clips - BBC One',
+            'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
+        },
+        'playlist_mincount': 142,
     }, {
         'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
         'only_matching': True,