rename _parse_mpd to _parse_mpd_formats and add default value for mpd namespace

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

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index ee0e3d8d162b709dde59e01fe0372ef73d78bad9..271ba37396692ea5242800d06896e5c991ea0de8 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -1,4 +1,4 @@
-from __future__ import unicode_literals
+from __future__ import unicode_literals, division
 
 import base64
 import datetime
@@ -1343,18 +1343,21 @@ class InfoExtractor(object):
         mpd, urlh = res
         mpd_base_url = re.match(r'https?://.+/', urlh.geturl()).group()
 
-        return self._parse_mpd(
+        return self._parse_mpd_formats(
             compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
 
-    def _parse_mpd(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
+    def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
         if mpd_doc.get('type') == 'dynamic':
             return []
 
-        namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace')
+        namespace = self._search_regex(r'(?i)^{([^}]+)?}MPD$', mpd_doc.tag, 'namespace', default=None)
 
         def _add_ns(path):
             return self._xpath_ns(path, namespace)
 
+        def is_drm_protected(element):
+            return element.find(_add_ns('ContentProtection')) is not None
+
         def extract_multisegment_info(element, ms_parent_info):
             ms_info = ms_parent_info.copy()
             segment_list = element.find(_add_ns('SegmentList'))
@@ -1406,8 +1409,12 @@ class InfoExtractor(object):
                 'timescale': 1,
             })
             for adaptation_set in period.findall(_add_ns('AdaptationSet')):
+                if is_drm_protected(adaptation_set):
+                    continue
                 adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info)
                 for representation in adaptation_set.findall(_add_ns('Representation')):
+                    if is_drm_protected(representation):
+                        continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)
                     mime_type = representation_attrib.get('mimeType')
@@ -1447,11 +1454,9 @@ class InfoExtractor(object):
                                 representation_ms_info['total_number'] = int(math.ceil(period_duration / segment_duration))
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
-                            media_template = re.sub(r'\$(Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
-                            media_template = media_template % {'Bandwidth': representation_attrib.get('bandwidth')}
-                            media_template = re.sub(r'\$(Number)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
                             media_template.replace('$$', '$')
-                            representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])]
+                            representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number, 'Bandwidth': representation_attrib.get('bandwidth')} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])]
                         if 'segment_urls' in representation_ms_info:
                             f.update({
                                 'segment_urls': representation_ms_info['segment_urls'],
@@ -1476,6 +1481,7 @@ class InfoExtractor(object):
                             existing_format.update(f)
                     else:
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
+        self._sort_formats(formats)
         return formats
 
     def _live_title(self, name):