Merge branch 'akamai_pv' of https://github.com/remitamine/youtube-dl into remitamine...

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

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index f337caf20e8d2b24692ac2c01903df8d9580f49b..a285ee7d898e0777005ff625b5fcc44f1013d683 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -21,15 +21,16 @@ from ..compat import (
     compat_os_name,
     compat_str,
     compat_urllib_error,
     compat_os_name,
     compat_str,
     compat_urllib_error,

-    compat_urllib_parse,
+    compat_urllib_parse_urlencode,
+    compat_urllib_request,

     compat_urlparse,
 )
     compat_urlparse,
 )

+from ..downloader.f4m import remove_encrypted_media

 from ..utils import (
     NO_DEFAULT,
     age_restricted,
     bug_reports_message,
     clean_html,
 from ..utils import (
     NO_DEFAULT,
     age_restricted,
     bug_reports_message,
     clean_html,

-    codec2ext,

     compiled_regex_type,
     determine_ext,
     error_to_compat_str,
     compiled_regex_type,
     determine_ext,
     error_to_compat_str,


@@ -49,6 +50,8 @@ from ..utils import (
     determine_protocol,
     parse_duration,
     mimetype2ext,
     determine_protocol,
     parse_duration,
     mimetype2ext,

+    update_Request,
+    update_url_query,

 )
 
 
 )
 
 


@@ -106,7 +109,7 @@ class InfoExtractor(object):
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",
                     * protocol   The protocol that will be used for the actual
                                  download, lower-case.
                                  "http", "https", "rtsp", "rtmp", "rtmpe",

-                                 "m3u8", or "m3u8_native".
+                                 "m3u8", "m3u8_native" or "http_dash_segments".

                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.
                     * preference Order number of this format. If this field is
                                  present and not None, the formats get sorted
                                  by this field, regardless of all other values.


@@ -229,6 +232,24 @@ class InfoExtractor(object):
     episode_number: Number of the video episode within a season, as an integer.
     episode_id:     Id of the video episode, as a unicode string.
 
     episode_number: Number of the video episode within a season, as an integer.
     episode_id:     Id of the video episode, as a unicode string.
 

+    The following fields should only be used when the media is a track or a part of
+    a music album:
+
+    track:          Title of the track.
+    track_number:   Number of the track within an album or a disc, as an integer.
+    track_id:       Id of the track (useful in case of custom indexing, e.g. 6.iii),
+                    as a unicode string.
+    artist:         Artist(s) of the track.
+    genre:          Genre(s) of the track.
+    album:          Title of the album the track belongs to.
+    album_type:     Type of the album (e.g. "Demo", "Full-length", "Split", "Compilation", etc).
+    album_artist:   List of all artists appeared on the album (e.g.
+                    "Ash Borer / Fell Voices" or "Various Artists", useful for splits
+                    and compilations).
+    disc_number:    Number of the disc or other physical medium the track belongs to,
+                    as an integer.
+    release_year:   Year (YYYY) when the album was released.
+

     Unless mentioned otherwise, the fields should be Unicode strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.
     Unless mentioned otherwise, the fields should be Unicode strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.


@@ -346,7 +367,7 @@ class InfoExtractor(object):
     def IE_NAME(self):
         return compat_str(type(self).__name__[:-2])
 
     def IE_NAME(self):
         return compat_str(type(self).__name__[:-2])
 

-    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
+    def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):

         """ Returns the response handle """
         if note is None:
             self.report_download_webpage(video_id)
         """ Returns the response handle """
         if note is None:
             self.report_download_webpage(video_id)


@@ -355,6 +376,14 @@ class InfoExtractor(object):
                 self.to_screen('%s' % (note,))
             else:
                 self.to_screen('%s: %s' % (video_id, note))
                 self.to_screen('%s' % (note,))
             else:
                 self.to_screen('%s: %s' % (video_id, note))

+        if isinstance(url_or_request, compat_urllib_request.Request):
+            url_or_request = update_Request(
+                url_or_request, data=data, headers=headers, query=query)
+        else:
+            if query:
+                url_or_request = update_url_query(url_or_request, query)
+            if data is not None or headers:
+                url_or_request = sanitized_Request(url_or_request, data, headers)

         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
         try:
             return self._downloader.urlopen(url_or_request)
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:


@@ -370,13 +399,13 @@ class InfoExtractor(object):
                 self._downloader.report_warning(errmsg)
                 return False
 
                 self._downloader.report_warning(errmsg)
                 return False
 

-    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None):
+    def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None, data=None, headers={}, query={}):

         """ Returns a tuple (page content as string, URL handle) """
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 
         """ Returns a tuple (page content as string, URL handle) """
         # Strip hashes from the URL (#1038)
         if isinstance(url_or_request, (compat_str, str)):
             url_or_request = url_or_request.partition('#')[0]
 

-        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal)
+        urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query)

         if urlh is False:
             assert not fatal
             return False
         if urlh is False:
             assert not fatal
             return False


@@ -463,13 +492,13 @@ class InfoExtractor(object):
 
         return content
 
 
         return content
 

-    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
+    def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None, data=None, headers={}, query={}):

         """ Returns the data of the page as a string """
         success = False
         try_count = 0
         while success is False:
             try:
         """ Returns the data of the page as a string """
         success = False
         try_count = 0
         while success is False:
             try:

-                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding)
+                res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding, data=data, headers=headers, query=query)

                 success = True
             except compat_http_client.IncompleteRead as e:
                 try_count += 1
                 success = True
             except compat_http_client.IncompleteRead as e:
                 try_count += 1


@@ -484,10 +513,10 @@ class InfoExtractor(object):
 
     def _download_xml(self, url_or_request, video_id,
                       note='Downloading XML', errnote='Unable to download XML',
 
     def _download_xml(self, url_or_request, video_id,
                       note='Downloading XML', errnote='Unable to download XML',

-                      transform_source=None, fatal=True, encoding=None):
+                      transform_source=None, fatal=True, encoding=None, data=None, headers={}, query={}):

         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(
         """Return the xml as an xml.etree.ElementTree.Element"""
         xml_string = self._download_webpage(

-            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding)
+            url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding, data=data, headers=headers, query=query)

         if xml_string is False:
             return xml_string
         if transform_source:
         if xml_string is False:
             return xml_string
         if transform_source:


@@ -498,10 +527,10 @@ class InfoExtractor(object):
                        note='Downloading JSON metadata',
                        errnote='Unable to download JSON metadata',
                        transform_source=None,
                        note='Downloading JSON metadata',
                        errnote='Unable to download JSON metadata',
                        transform_source=None,

-                       fatal=True, encoding=None):
+                       fatal=True, encoding=None, data=None, headers={}, query={}):

         json_string = self._download_webpage(
             url_or_request, video_id, note, errnote, fatal=fatal,
         json_string = self._download_webpage(
             url_or_request, video_id, note, errnote, fatal=fatal,

-            encoding=encoding)
+            encoding=encoding, data=data, headers=headers, query=query)

         if (not fatal) and json_string is False:
             return None
         return self._parse_json(
         if (not fatal) and json_string is False:
             return None
         return self._parse_json(


@@ -813,7 +842,7 @@ class InfoExtractor(object):
         for input in re.findall(r'(?i)<input([^>]+)>', html):
             if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
                 continue
         for input in re.findall(r'(?i)<input([^>]+)>', html):
             if not re.search(r'type=(["\'])(?:hidden|submit)\1', input):
                 continue

-            name = re.search(r'name=(["\'])(?P<value>.+?)\1', input)
+            name = re.search(r'(?:name|id)=(["\'])(?P<value>.+?)\1', input)

             if not name:
                 continue
             value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)
             if not name:
                 continue
             value = re.search(r'value=(["\'])(?P<value>.*?)\1', input)


@@ -856,6 +885,7 @@ class InfoExtractor(object):
             proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
 
             if f.get('vcodec') == 'none':  # audio only
             proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
 
             if f.get('vcodec') == 'none':  # audio only

+                preference -= 50

                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['aac', 'mp3', 'm4a', 'webm', 'ogg', 'opus']
                 else:


@@ -866,6 +896,8 @@ class InfoExtractor(object):
                 except ValueError:
                     audio_ext_preference = -1
             else:
                 except ValueError:
                     audio_ext_preference = -1
             else:

+                if f.get('acodec') == 'none':  # video only
+                    preference -= 40

                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['flv', 'mp4', 'webm']
                 else:
                 if self._downloader.params.get('prefer_free_formats'):
                     ORDER = ['flv', 'mp4', 'webm']
                 else:


@@ -967,12 +999,31 @@ class InfoExtractor(object):
         if manifest is False:
             return []
 
         if manifest is False:
             return []
 

+        return self._parse_f4m_formats(
+            manifest, manifest_url, video_id, preference=preference, f4m_id=f4m_id,
+            transform_source=transform_source, fatal=fatal)
+
+    def _parse_f4m_formats(self, manifest, manifest_url, video_id, preference=None, f4m_id=None,
+                           transform_source=lambda s: fix_xml_ampersands(s).strip(),
+                           fatal=True):
+        # currently youtube-dl cannot decode the playerVerificationChallenge as Akamai uses Adobe Alchemy
+        akamai_pv = manifest.find('{http://ns.adobe.com/f4m/1.0}pv-2.0')
+        if akamai_pv is not None and ';' in akamai_pv.text:
+            playerVerificationChallenge = akamai_pv.text.split(';')[0]
+            if playerVerificationChallenge.strip() != '':
+                return []
+

         formats = []
         manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
         if not media_nodes:
             manifest_version = '2.0'
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')
         formats = []
         manifest_version = '1.0'
         media_nodes = manifest.findall('{http://ns.adobe.com/f4m/1.0}media')
         if not media_nodes:
             manifest_version = '2.0'
             media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media')

+        # Remove unsupported DRM protected media from final formats
+        # rendition (see https://github.com/rg3/youtube-dl/issues/8573).
+        media_nodes = remove_encrypted_media(media_nodes)
+        if not media_nodes:
+            return formats

         base_url = xpath_text(
             manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'],
             'base URL', default=None)
         base_url = xpath_text(
             manifest, ['{http://ns.adobe.com/f4m/1.0}baseURL', '{http://ns.adobe.com/f4m/2.0}baseURL'],
             'base URL', default=None)


@@ -992,7 +1043,8 @@ class InfoExtractor(object):
                 # bitrate in f4m downloader
                 if determine_ext(manifest_url) == 'f4m':
                     formats.extend(self._extract_f4m_formats(
                 # bitrate in f4m downloader
                 if determine_ext(manifest_url) == 'f4m':
                     formats.extend(self._extract_f4m_formats(

-                        manifest_url, video_id, preference, f4m_id, fatal=fatal))
+                        manifest_url, video_id, preference=preference, f4m_id=f4m_id,
+                        transform_source=transform_source, fatal=fatal))

                     continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({
                     continue
             tbr = int_or_none(media_el.attrib.get('bitrate'))
             formats.append({


@@ -1004,8 +1056,6 @@ class InfoExtractor(object):
                 'height': int_or_none(media_el.attrib.get('height')),
                 'preference': preference,
             })
                 'height': int_or_none(media_el.attrib.get('height')),
                 'preference': preference,
             })

-        self._sort_formats(formats)
-

         return formats
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
         return formats
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,


@@ -1126,7 +1176,6 @@ class InfoExtractor(object):
                     last_media = None
                 formats.append(f)
                 last_info = {}
                     last_media = None
                 formats.append(f)
                 last_info = {}

-        self._sort_formats(formats)

         return formats
 
     @staticmethod
         return formats
 
     @staticmethod


@@ -1141,8 +1190,8 @@ class InfoExtractor(object):
                 out.append('{%s}%s' % (namespace, c))
         return '/'.join(out)
 
                 out.append('{%s}%s' % (namespace, c))
         return '/'.join(out)
 

-    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None):
-        smil = self._download_smil(smil_url, video_id, fatal=fatal)
+    def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None, transform_source=None):
+        smil = self._download_smil(smil_url, video_id, fatal=fatal, transform_source=transform_source)

 
         if smil is False:
             assert not fatal
 
         if smil is False:
             assert not fatal


@@ -1159,10 +1208,10 @@ class InfoExtractor(object):
             return {}
         return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
 
             return {}
         return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params)
 

-    def _download_smil(self, smil_url, video_id, fatal=True):
+    def _download_smil(self, smil_url, video_id, fatal=True, transform_source=None):

         return self._download_xml(
             smil_url, video_id, 'Downloading SMIL file',
         return self._download_xml(
             smil_url, video_id, 'Downloading SMIL file',

-            'Unable to download SMIL file', fatal=fatal)
+            'Unable to download SMIL file', fatal=fatal, transform_source=transform_source)

 
     def _parse_smil(self, smil, smil_url, video_id, f4m_params=None):
         namespace = self._parse_smil_namespace(smil)
 
     def _parse_smil(self, smil, smil_url, video_id, f4m_params=None):
         namespace = self._parse_smil_namespace(smil)


@@ -1283,7 +1332,7 @@ class InfoExtractor(object):
                         'plugin': 'flowplayer-3.2.0.1',
                     }
                 f4m_url += '&' if '?' in f4m_url else '?'
                         'plugin': 'flowplayer-3.2.0.1',
                     }
                 f4m_url += '&' if '?' in f4m_url else '?'

-                f4m_url += compat_urllib_parse.urlencode(f4m_params)
+                f4m_url += compat_urllib_parse_urlencode(f4m_params)

                 formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
                 continue
 
                 formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
                 continue
 


@@ -1300,8 +1349,6 @@ class InfoExtractor(object):
                 })
                 continue
 
                 })
                 continue
 

-        self._sort_formats(formats)
-

         return formats
 
     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):
         return formats
 
     def _parse_smil_subtitles(self, smil, namespace=None, subtitles_lang='en'):


@@ -1312,7 +1359,7 @@ class InfoExtractor(object):
             if not src or src in urls:
                 continue
             urls.append(src)
             if not src or src in urls:
                 continue
             urls.append(src)

-            ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type'))
+            ext = textstream.get('ext') or mimetype2ext(textstream.get('type')) or determine_ext(src)

             lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
             subtitles.setdefault(lang, []).append({
                 'url': src,
             lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
             subtitles.setdefault(lang, []).append({
                 'url': src,


@@ -1448,8 +1495,9 @@ class InfoExtractor(object):
                         continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)
                         continue
                     representation_attrib = adaptation_set.attrib.copy()
                     representation_attrib.update(representation.attrib)

-                    mime_type = representation_attrib.get('mimeType')
-                    content_type = mime_type.split('/')[0] if mime_type else representation_attrib.get('contentType')
+                    # According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory
+                    mime_type = representation_attrib['mimeType']
+                    content_type = mime_type.split('/')[0]

                     if content_type == 'text':
                         # TODO implement WebVTT downloading
                         pass
                     if content_type == 'text':
                         # TODO implement WebVTT downloading
                         pass


@@ -1472,7 +1520,7 @@ class InfoExtractor(object):
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,
                         f = {
                             'format_id': '%s-%s' % (mpd_id, representation_id) if mpd_id else representation_id,
                             'url': base_url,

-                            'ext': codec2ext(representation_attrib.get('codecs')),
+                            'ext': mimetype2ext(mime_type),

                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
                             'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),
                             'width': int_or_none(representation_attrib.get('width')),
                             'height': int_or_none(representation_attrib.get('height')),
                             'tbr': int_or_none(representation_attrib.get('bandwidth'), 1000),


@@ -1491,9 +1539,16 @@ class InfoExtractor(object):
                                 representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)
                                 representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
                             media_template = representation_ms_info['media_template']
                             media_template = media_template.replace('$RepresentationID$', representation_id)

-                            media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template)
+                            media_template = re.sub(r'\$(Number|Bandwidth)%([^$]+)\$', r'%(\1)\2', media_template)

                             media_template.replace('$$', '$')
                             media_template.replace('$$', '$')

-                            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'])]
+                            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'],
                         if 'segment_urls' in representation_ms_info:
                             f.update({
                                 'segment_urls': representation_ms_info['segment_urls'],


@@ -1518,7 +1573,6 @@ class InfoExtractor(object):
                             existing_format.update(f)
                     else:
                         self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
                             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):
         return formats
 
     def _live_title(self, name):