[YoutubeDL] remove compatiblity with the old subtitles system

[youtube-dl] / youtube_dl / YoutubeDL.py

diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index 14e92ddcf7258d60b38b8816005b089a0801cb37..70b364c9bb3e90afa063208925e7f2a2501e603a 100755 (executable)
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -25,6 +25,7 @@ if os.name == 'nt':
     import ctypes
 
 from .compat import (
     import ctypes
 
 from .compat import (

+    compat_basestring,

     compat_cookiejar,
     compat_expanduser,
     compat_http_client,
     compat_cookiejar,
     compat_expanduser,
     compat_http_client,


@@ -153,7 +154,7 @@ class YoutubeDL(object):
     allsubtitles:      Downloads all the subtitles of the video
                        (requires writesubtitles or writeautomaticsub)
     listsubtitles:     Lists all available subtitles for the video
     allsubtitles:      Downloads all the subtitles of the video
                        (requires writesubtitles or writeautomaticsub)
     listsubtitles:     Lists all available subtitles for the video

-    subtitlesformat:   Subtitle format [srt/sbv/vtt] (default=srt)
+    subtitlesformat:   The format code for subtitles

     subtitleslangs:    List of languages of the subtitles to download
     keepvideo:         Keep the video file after post-processing
     daterange:         A DateRange object, download only if the upload_date is in the range.
     subtitleslangs:    List of languages of the subtitles to download
     keepvideo:         Keep the video file after post-processing
     daterange:         A DateRange object, download only if the upload_date is in the range.


@@ -227,6 +228,12 @@ class YoutubeDL(object):
     external_downloader:  Executable of the external downloader to call.
     listformats:       Print an overview of available video formats and exit.
     list_thumbnails:   Print a table of all thumbnails and exit.
     external_downloader:  Executable of the external downloader to call.
     listformats:       Print an overview of available video formats and exit.
     list_thumbnails:   Print a table of all thumbnails and exit.

+    match_filter:      A function that gets called with the info_dict of
+                       every video.
+                       If it returns a message, the video is ignored.
+                       If it returns None, the video is downloaded.
+                       match_filter_func in utils.py is one example for this.
+    no_color:          Do not emit color codes in output.

 
 
     The following parameters are not used by YoutubeDL itself, they are used by
 
 
     The following parameters are not used by YoutubeDL itself, they are used by


@@ -484,7 +491,7 @@ class YoutubeDL(object):
         else:
             if self.params.get('no_warnings'):
                 return
         else:
             if self.params.get('no_warnings'):
                 return

-            if self._err_file.isatty() and os.name != 'nt':
+            if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':

                 _msg_header = '\033[0;33mWARNING:\033[0m'
             else:
                 _msg_header = 'WARNING:'
                 _msg_header = '\033[0;33mWARNING:\033[0m'
             else:
                 _msg_header = 'WARNING:'


@@ -496,7 +503,7 @@ class YoutubeDL(object):
         Do the same as trouble, but prefixes the message with 'ERROR:', colored
         in red if stderr is a tty file.
         '''
         Do the same as trouble, but prefixes the message with 'ERROR:', colored
         in red if stderr is a tty file.
         '''

-        if self._err_file.isatty() and os.name != 'nt':
+        if not self.params.get('no_color') and self._err_file.isatty() and os.name != 'nt':

             _msg_header = '\033[0;31mERROR:\033[0m'
         else:
             _msg_header = 'ERROR:'
             _msg_header = '\033[0;31mERROR:\033[0m'
         else:
             _msg_header = 'ERROR:'


@@ -553,7 +560,7 @@ class YoutubeDL(object):
             self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 
             self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
             return None
 

-    def _match_entry(self, info_dict):
+    def _match_entry(self, info_dict, incomplete):

         """ Returns None iff the file should be downloaded """
 
         video_title = info_dict.get('title', info_dict.get('id', 'video'))
         """ Returns None iff the file should be downloaded """
 
         video_title = info_dict.get('title', info_dict.get('id', 'video'))


@@ -582,9 +589,17 @@ class YoutubeDL(object):
             if max_views is not None and view_count > max_views:
                 return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
         if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
             if max_views is not None and view_count > max_views:
                 return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
         if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):

-            return 'Skipping "%s" because it is age restricted' % title
+            return 'Skipping "%s" because it is age restricted' % video_title

         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title
         if self.in_download_archive(info_dict):
             return '%s has already been recorded in archive' % video_title

+
+        if not incomplete:
+            match_filter = self.params.get('match_filter')
+            if match_filter is not None:
+                ret = match_filter(info_dict)
+                if ret is not None:
+                    return ret
+

         return None
 
     @staticmethod
         return None
 
     @staticmethod


@@ -778,7 +793,7 @@ class YoutubeDL(object):
                     'extractor_key': ie_result['extractor_key'],
                 }
 
                     'extractor_key': ie_result['extractor_key'],
                 }
 

-                reason = self._match_entry(entry)
+                reason = self._match_entry(entry, incomplete=True)

                 if reason is not None:
                     self.to_screen('[download] ' + reason)
                     continue
                 if reason is not None:
                     self.to_screen('[download] ' + reason)
                     continue


@@ -825,26 +840,43 @@ class YoutubeDL(object):
             '!=': operator.ne,
         }
         operator_rex = re.compile(r'''(?x)\s*\[
             '!=': operator.ne,
         }
         operator_rex = re.compile(r'''(?x)\s*\[

-            (?P<key>width|height|tbr|abr|vbr|filesize|fps)
+            (?P<key>width|height|tbr|abr|vbr|asr|filesize|fps)

             \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
             (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
             \]$
             ''' % '|'.join(map(re.escape, OPERATORS.keys())))
         m = operator_rex.search(format_spec)
             \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
             (?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
             \]$
             ''' % '|'.join(map(re.escape, OPERATORS.keys())))
         m = operator_rex.search(format_spec)

+        if m:
+            try:
+                comparison_value = int(m.group('value'))
+            except ValueError:
+                comparison_value = parse_filesize(m.group('value'))
+                if comparison_value is None:
+                    comparison_value = parse_filesize(m.group('value') + 'B')
+                if comparison_value is None:
+                    raise ValueError(
+                        'Invalid value %r in format specification %r' % (
+                            m.group('value'), format_spec))
+            op = OPERATORS[m.group('op')]
+

         if not m:
         if not m:

-            raise ValueError('Invalid format specification %r' % format_spec)
+            STR_OPERATORS = {
+                '=': operator.eq,
+                '!=': operator.ne,
+            }
+            str_operator_rex = re.compile(r'''(?x)\s*\[
+                \s*(?P<key>ext|acodec|vcodec|container|protocol)
+                \s*(?P<op>%s)(?P<none_inclusive>\s*\?)?
+                \s*(?P<value>[a-zA-Z0-9_-]+)
+                \s*\]$
+                ''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
+            m = str_operator_rex.search(format_spec)
+            if m:
+                comparison_value = m.group('value')
+                op = STR_OPERATORS[m.group('op')]

 
 

-        try:
-            comparison_value = int(m.group('value'))
-        except ValueError:
-            comparison_value = parse_filesize(m.group('value'))
-            if comparison_value is None:
-                comparison_value = parse_filesize(m.group('value') + 'B')
-            if comparison_value is None:
-                raise ValueError(
-                    'Invalid value %r in format specification %r' % (
-                        m.group('value'), format_spec))
-        op = OPERATORS[m.group('op')]
+        if not m:
+            raise ValueError('Invalid format specification %r' % format_spec)

 
         def _filter(f):
             actual_value = f.get(m.group('key'))
 
         def _filter(f):
             actual_value = f.get(m.group('key'))


@@ -937,6 +969,9 @@ class YoutubeDL(object):
             def has_header(self, h):
                 return h in self.headers
 
             def has_header(self, h):
                 return h in self.headers
 

+            def get_header(self, h, default=None):
+                return self.headers.get(h, default)
+

         pr = _PseudoRequest(info_dict['url'])
         self.cookiejar.add_cookie_header(pr)
         return pr.headers.get('Cookie')
         pr = _PseudoRequest(info_dict['url'])
         self.cookiejar.add_cookie_header(pr)
         return pr.headers.get('Cookie')


@@ -963,9 +998,11 @@ class YoutubeDL(object):
             thumbnails.sort(key=lambda t: (
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))
             thumbnails.sort(key=lambda t: (
                 t.get('preference'), t.get('width'), t.get('height'),
                 t.get('id'), t.get('url')))

-            for t in thumbnails:
+            for i, t in enumerate(thumbnails):

                 if 'width' in t and 'height' in t:
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])
                 if 'width' in t and 'height' in t:
                     t['resolution'] = '%dx%d' % (t['width'], t['height'])

+                if t.get('id') is None:
+                    t['id'] = '%d' % i

 
         if thumbnails and 'thumbnail' not in info_dict:
             info_dict['thumbnail'] = thumbnails[-1]['url']
 
         if thumbnails and 'thumbnail' not in info_dict:
             info_dict['thumbnail'] = thumbnails[-1]['url']


@@ -982,6 +1019,15 @@ class YoutubeDL(object):
                 info_dict['timestamp'])
             info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
 
                 info_dict['timestamp'])
             info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
 

+        if self.params.get('listsubtitles', False):
+            if 'automatic_captions' in info_dict:
+                self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions')
+            self.list_subtitles(info_dict['id'], info_dict.get('subtitles'), 'subtitles')
+            return
+        info_dict['requested_subtitles'] = self.process_subtitles(
+            info_dict['id'], info_dict.get('subtitles'),
+            info_dict.get('automatic_captions'))
+

         # This extractors handle format selection themselves
         if info_dict['extractor'] in ['Youku']:
             if download:
         # This extractors handle format selection themselves
         if info_dict['extractor'] in ['Youku']:
             if download:


@@ -1073,9 +1119,10 @@ class YoutubeDL(object):
                                 else self.params['merge_output_format'])
                             selected_format = {
                                 'requested_formats': formats_info,
                                 else self.params['merge_output_format'])
                             selected_format = {
                                 'requested_formats': formats_info,

-                                'format': rf,
-                                'format_id': rf,
-                                'ext': formats_info[0]['ext'],
+                                'format': '%s+%s' % (formats_info[0].get('format'),
+                                                     formats_info[1].get('format')),
+                                'format_id': '%s+%s' % (formats_info[0].get('format_id'),
+                                                        formats_info[1].get('format_id')),

                                 'width': formats_info[0].get('width'),
                                 'height': formats_info[0].get('height'),
                                 'resolution': formats_info[0].get('resolution'),
                                 'width': formats_info[0].get('width'),
                                 'height': formats_info[0].get('height'),
                                 'resolution': formats_info[0].get('resolution'),


@@ -1109,6 +1156,55 @@ class YoutubeDL(object):
         info_dict.update(formats_to_download[-1])
         return info_dict
 
         info_dict.update(formats_to_download[-1])
         return info_dict
 

+    def process_subtitles(self, video_id, normal_subtitles, automatic_captions):
+        """Select the requested subtitles and their format"""
+        available_subs = {}
+        if normal_subtitles and self.params.get('writesubtitles'):
+            available_subs.update(normal_subtitles)
+        if automatic_captions and self.params.get('writeautomaticsub'):
+            for lang, cap_info in automatic_captions.items():
+                if lang not in available_subs:
+                    available_subs[lang] = cap_info
+
+        if (not self.params.get('writesubtitles') and not
+                self.params.get('writeautomaticsub') or not
+                available_subs):
+            return None
+
+        if self.params.get('allsubtitles', False):
+            requested_langs = available_subs.keys()
+        else:
+            if self.params.get('subtitleslangs', False):
+                requested_langs = self.params.get('subtitleslangs')
+            elif 'en' in available_subs:
+                requested_langs = ['en']
+            else:
+                requested_langs = [list(available_subs.keys())[0]]
+
+        formats_query = self.params.get('subtitlesformat', 'best')
+        formats_preference = formats_query.split('/') if formats_query else []
+        subs = {}
+        for lang in requested_langs:
+            formats = available_subs.get(lang)
+            if formats is None:
+                self.report_warning('%s subtitles not available for %s' % (lang, video_id))
+                continue
+            for ext in formats_preference:
+                if ext == 'best':
+                    f = formats[-1]
+                    break
+                matches = list(filter(lambda f: f['ext'] == ext, formats))
+                if matches:
+                    f = matches[-1]
+                    break
+            else:
+                f = formats[-1]
+                self.report_warning(
+                    'No subtitle format found matching "%s" for language %s, '
+                    'using %s' % (formats_query, lang, f['ext']))
+            subs[lang] = f
+        return subs
+

     def process_info(self, info_dict):
         """Process a single resolved IE result."""
 
     def process_info(self, info_dict):
         """Process a single resolved IE result."""
 


@@ -1129,7 +1225,7 @@ class YoutubeDL(object):
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 
         if 'format' not in info_dict:
             info_dict['format'] = info_dict['ext']
 

-        reason = self._match_entry(info_dict)
+        reason = self._match_entry(info_dict, incomplete=False)

         if reason is not None:
             self.to_screen('[download] ' + reason)
             return
         if reason is not None:
             self.to_screen('[download] ' + reason)
             return


@@ -1211,15 +1307,22 @@ class YoutubeDL(object):
         subtitles_are_requested = any([self.params.get('writesubtitles', False),
                                        self.params.get('writeautomaticsub')])
 
         subtitles_are_requested = any([self.params.get('writesubtitles', False),
                                        self.params.get('writeautomaticsub')])
 

-        if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']:
+        if subtitles_are_requested and info_dict.get('requested_subtitles'):

             # subtitles download errors are already managed as troubles in relevant IE
             # that way it will silently go on when used with unsupporting IE
             # subtitles download errors are already managed as troubles in relevant IE
             # that way it will silently go on when used with unsupporting IE

-            subtitles = info_dict['subtitles']
-            sub_format = self.params.get('subtitlesformat', 'srt')
-            for sub_lang in subtitles.keys():
-                sub = subtitles[sub_lang]
-                if sub is None:
-                    continue
+            subtitles = info_dict['requested_subtitles']
+            for sub_lang, sub_info in subtitles.items():
+                sub_format = sub_info['ext']
+                if sub_info.get('data') is not None:
+                    sub_data = sub_info['data']
+                else:
+                    try:
+                        uf = self.urlopen(sub_info['url'])
+                        sub_data = uf.read().decode('utf-8')
+                    except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                        self.report_warning('Unable to download subtitle for "%s": %s' %
+                                            (sub_lang, compat_str(err)))
+                        continue

                 try:
                     sub_filename = subtitles_filename(filename, sub_lang, sub_format)
                     if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
                 try:
                     sub_filename = subtitles_filename(filename, sub_lang, sub_format)
                     if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):


@@ -1227,7 +1330,7 @@ class YoutubeDL(object):
                     else:
                         self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
                         with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
                     else:
                         self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
                         with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:

-                            subfile.write(sub)
+                            subfile.write(sub_data)

                 except (OSError, IOError):
                     self.report_error('Cannot write subtitles file ' + sub_filename)
                     return
                 except (OSError, IOError):
                     self.report_error('Cannot write subtitles file ' + sub_filename)
                     return


@@ -1522,7 +1625,6 @@ class YoutubeDL(object):
             line(f, idlen) for f in formats
             if f.get('preference') is None or f['preference'] >= -1000]
         if len(formats) > 1:
             line(f, idlen) for f in formats
             if f.get('preference') is None or f['preference'] >= -1000]
         if len(formats) > 1:

-            formats_s[0] += (' ' if self._format_note(formats[0]) else '') + '(worst)'

             formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
 
         header_line = line({
             formats_s[-1] += (' ' if self._format_note(formats[-1]) else '') + '(best)'
 
         header_line = line({


@@ -1549,6 +1651,17 @@ class YoutubeDL(object):
             ['ID', 'width', 'height', 'URL'],
             [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails]))
 
             ['ID', 'width', 'height', 'URL'],
             [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails]))
 

+    def list_subtitles(self, video_id, subtitles, name='subtitles'):
+        if not subtitles:
+            self.to_screen('%s has no %s' % (video_id, name))
+            return
+        self.to_screen(
+            'Available %s for %s:' % (name, video_id))
+        self.to_screen(render_table(
+            ['Language', 'formats'],
+            [[lang, ', '.join(f['ext'] for f in reversed(formats))]
+                for lang, formats in subtitles.items()]))
+

     def urlopen(self, req):
         """ Start an HTTP download """
 
     def urlopen(self, req):
         """ Start an HTTP download """
 


@@ -1558,7 +1671,7 @@ class YoutubeDL(object):
         # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
         # To work around aforementioned issue we will replace request's original URL with
         # percent-encoded one
         # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
         # To work around aforementioned issue we will replace request's original URL with
         # percent-encoded one

-        req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str)
+        req_is_string = isinstance(req, compat_basestring)

         url = req if req_is_string else req.get_full_url()
         url_escaped = escape_url(url)
 
         url = req if req_is_string else req.get_full_url()
         url_escaped = escape_url(url)