Merge remote-tracking branch 'h-collector/master'

[youtube-dl] / youtube_dl / YoutubeDL.py

diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py
index 4c3d45f48d99586c5e31487e8b91797e613aa349..0e73dc8ffe4a5fe8d0c890f0f4c1ccf28a688d2b 100755 (executable)
--- a/youtube_dl/YoutubeDL.py
+++ b/youtube_dl/YoutubeDL.py
@@ -54,6 +54,7 @@ from .utils import (
     PostProcessingError,
     platform_name,
     preferredencoding,
     PostProcessingError,
     platform_name,
     preferredencoding,

+    render_table,

     SameFileError,
     sanitize_filename,
     std_headers,
     SameFileError,
     sanitize_filename,
     std_headers,


@@ -145,6 +146,7 @@ class YoutubeDL(object):
     writeinfojson:     Write the video description to a .info.json file
     writeannotations:  Write the video annotations to a .annotations.xml file
     writethumbnail:    Write the thumbnail image to a file
     writeinfojson:     Write the video description to a .info.json file
     writeannotations:  Write the video annotations to a .annotations.xml file
     writethumbnail:    Write the thumbnail image to a file

+    write_all_thumbnails:  Write all thumbnail formats to files

     writesubtitles:    Write the video subtitles to a file
     writeautomaticsub: Write the automatic subtitles to a file
     allsubtitles:      Downloads all the subtitles of the video
     writesubtitles:    Write the video subtitles to a file
     writeautomaticsub: Write the automatic subtitles to a file
     allsubtitles:      Downloads all the subtitles of the video


@@ -221,6 +223,8 @@ class YoutubeDL(object):
                        youtube-dl servers for debugging.
     sleep_interval:    Number of seconds to sleep before each download.
     external_downloader:  Executable of the external downloader to call.
                        youtube-dl servers for debugging.
     sleep_interval:    Number of seconds to sleep before each download.
     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.

 
 
     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


@@ -892,6 +896,12 @@ class YoutubeDL(object):
             def get_full_url(self):
                 return self.url
 
             def get_full_url(self):
                 return self.url
 

+            def is_unverifiable(self):
+                return self.unverifiable
+
+            def has_header(self, h):
+                return h in self.headers
+

         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')


@@ -910,9 +920,14 @@ class YoutubeDL(object):
             info_dict['playlist_index'] = None
 
         thumbnails = info_dict.get('thumbnails')
             info_dict['playlist_index'] = None
 
         thumbnails = info_dict.get('thumbnails')

+        if thumbnails is None:
+            thumbnail = info_dict.get('thumbnail')
+            if thumbnail:
+                thumbnails = [{'url': thumbnail}]

         if thumbnails:
             thumbnails.sort(key=lambda t: (
         if thumbnails:
             thumbnails.sort(key=lambda t: (

-                t.get('width'), t.get('height'), t.get('url')))
+                t.get('preference'), t.get('width'), t.get('height'),
+                t.get('id'), t.get('url')))

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


@@ -984,9 +999,12 @@ class YoutubeDL(object):
             # element in the 'formats' field in info_dict is info_dict itself,
             # wich can't be exported to json
             info_dict['formats'] = formats
             # element in the 'formats' field in info_dict is info_dict itself,
             # wich can't be exported to json
             info_dict['formats'] = formats

-        if self.params.get('listformats', None):
+        if self.params.get('listformats'):

             self.list_formats(info_dict)
             return
             self.list_formats(info_dict)
             return

+        if self.params.get('list_thumbnails'):
+            self.list_thumbnails(info_dict)
+            return

 
         req_format = self.params.get('format')
         if req_format is None:
 
         req_format = self.params.get('format')
         if req_format is None:


@@ -1193,25 +1211,7 @@ class YoutubeDL(object):
                     self.report_error('Cannot write metadata to JSON file ' + infofn)
                     return
 
                     self.report_error('Cannot write metadata to JSON file ' + infofn)
                     return
 

-        if self.params.get('writethumbnail', False):
-            if info_dict.get('thumbnail') is not None:
-                thumb_format = determine_ext(info_dict['thumbnail'], 'jpg')
-                thumb_filename = os.path.splitext(filename)[0] + '.' + thumb_format
-                if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
-                    self.to_screen('[%s] %s: Thumbnail is already present' %
-                                   (info_dict['extractor'], info_dict['id']))
-                else:
-                    self.to_screen('[%s] %s: Downloading thumbnail ...' %
-                                   (info_dict['extractor'], info_dict['id']))
-                    try:
-                        uf = self.urlopen(info_dict['thumbnail'])
-                        with open(thumb_filename, 'wb') as thumbf:
-                            shutil.copyfileobj(uf, thumbf)
-                        self.to_screen('[%s] %s: Writing thumbnail to: %s' %
-                                       (info_dict['extractor'], info_dict['id'], thumb_filename))
-                    except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-                        self.report_warning('Unable to download thumbnail "%s": %s' %
-                                            (info_dict['thumbnail'], compat_str(err)))
+        self._write_thumbnails(info_dict, filename)

 
         if not self.params.get('skip_download', False):
             try:
 
         if not self.params.get('skip_download', False):
             try:


@@ -1494,8 +1494,26 @@ class YoutubeDL(object):
         header_line = line({
             'format_id': 'format code', 'ext': 'extension',
             'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)
         header_line = line({
             'format_id': 'format code', 'ext': 'extension',
             'resolution': 'resolution', 'format_note': 'note'}, idlen=idlen)

-        self.to_screen('[info] Available formats for %s:\n%s\n%s' %
-                       (info_dict['id'], header_line, '\n'.join(formats_s)))
+        self.to_screen(
+            '[info] Available formats for %s:\n%s\n%s' %
+            (info_dict['id'], header_line, '\n'.join(formats_s)))
+
+    def list_thumbnails(self, info_dict):
+        thumbnails = info_dict.get('thumbnails')
+        if not thumbnails:
+            tn_url = info_dict.get('thumbnail')
+            if tn_url:
+                thumbnails = [{'id': '0', 'url': tn_url}]
+            else:
+                self.to_screen(
+                    '[info] No thumbnails present for %s' % info_dict['id'])
+                return
+
+        self.to_screen(
+            '[info] Thumbnails for %s:' % info_dict['id'])
+        self.to_screen(render_table(
+            ['ID', 'width', 'height', 'URL'],
+            [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails]))

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


@@ -1641,3 +1659,39 @@ class YoutubeDL(object):
         if encoding is None:
             encoding = preferredencoding()
         return encoding
         if encoding is None:
             encoding = preferredencoding()
         return encoding

+
+    def _write_thumbnails(self, info_dict, filename):
+        if self.params.get('writethumbnail', False):
+            thumbnails = info_dict.get('thumbnails')
+            if thumbnails:
+                thumbnails = [thumbnails[-1]]
+        elif self.params.get('write_all_thumbnails', False):
+            thumbnails = info_dict.get('thumbnails')
+        else:
+            return
+
+        if not thumbnails:
+            # No thumbnails present, so return immediately
+            return
+
+        for t in thumbnails:
+            thumb_ext = determine_ext(t['url'], 'jpg')
+            suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
+            thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
+            thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
+
+            if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
+                self.to_screen('[%s] %s: Thumbnail %sis already present' %
+                               (info_dict['extractor'], info_dict['id'], thumb_display_id))
+            else:
+                self.to_screen('[%s] %s: Downloading thumbnail %s...' %
+                               (info_dict['extractor'], info_dict['id'], thumb_display_id))
+                try:
+                    uf = self.urlopen(t['url'])
+                    with open(thumb_filename, 'wb') as thumbf:
+                        shutil.copyfileobj(uf, thumbf)
+                    self.to_screen('[%s] %s: Writing thumbnail %sto: %s' %
+                                   (info_dict['extractor'], info_dict['id'], thumb_display_id, thumb_filename))
+                except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+                    self.report_warning('Unable to download thumbnail "%s": %s' %
+                                        (t['url'], compat_str(err)))