Merge tag 'upstream/2017.02.07'

[youtubedl] / youtube_dl / __init__.py

diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index ddf6260d1e9a4a11fd0140ccbc8d6a4c324df78b..5c5b8094bc1b6cbc68b09eba85b06a63a2ee785d 100644 (file)
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -1,5 +1,5 @@
 #!/usr/bin/env python
 #!/usr/bin/env python

-# -*- coding: utf-8 -*-
+# coding: utf-8

 
 from __future__ import unicode_literals
 
 
 from __future__ import unicode_literals
 


@@ -18,14 +18,15 @@ from .options import (
 from .compat import (
     compat_expanduser,
     compat_getpass,
 from .compat import (
     compat_expanduser,
     compat_getpass,

-    compat_print,
+    compat_shlex_split,

     workaround_optparse_bug9161,
 )
 from .utils import (
     DateRange,
     workaround_optparse_bug9161,
 )
 from .utils import (
     DateRange,

-    DEFAULT_OUTTMPL,

     decodeOption,
     decodeOption,

+    DEFAULT_OUTTMPL,

     DownloadError,
     DownloadError,

+    match_filter_func,

     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,
     MaxDownloadsReached,
     preferredencoding,
     read_batch_urls,


@@ -33,12 +34,14 @@ from .utils import (
     setproctitle,
     std_headers,
     write_string,
     setproctitle,
     std_headers,
     write_string,

+    render_table,

 )
 from .update import update_self
 from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors, list_extractors
 )
 from .update import update_self
 from .downloader import (
     FileDownloader,
 )
 from .extractor import gen_extractors, list_extractors

+from .extractor.adobepass import MSO_INFO

 from .YoutubeDL import YoutubeDL
 
 
 from .YoutubeDL import YoutubeDL
 
 


@@ -65,16 +68,16 @@ def _real_main(argv=None):
     # Custom HTTP headers
     if opts.headers is not None:
         for h in opts.headers:
     # Custom HTTP headers
     if opts.headers is not None:
         for h in opts.headers:

-            if h.find(':', 1) < 0:
+            if ':' not in h:

                 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
                 parser.error('wrong header formatting, it should be key:value, not "%s"' % h)

-            key, value = h.split(':', 2)
+            key, value = h.split(':', 1)

             if opts.verbose:
                 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
             std_headers[key] = value
 
     # Dump user agent
     if opts.dump_user_agent:
             if opts.verbose:
                 write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
             std_headers[key] = value
 
     # Dump user agent
     if opts.dump_user_agent:

-        compat_print(std_headers['User-Agent'])
+        write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)

         sys.exit(0)
 
     # Batch file verification
         sys.exit(0)
 
     # Batch file verification


@@ -84,23 +87,24 @@ def _real_main(argv=None):
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:
             if opts.batchfile == '-':
                 batchfd = sys.stdin
             else:

-                batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
+                batchfd = io.open(
+                    compat_expanduser(opts.batchfile),
+                    'r', encoding='utf-8', errors='ignore')

             batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
         except IOError:
             sys.exit('ERROR: batch file could not be read')
             batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
         except IOError:
             sys.exit('ERROR: batch file could not be read')

-    all_urls = batch_urls + args
-    all_urls = [url.strip() for url in all_urls]
+    all_urls = batch_urls + [url.strip() for url in args]  # batch_urls are already striped in read_batch_urls

     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
     if opts.list_extractors:
         for ie in list_extractors(opts.age_limit):
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
     if opts.list_extractors:
         for ie in list_extractors(opts.age_limit):

-            compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
+            write_string(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '') + '\n', out=sys.stdout)

             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             for mu in matchedUrls:
             matchedUrls = [url for url in all_urls if ie.suitable(url)]
             for mu in matchedUrls:

-                compat_print('  ' + mu)
+                write_string('  ' + mu + '\n', out=sys.stdout)

         sys.exit(0)
     if opts.list_extractor_descriptions:
         for ie in list_extractors(opts.age_limit):
         sys.exit(0)
     if opts.list_extractor_descriptions:
         for ie in list_extractors(opts.age_limit):


@@ -113,7 +117,11 @@ def _real_main(argv=None):
                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
                 _COUNTS = ('', '5', '10', 'all')
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
                 _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
                 _COUNTS = ('', '5', '10', 'all')
                 desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))

-            compat_print(desc)
+            write_string(desc + '\n', out=sys.stdout)
+        sys.exit(0)
+    if opts.ap_list_mso:
+        table = [[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]
+        write_string('Supported TV Providers:\n' + render_table(['mso', 'mso name'], table) + '\n', out=sys.stdout)

         sys.exit(0)
 
     # Conflicting, missing and erroneous options
         sys.exit(0)
 
     # Conflicting, missing and erroneous options


@@ -121,12 +129,22 @@ def _real_main(argv=None):
         parser.error('using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
         parser.error('account username missing\n')
         parser.error('using .netrc conflicts with giving username/password')
     if opts.password is not None and opts.username is None:
         parser.error('account username missing\n')

+    if opts.ap_password is not None and opts.ap_username is None:
+        parser.error('TV Provider account username missing\n')

     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error('using output template conflicts with using title, video ID or auto number')
     if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
         parser.error('using output template conflicts with using title, video ID or auto number')

+    if opts.autonumber_size is not None:
+        if opts.autonumber_size <= 0:
+            parser.error('auto number size must be positive')
+    if opts.autonumber_start is not None:
+        if opts.autonumber_start < 0:
+            parser.error('auto number start must be positive or 0')

     if opts.usetitle and opts.useid:
         parser.error('using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
         opts.password = compat_getpass('Type account password and press [Return]: ')
     if opts.usetitle and opts.useid:
         parser.error('using title conflicts with using video ID')
     if opts.username is not None and opts.password is None:
         opts.password = compat_getpass('Type account password and press [Return]: ')

+    if opts.ap_username is not None and opts.ap_password is None:
+        opts.ap_password = compat_getpass('Type TV provider account password and press [Return]: ')

     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:
     if opts.ratelimit is not None:
         numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
         if numeric_limit is None:


@@ -142,11 +160,32 @@ def _real_main(argv=None):
         if numeric_limit is None:
             parser.error('invalid max_filesize specified')
         opts.max_filesize = numeric_limit
         if numeric_limit is None:
             parser.error('invalid max_filesize specified')
         opts.max_filesize = numeric_limit

+    if opts.sleep_interval is not None:
+        if opts.sleep_interval < 0:
+            parser.error('sleep interval must be positive or 0')
+    if opts.max_sleep_interval is not None:
+        if opts.max_sleep_interval < 0:
+            parser.error('max sleep interval must be positive or 0')
+        if opts.max_sleep_interval < opts.sleep_interval:
+            parser.error('max sleep interval must be greater than or equal to min sleep interval')
+    else:
+        opts.max_sleep_interval = opts.sleep_interval
+    if opts.ap_mso and opts.ap_mso not in MSO_INFO:
+        parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
+
+    def parse_retries(retries):
+        if retries in ('inf', 'infinite'):
+            parsed_retries = float('inf')
+        else:
+            try:
+                parsed_retries = int(retries)
+            except (TypeError, ValueError):
+                parser.error('invalid retry count specified')
+        return parsed_retries

     if opts.retries is not None:
     if opts.retries is not None:

-        try:
-            opts.retries = int(opts.retries)
-        except (TypeError, ValueError):
-            parser.error('invalid retry count specified')
+        opts.retries = parse_retries(opts.retries)
+    if opts.fragment_retries is not None:
+        opts.fragment_retries = parse_retries(opts.fragment_retries)

     if opts.buffersize is not None:
         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
         if numeric_buffersize is None:
     if opts.buffersize is not None:
         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
         if numeric_buffersize is None:


@@ -164,8 +203,11 @@ def _real_main(argv=None):
         if not opts.audioquality.isdigit():
             parser.error('invalid audio quality specified')
     if opts.recodevideo is not None:
         if not opts.audioquality.isdigit():
             parser.error('invalid audio quality specified')
     if opts.recodevideo is not None:

-        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
+        if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:

             parser.error('invalid video recode format specified')
             parser.error('invalid video recode format specified')

+    if opts.convertsubtitles is not None:
+        if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
+            parser.error('invalid subtitle format specified')

 
     if opts.date is not None:
         date = DateRange.day(opts.date)
 
     if opts.date is not None:
         date = DateRange.day(opts.date)


@@ -181,18 +223,14 @@ def _real_main(argv=None):
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
 
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
 

-    if sys.version_info < (3,):
-        # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
-        if opts.outtmpl is not None:
-            opts.outtmpl = opts.outtmpl.decode(preferredencoding())
-    outtmpl = ((opts.outtmpl is not None and opts.outtmpl)
-               or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s')
-               or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s')
-               or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s')
-               or (opts.usetitle and '%(title)s-%(id)s.%(ext)s')
-               or (opts.useid and '%(id)s.%(ext)s')
-               or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s')
-               or DEFAULT_OUTTMPL)
+    outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
+               (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
+               (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
+               (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
+               (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
+               (opts.useid and '%(id)s.%(ext)s') or
+               (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
+               DEFAULT_OUTTMPL)

     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
         parser.error('Cannot download a video and extract audio into the same'
                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
     if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
         parser.error('Cannot download a video and extract audio into the same'
                      ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'


@@ -205,6 +243,11 @@ def _real_main(argv=None):
     # PostProcessors
     postprocessors = []
     # Add the metadata pp first, the other pps will copy it
     # PostProcessors
     postprocessors = []
     # Add the metadata pp first, the other pps will copy it

+    if opts.metafromtitle:
+        postprocessors.append({
+            'key': 'MetadataFromTitle',
+            'titleformat': opts.metafromtitle
+        })

     if opts.addmetadata:
         postprocessors.append({'key': 'FFmpegMetadata'})
     if opts.extractaudio:
     if opts.addmetadata:
         postprocessors.append({'key': 'FFmpegMetadata'})
     if opts.extractaudio:


@@ -219,25 +262,43 @@ def _real_main(argv=None):
             'key': 'FFmpegVideoConvertor',
             'preferedformat': opts.recodevideo,
         })
             'key': 'FFmpegVideoConvertor',
             'preferedformat': opts.recodevideo,
         })

+    if opts.convertsubtitles:
+        postprocessors.append({
+            'key': 'FFmpegSubtitlesConvertor',
+            'format': opts.convertsubtitles,
+        })

     if opts.embedsubtitles:
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
     if opts.embedsubtitles:
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',

-            'subtitlesformat': opts.subtitlesformat,

         })
         })

+    if opts.embedthumbnail:
+        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+        postprocessors.append({
+            'key': 'EmbedThumbnail',
+            'already_have_thumbnail': already_have_thumbnail
+        })
+        if not already_have_thumbnail:
+            opts.writethumbnail = True
+    # XAttrMetadataPP should be run after post-processors that may change file
+    # contents

     if opts.xattrs:
         postprocessors.append({'key': 'XAttrMetadata'})
     if opts.xattrs:
         postprocessors.append({'key': 'XAttrMetadata'})

-    if opts.embedthumbnail:
-        if not opts.addmetadata:
-            postprocessors.append({'key': 'FFmpegAudioFix'})
-        postprocessors.append({'key': 'AtomicParsley'})

     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
         postprocessors.append({
             'key': 'ExecAfterDownload',
     # Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
     # So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
     if opts.exec_cmd:
         postprocessors.append({
             'key': 'ExecAfterDownload',

-            'verboseOutput': opts.verbose,

             'exec_cmd': opts.exec_cmd,
         })
             'exec_cmd': opts.exec_cmd,
         })

+    external_downloader_args = None
+    if opts.external_downloader_args:
+        external_downloader_args = compat_shlex_split(opts.external_downloader_args)
+    postprocessor_args = None
+    if opts.postprocessor_args:
+        postprocessor_args = compat_shlex_split(opts.postprocessor_args)
+    match_filter = (
+        None if opts.match_filter is None
+        else match_filter_func(opts.match_filter))

 
     ydl_opts = {
         'usenetrc': opts.usenetrc,
 
     ydl_opts = {
         'usenetrc': opts.usenetrc,


@@ -245,6 +306,9 @@ def _real_main(argv=None):
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,

+        'ap_mso': opts.ap_mso,
+        'ap_username': opts.ap_username,
+        'ap_password': opts.ap_password,

         'quiet': (opts.quiet or any_getting or any_printing),
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
         'quiet': (opts.quiet or any_getting or any_printing),
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,


@@ -260,15 +324,18 @@ def _real_main(argv=None):
         'simulate': opts.simulate or any_getting,
         'skip_download': opts.skip_download,
         'format': opts.format,
         'simulate': opts.simulate or any_getting,
         'skip_download': opts.skip_download,
         'format': opts.format,

-        'format_limit': opts.format_limit,

         'listformats': opts.listformats,
         'outtmpl': outtmpl,
         'autonumber_size': opts.autonumber_size,
         'listformats': opts.listformats,
         'outtmpl': outtmpl,
         'autonumber_size': opts.autonumber_size,

+        'autonumber_start': opts.autonumber_start,

         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,

+        'force_generic_extractor': opts.force_generic_extractor,

         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'retries': opts.retries,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'retries': opts.retries,

+        'fragment_retries': opts.fragment_retries,
+        'skip_unavailable_fragments': opts.skip_unavailable_fragments,

         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'continuedl': opts.continue_dl,


@@ -277,6 +344,7 @@ def _real_main(argv=None):
         'playliststart': opts.playliststart,
         'playlistend': opts.playlistend,
         'playlistreverse': opts.playlist_reverse,
         'playliststart': opts.playliststart,
         'playlistend': opts.playlistend,
         'playlistreverse': opts.playlist_reverse,

+        'playlistrandom': opts.playlist_random,

         'noplaylist': opts.noplaylist,
         'logtostderr': opts.outtmpl == '-',
         'consoletitle': opts.consoletitle,
         'noplaylist': opts.noplaylist,
         'logtostderr': opts.outtmpl == '-',
         'consoletitle': opts.consoletitle,


@@ -286,6 +354,7 @@ def _real_main(argv=None):
         'writeannotations': opts.writeannotations,
         'writeinfojson': opts.writeinfojson,
         'writethumbnail': opts.writethumbnail,
         'writeannotations': opts.writeannotations,
         'writeinfojson': opts.writeinfojson,
         'writethumbnail': opts.writethumbnail,

+        'write_all_thumbnails': opts.write_all_thumbnails,

         'writesubtitles': opts.writesubtitles,
         'writeautomaticsub': opts.writeautomaticsub,
         'allsubtitles': opts.allsubtitles,
         'writesubtitles': opts.writesubtitles,
         'writeautomaticsub': opts.writeautomaticsub,
         'allsubtitles': opts.allsubtitles,


@@ -322,19 +391,35 @@ def _real_main(argv=None):
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
         'default_search': opts.default_search,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,

-        'exec_cmd': opts.exec_cmd,

         'extract_flat': opts.extract_flat,
         'extract_flat': opts.extract_flat,

+        'mark_watched': opts.mark_watched,

         'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,
         'fixup': opts.fixup,
         'source_address': opts.source_address,
         'call_home': opts.call_home,
         'merge_output_format': opts.merge_output_format,
         'postprocessors': postprocessors,
         'fixup': opts.fixup,
         'source_address': opts.source_address,
         'call_home': opts.call_home,

+        'sleep_interval': opts.sleep_interval,
+        'max_sleep_interval': opts.max_sleep_interval,
+        'external_downloader': opts.external_downloader,
+        'list_thumbnails': opts.list_thumbnails,
+        'playlist_items': opts.playlist_items,
+        'xattr_set_filesize': opts.xattr_set_filesize,
+        'match_filter': match_filter,
+        'no_color': opts.no_color,
+        'ffmpeg_location': opts.ffmpeg_location,
+        'hls_prefer_native': opts.hls_prefer_native,
+        'hls_use_mpegts': opts.hls_use_mpegts,
+        'external_downloader_args': external_downloader_args,
+        'postprocessor_args': postprocessor_args,
+        'cn_verification_proxy': opts.cn_verification_proxy,
+        'geo_verification_proxy': opts.geo_verification_proxy,
+        'config_location': opts.config_location,

     }
 
     with YoutubeDL(ydl_opts) as ydl:
         # Update version
         if opts.update_self:
     }
 
     with YoutubeDL(ydl_opts) as ydl:
         # Update version
         if opts.update_self:

-            update_self(ydl.to_screen, opts.verbose)
+            update_self(ydl.to_screen, opts.verbose, ydl._opener)

 
         # Remove cache dir
         if opts.rm_cachedir:
 
         # Remove cache dir
         if opts.rm_cachedir:


@@ -346,11 +431,13 @@ def _real_main(argv=None):
                 sys.exit()
 
             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
                 sys.exit()
 
             ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)

-            parser.error('you must provide at least one URL')
+            parser.error(
+                'You must provide at least one URL.\n'
+                'Type youtube-dl --help to see a list of all options.')

 
         try:
             if opts.load_info_filename is not None:
 
         try:
             if opts.load_info_filename is not None:

-                retcode = ydl.download_with_info_file(opts.load_info_filename)
+                retcode = ydl.download_with_info_file(compat_expanduser(opts.load_info_filename))

             else:
                 retcode = ydl.download(all_urls)
         except MaxDownloadsReached:
             else:
                 retcode = ydl.download(all_urls)
         except MaxDownloadsReached:


@@ -370,4 +457,5 @@ def main(argv=None):
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
 
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
 

+

 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']
 __all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']