New upstream version 2017.11.06

[youtubedl] / youtube_dl / __init__.py

diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 9f131f5db46e209a899fe3cc2d9b95ab17158bd5..ba684a0754bb4a70148148334d1bee474a1d234b 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
 


@@ -16,9 +16,7 @@ from .options import (
     parseOpts,
 )
 from .compat import (
     parseOpts,
 )
 from .compat import (

-    compat_expanduser,

     compat_getpass,
     compat_getpass,

-    compat_print,

     compat_shlex_split,
     workaround_optparse_bug9161,
 )
     compat_shlex_split,
     workaround_optparse_bug9161,
 )


@@ -27,6 +25,7 @@ from .utils import (
     decodeOption,
     DEFAULT_OUTTMPL,
     DownloadError,
     decodeOption,
     DEFAULT_OUTTMPL,
     DownloadError,

+    expand_path,

     match_filter_func,
     MaxDownloadsReached,
     preferredencoding,
     match_filter_func,
     MaxDownloadsReached,
     preferredencoding,


@@ -35,12 +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
 
 


@@ -67,16 +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


@@ -86,23 +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(
+                    expand_path(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):


@@ -115,7 +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


@@ -123,12 +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:


@@ -144,14 +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.retries is not None:
-        if opts.retries in ('inf', 'infinite'):
-            opts_retries = float('inf')
+    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:
         else:
             try:

-                opts_retries = int(opts.retries)
+                parsed_retries = int(retries)

             except (TypeError, ValueError):
                 parser.error('invalid retry count specified')
             except (TypeError, ValueError):
                 parser.error('invalid retry count specified')

+        return parsed_retries
+    if opts.retries is not None:
+        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:


@@ -162,7 +196,7 @@ def _real_main(argv=None):
     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
         raise ValueError('Playlist end must be greater than playlist start')
     if opts.extractaudio:
     if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
         raise ValueError('Playlist end must be greater than playlist start')
     if opts.extractaudio:

-        if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
+        if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:

             parser.error('invalid audio format specified')
     if opts.audioquality:
         opts.audioquality = opts.audioquality.strip('k').strip('K')
             parser.error('invalid audio format specified')
     if opts.audioquality:
         opts.audioquality = opts.audioquality.strip('k').strip('K')


@@ -172,7 +206,7 @@ def _real_main(argv=None):
         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
             parser.error('invalid video recode format specified')
     if opts.convertsubtitles is not None:
         if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
             parser.error('invalid video recode format specified')
     if opts.convertsubtitles is not None:

-        if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
+        if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:

             parser.error('invalid subtitle format specified')
 
     if opts.date is not None:
             parser.error('invalid subtitle format specified')
 
     if opts.date is not None:


@@ -204,18 +238,15 @@ def _real_main(argv=None):
 
     any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
     any_printing = opts.print_json
 
     any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
     any_printing = opts.print_json

-    download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
+    download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive

 
     # PostProcessors
     postprocessors = []
 
     # 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.metafromtitle:
         postprocessors.append({
             'key': 'MetadataFromTitle',
             'titleformat': opts.metafromtitle
         })

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

     if opts.extractaudio:
         postprocessors.append({
             'key': 'FFmpegExtractAudio',
     if opts.extractaudio:
         postprocessors.append({
             'key': 'FFmpegExtractAudio',


@@ -228,6 +259,16 @@ def _real_main(argv=None):
             'key': 'FFmpegVideoConvertor',
             'preferedformat': opts.recodevideo,
         })
             'key': 'FFmpegVideoConvertor',
             'preferedformat': opts.recodevideo,
         })

+    # FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
+    # FFmpegExtractAudioPP as containers before conversion may not support
+    # metadata (3gp, webm, etc.)
+    # And this post-processor should be placed before other metadata
+    # manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
+    # extra metadata. By default ffmpeg preserves metadata applicable for both
+    # source and target containers. From this point the container won't change,
+    # so metadata can be added here.
+    if opts.addmetadata:
+        postprocessors.append({'key': 'FFmpegMetadata'})

     if opts.convertsubtitles:
         postprocessors.append({
             'key': 'FFmpegSubtitlesConvertor',
     if opts.convertsubtitles:
         postprocessors.append({
             'key': 'FFmpegSubtitlesConvertor',


@@ -237,8 +278,6 @@ def _real_main(argv=None):
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
         })
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
         })

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

     if opts.embedthumbnail:
         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
         postprocessors.append({
     if opts.embedthumbnail:
         already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
         postprocessors.append({


@@ -247,6 +286,10 @@ def _real_main(argv=None):
         })
         if not already_have_thumbnail:
             opts.writethumbnail = True
         })
         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'})

     # 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:
     # 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:


@@ -254,12 +297,6 @@ def _real_main(argv=None):
             'key': 'ExecAfterDownload',
             'exec_cmd': opts.exec_cmd,
         })
             'key': 'ExecAfterDownload',
             'exec_cmd': opts.exec_cmd,
         })

-    if opts.xattr_set_filesize:
-        try:
-            import xattr
-            xattr  # Confuse flake8
-        except ImportError:
-            parser.error('setting filesize xattr requested but python-xattr is not available')

     external_downloader_args = None
     if opts.external_downloader_args:
         external_downloader_args = compat_shlex_split(opts.external_downloader_args)
     external_downloader_args = None
     if opts.external_downloader_args:
         external_downloader_args = compat_shlex_split(opts.external_downloader_args)


@@ -276,6 +313,9 @@ 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,


@@ -294,12 +334,16 @@ def _real_main(argv=None):
         '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,
         'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,
         'restrictfilenames': opts.restrictfilenames,
         'ignoreerrors': opts.ignoreerrors,
         'force_generic_extractor': opts.force_generic_extractor,
         'ratelimit': opts.ratelimit,
         'nooverwrites': opts.nooverwrites,

-        'retries': opts_retries,
+        'retries': opts.retries,
+        'fragment_retries': opts.fragment_retries,
+        'skip_unavailable_fragments': opts.skip_unavailable_fragments,
+        'keep_fragments': opts.keep_fragments,

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


@@ -308,6 +352,7 @@ 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,


@@ -355,12 +400,14 @@ def _real_main(argv=None):
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
         'extract_flat': opts.extract_flat,
         'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
         'encoding': opts.encoding,
         '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,
         'sleep_interval': opts.sleep_interval,
         '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,
         'external_downloader': opts.external_downloader,
         'list_thumbnails': opts.list_thumbnails,
         'playlist_items': opts.playlist_items,


@@ -369,9 +416,17 @@ def _real_main(argv=None):
         'no_color': opts.no_color,
         'ffmpeg_location': opts.ffmpeg_location,
         'hls_prefer_native': opts.hls_prefer_native,
         '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,
         '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,
+        'geo_bypass': opts.geo_bypass,
+        'geo_bypass_country': opts.geo_bypass_country,
+        # just for deprecation check
+        'autonumber': opts.autonumber if opts.autonumber is True else None,
+        'usetitle': opts.usetitle if opts.usetitle is True else None,

     }
 
     with YoutubeDL(ydl_opts) as ydl:
     }
 
     with YoutubeDL(ydl_opts) as ydl:


@@ -395,7 +450,7 @@ def _real_main(argv=None):
 
         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(expand_path(opts.load_info_filename))

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


@@ -415,4 +470,5 @@ 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']