Merge pull request #1 from e7appew/python3

[youtubedl] / youtube_dl / __init__.py

diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py
index 77b3384a05fa45d6d4cada65decdb5588ade9100..a9730292cd6801c1bbd7f68b586e288bad7fe21d 100644 (file)
--- a/youtube_dl/__init__.py
+++ b/youtube_dl/__init__.py
@@ -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,


@@ -38,18 +39,8 @@ from .update import update_self
 from .downloader import (
     FileDownloader,
 )
 from .downloader import (
     FileDownloader,
 )

-from .extractor import gen_extractors
+from .extractor import gen_extractors, list_extractors

 from .YoutubeDL import YoutubeDL
 from .YoutubeDL import YoutubeDL

-from .postprocessor import (
-    AtomicParsleyPP,
-    FFmpegAudioFixPP,
-    FFmpegMetadataPP,
-    FFmpegVideoConvertor,
-    FFmpegExtractAudioPP,
-    FFmpegEmbedSubtitlePP,
-    XAttrMetadataPP,
-    ExecAfterDownloadPP,
-)

 
 
 def _real_main(argv=None):
 
 
 def _real_main(argv=None):


@@ -75,16 +66,16 @@ 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


@@ -94,7 +85,9 @@ 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')
             batch_urls = read_batch_urls(batchfd)
             if opts.verbose:
                 write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')


@@ -105,27 +98,25 @@ def _real_main(argv=None):
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 
     _enc = preferredencoding()
     all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
 

-    extractors = gen_extractors()
-

     if opts.list_extractors:
     if opts.list_extractors:

-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
-            compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
+        for ie in list_extractors(opts.age_limit):
+            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:
         sys.exit(0)
     if opts.list_extractor_descriptions:

-        for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()):
+        for ie in list_extractors(opts.age_limit):

             if not ie._WORKING:
                 continue
             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
             if desc is False:
                 continue
             if hasattr(ie, 'SEARCH_KEY'):
             if not ie._WORKING:
                 continue
             desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
             if desc is False:
                 continue
             if hasattr(ie, 'SEARCH_KEY'):

-                _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny')
+                _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))
                 _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)
 
     # Conflicting, missing and erroneous options
         sys.exit(0)
 
     # Conflicting, missing and erroneous options


@@ -154,11 +145,30 @@ 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
+
+    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:


@@ -176,8 +186,12 @@ 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)
     else:
     if opts.date is not None:
         date = DateRange.day(opts.date)
     else:


@@ -192,33 +206,94 @@ 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'
                      ' template'.format(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'
                      ' template'.format(outtmpl))
 

-    any_printing = 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_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 = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 

+    # 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:
+        postprocessors.append({
+            'key': 'FFmpegExtractAudio',
+            'preferredcodec': opts.audioformat,
+            'preferredquality': opts.audioquality,
+            'nopostoverwrites': opts.nopostoverwrites,
+        })
+    if opts.recodevideo:
+        postprocessors.append({
+            'key': 'FFmpegVideoConvertor',
+            'preferedformat': opts.recodevideo,
+        })
+    if opts.convertsubtitles:
+        postprocessors.append({
+            'key': 'FFmpegSubtitlesConvertor',
+            'format': opts.convertsubtitles,
+        })
+    if opts.embedsubtitles:
+        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({
+            'key': 'EmbedThumbnail',
+            'already_have_thumbnail': already_have_thumbnail
+        })
+        if not already_have_thumbnail:
+            opts.writethumbnail = True
+    # 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',
+            '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)
+    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,
         'username': opts.username,
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,
     ydl_opts = {
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
         'twofactor': opts.twofactor,
         'videopassword': opts.videopassword,

-        'quiet': (opts.quiet or any_printing),
+        'quiet': (opts.quiet or any_getting or any_printing),

         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,
         'no_warnings': opts.no_warnings,
         'forceurl': opts.geturl,
         'forcetitle': opts.gettitle,


@@ -228,20 +303,21 @@ def _real_main(argv=None):
         'forceduration': opts.getduration,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,
         'forceduration': opts.getduration,
         'forcefilename': opts.getfilename,
         'forceformat': opts.getformat,

-        'forcejson': opts.dumpjson,
+        'forcejson': opts.dumpjson or opts.print_json,

         'dump_single_json': opts.dump_single_json,
         'dump_single_json': opts.dump_single_json,

-        'simulate': opts.simulate or any_printing,
+        'simulate': opts.simulate or any_getting,

         'skip_download': opts.skip_download,
         'format': opts.format,
         'skip_download': opts.skip_download,
         'format': opts.format,

-        'format_limit': opts.format_limit,

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

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


@@ -249,6 +325,7 @@ def _real_main(argv=None):
         'progress_with_newline': opts.progress_with_newline,
         'playliststart': opts.playliststart,
         'playlistend': opts.playlistend,
         'progress_with_newline': opts.progress_with_newline,
         'playliststart': opts.playliststart,
         'playlistend': opts.playlistend,

+        'playlistreverse': opts.playlist_reverse,

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


@@ -258,6 +335,7 @@ 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,


@@ -294,37 +372,35 @@ 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,
+        '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,
+

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

-        # PostProcessors
-        # Add the metadata pp first, the other pps will copy it
-        if opts.addmetadata:
-            ydl.add_post_processor(FFmpegMetadataPP())
-        if opts.extractaudio:
-            ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
-        if opts.recodevideo:
-            ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
-        if opts.embedsubtitles:
-            ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
-        if opts.xattrs:
-            ydl.add_post_processor(XAttrMetadataPP())
-        if opts.embedthumbnail:
-            if not opts.addmetadata:
-                ydl.add_post_processor(FFmpegAudioFixPP())
-            ydl.add_post_processor(AtomicParsleyPP())
-
-        # 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:
-            ydl.add_post_processor(ExecAfterDownloadPP(
-                verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))
-

         # Update version
         if opts.update_self:
         # 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:


@@ -336,11 +412,13 @@ 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:


@@ -359,3 +437,5 @@ def main(argv=None):
         sys.exit('ERROR: fixed output name but more than one file to download')
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')
         sys.exit('ERROR: fixed output name but more than one file to download')
     except KeyboardInterrupt:
         sys.exit('\nERROR: Interrupted by user')

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