added --srt-lang; updated README; extended the -g FAQ

This commit is contained in:
Filippo Valsorda 2012-03-15 14:56:08 +01:00
parent cfcf32d038
commit a0432a1e80
3 changed files with 111 additions and 13 deletions

View File

@ -75,6 +75,10 @@ which means you can modify it, redistribute it or use it however you like.
requested requested
--max-quality FORMAT highest quality format to download --max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats (currently youtube only) -F, --list-formats list all available formats (currently youtube only)
--write-srt write video closed captions to a .srt file
(currently youtube only)
--srt-lang LANG language of the closed captions to download
(optional) use IETF language tags like 'en'
### Authentication Options: ### Authentication Options:
-u, --username USERNAME account username -u, --username USERNAME account username
@ -106,7 +110,7 @@ Once the video is fully downloaded, use any video player, such as [vlc](http://w
### The links provided by youtube-dl -g are not working anymore ### The links provided by youtube-dl -g are not working anymore
The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
### ERROR: no fmt_url_map or conn information found in video info ### ERROR: no fmt_url_map or conn information found in video info

View File

@ -491,6 +491,7 @@ class FileDownloader(object):
writedescription: Write the video description to a .description file writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file writeinfojson: Write the video description to a .info.json file
writesubtitles: Write the video subtitles to a .srt file writesubtitles: Write the video subtitles to a .srt file
subtitleslang: Language of the subtitles to download
""" """
params = None params = None
@ -1443,17 +1444,24 @@ class YoutubeIE(InfoExtractor):
else: else:
srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list) srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list)
if srt_lang_list: if srt_lang_list:
if 'en' in srt_lang_list: srt_lang = 'en' if self._downloader.params.get('subtitleslang', False):
else: srt_lang = srt_lang_list[0] # TODO choose better and provide an override srt_lang = self._downloader.params.get('subtitleslang')
request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id)) elif 'en' in srt_lang_list:
try: srt_lang = 'en'
srt_xml = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
else: else:
video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) srt_lang = srt_lang_list[0]
if not srt_lang in srt_lang_list:
self._downloader.trouble(u'WARNING: no closed captions found in the specified language')
else:
request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id))
try:
srt_xml = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
else:
video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
else: else:
self._downloader.trouble(u'WARNING: video has no subtitles') self._downloader.trouble(u'WARNING: video has no closed captions')
# token # token
video_token = urllib.unquote_plus(video_info['token'][0]) video_token = urllib.unquote_plus(video_info['token'][0])
@ -4385,6 +4393,12 @@ def parseOpts():
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
video_format.add_option('-F', '--list-formats', video_format.add_option('-F', '--list-formats',
action='store_true', dest='listformats', help='list all available formats (currently youtube only)') action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
video_format.add_option('--write-srt',
action='store_true', dest='writesubtitles',
help='write video closed captions to a .srt file (currently youtube only)', default=False)
video_format.add_option('--srt-lang',
action='store', dest='subtitleslang', metavar='LANG',
help='language of the closed captions to download (optional) use IETF language tags like \'en\'')
verbosity.add_option('-q', '--quiet', verbosity.add_option('-q', '--quiet',
@ -4449,9 +4463,6 @@ def parseOpts():
filesystem.add_option('--write-info-json', filesystem.add_option('--write-info-json',
action='store_true', dest='writeinfojson', action='store_true', dest='writeinfojson',
help='write video metadata to a .info.json file', default=False) help='write video metadata to a .info.json file', default=False)
filesystem.add_option('--write-srt',
action='store_true', dest='writesubtitles',
help='write video subtitles to a .srt file', default=False)
postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False, postproc.add_option('--extract-audio', action='store_true', dest='extractaudio', default=False,
@ -4653,6 +4664,7 @@ def _real_main():
'writedescription': opts.writedescription, 'writedescription': opts.writedescription,
'writeinfojson': opts.writeinfojson, 'writeinfojson': opts.writeinfojson,
'writesubtitles': opts.writesubtitles, 'writesubtitles': opts.writesubtitles,
'subtitleslang': opts.subtitleslang,
'matchtitle': opts.matchtitle, 'matchtitle': opts.matchtitle,
'rejecttitle': opts.rejecttitle, 'rejecttitle': opts.rejecttitle,
'max_downloads': opts.max_downloads, 'max_downloads': opts.max_downloads,

View File

@ -490,6 +490,8 @@ class FileDownloader(object):
updatetime: Use the Last-modified header to set output file timestamps. updatetime: Use the Last-modified header to set output file timestamps.
writedescription: Write the video description to a .description file writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file writeinfojson: Write the video description to a .info.json file
writesubtitles: Write the video subtitles to a .srt file
subtitleslang: Language of the subtitles to download
""" """
params = None params = None
@ -681,6 +683,10 @@ class FileDownloader(object):
""" Report that the description file is being written """ """ Report that the description file is being written """
self.to_screen(u'[info] Writing video description to: ' + descfn) self.to_screen(u'[info] Writing video description to: ' + descfn)
def report_writesubtitles(self, srtfn):
""" Report that the subtitles file is being written """
self.to_screen(u'[info] Writing video subtitles to: ' + srtfn)
def report_writeinfojson(self, infofn): def report_writeinfojson(self, infofn):
""" Report that the metadata file has been written """ """ Report that the metadata file has been written """
self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn) self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
@ -809,6 +815,21 @@ class FileDownloader(object):
self.trouble(u'ERROR: Cannot write description file ' + descfn) self.trouble(u'ERROR: Cannot write description file ' + descfn)
return return
if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
# subtitles download errors are already managed as troubles in relevant IE
# that way it will silently go on when used with unsupporting IE
try:
srtfn = filename.rsplit('.', 1)[0] + u'.srt'
self.report_writesubtitles(srtfn)
srtfile = open(_encodeFilename(srtfn), 'wb')
try:
srtfile.write(info_dict['subtitles'].encode('utf-8'))
finally:
srtfile.close()
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
return
if self.params.get('writeinfojson', False): if self.params.get('writeinfojson', False):
infofn = filename + u'.info.json' infofn = filename + u'.info.json'
self.report_writeinfojson(infofn) self.report_writeinfojson(infofn)
@ -1206,6 +1227,10 @@ class YoutubeIE(InfoExtractor):
"""Report attempt to download video info webpage.""" """Report attempt to download video info webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id) self._downloader.to_screen(u'[youtube] %s: Downloading video info webpage' % video_id)
def report_video_subtitles_download(self, video_id):
"""Report attempt to download video info webpage."""
self._downloader.to_screen(u'[youtube] %s: Downloading video subtitles' % video_id)
def report_information_extraction(self, video_id): def report_information_extraction(self, video_id):
"""Report attempt to extract video information.""" """Report attempt to extract video information."""
self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id) self._downloader.to_screen(u'[youtube] %s: Extracting video information' % video_id)
@ -1218,6 +1243,23 @@ class YoutubeIE(InfoExtractor):
"""Indicate the download will use the RTMP protocol.""" """Indicate the download will use the RTMP protocol."""
self._downloader.to_screen(u'[youtube] RTMP download detected') self._downloader.to_screen(u'[youtube] RTMP download detected')
def _closed_captions_xml_to_srt(self, xml_string):
srt = ''
texts = re.findall(r'<text start="([\d\.]+)"( dur="([\d\.]+)")?>([^<]+)</text>', xml_string, re.MULTILINE)
# TODO parse xml instead of regex
for n, (start, dur_tag, dur, caption) in enumerate(texts):
if not dur: dur = '4'
start = float(start)
end = start + float(dur)
start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption)
caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional
srt += str(n) + '\n'
srt += start + ' --> ' + end + '\n'
srt += caption + '\n\n'
return srt
def _print_formats(self, formats): def _print_formats(self, formats):
print 'Available formats:' print 'Available formats:'
for x in formats: for x in formats:
@ -1390,6 +1432,37 @@ class YoutubeIE(InfoExtractor):
video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()')) video_description = u''.join(vwebpage_doc.xpath('id("eow-description")//text()'))
# TODO use another parser # TODO use another parser
# closed captions
video_subtitles = None
if self._downloader.params.get('writesubtitles', False):
self.report_video_subtitles_download(video_id)
request = urllib2.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
try:
srt_list = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
else:
srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list)
if srt_lang_list:
if self._downloader.params.get('subtitleslang', False):
srt_lang = self._downloader.params.get('subtitleslang')
elif 'en' in srt_lang_list:
srt_lang = 'en'
else:
srt_lang = srt_lang_list[0]
if not srt_lang in srt_lang_list:
self._downloader.trouble(u'WARNING: no closed captions found in the specified language')
else:
request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id))
try:
srt_xml = urllib2.urlopen(request).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'WARNING: unable to download video subtitles: %s' % str(err))
else:
video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8'))
else:
self._downloader.trouble(u'WARNING: video has no closed captions')
# token # token
video_token = urllib.unquote_plus(video_info['token'][0]) video_token = urllib.unquote_plus(video_info['token'][0])
@ -1461,6 +1534,7 @@ class YoutubeIE(InfoExtractor):
'thumbnail': video_thumbnail.decode('utf-8'), 'thumbnail': video_thumbnail.decode('utf-8'),
'description': video_description, 'description': video_description,
'player_url': player_url, 'player_url': player_url,
'subtitles': video_subtitles
}) })
except UnavailableVideoError, err: except UnavailableVideoError, err:
self._downloader.trouble(u'\nERROR: unable to download video') self._downloader.trouble(u'\nERROR: unable to download video')
@ -4319,6 +4393,12 @@ def parseOpts():
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
video_format.add_option('-F', '--list-formats', video_format.add_option('-F', '--list-formats',
action='store_true', dest='listformats', help='list all available formats (currently youtube only)') action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
video_format.add_option('--write-srt',
action='store_true', dest='writesubtitles',
help='write video closed captions to a .srt file (currently youtube only)', default=False)
video_format.add_option('--srt-lang',
action='store', dest='subtitleslang', metavar='LANG',
help='language of the closed captions to download (optional) use IETF language tags like \'en\'')
verbosity.add_option('-q', '--quiet', verbosity.add_option('-q', '--quiet',
@ -4583,6 +4663,8 @@ def _real_main():
'updatetime': opts.updatetime, 'updatetime': opts.updatetime,
'writedescription': opts.writedescription, 'writedescription': opts.writedescription,
'writeinfojson': opts.writeinfojson, 'writeinfojson': opts.writeinfojson,
'writesubtitles': opts.writesubtitles,
'subtitleslang': opts.subtitleslang,
'matchtitle': opts.matchtitle, 'matchtitle': opts.matchtitle,
'rejecttitle': opts.rejecttitle, 'rejecttitle': opts.rejecttitle,
'max_downloads': opts.max_downloads, 'max_downloads': opts.max_downloads,