Browse Source

Merge remote-tracking branch 'upstream/master'

master
Allan Zhou 11 years ago
parent
commit
39c6f507df
14 changed files with 382 additions and 136 deletions
  1. 16
      README.md
  2. 26
      devscripts/gh-pages/add-version.py
  3. 3
      devscripts/gh-pages/update-feed.py
  4. 2
      devscripts/release.sh
  5. 9
      devscripts/youtube_genalgo.py
  6. 39
      test/test_youtube_subtitles.py
  7. 236
      youtube_dl/PostProcessor.py
  8. 39
      youtube_dl/YoutubeDL.py
  9. 16
      youtube_dl/__init__.py
  10. 3
      youtube_dl/extractor/common.py
  11. 18
      youtube_dl/extractor/xhamster.py
  12. 106
      youtube_dl/extractor/youtube.py
  13. 3
      youtube_dl/utils.py
  14. 2
      youtube_dl/version.py

16
README.md

@ -120,18 +120,20 @@ which means you can modify it, redistribute it or use it however you like.
--max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats (currently youtube
only)
## Subtitle Options:
--write-sub write subtitle file (currently youtube only)
--write-auto-sub write automatic subtitle file (currently youtube
only)
--only-sub [deprecated] alias of --skip-download
--all-subs downloads all the available subtitles of the
video (currently youtube only)
video
--list-subs lists all available subtitles for the video
(currently youtube only)
--sub-format FORMAT subtitle format [srt/sbv/vtt] (default=srt)
(currently youtube only)
--sub-lang LANG language of the subtitles to download (optional)
use IETF language tags like 'en'
--sub-format FORMAT subtitle format (default=srt) ([sbv/vtt] youtube
only)
--sub-lang LANGS languages of the subtitles to download (optional)
separated by commas, use IETF language tags like
'en,pt'
## Authentication Options:
-u, --username USERNAME account username
@ -153,6 +155,8 @@ which means you can modify it, redistribute it or use it however you like.
processing; the video is erased by default
--no-post-overwrites do not overwrite post-processed files; the post-
processed files are overwritten by default
--embed-subs embed subtitles in the video (only for mp4
videos)
# CONFIGURATION

26
devscripts/gh-pages/add-version.py

@ -6,28 +6,32 @@ import hashlib
import urllib.request
if len(sys.argv) <= 1:
print('Specify the version number as parameter')
sys.exit()
print('Specify the version number as parameter')
sys.exit()
version = sys.argv[1]
with open('update/LATEST_VERSION', 'w') as f:
f.write(version)
f.write(version)
versions_info = json.load(open('update/versions.json'))
if 'signature' in versions_info:
del versions_info['signature']
del versions_info['signature']
new_version = {}
filenames = {'bin': 'youtube-dl', 'exe': 'youtube-dl.exe', 'tar': 'youtube-dl-%s.tar.gz' % version}
filenames = {
'bin': 'youtube-dl',
'exe': 'youtube-dl.exe',
'tar': 'youtube-dl-%s.tar.gz' % version}
for key, filename in filenames.items():
print('Downloading and checksumming %s...' %filename)
url = 'http://youtube-dl.org/downloads/%s/%s' % (version, filename)
data = urllib.request.urlopen(url).read()
sha256sum = hashlib.sha256(data).hexdigest()
new_version[key] = (url, sha256sum)
print('Downloading and checksumming %s...' % filename)
url = 'https://yt-dl.org/downloads/%s/%s' % (version, filename)
data = urllib.request.urlopen(url).read()
sha256sum = hashlib.sha256(data).hexdigest()
new_version[key] = (url, sha256sum)
versions_info['versions'][version] = new_version
versions_info['latest'] = version
json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
with open('update/versions.json', 'w') as jsonf:
json.dump(versions_info, jsonf, indent=4, sort_keys=True)

3
devscripts/gh-pages/update-feed.py

@ -22,7 +22,7 @@ entry_template=textwrap.dedent("""
<atom:link href="http://rg3.github.io/youtube-dl" />
<atom:content type="xhtml">
<div xmlns="http://www.w3.org/1999/xhtml">
Downloads available at <a href="http://youtube-dl.org/downloads/@VERSION@/">http://youtube-dl.org/downloads/@VERSION@/</a>
Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
</div>
</atom:content>
<atom:author>
@ -54,4 +54,3 @@ atom_template = atom_template.replace('@ENTRIES@', entries_str)
with open('update/releases.atom','w',encoding='utf-8') as atom_file:
atom_file.write(atom_template)

2
devscripts/release.sh

@ -67,7 +67,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
(cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
git checkout HEAD -- youtube-dl youtube-dl.exe
/bin/echo -e "\n### Signing and uploading the new binaries to youtube-dl.org..."
/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"

9
devscripts/youtube_genalgo.py

@ -20,9 +20,9 @@ tests = [
# 87
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
"uioplkjhgfdsazxcvbnm1t34567890QWE2TYUIOPLKJHGFDSAZXCVeNM!@#$^&*()_-+={[]}|:;?/>.<"),
# 86
# 86 - vflh9ybst 2013/08/23
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
"yuioplkjhgfdsazecvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<"),
"yuioplkjhgfdsazxcvbnm1234567890QWERrYUIOPLKqHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<"),
# 85
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
".>/?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ0q876543r1mnbvcx9asdfghjklpoiuyt2"),
@ -32,12 +32,15 @@ tests = [
# 83
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
".>/?;}[{=+_)(*&^%<#!MNBVCXZASPFGHJKLwOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytreq"),
# 82
# 82 - vflZK4ZYR 2013/08/23
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
"wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>.<"),
# 81 - vflLC8JvQ 2013/07/25
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.",
"C>/?;}[{=+-(*&^%$#@!MNBVYXZASDFGHKLPOIU.TREWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
# 80 - vflZK4ZYR 2013/08/23 (sporadic)
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>",
"wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>"),
# 79 - vflLC8JvQ 2013/07/25 (sporadic)
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/",
"Z?;}[{=+-(*&^%$#@!MNBVCXRASDFGHKLPOIUYT/EWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),

39
test/test_youtube_subtitles.py

@ -35,47 +35,47 @@ class TestYoutubeSubtitles(unittest.TestCase):
DL.params['writesubtitles'] = True
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
sub = info_dict[0]['subtitles']['en']
self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
def test_youtube_subtitles_it(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
DL.params['subtitleslang'] = 'it'
DL.params['subtitleslangs'] = ['it']
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d')
sub = info_dict[0]['subtitles']['it']
self.assertEqual(md5(sub), '164a51f16f260476a05b50fe4c2f161d')
def test_youtube_onlysubtitles(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
DL.params['onlysubtitles'] = True
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
sub = info_dict[0]['subtitles']['en']
self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
def test_youtube_allsubtitles(self):
DL = FakeYDL()
DL.params['allsubtitles'] = True
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
subtitles = info_dict[0]['subtitles']
self.assertEqual(len(subtitles), 13)
self.assertEqual(len(subtitles.keys()), 13)
def test_youtube_subtitles_sbv_format(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
DL.params['subtitlesformat'] = 'sbv'
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '13aeaa0c245a8bed9a451cb643e3ad8b')
sub = info_dict[0]['subtitles']['en']
self.assertEqual(md5(sub), '13aeaa0c245a8bed9a451cb643e3ad8b')
def test_youtube_subtitles_vtt_format(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
DL.params['subtitlesformat'] = 'vtt'
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '356cdc577fde0c6783b9b822e7206ff7')
sub = info_dict[0]['subtitles']['en']
self.assertEqual(md5(sub), '356cdc577fde0c6783b9b822e7206ff7')
def test_youtube_list_subtitles(self):
DL = FakeYDL()
DL.params['listsubtitles'] = True
@ -85,11 +85,20 @@ class TestYoutubeSubtitles(unittest.TestCase):
def test_youtube_automatic_captions(self):
DL = FakeYDL()
DL.params['writeautomaticsub'] = True
DL.params['subtitleslang'] = 'it'
DL.params['subtitleslangs'] = ['it']
IE = YoutubeIE(DL)
info_dict = IE.extract('8YoUxe5ncPo')
sub = info_dict[0]['subtitles'][0]
self.assertTrue(sub[2] is not None)
sub = info_dict[0]['subtitles']['it']
self.assertTrue(sub is not None)
def test_youtube_multiple_langs(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
langs = ['it', 'fr', 'de']
DL.params['subtitleslangs'] = langs
IE = YoutubeIE(DL)
subtitles = IE.extract('QRS8MkLhQmM')[0]['subtitles']
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
if __name__ == '__main__':
unittest.main()

236
youtube_dl/PostProcessor.py

@ -71,12 +71,17 @@ class FFmpegPostProcessor(PostProcessor):
programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
return dict((program, executable(program)) for program in programs)
def run_ffmpeg(self, path, out_path, opts):
def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
if not self._exes['ffmpeg'] and not self._exes['avconv']:
raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path)]
files_cmd = []
for path in input_paths:
files_cmd.extend(['-i', encodeFilename(path)])
cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
+ opts +
[encodeFilename(self._ffmpeg_filename_argument(out_path))])
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout,stderr = p.communicate()
if p.returncode != 0:
@ -84,6 +89,9 @@ class FFmpegPostProcessor(PostProcessor):
msg = stderr.strip().split('\n')[-1]
raise FFmpegPostProcessorError(msg)
def run_ffmpeg(self, path, out_path, opts):
self.run_ffmpeg_multiple_files([path], out_path, opts)
def _ffmpeg_filename_argument(self, fn):
# ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
if fn.startswith(u'-'):
@ -232,3 +240,227 @@ class FFmpegVideoConvertor(FFmpegPostProcessor):
information['format'] = self._preferedformat
information['ext'] = self._preferedformat
return False,information
class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
# See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
_lang_map = {
'aa': 'aar',
'ab': 'abk',
'ae': 'ave',
'af': 'afr',
'ak': 'aka',
'am': 'amh',
'an': 'arg',
'ar': 'ara',
'as': 'asm',
'av': 'ava',
'ay': 'aym',
'az': 'aze',
'ba': 'bak',
'be': 'bel',
'bg': 'bul',
'bh': 'bih',
'bi': 'bis',
'bm': 'bam',
'bn': 'ben',
'bo': 'bod',
'br': 'bre',
'bs': 'bos',
'ca': 'cat',
'ce': 'che',
'ch': 'cha',
'co': 'cos',
'cr': 'cre',
'cs': 'ces',
'cu': 'chu',
'cv': 'chv',
'cy': 'cym',
'da': 'dan',
'de': 'deu',
'dv': 'div',
'dz': 'dzo',
'ee': 'ewe',
'el': 'ell',
'en': 'eng',
'eo': 'epo',
'es': 'spa',
'et': 'est',
'eu': 'eus',
'fa': 'fas',
'ff': 'ful',
'fi': 'fin',
'fj': 'fij',
'fo': 'fao',
'fr': 'fra',
'fy': 'fry',
'ga': 'gle',
'gd': 'gla',
'gl': 'glg',
'gn': 'grn',
'gu': 'guj',
'gv': 'glv',
'ha': 'hau',
'he': 'heb',
'hi': 'hin',
'ho': 'hmo',
'hr': 'hrv',
'ht': 'hat',
'hu': 'hun',
'hy': 'hye',
'hz': 'her',
'ia': 'ina',
'id': 'ind',
'ie': 'ile',
'ig': 'ibo',
'ii': 'iii',
'ik': 'ipk',
'io': 'ido',
'is': 'isl',
'it': 'ita',
'iu': 'iku',
'ja': 'jpn',
'jv': 'jav',
'ka': 'kat',
'kg': 'kon',
'ki': 'kik',
'kj': 'kua',
'kk': 'kaz',
'kl': 'kal',
'km': 'khm',
'kn': 'kan',
'ko': 'kor',
'kr': 'kau',
'ks': 'kas',
'ku': 'kur',
'kv': 'kom',
'kw': 'cor',
'ky': 'kir',
'la': 'lat',
'lb': 'ltz',
'lg': 'lug',
'li': 'lim',
'ln': 'lin',
'lo': 'lao',
'lt': 'lit',
'lu': 'lub',
'lv': 'lav',
'mg': 'mlg',
'mh': 'mah',
'mi': 'mri',
'mk': 'mkd',
'ml': 'mal',
'mn': 'mon',
'mr': 'mar',
'ms': 'msa',
'mt': 'mlt',
'my': 'mya',
'na': 'nau',
'nb': 'nob',
'nd': 'nde',
'ne': 'nep',
'ng': 'ndo',
'nl': 'nld',
'nn': 'nno',
'no': 'nor',
'nr': 'nbl',
'nv': 'nav',
'ny': 'nya',
'oc': 'oci',
'oj': 'oji',
'om': 'orm',
'or': 'ori',
'os': 'oss',
'pa': 'pan',
'pi': 'pli',
'pl': 'pol',
'ps': 'pus',
'pt': 'por',
'qu': 'que',
'rm': 'roh',
'rn': 'run',
'ro': 'ron',
'ru': 'rus',
'rw': 'kin',
'sa': 'san',
'sc': 'srd',
'sd': 'snd',
'se': 'sme',
'sg': 'sag',
'si': 'sin',
'sk': 'slk',
'sl': 'slv',
'sm': 'smo',
'sn': 'sna',
'so': 'som',
'sq': 'sqi',
'sr': 'srp',
'ss': 'ssw',
'st': 'sot',
'su': 'sun',
'sv': 'swe',
'sw': 'swa',
'ta': 'tam',
'te': 'tel',
'tg': 'tgk',
'th': 'tha',
'ti': 'tir',
'tk': 'tuk',
'tl': 'tgl',
'tn': 'tsn',
'to': 'ton',
'tr': 'tur',
'ts': 'tso',
'tt': 'tat',
'tw': 'twi',
'ty': 'tah',
'ug': 'uig',
'uk': 'ukr',
'ur': 'urd',
'uz': 'uzb',
've': 'ven',
'vi': 'vie',
'vo': 'vol',
'wa': 'wln',
'wo': 'wol',
'xh': 'xho',
'yi': 'yid',
'yo': 'yor',
'za': 'zha',
'zh': 'zho',
'zu': 'zul',
}
def __init__(self, downloader=None, subtitlesformat='srt'):
super(FFmpegEmbedSubtitlePP, self).__init__(downloader)
self._subformat = subtitlesformat
@classmethod
def _conver_lang_code(cls, code):
"""Convert language code from ISO 639-1 to ISO 639-2/T"""
return cls._lang_map.get(code[:2])
def run(self, information):
if information['ext'] != u'mp4':
self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
return True, information
sub_langs = [key for key in information['subtitles']]
filename = information['filepath']
input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]
opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
for (i, lang) in enumerate(sub_langs):
opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text'])
lang_code = self._conver_lang_code(lang)
if lang_code is not None:
opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
opts.extend(['-f', 'mp4'])
temp_filename = filename + u'.temp'
self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
os.remove(encodeFilename(filename))
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
return True, information

39
youtube_dl/YoutubeDL.py

@ -76,7 +76,7 @@ class YoutubeDL(object):
allsubtitles: Downloads all the subtitles of the video
listsubtitles: Lists all available subtitles for the video
subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt)
subtitleslang: Language of the subtitles to download
subtitleslangs: List of languages of the subtitles to download
keepvideo: Keep the video file after post-processing
daterange: A DateRange object, download only if the upload_date is in the range.
skip_download: Skip the actual download of the video file
@ -483,41 +483,28 @@ class YoutubeDL(object):
self.report_error(u'Cannot write description file ' + descfn)
return
if (self.params.get('writesubtitles', False) or self.params.get('writeautomaticsub')) and 'subtitles' in info_dict and info_dict['subtitles']:
subtitles_are_requested = any([self.params.get('writesubtitles', False),
self.params.get('writeautomaticsub'),
self.params.get('allsubtitles', False)])
if subtitles_are_requested 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
subtitle = info_dict['subtitles'][0]
(sub_error, sub_lang, sub) = subtitle
subtitles = info_dict['subtitles']
sub_format = self.params.get('subtitlesformat')
if sub_error:
self.report_warning("Some error while getting the subtitles")
else:
for sub_lang in subtitles.keys():
sub = subtitles[sub_lang]
if sub is None:
continue
try:
sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
sub_filename = subtitles_filename(filename, sub_lang, sub_format)
self.report_writesubtitles(sub_filename)
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
subfile.write(sub)
subfile.write(sub)
except (OSError, IOError):
self.report_error(u'Cannot write subtitles file ' + descfn)
return
if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
subtitles = info_dict['subtitles']
sub_format = self.params.get('subtitlesformat')
for subtitle in subtitles:
(sub_error, sub_lang, sub) = subtitle
if sub_error:
self.report_warning("Some error while getting the subtitles")
else:
try:
sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
self.report_writesubtitles(sub_filename)
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
subfile.write(sub)
except (OSError, IOError):
self.report_error(u'Cannot write subtitles file ' + descfn)
return
if self.params.get('writeinfojson', False):
infofn = filename + u'.info.json'
self.report_writeinfojson(infofn)

16
youtube_dl/__init__.py

@ -83,6 +83,9 @@ def parseOpts(overrideArguments=None):
return "".join(opts)
def _comma_separated_values_options_callback(option, opt_str, value, parser):
setattr(parser.values, option.dest, value.split(','))
def _find_term_columns():
columns = os.environ.get('COLUMNS', None)
if columns:
@ -206,9 +209,10 @@ def parseOpts(overrideArguments=None):
subtitles.add_option('--sub-format',
action='store', dest='subtitlesformat', metavar='FORMAT',
help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
subtitles.add_option('--sub-lang', '--srt-lang',
action='store', dest='subtitleslang', metavar='LANG',
help='language of the subtitles to download (optional) use IETF language tags like \'en\'')
subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
action='callback', dest='subtitleslang', metavar='LANGS', type='str',
default=[], callback=_comma_separated_values_options_callback,
help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
downloader.add_option('-r', '--rate-limit',
dest='ratelimit', metavar='LIMIT', help='maximum download rate (e.g. 50k or 44.6m)')
@ -323,6 +327,8 @@ def parseOpts(overrideArguments=None):
help='keeps the video file on disk after the post-processing; the video is erased by default')
postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
help='do not overwrite post-processed files; the post-processed files are overwritten by default')
postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
help='embed subtitles in the video (only for mp4 videos)')
parser.add_option_group(general)
@ -571,7 +577,7 @@ def _real_main(argv=None):
'allsubtitles': opts.allsubtitles,
'listsubtitles': opts.listsubtitles,
'subtitlesformat': opts.subtitlesformat,
'subtitleslang': opts.subtitleslang,
'subtitleslangs': opts.subtitleslang,
'matchtitle': decodeOption(opts.matchtitle),
'rejecttitle': decodeOption(opts.rejecttitle),
'max_downloads': opts.max_downloads,
@ -611,6 +617,8 @@ def _real_main(argv=None):
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))
# Update version
if opts.update_self:

3
youtube_dl/extractor/common.py

@ -47,7 +47,8 @@ class InfoExtractor(object):
uploader_id: Nickname or id of the video uploader.
location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
subtitles: The subtitle file contents.
subtitles: The subtitle file contents as a dictionary in the format
{language: subtitles}.
view_count: How many users have watched the video on the platform.
urlhandle: [internal] The urlHandle to be used to download the file,
like returned by urllib.request.urlopen

18
youtube_dl/extractor/xhamster.py

@ -3,7 +3,8 @@ import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
unescapeHTML,
determine_ext,
ExtractorError,
)
@ -36,15 +37,16 @@ class XHamsterIE(InfoExtractor):
video_url = compat_urllib_parse.unquote(mobj.group('file'))
else:
video_url = mobj.group('server')+'/key='+mobj.group('file')
video_extension = video_url.split('.')[-1]
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
webpage, u'title')
# Can't see the description anywhere in the UI
# video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
# webpage, u'description', fatal=False)
# if video_description: video_description = unescapeHTML(video_description)
# Only a few videos have an description
mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
if mobj:
video_description = unescapeHTML(mobj.group('description'))
else:
video_description = None
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
if mobj:
@ -62,9 +64,9 @@ class XHamsterIE(InfoExtractor):
return [{
'id': video_id,
'url': video_url,
'ext': video_extension,
'ext': determine_ext(video_url),
'title': video_title,
# 'description': video_description,
'description': video_description,
'upload_date': video_upload_date,
'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail

106
youtube_dl/extractor/youtube.py

@ -423,7 +423,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
elif len(s) == 87:
return s[6:27] + s[4] + s[28:39] + s[27] + s[40:59] + s[2] + s[60:]
elif len(s) == 86:
return s[5:20] + s[2] + s[21:]
return s[5:40] + s[3] + s[41:48] + s[0] + s[49:86]
elif len(s) == 85:
return s[83:34:-1] + s[0] + s[33:27:-1] + s[3] + s[26:19:-1] + s[34] + s[18:3:-1] + s[27]
elif len(s) == 84:
@ -434,6 +434,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
return s[1:19] + s[0] + s[20:68] + s[19] + s[69:82]
elif len(s) == 81:
return s[56] + s[79:56:-1] + s[41] + s[55:41:-1] + s[80] + s[40:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9]
elif len(s) == 80:
return s[1:19] + s[0] + s[20:68] + s[19] + s[69:80]
elif len(s) == 79:
return s[54] + s[77:54:-1] + s[39] + s[53:39:-1] + s[78] + s[38:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9]
@ -456,11 +458,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
try:
sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'unable to download video subtitles: %s' % compat_str(err), None)
self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
return {}
sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
if not sub_lang_list:
return (u'video doesn\'t have subtitles', None)
self._downloader.report_warning(u'video doesn\'t have subtitles')
return {}
return sub_lang_list
def _list_available_subtitles(self, video_id):
@ -469,8 +473,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _request_subtitle(self, sub_lang, sub_name, video_id, format):
"""
Return tuple:
(error_message, sub_lang, sub)
Return the subtitle as a string or None if they are not found
"""
self.report_video_subtitles_request(video_id, sub_lang, format)
params = compat_urllib_parse.urlencode({
@ -483,21 +486,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
try:
sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
return
if not sub:
return (u'Did not fetch video subtitles', None, None)
return (None, sub_lang, sub)
self._downloader.report_warning(u'Did not fetch video subtitles')
return
return sub
def _request_automatic_caption(self, video_id, webpage):
"""We need the webpage for getting the captions url, pass it as an
argument to speed up the process."""
sub_lang = self._downloader.params.get('subtitleslang') or 'en'
sub_lang = (self._downloader.params.get('subtitleslangs') or ['en'])[0]
sub_format = self._downloader.params.get('subtitlesformat')
self.to_screen(u'%s: Looking for automatic captions' % video_id)
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
if mobj is None:
return [(err_msg, None, None)]
self._downloader.report_warning(err_msg)
return {}
player_config = json.loads(mobj.group(1))
try:
args = player_config[u'args']
@ -512,40 +518,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
})
subtitles_url = caption_url + '&' + params
sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
return [(None, sub_lang, sub)]
except KeyError:
return [(err_msg, None, None)]
def _extract_subtitle(self, video_id):
return {sub_lang: sub}
# An extractor error can be raise by the download process if there are
# no automatic captions but there are subtitles
except (KeyError, ExtractorError):
self._downloader.report_warning(err_msg)
return {}
def _extract_subtitles(self, video_id):
"""
Return a list with a tuple:
[(error_message, sub_lang, sub)]
Return a dictionary: {language: subtitles} or {} if the subtitles
couldn't be found
"""
sub_lang_list = self._get_available_subtitles(video_id)
available_subs_list = self._get_available_subtitles(video_id)
sub_format = self._downloader.params.get('subtitlesformat')
if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
return [(sub_lang_list[0], None, None)]
if self._downloader.params.get('subtitleslang', False):
sub_lang = self._downloader.params.get('subtitleslang')
elif 'en' in sub_lang_list:
sub_lang = 'en'
if not available_subs_list: #There was some error, it didn't get the available subtitles
return {}
if self._downloader.params.get('allsubtitles', False):
sub_lang_list = available_subs_list
else:
sub_lang = list(sub_lang_list.keys())[0]
if not sub_lang in sub_lang_list:
return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
return [subtitle]
def _extract_all_subtitles(self, video_id):
sub_lang_list = self._get_available_subtitles(video_id)
sub_format = self._downloader.params.get('subtitlesformat')
if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
return [(sub_lang_list[0], None, None)]
subtitles = []
if self._downloader.params.get('subtitleslangs', False):
reqested_langs = self._downloader.params.get('subtitleslangs')
elif 'en' in available_subs_list:
reqested_langs = ['en']
else:
reqested_langs = [list(available_subs_list.keys())[0]]
sub_lang_list = {}
for sub_lang in reqested_langs:
if not sub_lang in available_subs_list:
self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
continue
sub_lang_list[sub_lang] = available_subs_list[sub_lang]
subtitles = {}
for sub_lang in sub_lang_list:
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
subtitles.append(subtitle)
if subtitle:
subtitles[sub_lang] = subtitle
return subtitles
def _print_formats(self, formats):
@ -736,25 +745,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# subtitles
video_subtitles = None
if self._downloader.params.get('writesubtitles', False):
video_subtitles = self._extract_subtitle(video_id)
if video_subtitles:
(sub_error, sub_lang, sub) = video_subtitles[0]
if sub_error:
self._downloader.report_warning(sub_error)
if self._downloader.params.get('writeautomaticsub', False):
if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
video_subtitles = self._extract_subtitles(video_id)
elif self._downloader.params.get('writeautomaticsub', False):
video_subtitles = self._request_automatic_caption(video_id, video_webpage)
(sub_error, sub_lang, sub) = video_subtitles[0]
if sub_error:
self._downloader.report_warning(sub_error)
if self._downloader.params.get('allsubtitles', False):
video_subtitles = self._extract_all_subtitles(video_id)
for video_subtitle in video_subtitles:
(sub_error, sub_lang, sub) = video_subtitle
if sub_error:
self._downloader.report_warning(sub_error)
if self._downloader.params.get('listsubtitles', False):
self._list_available_subtitles(video_id)

3
youtube_dl/utils.py

@ -657,6 +657,9 @@ def determine_ext(url, default_ext=u'unknown_video'):
else:
return default_ext
def subtitles_filename(filename, sub_lang, sub_format):
return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
def date_from_str(date_str):
"""
Return a datetime object from a string in the format YYYYMMDD or

2
youtube_dl/version.py

@ -1,2 +1,2 @@
__version__ = '2013.08.22'
__version__ = '2013.08.23'
Loading…
Cancel
Save