mirror of https://github.com/yt-dlp/yt-dlp.git
Merge branch 'master' into subtitles_rework
This commit is contained in:
Ismael Mejia
commit
06a401c845
|
|
@ -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"),
|
||||
|
|
|
|||
|
|
@ -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 +240,226 @@ 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.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
|
||||
os.remove(encodeFilename(filename))
|
||||
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||
|
||||
return True, information
|
||||
|
|
|
|||
|
|
@ -221,16 +221,19 @@ class YoutubeDL(object):
|
|||
|
||||
def report_writesubtitles(self, sub_filename):
|
||||
""" Report that the subtitles file is being written """
|
||||
self.to_screen(u'[info] Writing subtitle: ' + sub_filename)
|
||||
|
||||
def report_existingsubtitles(self, sub_filename):
|
||||
""" Report that the subtitles file has been already written """
|
||||
self.to_screen(u'[info] Skipping existing subtitle: ' + sub_filename)
|
||||
self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
|
||||
|
||||
def report_writeinfojson(self, infofn):
|
||||
""" Report that the metadata file has been written """
|
||||
self.to_screen(u'[info] Video description metadata as JSON to: ' + infofn)
|
||||
|
||||
def report_file_already_downloaded(self, file_name):
|
||||
"""Report file has already been fully downloaded."""
|
||||
try:
|
||||
self.to_screen(u'[download] %s has already been downloaded' % file_name)
|
||||
except (UnicodeEncodeError) as err:
|
||||
self.to_screen(u'[download] The file has already been downloaded')
|
||||
|
||||
def increment_downloads(self):
|
||||
"""Increment the ordinal that assigns a number to each file."""
|
||||
self._num_downloads += 1
|
||||
|
|
@ -489,16 +492,12 @@ class YoutubeDL(object):
|
|||
# that way it will silently go on when used with unsupporting IE
|
||||
subtitles = info_dict['subtitles']
|
||||
sub_format = self.params.get('subtitlesformat')
|
||||
|
||||
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
|
||||
if os.path.isfile(encodeFilename(sub_filename)):
|
||||
self.report_existingsubtitles(sub_filename)
|
||||
continue
|
||||
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)
|
||||
|
|
|
|||
|
|
@ -320,6 +320,8 @@ 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)
|
||||
|
|
@ -608,6 +610,8 @@ 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:
|
||||
|
|
|
|||
|
|
@ -1,5 +1,6 @@
|
|||
import re
|
||||
import json
|
||||
import itertools
|
||||
import socket
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
|
@ -33,7 +34,7 @@ class DailyMotionSubtitlesIE(NoAutoSubtitlesIE):
|
|||
self._downloader.report_warning(u'video doesn\'t have subtitles')
|
||||
return {}
|
||||
|
||||
class DailymotionIE(DailyMotionSubtitlesIE):
|
||||
class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
|
||||
"""Information Extractor for Dailymotion"""
|
||||
|
||||
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
|
||||
|
|
@ -43,7 +44,7 @@ class DailymotionIE(DailyMotionSubtitlesIE):
|
|||
u'file': u'x33vw9.mp4',
|
||||
u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
|
||||
u'info_dict': {
|
||||
u"uploader": u"Alex and Van .",
|
||||
u"uploader": u"Alex and Van .",
|
||||
u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
|
||||
}
|
||||
}
|
||||
|
|
@ -85,9 +86,9 @@ class DailymotionIE(DailyMotionSubtitlesIE):
|
|||
for key in ['stream_h264_hd1080_url','stream_h264_hd_url',
|
||||
'stream_h264_hq_url','stream_h264_url',
|
||||
'stream_h264_ld_url']:
|
||||
if info.get(key): # key in info and info[key]:
|
||||
if info.get(key):#key in info and info[key]:
|
||||
max_quality = key
|
||||
self.to_screen(u'%s: Using %s' % (video_id, key))
|
||||
self.to_screen(u'Using %s' % key)
|
||||
break
|
||||
else:
|
||||
raise ExtractorError(u'Unable to extract video URL')
|
||||
|
|
|
|||
|
|
@ -24,6 +24,112 @@ from ..utils import (
|
|||
orderedSet,
|
||||
)
|
||||
|
||||
class YoutubeBaseInfoExtractor(InfoExtractor):
|
||||
"""Provide base functions for Youtube extractors"""
|
||||
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
|
||||
_LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1'
|
||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
|
||||
_NETRC_MACHINE = 'youtube'
|
||||
# If True it will raise an error if no login info is provided
|
||||
_LOGIN_REQUIRED = False
|
||||
|
||||
def report_lang(self):
|
||||
"""Report attempt to set language."""
|
||||
self.to_screen(u'Setting language')
|
||||
|
||||
def _set_language(self):
|
||||
request = compat_urllib_request.Request(self._LANG_URL)
|
||||
try:
|
||||
self.report_lang()
|
||||
compat_urllib_request.urlopen(request).read()
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self._downloader.report_warning(u'unable to set language: %s' % compat_str(err))
|
||||
return False
|
||||
return True
|
||||
|
||||
def _login(self):
|
||||
(username, password) = self._get_login_info()
|
||||
# No authentication to be performed
|
||||
if username is None:
|
||||
if self._LOGIN_REQUIRED:
|
||||
raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True)
|
||||
return False
|
||||
|
||||
request = compat_urllib_request.Request(self._LOGIN_URL)
|
||||
try:
|
||||
login_page = compat_urllib_request.urlopen(request).read().decode('utf-8')
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self._downloader.report_warning(u'unable to fetch login page: %s' % compat_str(err))
|
||||
return False
|
||||
|
||||
galx = None
|
||||
dsh = None
|
||||
match = re.search(re.compile(r'<input.+?name="GALX".+?value="(.+?)"', re.DOTALL), login_page)
|
||||
if match:
|
||||
galx = match.group(1)
|
||||
match = re.search(re.compile(r'<input.+?name="dsh".+?value="(.+?)"', re.DOTALL), login_page)
|
||||
if match:
|
||||
dsh = match.group(1)
|
||||
|
||||
# Log in
|
||||
login_form_strs = {
|
||||
u'continue': u'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
|
||||
u'Email': username,
|
||||
u'GALX': galx,
|
||||
u'Passwd': password,
|
||||
u'PersistentCookie': u'yes',
|
||||
u'_utf8': u'霱',
|
||||
u'bgresponse': u'js_disabled',
|
||||
u'checkConnection': u'',
|
||||
u'checkedDomains': u'youtube',
|
||||
u'dnConn': u'',
|
||||
u'dsh': dsh,
|
||||
u'pstMsg': u'0',
|
||||
u'rmShown': u'1',
|
||||
u'secTok': u'',
|
||||
u'signIn': u'Sign in',
|
||||
u'timeStmp': u'',
|
||||
u'service': u'youtube',
|
||||
u'uilel': u'3',
|
||||
u'hl': u'en_US',
|
||||
}
|
||||
# Convert to UTF-8 *before* urlencode because Python 2.x's urlencode
|
||||
# chokes on unicode
|
||||
login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items())
|
||||
login_data = compat_urllib_parse.urlencode(login_form).encode('ascii')
|
||||
request = compat_urllib_request.Request(self._LOGIN_URL, login_data)
|
||||
try:
|
||||
self.report_login()
|
||||
login_results = compat_urllib_request.urlopen(request).read().decode('utf-8')
|
||||
if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
|
||||
self._downloader.report_warning(u'unable to log in: bad username or password')
|
||||
return False
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
self._downloader.report_warning(u'unable to log in: %s' % compat_str(err))
|
||||
return False
|
||||
return True
|
||||
|
||||
def _confirm_age(self):
|
||||
age_form = {
|
||||
'next_url': '/',
|
||||
'action_confirm': 'Confirm',
|
||||
}
|
||||
request = compat_urllib_request.Request(self._AGE_URL, compat_urllib_parse.urlencode(age_form))
|
||||
try:
|
||||
self.report_age_confirmation()
|
||||
compat_urllib_request.urlopen(request).read().decode('utf-8')
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
|
||||
return True
|
||||
|
||||
def _real_initialize(self):
|
||||
if self._downloader is None:
|
||||
return
|
||||
if not self._set_language():
|
||||
return
|
||||
if not self._login():
|
||||
return
|
||||
self._confirm_age()
|
||||
|
||||
class YoutubeSubtitlesIE(SubtitlesIE):
|
||||
|
||||
|
|
@ -83,8 +189,7 @@ class YoutubeSubtitlesIE(SubtitlesIE):
|
|||
self._downloader.report_warning(err_msg)
|
||||
return {}
|
||||
|
||||
|
||||
class YoutubeIE(YoutubeSubtitlesIE):
|
||||
class YoutubeIE(YoutubeSubtitlesIE, YoutubeBaseInfoExtractor):
|
||||
IE_DESC = u'YouTube.com'
|
||||
_VALID_URL = r"""^
|
||||
(
|
||||
|
|
@ -95,7 +200,7 @@ class YoutubeIE(YoutubeSubtitlesIE):
|
|||
(?: # the various things that can precede the ID:
|
||||
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|
||||
|(?: # or the v= param in all its forms
|
||||
(?:watch|movie(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
|
||||
(?:(?:watch|movie)(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
|
||||
(?:\?|\#!?) # the params delimiter ? or # or #!
|
||||
(?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
|
||||
v=
|
||||
|
|
@ -375,6 +480,8 @@ class YoutubeIE(YoutubeSubtitlesIE):
|
|||
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]
|
||||
|
||||
|
|
@ -390,105 +497,6 @@ class YoutubeIE(YoutubeSubtitlesIE):
|
|||
# Fallback to the other algortihms
|
||||
return self._decrypt_signature(s)
|
||||
|
||||
|
||||
def _get_available_subtitles(self, video_id):
|
||||
self.report_video_subtitles_download(video_id)
|
||||
request = compat_urllib_request.Request('http://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id)
|
||||
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)
|
||||
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)
|
||||
return sub_lang_list
|
||||
|
||||
def _list_available_subtitles(self, video_id):
|
||||
sub_lang_list = self._get_available_subtitles(video_id)
|
||||
self.report_video_subtitles_available(video_id, sub_lang_list)
|
||||
|
||||
def _request_subtitle(self, sub_lang, sub_name, video_id, format):
|
||||
"""
|
||||
Return tuple:
|
||||
(error_message, sub_lang, sub)
|
||||
"""
|
||||
self.report_video_subtitles_request(video_id, sub_lang, format)
|
||||
params = compat_urllib_parse.urlencode({
|
||||
'lang': sub_lang,
|
||||
'name': sub_name,
|
||||
'v': video_id,
|
||||
'fmt': format,
|
||||
})
|
||||
url = 'http://www.youtube.com/api/timedtext?' + params
|
||||
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)
|
||||
if not sub:
|
||||
return (u'Did not fetch video subtitles', None, None)
|
||||
return (None, sub_lang, 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_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)]
|
||||
player_config = json.loads(mobj.group(1))
|
||||
try:
|
||||
args = player_config[u'args']
|
||||
caption_url = args[u'ttsurl']
|
||||
timestamp = args[u'timestamp']
|
||||
params = compat_urllib_parse.urlencode({
|
||||
'lang': 'en',
|
||||
'tlang': sub_lang,
|
||||
'fmt': sub_format,
|
||||
'ts': timestamp,
|
||||
'kind': 'asr',
|
||||
})
|
||||
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 a list with a tuple:
|
||||
[(error_message, sub_lang, sub)]
|
||||
"""
|
||||
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)]
|
||||
if self._downloader.params.get('subtitleslang', False):
|
||||
sub_lang = self._downloader.params.get('subtitleslang')
|
||||
elif 'en' in sub_lang_list:
|
||||
sub_lang = 'en'
|
||||
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 = []
|
||||
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)
|
||||
return subtitles
|
||||
|
||||
def _print_formats(self, formats):
|
||||
print('Available formats:')
|
||||
for x in formats:
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
|
|||
Loading…
Reference in New Issue